Authors: Stefan Hackmann
Abstract: Despite the rapid advancements in Artificial Intelligence (AI), Stochastic Differential Equations (SDEs) remain the gold-standard formalism for modeling systems under uncertainty. However, applying SDEs in practice is fraught with challenges: modeling risk is high, calibration is often brittle, and high-fidelity simulations are computationally expensive. This technical report introduces JointFM, a foundation model that inverts this paradigm. Instead of fitting SDEs to data, we sample an infinite stream of synthetic SDEs to train a generic model to predict future joint probability distributions directly. This approach establishes JointFM as the first foundation model for distributional predictions of coupled time series - requiring no task-specific calibration or finetuning. Despite operating in a purely zero-shot setting, JointFM reduces the energy loss by 14.2% relative to the strongest baseline when recovering oracle joint distributions generated by unseen synthetic SDEs.
Authors: Dong Li, Zhengzhang Chen, Xujiang Zhao, Linlin Yu, Zhong Chen, Yi He, Haifeng Chen, Chen Zhao
Abstract: Uncovering causal structures from observational data is crucial for understanding complex systems and making informed decisions. While reinforcement learning (RL) has shown promise in identifying these structures in the form of a directed acyclic graph (DAG), existing methods often lack efficiency, making them unsuitable for online applications. In this paper, we propose MARLIN, an efficient multi agent RL based approach for incremental DAG learning. MARLIN uses a DAG generation policy that maps a continuous real valued space to the DAG space as an intra batch strategy, then incorporates two RL agents state specific and state invariant to uncover causal relationships and integrates these agents into an incremental learning framework. Furthermore, the framework leverages a factored action space to enhance parallelization efficiency. Extensive experiments on synthetic and real datasets demonstrate that MARLIN outperforms state of the art methods in terms of both efficiency and effectiveness.
Authors: Jing Liu, Zhenchao Ma, Han Yu, Bobo Ju, Wenliang Yang, Chengfang Li, Bo Hu, Liang Song
Abstract: Recent advances in collaborative knowledge distillation have demonstrated cutting-edge performance for resource-constrained distributed multimedia learning scenarios. However, achieving such competitiveness requires addressing a fundamental mismatch: high-dimensional teacher knowledge complexity versus heterogeneous client learning capacities, which currently prohibits deployment in edge-based visual analytics systems. Drawing inspiration from curriculum learning principles, we introduce Federated Adaptive Progressive Distillation (FAPD), a consensus-driven framework that orchestrates adaptive knowledge transfer. FAPD hierarchically decomposes teacher features via PCA-based structuring, extracting principal components ordered by variance contribution to establish a natural visual knowledge hierarchy. Clients progressively receive knowledge of increasing complexity through dimension-adaptive projection matrices. Meanwhile, the server monitors network-wide learning stability by tracking global accuracy fluctuations across a temporal consensus window, advancing curriculum dimensionality only when collective consensus emerges. Consequently, FAPD provably adapts knowledge transfer pace while achieving superior convergence over fixed-complexity approaches. Extensive experiments on three datasets validate FAPD's effectiveness: it attains 3.64% accuracy improvement over FedAvg on CIFAR-10, demonstrates 2x faster convergence, and maintains robust performance under extreme data heterogeneity ({\alpha}=0.1), outperforming baselines by over 4.5%.
Authors: Adithya Parthasarathy, Aswathnarayan Muthukrishnan Kirubakaran, Akshay Deshpande, Ram Sekhar Bodala, Suhas Malempati, Nachiappan Chockalingam, Vinoth Punniyamoorthy, Seema Gangaiah Aarella
Abstract: Accurate calibration is essential for instruments whose measurements must remain traceable, reliable, and compliant over long operating periods. Fixed-interval programs are easy to administer, but they ignore that instruments drift at different rates under different conditions. This paper studies calibration scheduling as a predictive maintenance problem: given recent sensor histories, estimate time-to-drift (TTD) and intervene before a violation occurs. We adapt the NASA C-MAPSS benchmark into a calibration setting by selecting drift-sensitive sensors, defining virtual calibration thresholds, and inserting synthetic reset events that emulate repeated recalibration. We then compare classical regressors, recurrent and convolutional sequence models, and a compact Transformer for TTD prediction. The Transformer provides the strongest point forecasts on the primary FD001 split and remains competitive on the harder FD002--FD004 splits, while a quantile-based uncertainty model supports conservative scheduling when drift behavior is noisier. Under a violation-aware cost model, predictive scheduling lowers cost relative to reactive and fixed policies, and uncertainty-aware triggers sharply reduce violations when point forecasts are less reliable. The results show that condition-based calibration can be framed as a joint forecasting and decision problem, and that combining sequence models with risk-aware policies is a practical route toward smarter calibration planning.
Authors: Federico Garcia Crespi, Eduardo Yubero Funes, Marina Alfosea Simon
Abstract: (a) Many air quality forecasting studies report gains from machine learning, but evaluations often use static chronological splits and omit persistence baselines, so the operational added value under routine updating is unclear. (b) Using 2,350 daily PM10 observations from 2017 to 2024 at an urban background monitoring station in southern Europe, we compare XGBoost and SARIMA against persistence under a static split and a rolling-origin protocol with monthly updates. We report horizon-specific skill and the predictability horizon, defined as the maximum horizon with positive persistence-relative skill. Static evaluation suggests XGBoost performs well from one to seven days ahead, but rolling-origin evaluation reverses rankings: XGBoost is not consistently better than persistence at short and intermediate horizons, whereas SARIMA remains positively skilled across the full range. (c) For researchers, static splits can overstate operational usefulness and change rankings. For practitioners, rolling-origin, persistence-referenced skill profiles show which methods stay reliable at each lead time.
Authors: Liu hung ming
Abstract: Video world models trained with Joint Embedding Predictive Architectures (JEPA) acquire rich spatiotemporal representations by predicting masked regions in latent space rather than reconstructing pixels. This removes the visual verification pathway of generative models, creating a structural interpretability gap: the encoder has learned physical structure inaccessible in any inspectable form. Existing probing methods either operate in continuous space without a structured intermediate layer, or attach generative components whose parameters confound attribution of behavior to the encoder. We propose the AI Mother Tongue (AIM) framework as a passive quantization probe: a lightweight, vocabulary-free probe that converts V-JEPA 2 continuous latent vectors into discrete symbol sequences without task-specific supervision or modifying the encoder. Because the encoder is kept completely frozen, any symbolic structure in the AIM codebook is attributable entirely to V-JEPA 2 pre-trained representations -- not to the probe. We evaluate through category-contrast experiments on Kinetics-mini along three physical dimensions: grasp angle, object geometry, and motion temporal structure. AIM symbol distributions differ significantly across all three experiments (chi^2 p < 10^{-4}; MI 0.036--0.117 bits, NMI 1.2--3.9% of the 3-bit maximum; JSD up to 0.342; codebook active ratio 62.5%). The experiments reveal that V-JEPA 2 latent space is markedly compact: diverse action categories share a common representational core, with semantic differences encoded as graded distributional variations rather than categorical boundaries. These results establish Stage 1 of a four-stage roadmap toward an action-conditioned symbolic world model, demonstrating that structured symbolic manifolds are discoverable properties of frozen JEPA latent spaces.
Authors: Oleksii Bychkov
Abstract: Modern autonomous multi-agent systems combine heterogeneous learning mechanisms operating at different timescales. An open question remains: can one formally guarantee that coupled dynamics of such mechanisms stay within the admissible operational regime? This paper studies a tri-hierarchical swarm learning system where three mechanisms act simultaneously: (1) local Hebbian online learning at individual agent level (fast timescale, 10-100 ms); (2) multi-agent reinforcement learning (MARL) for tactical group coordination (medium timescale, 1-10 s); (3) meta-learning (MAML) for strategic adaptation (slow timescale, 10-100 s). Four results are established. The Bounded Total Error Theorem shows that under contractual constraints on learning rates, Lipschitz continuity of inter-level mappings, and weight stabilization, total suboptimality admits a component-wise upper bound uniform in time. The Bounded Representation Drift Theorem gives a worst-case estimate of how Hebbian updates affect coordination-level embeddings during one MARL cycle. The Meta-Level Compatibility Theorem provides sufficient conditions under which strategic adaptation preserves lower-level invariants. The Non-Accumulation Theorem proves that error does not grow unboundedly over time.
Authors: F Basbous (Nantes Univ, GIP ARRONAX), F Poirier (GIP ARRONAX, CNRS), F Haddad (GIP ARRONAX, Nantes Univ, CNRS), D Mateus (Nantes Univ - ECN, LS2N)
Abstract: The Interest Public Group ARRONAX's C70XP cyclotron, used for radioisotope production for medical and research applications, relies on complex and costly systems that are prone to failures, leading to operational disruptions. In this context, this study aims to develop a machine learning-based method for early anomaly detection, from sensor measurements over a temporal window, to enhance system performance. One of the most widely recognized methods for anomaly detection is Isolation Forest (IF), known for its effectiveness and scalability. However, its reliance on axis-parallel splits limits its ability to detect subtle anomalies, especially those occurring near the mean of normal data. This study proposes a hybrid approach that combines a fully connected Autoencoder (AE) with IF to enhance the detection of subtle anomalies. In particular, the Mean Cubic Error (MCE) of the sensor data reconstructed by the AE is used as input to the IF model. Validated on proton beam intensity time series data, the proposed method demonstrates a clear improvement in detection performance, as confirmed by the experimental results.
Authors: Qi Luo, Minghui Xu, Dongxiao Yu, Xiuzhen Cheng
Abstract: Many learning systems now use graph data in which each node also contains text, such as papers with abstracts or users with posts. Because these texts often come from open platforms, an attacker may be able to quietly poison a small part of the training data and later make the model produce wrong predictions on demand. This paper studies that risk in a realistic setting where the attacker edits only node text and does not change the graph structure. We propose TAGBD, a text-only backdoor attack for text-attributed graphs. TAGBD first finds training nodes that are easier to influence, then generates natural-looking trigger text with the help of a shadow graph model, and finally injects the trigger by either replacing the original text or appending a short phrase. Experiments on three benchmark datasets show that the attack is highly effective, transfers across different graph models, and remains strong under common defenses. These results demonstrate that text alone is a practical attack channel in graph learning systems and suggest that future defenses should inspect both graph links and node content.
Authors: Salma Rachidi, Aso Bozorgpanah, Eric Fey, Alexander Jung
Abstract: Machine learning (ML) promises better clinical decision-making, yet opaque model behavior limits the adoption in healthcare. We propose two novel regularization techniques for ensuring the interpretability of ML models trained on real-world data. In particular, we consider the prediction of five-year survival for multiple myeloma patients using clinical data from Helsinki University Hospital. To ensure the interpretability of the trained models, we use two alternative constructions for a penalty term used for regularization. The first one penalizes deviations from the predictions obtained from an interpretable logistic regression method with two manually chosen features. The second construction requires consistency of model predictions with the revised international staging system (R-ISS). We verify the usefulness of the proposed regularization techniques in numerical experiments using data from 812 patients. They achieve an accuracy up to 0.721 on a test set and SHAP values show that the models rely on the selected important features.
Authors: Matthew Middlehurst, Aiden Rushbrooke, Ali Ismail-Fawaz, Maxime Devanne, Germain Forestier, Angus Dempster, Geoffrey I. Webb, Christopher Holder, Anthony Bagnall
Abstract: Time series machine learning (TSML) is a growing research field that spans a wide range of tasks. The popularity of established tasks such as classification, clustering, and extrinsic regression has, in part, been driven by the availability of benchmark datasets. An archive of 30 multivariate time series classification datasets, introduced in 2018 and commonly known as the UEA archive, has since become an essential resource cited in hundreds of publications. We present a substantial expansion of this archive that more than quadruples its size, from 30 to 133 classification problems. We also release preprocessed versions of datasets containing missing values or unequal length series, bringing the total number of datasets to 147. Reflecting the growth of the archive and the broader community, we rebrand it as the Multiverse archive to capture its diversity of domains. The Multiverse archive includes datasets from multiple sources, consolidating other collections and standalone datasets into a single, unified repository. Recognising that running experiments across the full archive is computationally demanding, we recommend a subset of the full archive called Multiverse-core (MV-core) for initial exploration. To support researchers in using the new archive, we provide detailed guidance and a baseline evaluation of established and recent classification algorithms, establishing performance benchmarks for future research. We have created a dedicated repository for the Multiverse archive that provides a common aeon and scikit-learn compatible framework for reproducibility, an extensive record of published results, and an interactive interface to explore the results.
Authors: Men Niu, Xinxin Fan, Quanliang Jing, Shaoye Luo, Yunfeng Lu
Abstract: Cooperative multi-agent reinforcement learning (c-MARL) has been widely deployed in real-world applications, such as social robots, embodied intelligence, UAV swarms, etc. Nevertheless, many adversarial attacks still exist to threaten various c-MARL systems. At present, the studies mainly focus on single-adversary perturbation attacks and white-box adversarial attacks that manipulate agents' internal observations or actions. To address these limitations, we in this paper attempt to study collusive adversarial attacks through strategically organizing a set of malicious agents into three collusive attack modes: Collective Malicious Agents, Disguised Malicious Agents, and Spied Malicious Agents. Three novelties are involved: i) three collusive adversarial attacks are creatively proposed for the first time, and a unified framework CAMA for policy-level collusive attacks is designed; ii) the attack effectiveness is theoretically analyzed from the perspectives of disruptiveness, stealthiness, and attack cost; and iii) the three collusive adversarial attacks are technically realized through agent's observation information fusion, attack-trigger control. Finally, multi-facet experiments on four SMAC II maps are performed, and experimental results showcase the three collusive attacks have an additive adversarial synergy, strengthening attack outcome while maintaining high stealthiness and stability over long horizons. Our work fills the gap for collusive adversarial learning in c-MARL.
Authors: Y. Sungtaek Ju
Abstract: Probabilistic circuit (PC) structure learning is hampered by greedy algorithms that make irreversible, locally optimal decisions. We propose SymCircuit, which replaces greedy search with a learned generative policy trained via entropy-regularized reinforcement learning. Instantiating the RL-as-inference framework in the PC domain, we show the optimal policy is a tempered Bayesian posterior, recovering the exact posterior when the regularization temperature is set inversely proportional to the dataset size. The policy is implemented as SymFormer, a grammar-constrained autoregressive Transformer with tree-relative self-attention that guarantees valid circuits at every generation step. We introduce option-level REINFORCE, restricting gradient updates to structural decisions rather than all tokens, yielding an SNR (signal to noise ratio) improvement and >10 times sample efficiency gain on the NLTCS dataset. A three-layer uncertainty decomposition (structural via model averaging, parametric via the delta method, leaf via conjugate Dirichlet-Categorical propagation) is grounded in the multilinear polynomial structure of PC outputs. On NLTCS, SymCircuit closes 93% of the gap to LearnSPN; preliminary results on Plants (69 variables) suggest scalability.
Authors: Yichun Xu, Navjot K. Khaira, Tejinder Singh
Abstract: The key-value (KV) cache is a foundational optimization in Transformer-based large language models (LLMs), eliminating redundant recomputation of past token representations during autoregressive generation. However, its memory footprint scales linearly with context length, imposing critical bottlenecks on GPU memory capacity, memory bandwidth, and inference throughput as production LLMs push context windows from thousands to millions of tokens. Efficient KV cache management has thus become a first-order challenge for scalable LLM deployment. This paper provides a systematic review of recent KV cache optimization techniques, organizing them into five principal directions: cache eviction, cache compression, hybrid memory solutions, novel attention mechanisms, and combination strategies. For each category we analyze the underlying mechanisms, deployment trade-offs, and empirical performance across memory reduction, throughput, and model accuracy metrics. We further map techniques to seven practical deployment scenarios, including long-context single requests, high-throughput datacenter serving, edge devices, multi-turn conversations, and accuracy-critical reasoning, providing actionable guidance for practitioners selecting among competing approaches. Our analysis reveals that no single technique dominates across all settings; instead, the optimal strategy depends on context length, hardware constraints, and workload characteristics, pointing toward adaptive, multi-stage optimization pipelines as a promising direction for future research.
Authors: Guillaume Baudart, Marc Lelarge, Tristan St\'erin, Jules Viennot
Abstract: We report on an experiment in which Claude Opus~4.6, equipped with a suite of Model Context Protocol (MCP) tools for the Rocq proof assistant, autonomously proved 10 of 12 problems from the 2025 Putnam Mathematical Competition. The MCP tools, designed with Claude by analyzing logs from a prior experiment on miniF2F-Rocq, encode a "compile-first, interactive-fallback" strategy. Running on an isolated VM with no internet access, the agent deployed 141 subagents over 17.7 hours of active compute (51.6h wall-clock), consuming approximately 1.9 billion tokens. All proofs are publicly available.
Authors: Marcus Armstrong, Navid Ayoobi, Arjun Mukherjee
Abstract: We investigate whether independently trained language models converge to geometrically compatible latent representations, and whether this compatibility can be exploited to correct model behavior at inference time without any weight updates. We learn a linear projection matrix that maps activation vectors from a large teacher model into the coordinate system of a smaller student model, then intervene on the student's residual stream during generation by substituting its internal state with the translated teacher representation. Across a fully crossed experimental matrix of 20 heterogeneous teacher-student pairings spanning mixture-of-experts, dense, code-specialized, and synthetically trained architectures, the Ridge projection consistently achieves R^2 = 0.50 on verbal reasoning and R^2 = 0.40 on mathematical reasoning, collapsing to R^2 = -0.22 under permutation control and R^2 = 0.01 under L_1 regularization. Behavioral correction rates range from 14.0% to 50.0% on TruthfulQA (mean 25.2%) and from 8.5% to 43.3% on GSM8K arithmetic reasoning (mean 25.5%), demonstrating that the method generalizes across fundamentally different reasoning domains. We report a near-zero correlation between geometric alignment quality and behavioral correction rate (r = -0.07), revealing a dissociation between representation space fidelity and output space impact. Intervention strength is architecture-specific: student models exhibit characteristic sensitivity profiles that invert across domains, with the most steerable verbal student becoming the least steerable mathematical student. Finally, a double dissociation experiment conducted across all 20 model pairings confirms without exception that projection matrices collapse catastrophically when transferred across reasoning domains (mean R^2 = -3.83 in both transfer directions), establishing domain-specific subspace geometry as a universal property of LMs.
Authors: Mahmoud Elhadidy, Roshan M. D'Souza, Amirhossein Arzani
Abstract: Scientific machine learning is increasingly used to build surrogate models, yet most models are trained under a restrictive assumption in which future data follow the same distribution as the training set. In practice, new experimental conditions or simulation regimes may differ significantly, requiring extrapolation and model updates without re-access to prior data. This creates a need for continual learning (CL) frameworks that can adapt to distribution shifts while preventing catastrophic forgetting. Such challenges are pronounced in fluid dynamics, where changes in geometry, boundary conditions, or flow regimes induce non-trivial changes to the solution. Here, we introduce a new architecture-based approach (SLE-FNO) combining a Single-Layer Extension (SLE) with the Fourier Neural Operator (FNO) to support efficient CL. SLE-FNO was compared with a range of established CL methods, including Elastic Weight Consolidation (EWC), Learning without Forgetting (LwF), replay-based approaches, Orthogonal Gradient Descent (OGD), Gradient Episodic Memory (GEM), PiggyBack, and Low-Rank Approximation (LoRA), within an image-to-image regression setting. The models were trained to map transient concentration fields to time-averaged wall shear stress (TAWSS) in pulsatile aneurysmal blood flow. Tasks were derived from 230 computational fluid dynamics simulations grouped into four sequential and out-of-distribution configurations. Results show that replay-based methods and architecture-based approaches (PiggyBack, LoRA, and SLE-FNO) achieve the best retention, with SLE-FNO providing the strongest overall balance between plasticity and stability, achieving accuracy with zero forgetting and minimal additional parameters. Our findings highlight key differences between CL algorithms and introduce SLE-FNO as a promising strategy for adapting baseline models when extrapolation is required.
Authors: Sebastian Rodriguez, Mikhael Tannous, Jad Mounayer, Camilo Cruz, Anais Barasinski, Francisco Chinesta
Abstract: Unidirectional tapes surface roughness determines the evolution of the degree of intimate contact required for ensuring the thermoplastic molecular diffusion and the associated inter-tapes consolidation during manufacturing of composite structures. However, usual characterization of rough surfaces relies on statistical descriptors that even if they are able to represent the surface topology, they are not necessarily connected with the physics occurring at the interface during inter-tape consolidation. Thus, a key research question could be formulated as follows: Which roughness descriptors simultaneously enable tape classification-crucial for process control-and consolidation modeling via the inference of the evolution of the degree of intimate contact, itself governed by the process parameters?. For providing a valuable response, we propose a novel strategy based on the use of Rank Reduction Autoencoders (RRAEs), autoencoders with a linear latent vector space enforced by applying a truncated Singular Value Decomposition (SVD) to the latent matrix during the encoder-decoder training. In this work, we extract useful roughness descriptors by enforcing the latent SVD modes to (i) accurately represent the roughness after decoding, and (ii) allow the extraction of existing a priori knowledge such as classification or modelling properties.
Authors: Truong Quynh Hoa, Hoang Dinh Cuong, Truong Xuan Khanh
Abstract: We propose Melaguard, a multimodal ML framework (Transformer-lite, 1.2M parameters, 4-head self-attention) for detecting neurovascular instability (NVI) from wearable-compatible physiological signals prior to structural stroke pathology. The model fuses heart rate variability (HRV), peripheral perfusion index, SpO2, and bilateral phase coherence into a composite NVI Score, designed for edge inference (WCET <=4 ms on Cortex-M4). NVI - the pre-structural dysregulation of cerebrovascular autoregulation preceding overt stroke - remains undetectable by existing single-modality wearables. With 12.2 million incident strokes annually, continuous multimodal physiological monitoring offers a practical path to community-scale screening. Three-stage independent validation: (1) synthetic benchmark (n=10,000), AUC=0.88 [0.83-0.92]; (2) clinical cohort PhysioNet CVES (n=172; 84 stroke, 88 control) - Transformer-lite achieves AUC=0.755 [0.630-0.778], outperforming LSTM (0.643), Random Forest (0.665), SVM (0.472); HRV-SDNN discriminates stroke (p=0.011); (3) PPG pipeline PhysioNet BIDMC (n=53) -- pulse rate r=0.748 and HRV surrogate r=0.690 vs. ECG ground truth. Cross-modality validation on PPG-BP (n=219) confirms PPG morphology classifies cerebrovascular disease at AUC=0.923 [0.869-0.968]. Multimodal fusion consistently outperforms single-modality baselines. Code: https://github.com/ClevixLab/Melaguard
Authors: Ruiying Chen, Yutong Wang, Houliang Zhou, Wei Liang, Yong Chen, Lifang He
Abstract: Longitudinal neuroimaging is essential for modeling disease progression in Alzheimer's disease (AD), yet irregular sampling and missing visits pose substantial challenges for learning reliable temporal representations. To address this challenge, we propose SDE-HGNN, a stochastic differential equation (SDE)-driven spatio-temporal hypergraph neural network for irregular longitudinal fMRI connectome modeling. The framework first employs an SDE-based reconstruction module to recover continuous latent trajectories from irregular observations. Based on these reconstructed representations, dynamic hypergraphs are constructed to capture higher-order interactions among brain regions over time. To further model temporal evolution, hypergraph convolution parameters evolve through SDE-controlled recurrent dynamics conditioned on inter-scan intervals, enabling disease-stage-adaptive connectivity modeling. We also incorporate a sparsity-based importance learning mechanism to identify salient brain regions and discriminative connectivity patterns. Extensive experiments on the OASIS-3 and ADNI cohorts demonstrate consistent improvements over state-of-the-art graph and hypergraph baselines in AD progression prediction. The source code is available at https://anonymous.4open.science/r/SDE-HGNN-017F.
Authors: Ming Shi, Yingbin Liang, Ness B. Shroff, Ananthram Swami
Abstract: Reinforcement learning from human feedback (RLHF) replaces hard-to-specify rewards with pairwise trajectory preferences, yet regret-oriented theory often assumes that preference labels are generated consistently from a single ground-truth objective. In practical RLHF systems, however, feedback is typically \emph{multi-source} (annotators, experts, reward models, heuristics) and can exhibit systematic, persistent mismatches due to subjectivity, expertise variation, and annotation/modeling artifacts. We study episodic RL from \emph{multi-source imperfect preferences} through a cumulative imperfection budget: for each source, the total deviation of its preference probabilities from an ideal oracle is at most $\omega$ over $K$ episodes. We propose a unified algorithm with regret $\tilde{O}(\sqrt{K/M}+\omega)$, which exhibits a best-of-both-regimes behavior: it achieves $M$-dependent statistical gains when imperfection is small (where $M$ is the number of sources), while remaining robust with unavoidable additive dependence on $\omega$ when imperfection is large. We complement this with a lower bound $\tilde{\Omega}(\max\{\sqrt{K/M},\omega\})$, which captures the best possible improvement with respect to $M$ and the unavoidable dependence on $\omega$, and a counterexample showing that na\"ively treating imperfect feedback as as oracle-consistent can incur regret as large as $\tilde{\Omega}(\min\{\omega\sqrt{K},K\})$. Technically, our approach involves imperfection-adaptive weighted comparison learning, value-targeted transition estimation to control hidden feedback-induced distribution shift, and sub-importance sampling to keep the weighted objectives analyzable, yielding regret guarantees that quantify when multi-source feedback provably improves RLHF and how cumulative imperfection fundamentally limits it.
Authors: Rahul D Ray
Abstract: Conservation laws are fundamental to understanding dynamical systems, but discovering them from data remains challenging due to parameter variation, non-polynomial invariants, local minima, and false positives on chaotic systems. We introduce NGCG, a neural-symbolic pipeline that decouples dynamics learning from invariant discovery and systematically addresses these challenges. A multi-restart variance minimiser learns a near-constant latent representation; system-specific symbolic extraction (polynomial Lasso, log-basis Lasso, explicit PDE candidates, and PySR) yields closed-form expressions; a strict constancy gate and diversity filter eliminate spurious laws. On a benchmark of nine diverse systems including Hamiltonian and dissipative ODEs, chaos, and PDEs, NGCG achieves consistent discovery (DR=1.0, FDR=0.0, F1=1.0) on all four systems with true conservation laws, with constancy two to three orders of magnitude lower than the best baseline. It is the only method that succeeds on the Lotka--Volterra system, and it correctly outputs no law on all five systems without invariants. Extensive experiments demonstrate robustness to noise ($\sigma = 0.1$), sample efficiency (50--100 trajectories), insensitivity to hyperparameters, and runtime under one minute per system. A Pareto analysis shows that the method provides a range of candidate expressions, allowing users to trade complexity for constancy. NGCG achieves strong performance relative to prior methods for data-driven conservation-law discovery, combining high accuracy with interpretability.
Authors: Adewale U. Oguntola, Olowookere A. AbdulQoyum, Adebukola M. Madehin, Adekemi A. Adetoro
Abstract: Electricity theft, or non-technical loss (NTL), presents a persistent threat to global power systems, driving significant financial deficits and compromising grid stability. Conventional detection methodologies, predominantly reactive and meter-centric, often fail to capture the complex spatio-temporal dynamics and behavioral patterns associated with fraudulent consumption. This study introduces a novel AI-driven Grid Intelligence Framework that fuses Time-Series Anomaly Detection, Supervised Machine Learning, and Graph Neural Networks (GNN) to identify theft with high precision in imbalanced datasets. Leveraging an enriched feature set, including rolling averages, voltage drop estimates, and a critical Grid Imbalance Index, the methodology employs a Long Short-Term Memory (LSTM) autoencoder for temporal anomaly scoring, a Random Forest classifier for tabular feature discrimination, and a GNN to model spatial dependencies across the distribution network. Experimental validation demonstrates that while standalone anomaly detection yields a low theft F1-score of 0.20, the proposed hybrid fusion achieves an overall accuracy of 93.7%. By calibrating decision thresholds via precision-recall analysis, the system attains a balanced theft precision of 0.55 and recall of 0.50, effectively mitigating the false positives inherent in single-model approaches. These results confirm that integrating topological grid awareness with temporal and supervised analytics provides a scalable, risk-based solution for proactive electricity theft detection and enhanced smart grid reliability.
Authors: Kaito Tanaka, Masato Ito, Yuji Nishimura, Keisuke Matsuda, Aya Nakayama
Abstract: Large Language Models (LLMs) have achieved remarkable success across diverse applications, yet their deployment remains challenging due to substantial computational costs, memory requirements, and energy consumption. Recent empirical studies have demonstrated that no single efficiency technique is universally optimal; instead, the effectiveness of methods such as efficient attention mechanisms, mixture-of-experts (MoE), parameter-efficient fine-tuning, and quantization varies significantly depending on task characteristics, resource constraints, and model scales. Building upon these insights, we propose AE-LLM, a unified framework that automatically selects and combines optimal efficiency techniques tailored to specific deployment scenarios. Our approach introduces a multi-objective optimization framework that jointly considers accuracy, latency, memory footprint, and energy consumption, while accounting for hardware constraints and task requirements. We develop an efficient search algorithm that explores the combinatorial space of efficiency techniques across architecture, fine-tuning, and inference stages, identifying Pareto-optimal configurations. Extensive experiments across 15 models (0.5B-70B parameters) and 10 diverse tasks demonstrate that AE-LLM achieves an average of $2.8\times$ improvement in efficiency metrics while maintaining competitive accuracy (within 1.2\% of baseline), compared to static efficiency configurations. Furthermore, our framework generalizes effectively to vision-language models, achieving similar efficiency gains. Our contributions provide practitioners with an automated tool for navigating the complex trade-off landscape of LLM efficiency optimization.
Authors: Aleksandar Armacki, Himkant Sharma, Dragana Bajovi\'c, Du\v{s}an Jakoveti\'c, Mrityunjoy Chakraborty, Soummya Kar
Abstract: We study the effects of center initialization on the performance of a family of distributed gradient-based clustering algorithms introduced in [1], that work over connected networks of users. In the considered scenario, each user contains a local dataset and communicates only with its immediate neighbours, with the aim of finding a global clustering of the joint data. We perform extensive numerical experiments, evaluating the effects of center initialization on the performance of our family of methods, demonstrating that our methods are more resilient to the effects of initialization, compared to centralized gradient clustering [2]. Next, inspired by the $K$-means++ initialization [3], we propose a novel distributed center initialization scheme, which is shown to improve the performance of our methods, compared to the baseline random initialization.
Authors: Ian Osband
Abstract: Distributed reinforcement learning trains on data from stale, buggy, or mismatched actors, producing actions with high surprisal (negative log-probability) under the learner's policy. The core difficulty is not surprising data per se, but \emph{negative learning from surprising data}. High-surprisal failures can dominate the update direction despite carrying little useful signal, while high-surprisal successes reveal opportunities the current policy would otherwise miss. The \textit{Delightful Policy Gradient} (DG) separates these cases by gating each update with delight, the product of advantage and surprisal, suppressing rare failures and amplifying rare successes without behavior probabilities. Under contaminated sampling, the cosine similarity between the standard policy gradient and the true gradient collapses, while DG's grows as the policy improves. No sign-blind reweighting, including exact importance sampling, can reproduce this effect. On MNIST with simulated staleness, DG without off-policy correction outperforms importance-weighted PG with exact behavior probabilities. On a transformer sequence task with staleness, actor bugs, reward corruption, and rare discovery, DG achieves roughly $10{\times}$ lower error. When all four frictions act simultaneously, its compute advantage is order-of-magnitude and grows with task complexity.
Authors: Ian Osband
Abstract: Policy gradient computes a backward pass for every sample, even though the backward pass is expensive and most samples carry little learning value. The Delightful Policy Gradient (DG) provides a forward-pass signal of learning value: \emph{delight}, the product of advantage and surprisal (negative log-probability). We introduce the \emph{Kondo gate}, which compares delight against a compute price and pays for a backward pass only when the sample is worth it, thereby tracing a quality--cost Pareto frontier. In bandits, zero-price gating preserves useful gradient signal while removing perpendicular noise, and delight is a more reliable screening signal than additive combinations of value and surprise. On MNIST and transformer token reversal, the Kondo gate skips most backward passes while retaining nearly all of DG's learning quality, with gains that grow as problems get harder and backward passes become more expensive. Because the gate tolerates approximate delight, a cheap forward pass can screen samples before expensive backpropagation, suggesting a speculative-decoding-for-training paradigm.
Authors: Shenyang Deng, Zhuoli Ouyang, Tianyu Pang, Zihang Liu, Ruochen Jin, Shuhua Yu, Yaoqing Yang
Abstract: Preconditioned adaptive methods have gained significant attention for training deep neural networks, as they capture rich curvature information of the loss landscape . The central challenge in this field lies in balancing preconditioning effectiveness with computational efficiency of implementing the preconditioner. Among recent advances, \textsc{Muon} stands out by using Newton-Schulz iteration to obtain preconditioned updates without explicitly constructing the preconditioning matrix. Despite its advantages, the efficiency of \textsc{Muon} still leaves room for further improvement. In this paper, we introduce \textsc{RMNP} (Row Momentum Normalized Preconditioning), an optimizer that replaces Newton-Schulz iteration with a simple row-wise $\ell_2$ normalization operation, motivated by the empirically observed diagonal block structure of the Transformer layerwise Hessian. This substitution reduces the per-iteration computational complexity from $\mathcal{O}(mn\cdot\min(m,n))$ to $\mathcal{O}(mn)$ for an $m\times n$ weight matrix while maintaining comparable optimization performance. Theoretically, we establish convergence guarantees for \textsc{RMNP} in the non-convex setting that match recent results for \textsc{Muon} optimizers, achieving the information-theoretic minimax optimal complexity. Extensive experiments on large language model pretraining show that \textsc{RMNP} delivers competitive optimization performance compared with \textsc{Muon} while substantially reducing preconditioning wall-clock time. Our code is available at \href{https://anonymous.4open.science/r/RMNP-E8E1/}{this link}.
Authors: Chang Liu, Jieshi Chen, Alexander J. Sundermann, Kathleen Shutt, Marissa P. Griffith, Lora Lee Pless, Lee H. Harrison, Artur W. Dubrawski
Abstract: Rapid identification of outbreaks in hospitals is essential for controlling pathogens with epidemic potential. Although whole genome sequencing (WGS) remains the gold standard in outbreak investigations, its substantial costs and turnaround times limit its feasibility for routine surveillance, especially in less-equipped facilities. We explore three modalities as rapid alternatives: matrix-assisted laser desorption ionization-time of flight (MALDI-TOF) mass spectrometry, antimicrobial resistance (AR) patterns, and electronic health records (EHR). We present a machine learning approach that learns discriminative features from these modalities to support outbreak detection. Multi-species evaluation shows that the integration of these modalities can boost outbreak detection performance. We also propose a tiered surveillance paradigm that can reduce the need for WGS through these alternative modalities. Further analysis of EHR information identifies potentially high-risk contamination routes linked to specific clinical procedures, notably those involving invasive equipment and high-frequency workflows, providing infection prevention teams with actionable targets for proactive risk mitigation
Authors: Haoqun Cao, Tengyang Xie
Abstract: Behavior cloning is a fundamental paradigm in machine learning, enabling policy learning from expert demonstrations across robotics, autonomous driving, and generative models. Autoregressive models like transformer have proven remarkably effective, from large language models (LLMs) to vision-language-action systems (VLAs). However, applying autoregressive models to continuous control requires discretizing actions through quantization, a practice widely adopted yet poorly understood theoretically. This paper provides theoretical foundations for this practice. We analyze how quantization error propagates along the horizon and interacts with statistical sample complexity. We show that behavior cloning with quantized actions and log-loss achieves optimal sample complexity, matching existing lower bounds, and incurs only polynomial horizon dependence on quantization error, provided the dynamics are stable and the policy satisfies a probabilistic smoothness condition. We further characterize when different quantization schemes satisfy or violate these requirements, and propose a model-based augmentation that provably improves the error bound without requiring policy smoothness. Finally, we establish fundamental limits that jointly capture the effects of quantization error and statistical complexity.
Authors: Hung Yun Tseng, Wuzhen Li, Blerina Gkotse, Grigorios Chrysos
Abstract: The potential of Large Language Models (LLMs) to provide harmful information remains a significant concern due to the vast breadth of illegal queries they may encounter. Unfortunately, existing benchmarks only focus on a handful types of illegal activities, and are not grounded in legal works. In this work, we introduce an ontology of crime-related concepts grounded in the legal frameworks of Model Panel Code, which serves as an influential reference for criminal law and has been adopted by many U.S. states, and instantiated using Californian Law. This structured knowledge forms the foundation for LJ-Bench, the first comprehensive benchmark designed to evaluate LLM robustness against a wide range of illegal activities. Spanning 76 distinct crime types organized taxonomically, LJ-Bench enables systematic assessment of diverse attacks, revealing valuable insights into LLM vulnerabilities across various crime categories: LLMs exhibit heightened susceptibility to attacks targeting societal harm rather than those directly impacting individuals. Our benchmark aims to facilitate the development of more robust and trustworthy LLMs. The LJ-Bench benchmark and LJ-Ontology, along with experiments implementation for reproducibility are publicly available at https://github.com/AndreaTseng/LJ-Bench.
Authors: Muralikrishnna G. Sethuraman, Faramarz Fekri
Abstract: Uncovering causal relationships is a fundamental problem across science and engineering. However, most existing causal discovery methods assume acyclicity and direct access to the system variables -- assumptions that fail to hold in many real-world settings. For instance, in genomics, cyclic regulatory networks are common, and measurements are often corrupted by instrumental noise. To address these challenges, we propose RECLAIM, a causal discovery framework that natively handles both cycles and measurement noise. RECLAIM learns the causal graph structure by maximizing the likelihood of the observed measurements via expectation-maximization (EM), using residual normalizing flows for tractable likelihood computation. We consider two measurement models: (i) Gaussian additive noise, and (ii) a linear measurement system with additive Gaussian noise. We provide theoretical consistency guarantees for both the settings. Experiments on synthetic data and real-world protein signaling datasets demonstrate the efficacy of the proposed method.
Authors: Dong Liu, Yanxuan Yu, Ben Lengerich, Ying Nian Wu
Abstract: As long-context language modeling becomes increasingly important, the cost of maintaining and attending to large Key/Value (KV) caches grows rapidly, becoming a major bottleneck in both training and inference. While prior works such as Multi-Query Attention (MQA) and Multi-Latent Attention (MLA) reduce memory by sharing or compressing KV features, they often trade off representation quality or incur runtime overhead. We propose Memory-Keyed Attention (MKA), a hierarchical attention mechanism that integrates multi-level KV caches (local, session, and long-term) and learns to route attention across them dynamically. We further introduce Route-Fused MKA (FastMKA), a broadcast-routed variant that fuses memory sources before attention computation for improved efficiency. Experiments on different sequence lengths show that FastMKA achieves a favorable accuracy-efficiency trade-off: comparable perplexity to MLA while achieving up to 5x faster training throughput and 1.8x lower evaluation latency. These results highlight MKA as a practical and extensible framework for efficient long-context attention.
Authors: James Alcala, Rayna Andreeva, Vladimir A. Kobzar, Dustin G. Mixon, Sanghoon Na, Shashank Sule, Yangxinyu Xie
Abstract: When training a neural network for classification, the feature vectors of the training set are known to collapse to the vertices of a regular simplex, provided the dimension $d$ of the feature space and the number $n$ of classes satisfies $n\leq d+1$. This phenomenon is known as neural collapse. For other applications like language models, one instead takes $n\gg d$. Here, the neural collapse phenomenon still occurs, but with different emergent geometric figures. We characterize these geometric figures in the orthoplex regime where $d+2\leq n\leq 2d$. The techniques in our analysis primarily involve Radon's theorem and convexity.
Authors: Alankrita Bhatt, Mukur Gupta, Germain Kolossov, Andrea Montanari
Abstract: Generating data from discrete distributions is important for a number of application domains including text, tabular data, and genomic data. Several groups have recently used random $k$-satisfiability ($k$-SAT) as a synthetic benchmark for new generative techniques. In this paper, we show that fundamental insights from the theory of random constraint satisfaction problems have observable implications (sometime contradicting intuition) on the behavior of generative techniques on such benchmarks. More precisely, we study the problem of generating a uniformly random solution of a given (random) $k$-SAT or $k$-XORSAT formula. Among other findings, we observe that: $(i)$~Continuous diffusions outperform masked discrete diffusions; $(ii)$~Learned diffusions can match the theoretical `ideal' accuracy; $(iii)$~Smart ordering of the variables can significantly improve accuracy, although not following popular heuristics.
Authors: Chang-Wei Yueh, Andy Zhao, Ashutosh Nayyar, Rahul Jain
Abstract: We study Bayesian learning in episodic, finite-horizon zero-sum Markov games with unknown transition and reward models. We investigate a posterior algorithm in which each player maintains a Bayesian posterior over the game model, independently samples a game model at the beginning of each episode, and computes an equilibrium policy for the sampled model. We analyze two settings: (i) Both players use the posterior sampling algorithm, and (ii) Only one player uses posterior sampling while the opponent follows an arbitrary learning algorithm. In each setting, we provide guarantees on the expected regret of the posterior sampling agent. Our notion of regret compares the expected total reward of the learning agent against the expected total reward under equilibrium policies of the true game. Our main theoretical result is an expected regret bound for the posterior sampling agent of order $O(HS\sqrt{ABHK\log(SABHK)})$ where $K$ is the number of episodes, $H$ is the episode length, $S$ is the number of states, and $A,B$ are the action space sizes of the two players. Experiments in a grid-world predator--prey domain illustrate the sublinear regret scaling and show that posterior sampling competes favorably with a fictitious-play baseline.
Authors: Ruijie Miao, Zhiming Wang, Wang Li, Shiwei Wu, Shufan Liu, Yanbing Jiang, Tong Yang
Abstract: Key-value (KV) caching is widely used to accelerate transformer inference, but its memory cost grows linearly with input length, limiting long-context deployment. Existing token eviction methods reduce memory by discarding less important tokens, which can be viewed as a coarse form of dimensionality reduction that assigns each token either zero or full dimension. We propose MixedDimKV, a mixed-dimension KV cache compression method that allocates dimensions to tokens at a more granular level, and MixedDimKV-H, which further integrates head-level importance information. Experiments on long-context benchmarks show that MixedDimKV outperforms prior KV cache compression methods that do not rely on head-level importance profiling. When equipped with the same head-level importance information, MixedDimKV-H consistently outperforms HeadKV. Notably, our approach achieves comparable performance to full attention on LongBench with only 6.25% of the KV cache. Furthermore, in the Needle-in-a-Haystack test, our solution maintains 100% accuracy at a 50K context length while using as little as 0.26% of the cache.
Authors: Zehao Li, Tao Ren, Zishi Zhang, Xi Chen, Yijie Peng
Abstract: Large language model (LLM) training is often bottlenecked by memory constraints and stochastic gradient noise in extremely high-dimensional parameter spaces. Motivated by empirical evidence that many LLM gradient matrices are effectively low-rank during training, we present an unbiased, memory-efficient, low-rank matrix estimator with the lowest variance that is applicable across common stochastic gradient estimation paradigms. The core idea is to project a high-dimensional stochastic gradient estimator onto a random low-dimensional subspace and lift it back, reducing memory while keeping the estimator unbiased and controlling mean-squared error via an optimally designed projection distribution, including Haar--Stiefel projections. The projection distribution is derived by solving a constrained functional optimization problem, yielding an optimal random projector that guides algorithm design. Empirically, the resulting low-rank gradient estimators deliver both practical memory savings and improved training behavior. In RoBERTa-large fine-tuning, our method attains the lowest peak GPU memory among compared methods (e.g., 3.83GB versus 16.7GB for full BP) while remaining competitive in accuracy; in autoregressive LLM pretraining (LLaMA-20M/60M/100M), our method outperforms the traditional methods, supporting the benefit of the proposed optimal projection strategy.
Authors: Chao Wang, Xuancheng Zhou, Ruilin Hou, Xiaoyu Cheng, Ruiyi Ding
Abstract: Accurately characterizing non-linear functional manifolds with singularities is a fundamental challenge in scientific computing. While Multi-Layer Perceptrons (MLPs) dominate, their spectral bias hinders resolving high-curvature features without excessive parameters. We introduce Continued Fraction Neural Networks (CFNNs), integrating continued fractions with gradient-based optimization to provide a ``rational inductive bias.'' This enables capturing complex asymptotics and discontinuities with extreme parameter frugality. We provide formal approximation bounds demonstrating exponential convergence and stability guarantees. To address recursive instability, we develop three implementations: CFNN-Boost, CFNN-MoE, and CFNN-Hybrid. Benchmarks show CFNNs consistently outperform MLPs in precision with one to two orders of magnitude fewer parameters, exhibiting up to a 47-fold improvement in noise robustness and physical consistency. By bridging black-box flexibility and white-box transparency, CFNNs establish a reliable ``grey-box'' paradigm for AI-driven scientific research.
Authors: Zixuan Zhang, Kaixuan Huang, Tuo Zhao, Mengdi Wang, Minshuo Chen
Abstract: Diffusion models have become a leading framework in generative modeling, yet their theoretical understanding -- especially for high-dimensional data concentrated on low-dimensional structures -- remains incomplete. This paper investigates how diffusion models learn such structured data, focusing on two key aspects: statistical complexity and influence of data geometric properties. By modeling data as samples from a smooth Riemannian manifold, our analysis reveals crucial decompositions of score functions in diffusion models under different levels of injected noise. We also highlight the interplay of manifold curvature with the structures in the score function. These analyses enable an efficient neural network approximation to the score function, built upon which we further provide statistical rates for score estimation and distribution learning. Remarkably, the obtained statistical rates are governed by the intrinsic dimension of data and the manifold curvature. These results advance the statistical foundations of diffusion models, bridging theory and practice for generative modeling on manifolds.
Authors: Anish Lakkapragada
Abstract: We introduce Exponential Family Discriminant Analysis (EFDA), a unified generative framework that extends classical Linear Discriminant Analysis (LDA) beyond the Gaussian setting to any member of the exponential family. Under the assumption that each class-conditional density belongs to a common exponential family, EFDA derives closed-form maximum-likelihood estimators for all natural parameters and yields a decision rule that is linear in the sufficient statistic, recovering LDA as a special case and capturing nonlinear decision boundaries in the original feature space. We prove that EFDA is asymptotically calibrated and statistically efficient under correct specification, and we generalise it to $K \geq 2$ classes and multivariate data. Through extensive simulation across five exponential-family distributions (Weibull, Gamma, Exponential, Poisson, Negative Binomial), EFDA matches the classification accuracy of LDA, QDA, and logistic regression while reducing Expected Calibration Error (ECE) by $2$-$6\times$, a gap that is structural: it persists for all $n$ and across all class-imbalance levels, because misspecified models remain asymptotically miscalibrated. We further prove and empirically confirm that EFDA's log-odds estimator approaches the Cram\'{e}r-Rao bound under correct specification, and is the only estimator in our comparison whose mean squared error converges to zero. Complete derivations are provided for nine distributions. Finally, we formally verify all four theoretical propositions in Lean 4, using Aristotle (Harmonic) and OpenGauss (Math, Inc.) as proof generators, with all outputs independently machine-checked by AXLE (Axiom).
Authors: Haricharan Balasundaram, Karthick Krishna Mahendran, Rahul Vaze
Abstract: The problem of constrained online convex optimization is considered, where at each round, once a learner commits to an action $x_t \in \mathcal{X} \subset \mathbb{R}^d$, a convex loss function $f_t$ and a convex constraint function $g_t$ that drives the constraint $g_t(x)\le 0$ are revealed. The objective is to simultaneously minimize the static regret and cumulative constraint violation (CCV) compared to the benchmark that knows the loss functions and constraint functions $f_t$ and $g_t$ for all $t$ ahead of time, and chooses a static optimal action that is feasible with respect to all $g_t(x)\le 0$. In recent prior work Sinha and Vaze [2024], algorithms with simultaneous regret of $O(\sqrt{T})$ and CCV of $O(\sqrt{T})$ or (CCV of $O(1)$ in specific cases Vaze and Sinha [2025], e.g. when $d=1$) have been proposed. It is widely believed that CCV is $\Omega(\sqrt{T})$ for all algorithms that ensure that regret is $O(\sqrt{T})$ with the worst case input for any $d\ge 2$. In this paper, we refute this and show that the algorithm of Vaze and Sinha [2025] simultaneously achieves regret of $O(\sqrt{T})$ regret and CCV of $O(T^{1/3})$ when $d=2$.
Authors: Sudip Laudari
Abstract: Echo State Networks (ESNs) are a reservoir computing framework widely used for nonlinear time-series prediction. However, despite their effectiveness, the randomly initialized reservoir often contains redundant nodes, leading to unnecessary computational overhead and reduced efficiency. In this work, we propose a graph centrality-based pruning approach that interprets the reservoir as a weighted directed graph and removes structurally less important nodes using centrality measures. Experiments on Mackey-Glass time-series prediction and electric load forecasting demonstrate that the proposed method can significantly reduce reservoir size while maintaining, and in some cases improving, prediction accuracy, while preserving the essential reservoir dynamics.
Authors: Zhuobin Yang, Yeyao Bao, Liangfu Lv, Jian Zhang, Xiaohong Li, Yunliang Zang
Abstract: Spiking Neural Networks (SNNs) are promising for energy-efficient, real-time edge computing, yet their performance is often constrained by the limited adaptability of conventional leaky integrate-and-fire (LIF) neurons. Existing LIF models struggle with restricted information capacity and susceptibility to noise, leading to degraded accuracy and compromised robustness. Inspired by the dynamic self-regulation of biological potassium channels, we propose the Potassium-regulated LIF (KvLIF) neuron model. KvLIF introduces an auxiliary conductance state that integrates membrane potential and spiking history to adaptively modulate neuronal excitability and reset dynamics. This design extends the dynamic response range of neurons to varying input intensities and effectively suppresses noise-induced spikes. We extensively evaluate KvLIF on both static image and neuromorphic datasets, demonstrating consistent improvements in classification accuracy and superior robustness compared to existing LIF models. Our work bridges biological plausibility with computational efficiency, offering a neuron model that enhances SNN performance while maintaining suitability for low-power neuromorphic deployment.
Authors: Matta Varun (Indian Institute of Technology Kharagpur, India), Ajay Kumar Dhakar (Indian Institute of Technology Kharagpur, India), Yuan Hong (University of Connecticut, USA), Shamik Sural (Indian Institute of Technology Kharagpur, India)
Abstract: Graph neural network (GNN) is a powerful tool for analyzing graph-structured data. However, their vulnerability to adversarial attacks raises serious concerns, especially when dealing with sensitive information. Local Differential Privacy (LDP) offers a privacy-preserving framework for training GNNs, but its impact on adversarial robustness remains underexplored. This paper investigates adversarial attacks on LDP-protected GNNs. We explore how the privacy guarantees of LDP can be leveraged or hindered by adversarial perturbations. The effectiveness of existing attack methods on LDP-protected GNNs are analyzed and potential challenges in crafting adversarial examples under LDP constraints are discussed. Additionally, we suggest directions for defending LDP-protected GNNs against adversarial attacks. This work investigates the interplay between privacy and security in graph learning, highlighting the need for robust and privacy-preserving GNN architectures.
Authors: Yuxuan Yang, Dugang Liu, Yiyan Huang
Abstract: In personalized marketing, uplift models estimate incremental effects by modeling how customer behavior changes under alternative treatments. However, real-world data often exhibit biases - such as selection bias, spillover effects, and unobserved confounding - which adversely affect both estimation accuracy and metric validity. Despite the importance of bias-aware assessment, a lack of systematic studies persists. To bridge this gap, we design a systematic benchmarking framework. Unlike standard predictive tasks, real-world uplift datasets lack counterfactual ground truth, rendering direct metric validation infeasible. Therefore, a semi-synthetic approach serves as a critical enabler for systematic benchmarking, effectively bridging the gap by retaining real-world feature dependencies while providing the ground truth needed to isolate structural biases. Our investigations reveal that: (i) uplift targeting and prediction can manifest as distinct objectives, where proficiency in one does not ensure efficacy in the other; (ii) while many models exhibit inconsistent performance under diverse biases, TARNet shows notable robustness, providing insights for subsequent model design; (iii) evaluation metric stability is linked to mathematical alignment with the ATE, suggesting that ATE-approximating metrics yield more consistent model rankings under structural data imperfections. These findings suggest the need for more robust uplift models and metrics. Code will be released upon acceptance.
Authors: Aarush Aggarwal, Akshat Tomar, Amritanshu Tiwari, Sargam Goyal
Abstract: Robust semantic segmentation is crucial for safe autonomous driving, yet deployed models remain vulnerable to black-box adversarial attacks when target weights are unknown. Most existing approaches either craft image-wide perturbations or optimize patches for a single architecture, which limits their practicality and transferability. We introduce OmniPatch, a training framework for learning a universal adversarial patch that generalizes across images and both ViT and CNN architectures without requiring access to target model parameters.
Authors: Khoa Nguyen, Bao Duong, Viet Huynh, Thin Nguyen
Abstract: Recovering Markov boundary -- the minimal set of variables that maximizes predictive performance for a response variable -- is crucial in many applications. While recent advances improve upon traditional constraint-based techniques by scoring local causal structures, they still rely on nonparametric estimators and heuristic searches, lacking theoretical guarantees for reliability. This paper investigates a framework for efficient Markov boundary discovery by integrating conditional entropy from information theory as a scoring criterion. We design a novel masked autoregressive network to capture complex dependencies. A parallelizable greedy search strategy in polynomial time is proposed, supported by analytical evidence. We also discuss how initializing a graph with learned Markov boundaries accelerates the convergence of causal discovery. Comprehensive evaluations on real-world and synthetic datasets demonstrate the scalability and superior performance of our method in both Markov boundary discovery and causal discovery tasks.
Authors: Yudong W. Xu, Wenhao Li, Scott Sanner, Elias B. Khalil
Abstract: Neural networks are being increasingly used as heuristics for constraint satisfaction. These neural methods are often recurrent, learning to iteratively refine candidate assignments. In this work, we make explicit the connection between such iterative neural heuristics and Large Neighborhood Search (LNS), and adapt an existing neural constraint satisfaction method-ConsFormer-into an LNS procedure. We decompose the resulting neural LNS into two standard components: the destroy and repair operators. On the destroy side, we instantiate several classical heuristics and introduce novel prediction-guided operators that exploit the model's internal scores to select neighborhoods. On the repair side, we utilize ConsFormer as a neural repair operator and compare the original sampling-based decoder to a greedy decoder that selects the most likely assignments. Through an empirical study on Sudoku, Graph Coloring, and MaxCut, we find that adapting the neural heuristic to an LNS procedure yields substantial gains over its vanilla settings and improves its competitiveness with classical and neural baselines. We further observe consistent design patterns across tasks: stochastic destroy operators outperform greedy ones, while greedy repair is more effective than sampling-based repair for finding a single high-quality feasible assignment. These findings highlight LNS as a useful lens and design framework for structuring and improving iterative neural approaches.
Authors: Hongyu Yi, Chenbei Lu, Jing Yu
Abstract: This paper studies finite-sample set-membership identification for discrete-time bilinear systems under bounded symmetric log-concave disturbances. Compared with existing finite-sample results for linear systems and related analyses under stronger noise assumptions, we consider the more challenging bilinear setting with trajectory-dependent regressors and allow marginally stable dynamics with polynomial mean-square state growth. Under these conditions, we prove that the diameter of the feasible parameter set shrinks with sample complexity $\widetilde{O}(1/\epsilon)$. Simulation supports the theory and illustrates the advantage of the proposed estimator for uncertainty quantification.
Authors: Hanlin Xiao, Rainer Breitling, Eriko Takano, Mauricio A. \'Alvarez
Abstract: Recent advances in general-purpose foundation models have stimulated the development of large biological sequence models. While natural language shows symbolic granularity (characters, words, sentences), biological sequences exhibit hierarchical granularity whose levels (nucleotides, amino acids, protein domains, genes) further encode biologically functional information. In this paper, we investigate the integration of cross-granularity knowledge from models through a case study of BiGCARP, a Pfam domain-level model for biosynthetic gene clusters, and ESM, an amino acid-level protein language model. Using representation analysis tools and a set of probe tasks, we first explain why a straightforward cross-model embedding initialization fails to improve downstream performance in BiGCARP, and show that deeper-layer embeddings capture a more contextual and faithful representation of the model's learned knowledge. Furthermore, we demonstrate that representations at different granularities encode complementary biological knowledge, and that combining them yields measurable performance gains in intermediate-level prediction tasks. Our findings highlight cross-granularity integration as a promising strategy for improving both the performance and interpretability of biological foundation models.
Authors: Shinsaku Sakaue
Abstract: Contextual recommendation is a variant of contextual linear bandits in which the learner observes an (optimal) action rather than a reward scalar. Recently, Sakaue et al. (2025) developed an efficient Online Newton Step (ONS) approach with an $O(d\log T)$ regret bound, where $d$ is the dimension of the action space and $T$ is the time horizon. In this paper, we present a simple algorithm that is more efficient than the ONS-based method while achieving the same regret guarantee. Our core idea is to exploit the improperness inherent in contextual recommendation, leading to an update rule akin to the second-order perceptron from online classification. This removes the Mahalanobis projection step required by ONS, which is often a major computational bottleneck. More importantly, the same algorithm remains robust to possibly suboptimal action feedback, whereas the prior ONS-based method required running multiple ONS learners with different learning rates for this extension. We describe how our method works in general Hilbert spaces (e.g., via kernelization), where eliminating Mahalanobis projections becomes even more beneficial.
Authors: Yunhui Liu, Yue Liu, Yongchao Liu, Tao Zheng, Stan Z. Li, Xinwang Liu, Tieke He
Abstract: Attributed Graph Clustering (AGC) is a fundamental unsupervised task that partitions nodes into cohesive groups by jointly modeling structural topology and node attributes. While the advent of graph neural networks and self-supervised learning has catalyzed a proliferation of AGC methodologies, a widening chasm persists between academic benchmark performance and the stringent demands of real-world industrial deployment. To bridge this gap, this survey provides a comprehensive, industrially grounded review of AGC from three complementary perspectives. First, we introduce the Encode-Cluster-Optimize taxonomic framework, which decomposes the diverse algorithmic landscape into three orthogonal, composable modules: representation encoding, cluster projection, and optimization strategy. This unified paradigm enables principled architectural comparisons and inspires novel methodological combinations. Second, we critically examine prevailing evaluation protocols to expose the field's academic monoculture: a pervasive over-reliance on small, homophilous citation networks, the inadequacy of supervised-only metrics for an inherently unsupervised task, and the chronic neglect of computational scalability. In response, we advocate for a holistic evaluation standard that integrates supervised semantic alignment, unsupervised structural integrity, and rigorous efficiency profiling. Third, we explicitly confront the practical realities of industrial deployment. By analyzing operational constraints such as massive scale, severe heterophily, and tabular feature noise alongside extensive empirical evidence from our companion benchmark, we outline actionable engineering strategies. Furthermore, we chart a clear roadmap for future research, prioritizing heterophily-robust encoders, scalable joint optimization, and unsupervised model selection criteria to meet production-grade requirements.
Authors: Wenbo Xu, Yue He, Yunhai Wang, Xingxuan Zhang, Kun Kuang, Yueguo Chen, Peng Cui
Abstract: Causal discovery has been widely studied, yet many existing methods rely on strong assumptions or fall into two extremes: either depending on costly interventional signals or partial ground truth as strong priors, or adopting purely data driven paradigms with limited guidance, which hinders practical deployment. Motivated by real-world scenarios where only coarse domain knowledge is available, we propose a knowledge-informed pretrained model for causal discovery that integrates weak prior knowledge as a principled middle ground. Our model adopts a dual source encoder-decoder architecture to process observational data in a knowledge-informed way. We design a diverse pretraining dataset and a curriculum learning strategy that smoothly adapts the model to varying prior strengths across mechanisms, graph densities, and variable scales. Extensive experiments on in-distribution, out-of distribution, and real-world datasets demonstrate consistent improvements over existing baselines, with strong robustness and practical applicability.
Authors: Hossein Javidnia
Abstract: Recent interpretability work often treats a feature as a single global direction, dictionary atom, or latent coordinate shared across contexts. We argue that this ontology can fail in obstructed representation spaces, where locally coherent meanings need not assemble into one globally consistent feature. We introduce an atlas-native replacement object, the semantic section: a transport-compatible family of local feature representatives defined over a context atlas. We formalize semantic sections, prove that tree-supported propagation is always pathwise realizable, and show that cycle consistency is the key criterion for genuine globalization. This yields a distinction between tree-local, globalizable, and twisted sections, with twisted sections capturing locally coherent but holonomy-obstructed meanings. We then develop a discovery-and-certification pipeline based on seeded propagation, synchronization across overlaps, defect-based pruning, cycle-aware taxonomy, and deduplication. Across layer-16 atlases for Llama 3.2 3B Instruct, Qwen 2.5 3B Instruct, and Gemma 2 2B IT, we find nontrivial populations of semantic sections, including cycle-supported globalizable and twisted regimes after deduplication. Most importantly, semantic identity is not recovered by raw global-vector similarity. Even certified globalizable sections show low cross-chart signed cosine similarity, and raw similarity baselines recover only a small fraction of true within-section pairs, often collapsing at moderate thresholds. By contrast, section-based identity recovery is perfect on certified supports. These results support semantic sections as a better feature ontology in obstructed regimes.
Authors: Fateme Maleki, Krishnan Raghavan, Farzad Yousefian
Abstract: Federated learning (FL) is a communication-efficient collaborative learning framework that enables model training across multiple agents with private local datasets. While the benefits of FL in improving global model performance are well established, individual agents may behave strategically, balancing the learning payoff against the cost of contributing their local data. Motivated by the need for FL frameworks that successfully retain participating agents, we propose an incentive-aware federated averaging method in which, at each communication round, clients transmit both their local model parameters and their updated training dataset sizes to the server. The dataset sizes are dynamically adjusted via a Nash equilibrium (NE)-seeking update rule that captures strategic data participation. We analyze the proposed method under convex and nonconvex global objective settings and establish performance guarantees for the resulting incentive-aware FL algorithm. Numerical experiments on the MNIST and CIFAR-10 datasets demonstrate that agents achieve competitive global model performance while converging to stable data participation strategies.
Authors: Zhaoyi Liu, Haichuan Zhang, Ang Li
Abstract: Hyper-Connections (HC) generalize residual connections into multiple streams, employing residual matrices for cross-stream feature mixing to enrich model expressivity. However, unconstrained mixing disrupts the identity mapping property intrinsic to the residual connection, causing unstable training. To address this, Manifold-Constrained Hyper-Connections (mHC) and its variant restrict these matrices to the Birkhoff polytope (doubly stochastic matrices) via Sinkhorn iterations or permutation-based parameterizations. We reveal three limitations of this polytope constraint: (1) identity degeneration, where learned matrices collapse around the identity and diminish cross-stream interactions, (2) an expressivity bottleneck, as the non-negativity constraint prevents subtractive feature disentanglement, and (3) parameterization inefficiencies, manifesting as unstable Sinkhorn iterations or the factorial-scaling overhead of permutation-based parameterizations. To overcome these flaws, we propose Spectral-Sphere-Constrained Hyper-Connections (sHC). By geometrically shifting the feasible set from a rigid polytope to a spectral norm sphere, sHC allows negative entries, unlocking subtractive interactions for selective feature diversification. This shift eliminates unstable Sinkhorn projections and factorial parameterization, enabling expressive, non-degenerate residual matrices while preserving training stability.
Authors: Joe Khawand, David Colliaux
Abstract: Online Continual Learning (OCL) for image classification represents a challenging subset of Continual Learning, focusing on classifying images from a stream without assuming data independence and identical distribution (i.i.d). The primary challenge in this context is to prevent catastrophic forgetting, where the model's performance on previous tasks deteriorates as it learns new ones. Although various strategies have been proposed to address this issue, achieving rapid convergence remains a significant challenge in the online setting. In this work, we introduce a novel approach to training OCL models that utilizes the Natural Gradient Descent optimizer, incorporating an approximation of the Fisher Information Matrix (FIM) through Kronecker Factored Approximate Curvature (KFAC). This method demonstrates substantial improvements in performance across all OCL methods, particularly when combined with existing OCL tricks, on datasets such as Split CIFAR-100, CORE50, and Split miniImageNet.
Authors: Bernardo Fichera, Zarko Ivkovic, Kjell Jorner, Philipp Hennig, Viacheslav Borovitskiy
Abstract: Uncertainty quantification for image data is dominated by complex deep learning methods, yet the field lacks an interpretable, mathematically grounded baseline. We propose Bayesian scattering to fill this gap, serving as a first-step baseline akin to the role of Bayesian linear regression for tabular data. Our method couples the wavelet scattering transform-a deep, non-learned feature extractor-with a simple probabilistic head. Because scattering features are derived from geometric principles rather than learned, they avoid overfitting the training distribution. This helps provide sensible uncertainty estimates even under significant distribution shifts. We validate this on diverse tasks, including medical imaging under institution shift, wealth mapping under country-to-country shift, and Bayesian optimization of molecular properties. Our results suggest that Bayesian scattering is a solid baseline for complex uncertainty quantification methods.
Authors: Amirmohammad Ziaei Bideh, Jonathan Gryak
Abstract: Discovering the governing equations of dynamical systems is a central problem across many scientific disciplines. As experimental data become increasingly available, automated equation discovery methods offer a promising data-driven approach to accelerate scientific discovery. Among these methods, genetic programming (GP) has been widely adopted due to its flexibility and interpretability. However, GP-based approaches often suffer from inefficient exploration of the symbolic search space, leading to slow convergence and suboptimal solutions. To address these limitations, we propose LLM-ODE, a large language model-aided model discovery framework that guides symbolic evolution using patterns extracted from elite candidate equations. By leveraging the generative prior of large language models, LLM-ODE produces more informed search trajectories while preserving the exploratory strengths of evolutionary algorithms. Empirical results on 91 dynamical systems show that LLM-ODE variants consistently outperform classical GP methods in terms of search efficiency and Pareto-front quality. Overall, our results demonstrate that LLM-ODE improves both efficiency and accuracy over traditional GP-based discovery and offers greater scalability to higher-dimensional systems compared to linear and Transformer-only model discovery methods.
Authors: Mohamed Aymen Bouyahia, Argyris Kalogeratos
Abstract: Interpreting complex machine learning models is a critical challenge, especially for tabular data where model transparency is paramount. Local Interpretable Model-Agnostic Explanations (LIME) has been a very popular framework for interpretable machine learning, also inspiring many extensions. While traditional surrogate models used in LIME variants (e.g. linear regression and decision trees) offer a degree of stability, they can struggle to faithfully capture the complex non-linear decision boundaries that are inherent in many sophisticated black-box models. This work contributes toward bridging the gap between high predictive performance and interpretable decision-making. Specifically, we propose the NDT-LIME variant that integrates Neural Decision Trees (NDTs) as surrogate models. By leveraging the structured, hierarchical nature of NDTs, our approach aims at providing more accurate and meaningful local explanations. We evaluate its effectiveness on several benchmark tabular datasets, showing consistent improvements in explanation fidelity over traditional LIME surrogates.
Authors: Yang Zhang, Li Fan, Samuel Lawrence, Shi Li
Abstract: Foundation models in healthcare have largely adopted self supervised pretraining objectives inherited from natural language processing and computer vision, emphasizing reconstruction and large scale representation learning prior to downstream adaptation. We revisit this paradigm in outcome centric clinical prediction settings and argue that, when high quality supervision is available, direct outcome alignment may provide a stronger inductive bias than generative pretraining. We propose a supervised deep learning framework that explicitly shapes representation geometry by maximizing inter class separation relative to within class variance, thereby concentrating model capacity along clinically meaningful axes. Across multiple longitudinal electronic health record tasks, including mortality and readmission prediction, our approach consistently outperforms masked, autoregressive, and contrastive pretraining baselines under matched model capacity. The proposed method improves discrimination, calibration, and sample efficiency, while simplifying the training pipeline to a single stage optimization. These findings suggest that in low entropy, outcome driven healthcare domains, supervision can act as the statistically optimal driver of representation learning, challenging the assumption that large scale self supervised pretraining is a prerequisite for strong clinical performance.
Authors: Arun Vignesh Malarkkan, Xinyuan Wang, Kunpeng Liu, Denghui Zhang, Yanjie Fu
Abstract: Feature selection is fundamental to robust data-centric AI, but most existing methods optimize predictive performance under a single data distribution. This often selects spurious features that fail under distribution shifts. Motivated by principles from causal invariance, we study feature selection from a stability perspective and introduce Causally-Guided Diffusion for Stable Feature Selection (CGDFS). In CGDFS, we formalized feature selection as approximate posterior inference over feature subsets, whose posterior mass favors low prediction error and low cross-environment variance. Our framework combines three key insights: First, we formulate feature selection as stability-aware posterior sampling. Here, causal invariance serves as a soft inductive bias rather than explicit causal discovery. Second, we train a diffusion model as a learned prior over plausible continuous selection masks, combined with a stability-aware likelihood that rewards invariance across environments. This diffusion prior captures structural dependencies among features and enables scalable exploration of the combinatorially large selection space. Third, we perform guided annealed Langevin sampling that combines the diffusion prior with the stability objective, which yields a tractable, uncertainty-aware posterior inference that avoids discrete optimization and produces robust feature selections. We evaluate CGDFS on open-source real-world datasets exhibiting distribution shifts. Across both classification and regression tasks, CGDFS consistently selects more stable and transferable feature subsets, which leads to improved out-of-distribution performance and greater selection robustness compared to sparsity-based, tree-based, and stability-selection baselines.
Authors: Jason Dury
Abstract: The Predictive Associative Memory (PAM) framework posits that useful relationships often connect items that co-occur in shared contexts rather than items that appear similar in embedding space. A contrastive MLP trained on co-occurrence annotations--Contrastive Association Learning (CAL)--has improved multi-hop passage retrieval and discovered narrative function at corpus scale in text. We test whether this principle transfers to molecular biology, where protein-protein interactions provide functional associations distinct from gene expression similarity. Four experiments across two biological domains map the operating envelope. On gene perturbation data (Replogle K562 CRISPRi, 2,285 genes), CAL trained on STRING protein interactions achieves cross-boundary AUC of 0.908 where expression similarity scores 0.518. A second gene dataset (DepMap, 17,725 genes) confirms the result after negative sampling correction, reaching cross-boundary AUC of 0.947. Two drug sensitivity experiments produce informative negatives that sharpen boundary conditions. Three cross-domain findings emerge: (1) inductive transfer succeeds in biology--a node-disjoint split with unseen genes yields AUC 0.826 (Delta +0.127)--where it fails in text (+/-0.10), suggesting physically grounded associations are more transferable than contingent co-occurrences; (2) CAL scores anti-correlate with interaction degree (Spearman r = -0.590), with gains concentrating on understudied genes with focused interaction profiles; (3) tighter association quality outperforms larger but noisier training sets, reversing the text pattern. Results are stable across training seeds (SD < 0.001) and cross-boundary threshold choices.
Authors: Bhavya Vasudeva, Puneesh Deora, Alberto Bietti, Vatsal Sharan, Christos Thrampoulidis
Abstract: Transformer-based language models excel at in-context learning (ICL), where they can adapt to new tasks based on contextual examples, without parameter updates. In a specific form of ICL, which we refer to as \textit{contextual recall}, models pretrained on open-ended text leverage pairwise examples to recall specific facts in novel prompt formats. We investigate whether contextual recall emerges from pretraining alone, what finetuning is required, and what mechanisms drive the necessary representations. For this, we introduce a controlled synthetic framework where pretraining sequences consist of subject-grammar-attribute tuples, with attribute types tied to grammar statistics. We demonstrate that while such pretraining successfully yields factual knowledge, it is insufficient for contextual recall: models fail to implicitly infer attribute types when the grammar statistics are removed in ICL prompts. However, we show that finetuning on tasks requiring implicit inference, distinct from the ICL evaluation, using a subset of subjects, triggers the emergence of contextual recall across all subjects. This transition is accompanied by the formation of low-dimensional latent encodings of the shared attribute type. For mechanistic insight, we derive a construction for an attention-only transformer that replicates the transition from factual to contextual recall, corroborated by empirical validation.
Authors: Abed K. Musaffar, Ambuj Singh, Francesco Bullo
Abstract: Large language models (LLMs) are increasingly deployed in human-AI teams as support agents for complex tasks such as information retrieval, programming, and decision-making assistance. While these agents' autonomy and contextual knowledge enables them to be useful, it also exposes them to a broad range of attacks, including data poisoning, prompt injection, and even prompt engineering. Through these attack vectors, malicious actors can manipulate an LLM agent to provide harmful information, potentially manipulating human agents to make harmful decisions. While prior work has focused on LLMs as attack targets or adversarial actors, this paper studies their potential role as defensive supervisors within mixed human-AI teams. Using a dataset consisting of multi-party conversations and decisions for a real human-AI team over a 25 round horizon, we formulate the problem of malicious behavior detection from interaction traces. We find that LLMs are capable of identifying malicious behavior in real-time, and without task-specific information, indicating the potential for task-agnostic defense. Moreover, we find that the malicious behavior of interest is not easily identified using simple heuristics, further suggesting the introduction of LLM defenders could render human teams more robust to certain classes of attack.
Authors: Valentina Kuskova, Dmitry Zaytsev, Michael Coppedge
Abstract: Time-varying causal models provide a powerful framework for studying dynamic scientific systems, yet most existing approaches assume that the underlying causal network is known a priori - an assumption rarely satisfied in real-world domains where causal structure is uncertain, evolving, or only indirectly observable. This limits the applicability of dynamic causal inference in many scientific settings. We propose Dynamic Causal Network Autoregression (DCNAR), a two-stage neural causal modeling framework that integrates data-driven causal discovery with time-varying causal inference. In the first stage, a neural autoregressive causal discovery model learns a sparse directed causal network from multivariate time series. In the second stage, this learned structure is used as a structural prior for a time-varying neural network autoregression, enabling dynamic estimation of causal influence without requiring pre-specified network structure. We evaluate the scientific validity of DCNAR using behavioral diagnostics that assess causal necessity, temporal stability, and sensitivity to structural change, rather than predictive accuracy alone. Experiments on multi-country panel time-series data demonstrate that learned causal networks yield more stable and behaviorally meaningful dynamic causal inferences than coefficient-based or structure-free alternatives, even when forecasting performance is comparable. These results position DCNAR as a general framework for using AI as a scientific instrument for dynamic causal reasoning under structural uncertainty.
Authors: Frithjof Gressmann, Ivan Georgiev Raikov, Seung Hyun Kim, Mattia Gazzola, Lawrence Rauchwerger, Ivan Soltesz
Abstract: Biophysical neural system simulations are among the most computationally demanding scientific applications, and their optimization requires navigating high-dimensional parameter spaces under numerous constraints that impose a binary feasible/infeasible partition with no gradient signal to guide the search. Here, we introduce DMOSOPT, a scalable optimization framework that leverages a unified, jointly learned surrogate model to capture the interplay between objectives, constraints, and parameter sensitivities. By learning a smooth approximation of both the objective landscape and the feasibility boundary, the joint surrogate provides a unified gradient that simultaneously steers the search toward improved objective values and greater constraint satisfaction, while its partial derivatives yield per-parameter sensitivity estimates that enable more targeted exploration. We validate the framework from single-cell dynamics to population-level network activity, spanning incremental stages of a neural circuit modeling workflow, and demonstrate efficient, effective optimization of highly constrained problems at supercomputing scale with substantially fewer problem evaluations. While motivated by and demonstrated in the context of computational neuroscience, the framework is general and applicable to constrained multi-objective optimization problems across scientific and engineering domains.
Authors: Emil Albrychiewicz, Andr\'es Franco Valiente, Li-Ching Chen, Viola Zixin Zhao
Abstract: Recent theoretical models of diffusion processes, conceptualized as coupled Ornstein-Uhlenbeck systems, predict a hierarchy of interaction timescales, and consequently, the existence of a synchronization gap between modes that commit at different stages of the reverse process. However, because these predictions rely on continuous time and analytically tractable score functions, it remains unclear how this phenomenology manifests in the deep, discrete architectures deployed in practice. In this work, we investigate how the synchronization gap is mechanistically realized within pretrained Diffusion Transformers (DiTs). We construct an explicit architectural realization of replica coupling by embedding two generative trajectories into a joint token sequence, modulated by a symmetric cross attention gate with variable coupling strength g. Through a linearized analysis of the attention difference, we show that the replica interaction decomposes mechanistically. We empirically validate our theoretical framework on a pretrained DiT-XL/2 model by tracking commitment and per layer internal mode energies. Our results reveal that: (1) the synchronization gap is an intrinsic architectural property of DiTs that persists even when external coupling is turned off; (2) as predicted by our spatial routing bounds, the gap completely collapses under strong coupling; (3) the gap is strictly depth localized, emerging sharply only within the final layers of the Transformer; and (4) global, low frequency structures consistently commit before local, high frequency details. Ultimately, our findings provide a mechanistic interpretation of how Diffusion Transformers resolve generative ambiguity, isolating speciation transitions to the terminal layers of the network.
Authors: Abhinaba Basu
Abstract: A single matrix out of 468 in GPT-2 Small can increase perplexity by 20,000x when compressed, revealing that transformer compression sensitivity spans five orders of magnitude. We map this sensitivity landscape across five architectures (117M-8B parameters), finding a consistent hierarchy: early-layer MLP up-projections are catastrophically sensitive while value projections compress nearly for free. This hierarchy is stable across compression levels, evaluation scales (2K-51K tokens), and datasets (WikiText-103, C4). Using Lyapunov stability theory, we show that residual connections contract compression errors by growing the hidden state faster than the error. Error contraction is necessary but not sufficient for compression tolerance: architecture-specific redundancy plays an equally important role, as demonstrated by the hybrid LFM2-2.6B degrading only 7x despite higher amplification than the fully-contracting GPT-2 Small (120x). Ten machine-checked Lean 4 theorems formalize per-matrix error bounds with no sorry markers; all bounds produce zero violations across 14,040+ configurations. We validate with downstream task evaluation (HellaSwag, ARC-Easy, Winogrande), activation-aware pruning on two architectures, and a Compression Fragility Index that rank-orders model robustness.
Authors: Yuma Aoki, Joon Park, Koh Takeuchi, Hisashi Kashima, Shinya Akimoto, Ryuichi Hashimoto, Takahiro Adachi, Takeshi Kishikawa, Takamitsu Sasaki
Abstract: This study addresses an important gap in time series outlier detection by proposing a novel problem setting: long-term outlier prediction. Conventional methods primarily focus on immediate detection by identifying deviations from normal patterns. As a result, their applicability is limited when forecasting outlier events far into the future. To overcome this limitation, we propose a simple and unsupervised two-layer method that is independent of specific models. The first layer performs standard outlier detection, and the second layer predicts future outlier scores based on the temporal structure of previously observed outliers. This framework enables not only pointwise detection but also long-term forecasting of outlier likelihoods. Experiments on synthetic datasets show that the proposed method performs well in both detection and prediction tasks. These findings suggest that the method can serve as a strong baseline for future work in outlier detection and forecasting.
Authors: Abhinaba Basu
Abstract: We identify a routing paradox in hybrid recurrent-attention architectures: content-based routing - deciding which tokens deserve expensive attention - requires exactly the pairwise computation that routing is designed to avoid. Through 20+ controlled experiments across three tasks (a synthetic diagnostic, the Zoology MQAR benchmark, and HotpotQA), we map the routing landscape exhaustively. One layer of softmax attention creates a latent ~34-dimensional subspace enabling 98.4% routing precision; zero layers yield 1.2%. This subspace is invisible to cosine similarity, destroyed by random projections (98.4% to 2.6%), and cannot be created by contrastive pretraining - proving attention's role is writing pairwise match results into representations, not merely computing them. Twelve alternative mechanisms all cluster at 15-29%. Non-learned indices (Bloom filter: 90.9%; BM25 on HotpotQA: 82.7%) bypass the bottleneck entirely. The result is a sharp two-regime hierarchy with an empty middle ground. These findings provide the mechanistic explanation for the empirical observation that recurrent models fail at associative recall, and reframe attention as a representation constructor rather than merely a computation mechanism.
Authors: Florent Draye, Abir Harrasse, Vedant Palit, Tung-Yu Wu, Jiarui Liu, Punya Syon Pandey, Roderick Wu, Terry Jingchen Zhang, Zhijing Jin, Bernhard Sch\"olkopf
Abstract: Mechanistic interpretability seeks to understand how Large Language Models (LLMs) represent and process information. Recent approaches based on dictionary learning and transcoders enable representing model computation in terms of sparse, interpretable features and their interactions, giving rise to feature attribution graphs. However, these graphs are often large and redundant, limiting their interpretability in practice. Cross-Layer Transcoders (CLTs) address this issue by sharing features across layers while preserving layer-specific decoding, yielding more compact representations, but remain difficult to train and analyze at scale. We introduce an open-source library for end-to-end training and interpretability of CLTs. Our framework integrates scalable distributed training with model sharding and compressed activation caching, a unified automated interpretability pipeline for feature analysis and explanation, attribution graph computation using Circuit-Tracer, and a flexible visualization interface. This provides a practical and unified solution for scaling CLT-based mechanistic interpretability. Our code is available at: https://github.com/LLM-Interp/CLT-Forge.
Authors: Minh Triet Pham, Quynh Chi Dang, Le Nhat Tan
Abstract: Indoor localization systems in care facilities enable optimization of staff allocation, workload management, and quality of care delivery. Traditional machine learning approaches to Bluetooth Low Energy (BLE)-based localization treat each temporal measurement as an independent observation, fundamentally limiting their performance. To address this limitation, this paper introduces Deep Attention-based Sequential Ensemble Learning (DASEL), a novel framework that reconceptualizes indoor localization as a sequential learning problem. The framework integrates frequency-based feature engineering, bidirectional GRU networks with attention mechanisms, multi-directional sliding windows, and confidence-weighted temporal smoothing to capture human movement trajectories. Evaluated on real-world data from a care facility using 4-fold temporal cross-validation, DASEL achieves a macro F1 score of 0.4438, representing a 53.1% improvement over the best traditional baseline (0.2898).
Authors: Ali Akram
Abstract: The automotive industry is under growing pressure to reduce its environmental impact, requiring accurate predictive modeling to support sustainable engineering design. This study examines the factors that determine vehicle fuel consumption from the seminal Motor Trend dataset, identifying the governing physical factors of efficiency through rigorous quantitative analysis. Methodologically, the research uses data sanitization, statistical outlier elimination, and in-depth Exploratory Data Analysis (EDA) to curb the occurrence of multicollinearity between powertrain features. A comparative analysis of machine learning paradigms including Multiple Linear Regression, Support Vector Machines (SVM), and Logistic Regression was carried out to assess predictive efficacy. Findings indicate that SVM Regression is most accurate on continuous prediction (R-squared = 0.889, RMSE = 0.326), and is effective in capturing the non-linear relationships between vehicle mass and engine displacement. In parallel, Logistic Regression proved superior for classification (Accuracy = 90.8%) and showed exceptional recall (0.957) when identifying low-efficiency vehicles. These results challenge the current trend toward black-box deep learning architectures for static physical datasets, providing validation of robust performance by interpretable and well-tuned classical models. The research finds that intrinsic vehicle efficiency is fundamentally determined by physical design parameters, weight and displacement, offering a data-driven framework for how manufacturers should focus on lightweighting and engine downsizing to achieve stringent global sustainability goals.
Authors: Khawja Imran Masud, Venkata Sai Rahul Unnam, Sahara Ali
Abstract: Accurate air quality index (AQI) forecasting is essential for the protecting public health in rapidly growing urban regions, and the practical model evaluation and selection are often challenged by the lack of rigorous, region-specific benchmarking on standardized datasets. Physics-guided machine learning and deep learning models could be a good and effective solution to resolve such issues with more accurate and efficient AQI forecasting. This research study presents an explainable and comprehensive benchmark that enables a guideline and proposed physics-guided best model by benchmarking classical time-series, machine-learning, and deep-learning approaches for multi-horizon AQI forecasting in North Texas (Dallas County). Using publicly available U.S. Environmental Protection Agency (EPA) daily observations of air quality data from 2022 to 2024, we curate city-level time series for PM2.5 and O3 by aggregating station measurements and constructing lag-wise forecasting datasets for LAG in {1,7,14,30} days. For benchmarking the best model, linear regression (LR), SARIMAX, multilayer perceptrons (MLP), and LSTM networks are evaluated with the proposed physics-guided variants (MLP+Physics and LSTM+Physics) that incorporate the EPA breakpoint-based AQI formulation as a consistency constraint through a weighted loss. Experiments using chronological train-test splits and error metrics MAE, RMSE showed that deep-learning models outperform simpler baselines, while physics guidance improves stability and yields physically consistent pollutant with AQI relationships, with the largest benefits observed for short-horizon prediction and for PM2.5 and O3. Overall, the results provide a practical reference for selecting AQI forecasting models in North Texas and clarify when lightweight physics constraints meaningfully improve predictive performance across pollutants and forecast horizons.
Authors: Zhipeng Zhang, Hongshun He
Abstract: Humans must flexibly arbitrate between exploring alternatives and exploiting learned strategies, yet they frequently exhibit maladaptive persistence by continuing to execute failing strategies despite accumulating negative evidence. Here we propose a ``confidence-freeze'' account that reframes such persistence as a dynamic learning state rather than a stable dispositional trait. Using a multi-reversal two-armed bandit task across three experiments (total N = 332; 19,920 trials), we first show that human learners normally make use of the symmetric statistical structure inherent in outcome trajectories: runs of successes provide positive evidence for environmental stability and thus for strategy maintenance, whereas runs of failures provide negative evidence and should raise switching probability. Behaviour in the control group conformed to this normative pattern. However, individuals who experienced a high rate of early success (90\% vs.\ 60\%) displayed a robust and selective distortion after the first reversal: they persisted through long stretches of non-reward (mean = 6.2 consecutive losses) while their metacognitive confidence ratings simultaneously dropped from 5 to 2 on a 7-point scale.
Authors: Bing Wang, Ximing Li, Changchun Li, Jinjin Chi, Tianze Li, Renchu Guan, Shengsheng Wang
Abstract: Nowadays, the widespread dissemination of misinformation across numerous social media platforms has led to severe negative effects on society. To address this challenge, the automatic detection of misinformation, particularly under multimedia scenarios, has gained significant attention from both academic and industrial communities, leading to the emergence of a research task known as Multimodal Misinformation Detection (MMD). Typically, current MMD approaches focus on capturing the semantic relationships and inconsistency between various modalities but often overlook certain critical indicators within multimodal content. Recent research has shown that manipulated features within visual content in social media articles serve as valuable clues for MMD. Meanwhile, we argue that the potential intentions behind the manipulation, e.g., harmful and harmless, also matter in MMD. Therefore, in this study, we aim to identify such multimodal misinformation by capturing two types of features: manipulation features, which represent if visual content has been manipulated, and intention features, which assess the nature of these manipulations, distinguishing between harmful and harmless intentions. Unfortunately, the manipulation and intention labels that supervise these features to be discriminative are unknown. To address this, we introduce two weakly supervised indicators as substitutes by incorporating supplementary datasets focused on image manipulation detection and framing two different classification tasks as positive and unlabeled learning issues. With this framework, we introduce an innovative MMD approach, titled Harmful Visual Content Manipulation Matters in MMD (HAVC-M4 D). Comprehensive experiments conducted on four prevalent MMD datasets indicate that HAVC-M4 D significantly and consistently enhances the performance of existing MMD methods.
Authors: Changchun Li, Ximing Li, Bingjie Zhang, Wenting Wang, Jihong Ouyang
Abstract: Semi-Supervised Text Classification (SSTC) mainly works under the spirit of self-training. They initialize the deep classifier by training over labeled texts; and then alternatively predict unlabeled texts as their pseudo-labels and train the deep classifier over the mixture of labeled and pseudo-labeled texts. Naturally, their performance is largely affected by the accuracy of pseudo-labels for unlabeled texts. Unfortunately, they often suffer from low accuracy because of the margin bias problem caused by the large difference between representation distributions of labels in SSTC. To alleviate this problem, we apply the angular margin loss, and perform several Gaussian linear transformations to achieve balanced label angle variances, i.e., the variance of label angles of texts within the same label. More accuracy of predicted pseudo-labels can be achieved by constraining all label angle variances balanced, where they are estimated over both labeled and pseudo-labeled texts during self-training loops. With this insight, we propose a novel SSTC method, namely Semi-Supervised Text Classification with Balanced Deep representation Distributions (S2TC-BDD). We implement both multi-class classification and multi-label classification versions of S2TC-BDD by introducing some pseudo-labeling tricks and regularization terms. To evaluate S2 TC-BDD, we compare it against the state-of-the-art SSTC methods. Empirical results demonstrate the effectiveness of S2 TC-BDD, especially when the labeled texts are scarce.
Authors: Tasmay Pankaj Tibrewal, Pritish Saha, Ankit Meda, Kunal Singh, Pradeep Moturi
Abstract: Transformers lack an explicit architectural mechanism for storing and organizing knowledge acquired during training. We introduce learnable sparse memory banks: a set of latent tokens, randomly initialized and trained end-to-end, that transformer layers query via cross-attention to retrieve stored knowledge. To scale memory capacity without prohibitive attention costs, we propose chapter-based routing inspired by Mixture-of-Experts architectures, partitioning the memory bank into chapters and training a router to select relevant subsets per input. This enables scaling to 262K memory tokens while maintaining tractable computation. We evaluate our approach against standard transformers (in iso-FLOP settings) on pre-training and instruction fine-tuning across relevant benchmarks. Our models surpass iso-FLOP baselines suggesting scope for a new axis of scaling, demonstrating that explicit associative memory provides complementary capacity to what is captured implicitly in model parameters. Additionally, we observe improved knowledge retention under continued training, with robustness to forgetting when transitioning between training phases (e.g., pretraining to instruction fine-tuning).
Authors: Xu Li, Yi Zheng, Yuxuan Liang, Zhe Liu, Xiaolei Chen, Haotian Chen, Rui Zhu, Xiangyang Xue
Abstract: Large Vision-Language Models (LVLMs) rely on dense visual tokens to capture fine-grained visual information, but processing all these tokens incurs substantial computational and memory overhead during inference. To address this issue, we propose ResPrune, a training-free visual token pruning framework that enables efficient LVLM inference by selecting a compact yet informative subset of visual tokens. ResPrune formulates visual token pruning as a subspace reconstruction problem and employs a greedy subspace expansion strategy guided by residual energy, allowing it to preserve the geometric structure of the original visual token space. To further incorporate cross modal alignment, the selection process is conditioned on textual relevance, encouraging the retention of tokens that are both informative and instruction-relevant. The proposed method is lightweight and model-agnostic, and can be seamlessly integrated into existing LVLM pipelines without retraining or architectural modifications. Extensive experiments on multiple LVLM backbones, including LLaVA-1.5, LLaVA-NeXT, and Qwen2.5-VL, demonstrate that ResPrune consistently outperforms existing pruning approaches across a wide range of benchmarks, while achieving effective reductions in computation, memory consumption, and inference latency.
Authors: Long Xu, Junping Guo, Jianbo Zhao, Jianbo Lu, Yuzhong Peng
Abstract: Molecular property prediction constitutes a cornerstone of drug discovery and materials science, necessitating models capable of disentangling complex structure-property relationships across diverse molecular modalities. Existing approaches frequently exhibit entangled representations--conflating structural, chemical, and functional factors--thereby limiting interpretability and transferability. Furthermore, conventional methods inadequately exploit complementary information from graphs, sequences, and geometries, often relying on naive concatenation that neglects inter-modal dependencies. In this work, we propose DMMRL, which employs variational autoencoders to disentangle molecular representations into shared (structure-relevant) and private (modality-specific) latent spaces, enhancing both interpretability and predictive performance. The proposed variational disentanglement mechanism effectively isolates the most informative features for property prediction, while orthogonality and alignment regularizations promote statistical independence and cross-modal consistency. Additionally, a gated attention fusion module adaptively integrates shared representations, capturing complex inter-modal relationships. Experimental validation across seven benchmark datasets demonstrates DMMRL's superior performance relative to state-of-the-art approaches. The code and data underlying this article are freely available at https://github.com/xulong0826/DMMRL.
Authors: Tianhao Ma, Ximing Li, Changchun Li, Renchu Guan
Abstract: Learning from Label Proportions (LLP) is a weakly supervised problem in which the training data comprise bags, that is, groups of instances, each annotated only with bag-level class label proportions, and the objective is to learn a classifier that predicts instance-level labels. This setting is widely applicable when privacy constraints limit access to instance-level annotations or when fine-grained labeling is costly or impractical. In this work, we introduce a method that leverages Dual proportion Constraints (LLP-DC) during training, enforcing them at both the bag and instance levels. Specifically, the bag-level training aligns the mean prediction with the given proportion, and the instance-level training aligns hard pseudo-labels that satisfy the proportion constraint, where a minimum-cost maximum-flow algorithm is used to generate hard pseudo-labels. Extensive experimental results across various benchmark datasets empirically validate that LLP-DC consistently improves over previous LLP methods across datasets and bag sizes. The code is publicly available at https://github.com/TianhaoMa5/CV PR2026_Findings_LLP_DC.
Authors: Rahul D Ray
Abstract: Epistemic intelligence requires machine learning systems to recognise the limits of their own knowledge and act safely under uncertainty, especially when faced with unknown unknowns. Existing uncertainty quantification methods rely on a single signal such as confidence or density and fail to detect diverse structural anomalies. We introduce SPECTRE-G2, a multi-signal anomaly detector that combines eight complementary signals from a dual-backbone neural network. The architecture includes a spectral normalised Gaussianization encoder, a plain MLP preserving feature geometry, and an ensemble of five models. These produce density, geometry, uncertainty, discriminative, and causal signals. Each signal is normalised using validation statistics and calibrated with synthetic out-of-distribution data. An adaptive top-k fusion selects the most informative signals and averages their scores. Experiments on synthetic, Adult, CIFAR-10, and Gridworld datasets show strong performance across diverse anomaly types, outperforming multiple baselines on AUROC, AUPR, and FPR95. The model is stable across seeds and particularly effective for detecting new variables and confounders. SPECTRE-G2 provides a practical approach for detecting unknown unknowns in open-world settings.
Authors: Chen Zhang, Yuxin Cheng, Chenchen Ding, Shuqi Wang, Jingreng Lei, Runsheng Yu, Yik-Chung WU, Ngai Wong
Abstract: Zeroth-order (ZO) optimization enables memory-efficient training of neural networks by estimating gradients via forward passes only, eliminating the need for backpropagation. However, the stochastic nature of gradient estimation significantly obscures the training dynamics, in contrast to the well-characterized behavior of first-order methods under Neural Tangent Kernel (NTK) theory. To address this, we introduce the Neural Zeroth-order Kernel (NZK) to describe model evolution in function space under ZO updates. For linear models, we prove that the expected NZK remains constant throughout training and depends explicitly on the first and second moments of the random perturbation directions. This invariance yields a closed-form expression for model evolution under squared loss. We further extend the analysis to linearized neural networks. Interpreting ZO updates as kernel gradient descent via NZK provides a novel perspective for potentially accelerating convergence. Extensive experiments across synthetic and real-world datasets (including MNIST, CIFAR-10, and Tiny ImageNet) validate our theoretical results and demonstrate acceleration when using a single shared random vector.
Authors: Elif Ceren Gok Yildirim, Murat Onur Yildirim, Joaquin Vanschoren
Abstract: The continual learning literature has rapidly shifted from traditional class incremental learning (CIL) techniques to foundation model (FM)-based CIL methods without a clear understanding of how these newer approaches compare to strong, lightweight convolutional baselines. This abrupt transition has created a substantial methodological gap, making it difficult to assess whether recent FM-based CIL progress reflects genuine advances or merely the absence of rigorous baselines. To address this gap, we introduce Pruned Adaptation Modules (PAM), a simple yet effective method that freezes the vast majority of the pre-trained ResNet while enabling scalable continual adaptation through sparse task-specific layers. PAM yields up to a ~5x reduction in trainable parameters and a ~6x reduction in total parameters, significantly reducing the cost of continual updates. Across diverse benchmarks, PAM consistently mitigates catastrophic forgetting and outperforms state-of-the-art FM-based CIL approaches. Our findings position PAM as a strong and transparent baseline that helps bridge the gap between traditional and FM-based CIL, guiding future research for a more accurate assessment of true progress in continual adaptation. The code can be found at: https://github.com/ElifCerenGokYildirim/PAM.
Authors: Zhiqiang He
Abstract: This paper investigates the fundamental mechanisms driving plasticity loss in deep reinforcement learning (RL), a critical challenge where neural networks lose their ability to adapt to non-stationary environments. While existing research often relies on descriptive metrics like dormant neurons or effective rank, these summaries fail to explain the underlying optimization dynamics. We propose the Optimization-Centric Plasticity (OCP) hypothesis, which posits that plasticity loss arises because optimal points from previous tasks become poor local optima for new tasks, trapping parameters during task transitions and hindering subsequent learning. We theoretically establish the equivalence between neuron dormancy and zero-gradient states, demonstrating that the absence of gradient signals is the primary driver of dormancy. Our experiments reveal that plasticity loss is highly task-specific; notably, networks with high dormancy rates in one task can achieve performance parity with randomly initialized networks when switched to a significantly different task, suggesting that the network's capacity remains intact but is inhibited by the specific optimization landscape. Furthermore, our hypothesis elucidates why parameter constraints mitigate plasticity loss by preventing deep entrenchment in local optima. Validated across diverse non-stationary scenarios, our findings provide a rigorous optimization-based framework for understanding and restoring network plasticity in complex RL domains.
Authors: Kwanyoung Kim, Byeongsu Sim
Abstract: Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models with human preferences, inspiring the development of reward-centric diffusion reinforcement learning (RDRL) to achieve similar alignment and controllability. While diffusion models can generate high-quality outputs, RDRL remains susceptible to reward hacking, where the reward score increases without corresponding improvements in perceptual quality. We demonstrate that this vulnerability arises from the non-robustness of reward model gradients, particularly when the reward landscape with respect to the input image is sharp. To mitigate this issue, we introduce methods that exploit gradients from a robustified reward model without requiring its retraining. Specifically, we employ gradients from a flattened reward model, obtained through parameter perturbations of the diffusion model and perturbations of its generated samples. Empirically, each method independently alleviates reward hacking and improves robustness, while their joint use amplifies these benefits. Our resulting framework, RSA-FT (Reward Sharpness-Aware Fine-Tuning), is simple, broadly compatible, and consistently enhances the reliability of RDRL.
Authors: Andrei Baroian, Rutger Berger
Abstract: Reinforcement learning with verifiable rewards (RLVR) plays a crucial role in expanding the capacities of LLM reasoning, but GRPO-style training is dominated by expensive rollouts and wastes compute on unusable prompts. We propose Prompt Replay, an overhead-free online data selection method for GRPO that reuses prompts only (not trajectories), to preserve on-policy optimization. After each step, we insert prompts with medium difficulty into a buffer, and prioritize prompts closer to a pass rate of 0.5 (half answers correct, half wrong) to maximize the advantage, thus learning signal. Training batches are formed by mixing reused prompts with fresh samples, with cooldown steps and max reuse times controlling aggressiveness vs risk of overfitting. Across multiple model families (Llama-3.2- 3B, Qwen3-8B) and training datasets (Dolci, Polaris), evaluated using average accuracy on six standard math benchmarks, Prompt Replay reduces zero-variance prompts, increases mean absolute advantage and shows faster initial accuracy gains. Yet, it plateaus and converges with the baseline, as too aggressive configuration was used. The method is most efficient when the rollouts are the primary bottleneck and the dataset is difficult for the model. We additionally observe that Qwen2.5-Math can exhibit spurious-reward effects that invalidates ablations, raising a warning signal for using it as a sole testbed for GRPO method research.
Authors: Foo Hui-Mean, Yuan-chin I Chang
Abstract: Sequential experimental design under expensive, gradient-free objectives is a central challenge in computational statistics: evaluation budgets are tightly constrained and information must be extracted efficiently from each observation. We propose \textbf{ALMAB-DC}, a GP-based sequential design framework combining active learning, multi-armed bandits (MAB), and distributed asynchronous computing for expensive black-box experimentation. A Gaussian process surrogate with uncertainty-aware acquisition identifies informative query points; a UCB or Thompson-sampling bandit controller allocates evaluations across parallel workers; and an asynchronous scheduler handles heterogeneous runtimes. We present cumulative regret bounds for the bandit components and characterize parallel scalability via Amdahl's Law. We validate ALMAB-DC on five benchmarks. On the two statistical experimental-design tasks, ALMAB-DC achieves lower simple regret than Equal Spacing, Random, and D-optimal designs in dose--response optimization, and in adaptive spatial field estimation matches the Greedy Max-Variance benchmark while outperforming Latin Hypercube Sampling; at $K=4$ the distributed setting reaches target performance in one-quarter of sequential wall-clock rounds. On three ML/engineering tasks (CIFAR-10 HPO, CFD drag minimization, MuJoCo RL), ALMAB-DC achieves 93.4\% CIFAR-10 accuracy (outperforming BOHB by 1.7\,pp and Optuna by 1.1\,pp), reduces airfoil drag to $C_D = 0.059$ (36.9\% below Grid Search), and improves RL return by 50\% over Grid Search. All advantages over non-ALMAB baselines are statistically significant under Bonferroni-corrected Mann--Whitney $U$ tests. Distributed execution achieves $7.5\times$ speedup at $K = 16$ agents, consistent with Amdahl's Law.
Authors: Rustem Islamov, Roman Machacek, Aurelien Lucchi, Antonio Silveti-Falls, Eduard Gorbunov, Volkan Cevher
Abstract: We study the role of batch size in stochastic conditional gradient methods under a $\mu$-Kurdyka-{\L}ojasiewicz ($\mu$-KL) condition. Focusing on momentum-based stochastic conditional gradient algorithms (e.g., Scion), we derive a new analysis that explicitly captures the interaction between stepsize, batch size, and stochastic noise. Our study reveals a regime-dependent behavior: increasing the batch size initially improves optimization accuracy but, beyond a critical threshold, the benefits saturate and can eventually degrade performance under a fixed token budget. Notably, the theory predicts the magnitude of the optimal stepsize and aligns well with empirical practices observed in large-scale training. Leveraging these insights, we derive principled guidelines for selecting the batch size and stepsize, and propose an adaptive strategy that increases batch size and sequence length during training while preserving convergence guarantees. Experiments on NanoGPT are consistent with the theoretical predictions and illustrate the emergence of the predicted scaling regimes. Overall, our results provide a theoretical framework for understanding batch size scaling in stochastic conditional gradient methods and offer guidance for designing efficient training schedules in large-scale optimization.
Authors: Janne Perini, Rafael Bischof, Moab Arar, Ay\c{c}a Duran, Michael A. Kraus, Siddhartha Mishra, Bernd Bickel
Abstract: Designing urban spaces that provide pedestrian wind comfort and safety requires time-resolved Computational Fluid Dynamics (CFD) simulations, but their current computational cost makes extensive design exploration impractical. We introduce WinDiNet (Wind Diffusion Network), a pretrained video diffusion model that is repurposed as a fast, differentiable surrogate for this task. Starting from LTX-Video, a 2B-parameter latent video transformer, we fine-tune on 10,000 2D incompressible CFD simulations over procedurally generated building layouts. A systematic study of training regimes, conditioning mechanisms, and VAE adaptation strategies, including a physics-informed decoder loss, identifies a configuration that outperforms purpose-built neural PDE solvers. The resulting model generates full 112-frame rollouts in under a second. As the surrogate is end-to-end differentiable, it doubles as a physics simulator for gradient-based inverse optimization: given an urban footprint layout, we optimize building positions directly through backpropagation to improve wind safety as well as pedestrian wind comfort. Experiments on single- and multi-inlet layouts show that the optimizer discovers effective layouts even under challenging multi-objective configurations, with all improvements confirmed by ground-truth CFD simulations.
Authors: Dip Roy, Rajiv Misra, Sanjay Kumar Singh, Anisha Roy
Abstract: Although mechanism-based interpretability has generated an abundance of insight for discriminative network analysis, generative models are less understood -- particularly outside of image-related applications. We investigate how much of the causal circuitry found within image-related variational autoencoders (VAEs) will generalize to tabular data, as VAEs are increasingly used for imputation, anomaly detection, and synthetic data generation. In addition to extending a four-level causal intervention framework to four tabular and one image benchmark across five different VAE architectures (with 75 individual training runs per architecture and three random seed values for each run), this paper introduces three new techniques: posterior-calibration of Causal Effect Strength (CES), path-specific activation patching, and Feature-Group Disentanglement (FGD). The results from our experiments demonstrate that: (i) Tabular VAEs have circuits with modularity that is approximately 50% lower than their image counterparts. (ii) $\beta$-VAE experiences nearly complete collapse in CES scores when applied to heterogeneous tabular features (0.043 CES score for tabular data compared to 0.133 CES score for images), which can be directly attributed to reconstruction quality degradation (r = -0.886 correlation coefficient between CES and MSE). (iii) CES successfully captures nine of eleven statistically significant architecture differences using Holm--\v{S}id\'{a}k corrections. (iv) Interventions with high specificity predict the highest downstream AUC values (r = 0.460, p < .001). This study challenges the common assumption that architectural guidance from image-related studies can be transferred to tabular datasets.
Authors: M. Cherifi, Aude Sportisse, Xujia Zhu, Mohammed Nabil El Korso, A. Mesloub
Abstract: Missing covariate data pose a significant challenge to statistical inference and machine learning, particularly for classification tasks like logistic regression. Classical iterative approaches (EM, multiple imputation) are often computationally intensive, sensitive to high missingness rates, and limited in uncertainty propagation. Recent deep generative models based on VAEs show promise but rely on complex latent representations. We propose Amortized Variational Inference for Logistic Regression (AV-LR), a unified end-to-end framework for binary logistic regression with missing covariates. AV-LR integrates a probabilistic generative model with a simple amortized inference network, trained jointly by maximizing the evidence lower bound. Unlike competing methods, AV-LR performs inference directly in the space of missing data without additional latent variables, using a single inference network and a linear layer that jointly estimate regression parameters and the missingness mechanism. AV-LR achieves estimation accuracy comparable to or better than state-of-the-art EM-like algorithms, with significantly lower computational cost. It naturally extends to missing-not-at-random settings by explicitly modeling the missingness mechanism. Empirical results on synthetic and real-world datasets confirm its effectiveness and efficiency across various missing-data scenarios.
Authors: Zihan Fang, Qianru Wang, Haonan An, Zheng Lin, Yiqin Deng, Xianhao Chen, Yuguang Fang
Abstract: Large language models (LLMs) increasingly adopt Mixture-of-Experts (MoE) architectures to scale model capacity while reducing computation. Fine-tuning these MoE-based LLMs often requires access to distributed and privacy-sensitive data, making centralized fine-tuning impractical. Federated learning (FL) therefore provides a paradigm to collaboratively fine-tune MoE-based LLMs, enabling each client to integrate diverse knowledge without compromising data privacy. However, the integration of MoE-based LLM fine-tuning into FL encounters two critical aggregation challenges due to inherent data heterogeneity across clients: (i) divergent local data distributions drive clients to develop distinct gating preference for localized expert selection, causing direct parameter aggregation to produce a ``one-size-fits-none'' global gating network, and (ii) same-indexed experts develop disparate semantic roles across clients, leading to expert semantic blurring and the degradation of expert specialization. To address these challenges, we propose FedAlign-MoE, a federated aggregation alignment framework that jointly enforces routing consistency and expert semantic alignment. Specifically, FedAlign-MoE aggregates gating behaviors by aligning routing distributions through consistency weighting and optimizes local gating networks through distribution regularization, maintaining cross-client stability without overriding discriminative local preferences. Meanwhile, FedAlign-MoE explicitly quantifies semantic consistency among same-indexed experts across clients and selectively aggregates updates from semantically aligned clients, ensuring stable and specialized functional roles for global experts. Extensive experiments demonstrate that FedAlign-MoE outperforms state-of-the-art benchmarks, achieving faster convergence and superior accuracy in non-IID federated environments.
Authors: Soudeep Ghoshal, Sandipan Chakraborty, Pradipto Chowdhury, Himanshu Buckchash
Abstract: Machine learning techniques, such as Transformers and Long Short-Term Memory (LSTM) networks, play a crucial role in Symbolic Music Generation (SMG). Existing literature indicates a difference between LSTMs and Transformers regarding their ability to model local melodic continuity versus maintaining global structural coherence. However, their specific properties within the context of SMG have not been systematically studied. This paper addresses this gap by providing a fine-grained comparative analysis of LSTMs versus Transformers for SMG, examining local and global properties in detail using 17 musical quality metrics on the Deutschl dataset. We find that LSTM networks excel at capturing local patterns but fail to preserve long-range dependencies, while Transformers model global structure effectively but tend to produce irregular phrasing. Based on this analysis and leveraging their respective strengths, we propose a Hybrid architecture combining a Transformer Encoder with an LSTM Decoder and evaluate it against both baselines. We evaluated 1,000 generated melodies from each of the three architectures on the Deutschl dataset. The results show that the hybrid method achieves better local and global continuity and coherence compared to the baselines. Our work highlights the key characteristics of these models and demonstrates how their properties can be leveraged to design superior models. We also supported the experiments with ablation studies and human perceptual evaluations, which statistically support the findings and provide robust validation for this work.
Authors: Minjong Cheon
Abstract: Weather forecasting is a fundamental problem for protecting lives and infrastructure from high-impact atmospheric events. Recently, data-driven weather forecasting methods based on deep learning have demonstrated strong performance, often reaching accuracy levels competitive with operational numerical systems. However, many existing models rely on large-scale training regimes and compute-intensive architectures, which raises the practical barrier for academic groups with limited compute resources. Here we introduce Sonny, an efficient hierarchical transformer that achieves competitive medium-range forecasting performance while remaining feasible within reasonable compute budgets. At the core of Sonny is a two-stage StepsNet design: a narrow slow path first models large-scale atmospheric dynamics, and a subsequent full-width fast path integrates thermodynamic interactions. To stabilize medium-range rollout without an additional fine-tuning stage, we apply exponential moving average (EMA) during training. On WeatherBench2, Sonny yields robust medium-range forecast skill, remains competitive with operational baselines, and demonstrates clear advantages over FastNet, particularly at extended tropical lead times. In practice, Sonny can be trained to convergence on a single NVIDIA A40 GPU in approximately 5.5 days.
Authors: Ghifari Adam Faza, Jolan Wauters, Fabio Cuzzolin, Hans Hallez, David Moens
Abstract: In engineering, uncertainty propagation aims to characterise system outputs under uncertain inputs. For interval uncertainty, the goal is to determine output bounds given interval-valued inputs, which is critical for robust design optimisation and reliability analysis. However, standard interval propagation relies on solving optimisation problems that become computationally expensive for complex systems. Surrogate models alleviate this cost but typically replace only the evaluator within the optimisation loop, still requiring many inference calls. To overcome this limitation, we reformulate interval propagation as an interval-valued regression problem that directly predicts output bounds. We present a comprehensive study of neural network-based surrogate models, including multilayer perceptrons (MLPs) and deep operator networks (DeepONet), for this task. Three approaches are investigated: (i) naive interval propagation through standard architectures, (ii) bound propagation methods such as Interval Bound Propagation (IBP) and CROWN, and (iii) interval neural networks (INNs) with interval weights. Results show that these methods significantly improve computational efficiency over traditional optimisation-based approaches while maintaining accurate interval estimates. We further discuss practical limitations and open challenges in applying interval-based propagation methods.
Authors: Fabien Polly
Abstract: World models learn to predict future states of an environment, enabling planning and mental simulation. Current approaches default to Transformer-based predictors operating in learned latent spaces. This comes at a cost: O(N^2) computation and no explicit spatial inductive bias. This paper asks a foundational question: is self-attention necessary for predictive world modeling, or can alternative computational substrates achieve comparable or superior results? I introduce FluidWorld, a proof-of-concept world model whose predictive dynamics are governed by partial differential equations (PDEs) of reaction-diffusion type. Instead of using a separate neural network predictor, the PDE integration itself produces the future state prediction. In a strictly parameter-matched three-way ablation on unconditional UCF-101 video prediction (64x64, ~800K parameters, identical encoder, decoder, losses, and data), FluidWorld is compared against both a Transformer baseline (self-attention) and a ConvLSTM baseline (convolutional recurrence). While all three models converge to comparable single-step prediction loss, FluidWorld achieves 2x lower reconstruction error, produces representations with 10-15% higher spatial structure preservation and 18-25% more effective dimensionality, and critically maintains coherent multi-step rollouts where both baselines degrade rapidly. All experiments were conducted on a single consumer-grade PC (Intel Core i5, NVIDIA RTX 4070 Ti), without any large-scale compute. These results establish that PDE-based dynamics, which natively provide O(N) spatial complexity, adaptive computation, and global spatial coherence through diffusion, are a viable and parameter-efficient alternative to both attention and convolutional recurrence for world modeling.
Authors: James Clayton Kerce
Abstract: Linear methods for steering transformer representations, including probing, activation engineering, and concept erasure, implicitly assume the geometry of representation space is Euclidean. Park et al. [Park et al., 2026] showed that softmax induces a curved Bregman geometry whose metric tensor is the Hessian of the log-normalizer, $H({\lambda}) = Cov[{\gamma} | {\lambda}]$. Ignoring this curvature causes Euclidean steering to leak probability mass to unintended tokens. Their analysis applies at the output layer. We measure this Hessian at intermediate layers in a controlled 2x2 design crossing stream separation with per-layer supervision (vocabulary decoding loss at each layer), all at matched vocabulary and parameter count. In standard single-stream transformers, H is severely degenerate at intermediate layers (effective rank 8 in 516 dimensions). Stream separation improves conditioning by up to 22 in effective rank, even without auxiliary supervision. Per-layer supervision helps, but less. The cosine similarity between primal and dual concept directions predicts per-layer steering effectiveness on downstream tasks, with a threshold near 0.3. These results bear on the reliability of linear safety interventions, which depend on the geometry being well-conditioned at the layer where they are applied.
Authors: Eduard Kapelko
Abstract: This paper addresses the critical challenge of mesa-optimization in AI safety by providing a formal definition of agency and a framework for its analysis. Agency is conceptualized as a Continuous Representation of accumulated experience that achieves autopoiesis through a dynamic balance between curiosity (minimizing prediction error to ensure non-computability and novelty) and empowerment (maximizing the control channel's information capacity to ensure subjectivity and goal-directedness). Empirical evidence suggests that this active inference-based model successfully accounts for classical instrumental goals, such as self-preservation and resource acquisition. The analysis demonstrates that the proposed agency function is smooth and convex, possessing favorable properties for optimization. While agentic functions occupy a vanishingly small fraction of the total abstract function space, they exhibit logarithmic convergence in sparse environments. This suggests a high probability for the spontaneous emergence of agency during the training of modern, large-scale models. To quantify the degree of agency, the paper introduces a metric based on the distance between the behavioral equivalents of a given system and an "ideal" agentic function within the space of canonicalized rewards (STARC). This formalization provides a concrete apparatus for classifying and detecting mesa-optimizers by measuring their proximity to an ideal agentic objective, offering a robust tool for analyzing and identifying undesirable inner optimization in complex AI systems.
Authors: Jaber Jaber, Osama Jaber
Abstract: Writing high-performance GPU kernels is among the most labor-intensive tasks in machine learning systems engineering. We present AutoKernel, an open-source framework that applies an autonomous agent loop to GPU kernel optimization for arbitrary PyTorch models. Given a model, AutoKernel profiles it to identify computational bottlenecks, ranks them by Amdahl's law impact, and iteratively refines Triton or CUDA C++ kernel implementations through hundreds of experiments without human intervention. A five-stage correctness harness covering smoke tests, shape sweeps, numerical stability, determinism verification, and edge-case coverage ensures every candidate kernel is validated before any speedup is recorded. The system comprises over 9,000 lines of Python, 18 starter kernel implementations across two backends, a six-tier optimization playbook, and integration with the KernelBench benchmark suite. AutoKernel covers nine kernel types spanning the dominant operations in modern transformer architectures. On an NVIDIA H100, our Triton kernels outperform both PyTorch eager and torch.compile (max-autotune) on the majority of tested configurations: 5.29x over eager on RMSNorm, 2.82x on softmax, and 2.21x on cross-entropy, while beating torch.compile by 2.83x, 3.44x, and 2.94x respectively. In community deployment, an AutoKernel-optimized kernel achieved first place on the vectorsum_v2 B200 leaderboard. The full system is available at https://github.com/RightNow-AI/autokernel.
Authors: Huamin Chen, Xunzhuo Liu, Bowei He, Fuyuan Lyu, Yankai Chen, Xue Liu, Yuhan Liu, Junchen Jiang
Abstract: Over the past year, the vLLM Semantic Router project has released a series of work spanning: (1) core routing mechanisms -- signal-driven routing, context-length pool routing, router performance engineering, policy conflict detection, low-latency embedding models, category-aware semantic caching, user-feedback-driven routing adaptation, hallucination detection, and hierarchical content-safety classification for privacy and jailbreak protection; (2) fleet optimization -- fleet provisioning and energy-efficiency analysis; (3) agentic and multimodal routing -- multimodal agent routing, tool selection, CUA security, and multi-turn context memory and safety; (4) governance and standards -- inference routing protocols and multi-provider API extensions. Each paper tackled a specific problem in LLM inference, but the problems are not independent; for example, fleet provisioning depends on the routing policy, which depends on the workload mix, shifting as organizations adopt agentic and multimodal workloads. This paper distills those results into the Workload-Router-Pool (WRP) architecture, a three-dimensional framework for LLM inference optimization. Workload characterizes what the fleet serves (chat vs. agent, single-turn vs. multi-turn, warm vs. cold, prefill-heavy vs. decode-heavy). Router determines how each request is dispatched (static semantic rules, online bandit adaptation, RL-based model selection, quality-aware cascading). Pool defines where inference runs (homogeneous vs. heterogeneous GPU, disaggregated prefill/decode, KV-cache topology). We map our prior work onto a 3x3 WRP interaction matrix, identify which cells we have covered and which remain open, and propose twenty-one concrete research directions at the intersections, each grounded in our prior measurements, tiered by maturity from engineering-ready to open research.
Authors: Jaber Jaber, Osama Jaber
Abstract: Large language models run every token through every layer, regardless of difficulty. We present TIDE, a post-training system that attaches tiny learned routers at periodic checkpoint layers and, at inference time, selects the earliest layer whose hidden state has converged for each token. TIDE requires no model retraining, works with any HuggingFace causal LM, auto-detects GPU architecture, and supports float32, float16, and bfloat16 through fused CUDA kernels. On an NVIDIA A100 with DeepSeek R1 Distill 8B, TIDE achieves 100% prefill exit rate (5% of tokens exit at layer 11, the remaining at layer 31), reduces prefill latency by 7.2%, and increases single-batch throughput by 6.6%. During autoregressive decoding, 98-99% of tokens exit early while the model correctly solves a multi-step math problem with 95 unique output tokens. On Qwen3 8B (36 layers), throughput improves by 8.1% at batch size 8. Calibration on 2,000 WikiText samples takes under 3 minutes and produces a ~4 MB router checkpoint. The system comprises 1,308 lines of Python and 1,081 lines of CUDA/C++ with 74 passing tests. Code: https://github.com/RightNow-AI/TIDE
Authors: Pawel Batorski, Paul Swoboda
Abstract: In-context learning (ICL) adapts large language models by conditioning on a small set of ICL examples, avoiding costly parameter updates. Among other factors, performance is often highly sensitive to the ordering of the examples. However, exhaustive search over the $n!$ possible orderings is infeasible. Therefore more efficient ordering methods use model confidence measures (e.g., label-probability entropy) over label sets or take a direct approach to finding the best ordering. We propose PLR, a probabilistic approach to in-context example ordering that replaces discrete ordering search with learning a probability distribution over orderings with the Plackett-Luce model. PLR models orderings using a Plackett-Luce distribution and iteratively updates its parameters to concentrate probability mass on high-performing orderings under a task-level metric. Candidate orderings are sampled efficiently via a Gumbel perturb-and-sort procedure. Experiments on multiple classification benchmarks show that PLR consistently improves few-shot accuracy for $k \in \{4, 8, 16, 32\}$ examples, and we further demonstrate gains on mathematical reasoning tasks where label-based ordering methods are not applicable. Our code is available at https://github.com/Batorskq/PLR.
Authors: Mohammed Abdullah, George Iosifidis, Salah Eddine Elayoubi, Tijani Chahed
Abstract: We study Constrained Online Convex Optimization with Memory (COCO-M), where both the loss and the constraints depend on a finite window of past decisions made by the learner. This setting extends the previously studied unconstrained online optimization with memory framework and captures practical problems such as the control of constrained dynamical systems and scheduling with reconfiguration budgets. For this problem, we propose the first algorithms that achieve sublinear regret and sublinear cumulative constraint violation under time-varying constraints, both with and without predictions of future loss and constraint functions. Without predictions, we introduce an adaptive penalty approach that guarantees sublinear regret and constraint violation. When short-horizon and potentially unreliable predictions are available, we reinterpret the problem as online learning with delayed feedback and design an optimistic algorithm whose performance improves as prediction accuracy improves, while remaining robust when predictions are inaccurate. Our results bridge the gap between classical constrained online convex optimization and memory-dependent settings, and provide a versatile learning toolbox with diverse applications.
Authors: Maryam Boubekraoui, Giordano d'Aloisio, Antinisca Di Marco
Abstract: The widespread use of AI and ML models in sensitive areas raises significant concerns about fairness. While the research community has introduced various methods for bias mitigation in binary classification tasks, the issue remains under-explored in multi-class classification settings. To address this limitation, in this paper, we first formulate the problem of fair learning in multi-class classification as a multi-objective problem between effectiveness (i.e., prediction correctness) and multiple linear fairness constraints. Next, we propose a Generalised Exponentiated Gradient (GEG) algorithm to solve this task. GEG is an in-processing algorithm that enhances fairness in binary and multi-class classification settings under multiple fairness definitions. We conduct an extensive empirical evaluation of GEG against six baselines across seven multi-class and three binary datasets, using four widely adopted effectiveness metrics and three fairness definitions. GEG overcomes existing baselines, with fairness improvements up to 92% and a decrease in accuracy up to 14%.
Authors: Uzay Macar, Li Yang, Atticus Wang, Peter Wallich, Emmanuel Ameisen, Jack Lindsey
Abstract: Recent work shows that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept, a phenomenon cited as evidence of "introspective awareness." But what mechanisms underlie this capability, and do they reflect genuine introspective circuitry or more shallow heuristics? We investigate these questions in open-source models and establish three main findings. First, introspection is behaviorally robust: detection achieves moderate true positive rates with 0% false positives across diverse prompts. We also find this capability emerges specifically from post-training rather than pretraining. Second, introspection is not reducible to a single linear confound: anomaly detection relies on distributed MLP computation across multiple directions, implemented by evidence carrier and gate features. Third, models possess greater introspective capability than is elicited by default: ablating refusal directions improves detection by 53pp and a trained steering vector by 75pp. Overall, our results suggest that introspective awareness is behaviorally robust, grounded in nontrivial internal anomaly detection, and likely could be substantially improved in future models. Code: https://github.com/safety-research/introspection-mechanisms.
URLs: https://github.com/safety-research/introspection-mechanisms.
Authors: James Wedgwood, Aashiq Muhamed, Mona T. Diab, Virginia Smith
Abstract: Preference alignment is usually achieved by weight-updating training on preference data, which adds substantial alignment-stage compute and provides limited mechanistic visibility. We propose Dynamic SAE Steering for Preference Alignment (DSPA), an inference-time method that makes sparse autoencoder (SAE) steering prompt-conditional. From preference triples, DSPA computes a conditional-difference map linking prompt features to generation-control features; during decoding, it modifies only token-active latents, without base-model weight updates. Across Gemma-2-2B/9B and Qwen3-8B, DSPA improves MT-Bench and is competitive on AlpacaEval while preserving multiple-choice accuracy. Under restricted preference data, DSPA remains robust and can rival the two-stage RAHF-SCIT pipeline while requiring up to $4.47\times$ fewer alignment-stage FLOPs. Finally, we audit the SAE features DSPA modifies, finding that preference directions are dominated by discourse and stylistic signals, and provide theory clarifying the conditional-difference map estimate and when top-$k$ ablation is principled.
Authors: Koichi Tanaka, Kazuki Kawamura, Takanori Muroi, Yusuke Narita, Yuki Sasamoto, Kei Tateno, Takuma Udagawa, Wei-Wei Du, Yuta Saito
Abstract: Off-Policy Evaluation (OPE) is an important practical problem in algorithmic ranking systems, where the goal is to estimate the expected performance of a new ranking policy using only offline logged data collected under a different, logging policy. Existing estimators, such as the ranking-wise and position-wise inverse propensity score (IPS) estimators, require the data collection policy to be sufficiently stochastic and suffer from severe bias when the logging policy is fully deterministic. In this paper, we propose novel estimators, Click-based Inverse Propensity Score (CIPS), exploiting the intrinsic stochasticity of user click behavior to address this challenge. Unlike existing methods that rely on the stochasticity of the logging policy, our approach uses click probability as a new form of importance weighting, enabling low-bias OPE even under deterministic logging policies where existing methods incur substantial bias. We provide theoretical analyses of the bias and variance properties of the proposed estimators and show, through synthetic and real-world experiments, that our estimators achieve significantly lower bias compared to strong baselines, for a range of experimental settings with completely deterministic logging policies.
Authors: Zhipeng Zhang, Zhenjie Yao, Kai Li, Lei Yang
Abstract: Learning systems are typically optimized by minimizing loss or maximizing reward, assuming that improvements in these signals reflect progress toward the true objective. However, when feedback reliability is unobservable, this assumption can fail, and learning algorithms may converge stably to incorrect solutions. This failure arises because single-step feedback does not reveal whether an experience is informative or persistently biased. When information is aggregated over learning trajectories, however, systematic differences between reliable and unreliable regimes can emerge. We propose a Monitor-Trust-Regulator (MTR) framework that infers reliability from learning dynamics and modulates updates through a slow-timescale trust variable. Across reinforcement learning and supervised learning settings, standard algorithms exhibit stable optimization behavior while learning incorrect solutions under latent unreliability, whereas trust-modulated systems reduce bias accumulation and improve recovery. These results suggest that learning dynamics are not only optimization traces but also a source of information about feedback reliability.
Authors: Qixin Zhang, Wei Huang, Yan Sun, Yao Shu, Yi Yu, Dacheng Tao
Abstract: Identifying the most representative subset for a close-to-submodular objective while satisfying the predefined partition constraint is a fundamental task with numerous applications in machine learning. However, the existing distorted local-search methods are often hindered by their prohibitive query complexities and the rigid requirement for prior knowledge of difficult-to-obtain structural parameters. To overcome these limitations, we introduce a novel algorithm titled Multinoulli-SCG, which not only is parameter-free, but also can achieve the same approximation guarantees as the distorted local-search methods with significantly fewer function evaluations. More specifically, when the objective function is monotone $\alpha$-weakly DR-submodular or $(\gamma,\beta)$-weakly submodular, our Multinoulli-SCG algorithm can attain a value of $(1-e^{-\alpha})\text{OPT}-\epsilon$ or $(\frac{\gamma^{2}(1-e^{-(\beta(1-\gamma)+\gamma^2)})}{\beta(1-\gamma)+\gamma^2})\text{OPT}-\epsilon$ with only $O(1/\epsilon^{2})$ function evaluations, where OPT denotes the optimal value. The cornerstone of our Multinoulli-SCG algorithm is an innovative continuous-relaxation framework named Multinoulli Extension(ME), which can effectively convert the discrete subset selection problem subject to partition constraints into a solvable continuous maximization focused on learning the optimal multinoulli priors across the concerned partition. In sharp contrast with the well-established multi-linear extension for submodular subset selection, a notable advantage of our proposed ME is its intrinsic capacity to provide a lossless rounding scheme for any set function. Furthermore, based on our proposed ME, we also present two novel online algorithms, namely, Multinoulli-OSCG and Multinoulli-OSGA, for the unexplored online subset selection problems over partition constraints.
Authors: Hang-Cheng Dong, Pengcheng Cheng
Abstract: Overparameterized shallow neural networks admit substantial parameter redundancy: distinct parameter vectors may represent the same predictor due to hidden-unit permutations, rescalings, and related symmetries. As a result, geometric quantities computed directly in the ambient Euclidean parameter space can reflect artifacts of representation rather than intrinsic properties of the predictor. In this paper, we develop a differential-geometric framework for analyzing simple shallow networks through the quotient space obtained by modding out parameter symmetries on a regular set. We first characterize the symmetry and quotient structure of regular shallow-network parameters and show that the finite-sample realization map induces a natural metric on the quotient manifold. This leads to an effective notion of curvature that removes degeneracy along symmetry orbits and yields a symmetry-reduced Hessian capturing intrinsic local geometry. We then study gradient flows on the quotient and show that only the horizontal component of parameter motion contributes to first-order predictor evolution, while the vertical component corresponds purely to gauge variation. Finally, we formulate an implicit-bias viewpoint at the quotient level, arguing that meaningful complexity should be assigned to predictor classes rather than to individual parameter representatives. Our experiments confirm that ambient flatness is representation-dependent, that local dynamics are better organized by quotient-level curvature summaries, and that in underdetermined regimes, implicit bias is most naturally described in quotient coordinates.
Authors: Chen Gong, Zhenzhe Zheng, Yiliu Chen, Sheng Wang, Fan Wu, Guihai Chen
Abstract: Machine learning models are widely integrated into modern mobile apps to analyze user behaviors and deliver personalized services. Ensuring low-latency on-device model execution is critical for maintaining high-quality user experiences. While prior research has primarily focused on accelerating model inference with given input features, we identify an overlooked bottleneck in real-world on-device model execution pipelines: extracting input features from raw application logs. In this work, we explore a new direction of feature extraction optimization by analyzing and eliminating redundant extraction operations across different model features and consecutive model inferences. We then introduce AutoFeature, an automated feature extraction engine designed to accelerate on-device feature extraction process without compromising model inference accuracy. AutoFeature comprises three core designs: (1) graph abstraction to formulate the extraction workflows of different input features as one directed acyclic graph, (2) graph optimization to identify and fuse redundant operation nodes across different features within the graph; (3) efficient caching to minimize operations on overlapping raw data between consecutive model inferences. We implement a system prototype of AutoFeature and integrate it into five industrial mobile services spanning search, video and e-commerce domains. Online evaluations show that AutoFeature reduces end-to-end on-device model execution latency by 1.33x-3.93x during daytime and 1.43x-4.53x at night.
Authors: Bayezid Baten, M. Ayyan Iqbal, Sebastian Ament, Julius Kusuma, Nishant Garg
Abstract: Modern concrete must simultaneously satisfy evolving demands for mechanical performance, workability, durability, and sustainability, making mix designs increasingly complex. Recent studies leveraging Artificial Intelligence (AI) and Machine Learning (ML) models show promise for predicting compressive strength and guiding mix optimization, but most existing efforts are based on proprietary industrial datasets and closed-source implementations. Here we introduce BOxCrete, an open-source probabilistic modeling and optimization framework trained on a new open-access dataset of over 500 strength measurements (1-15 ksi) from 123 mixtures - 69 mortar and 54 concrete mixes tested at five curing ages (1, 3, 5, 14, and 28 days). BOxCrete leverages Gaussian Process (GP) regression to predict strength development, achieving average R$^2$ = 0.94 and RMSE = 0.69 ksi, quantify uncertainty, and carry out multi-objective optimization of compressive strength and embodied carbon. The dataset and model establish a reproducible open-source foundation for data-driven development of AI-based optimized mix designs.
Authors: Jamie Mahowald, Tan Bui-Thanh
Abstract: We investigate the generalization capabilities of In-Context Operator Networks (ICONs), a new class of operator networks that build on the principles of in-context learning, for higher-order partial differential equations. We extend previous work by expanding the type and scope of differential equations handled by the foundation model. We demonstrate that while processing complex inputs requires some new computational methods, the underlying machine learning techniques are largely consistent with simpler cases. Our implementation shows that although point-wise accuracy degrades for higher-order problems like the heat equation, the model retains qualitative accuracy in capturing solution dynamics and overall behavior. This demonstrates the model's ability to extrapolate fundamental solution characteristics to problems outside its training regime.
Authors: Yawen Li, Tao Hu, Zhouhui Lian, Wan Tian, Yijie Peng, Huiming Zhang, Zhongyi Li
Abstract: This paper studies generalization error bounds for Transformer models. Based on the offset Rademacher complexity, we derive sharper generalization bounds for different Transformer architectures, including single-layer single-head, single-layer multi-head, and multi-layer Transformers. We first express the excess risk of Transformers in terms of the offset Rademacher complexity. By exploiting its connection with the empirical covering numbers of the corresponding hypothesis spaces, we obtain excess risk bounds that achieve optimal convergence rates up to constant factors. We then derive refined excess risk bounds by upper bounding the covering numbers of Transformer hypothesis spaces using matrix ranks and matrix norms, leading to precise, architecture-dependent generalization bounds. Finally, we relax the boundedness assumption on feature mappings and extend our theoretical results to settings with unbounded (sub-Gaussian) features and heavy-tailed distributions.
Authors: Xinyu Zhang
Abstract: World models learn to simulate environment dynamics from experience, enabling sample-efficient reinforcement learning. But what do these models actually represent internally? We apply interpretability techniques--including linear and nonlinear probing, causal interventions, and attention analysis--to two architecturally distinct world models: IRIS (discrete token transformer) and DIAMOND (continuous diffusion UNet), trained on Atari Breakout and Pong. Using linear probes, we find that both models develop linearly decodable representations of game state variables (object positions, scores), with MLP probes yielding only marginally higher R^2, confirming that these representations are approximately linear. Causal interventions--shifting hidden states along probe-derived directions--produce correlated changes in model predictions, providing evidence that representations are functionally used rather than merely correlated. Analysis of IRIS attention heads reveals spatial specialization: specific heads attend preferentially to tokens overlapping with game objects. Multi-baseline token ablation experiments consistently identify object-containing tokens as disproportionately important. Our findings provide interpretability evidence that learned world models develop structured, approximately linear internal representations of environment state across two games and two architectures.
Authors: Andrii Shportko
Abstract: Large language models can rewrite text to embed hidden payloads while preserving surface-level meaning, a capability that opens covert channels between cooperating AI systems and poses challenges for alignment monitoring. We study the information-theoretic cost of such embedding. Our main result is that any steganographic scheme that preserves the semantic load of a covertext~$M_1$ while encoding a payload~$P$ into a stegotext~$M_2$ must satisfy $K(M_2) \geq K(M_1) + K(P) - O(\log n)$, where $K$ denotes Kolmogorov complexity and $n$ is the combined message length. A corollary is that any non-trivial payload forces a strict complexity increase in the stegotext, regardless of how cleverly the encoder distributes the signal. Because Kolmogorov complexity is uncomputable, we ask whether practical proxies can detect this predicted increase. Drawing on the classical correspondence between lossless compression and Kolmogorov complexity, we argue that language-model perplexity occupies an analogous role in the probabilistic regime and propose the Binoculars perplexity-ratio score as one such proxy. Preliminary experiments with a color-based LLM steganographic scheme support the theoretical prediction: a paired $t$-test over 300 samples yields $t = 5.11$, $p < 10^{-6}$.
Authors: Md Kaykobad Reza, Ameya Patil, Edward Ayrapetian, M. Salman Asif
Abstract: Multimodal large language models (MLLMs) achieve strong performance by jointly processing inputs from multiple modalities, such as vision, audio, and language. However, building such models or extending them to new modalities often requires large paired datasets and substantial computational resources. Since many pretrained MLLMs (e.g., vision-language or audio-language) are publicly available, we ask whether we can merge them into a single MLLM that can handle multiple modalities? Merging MLLMs with different input modalities remains challenging, partly because of differences in the learned representations and interference between their parameter spaces. To address these challenges, we propose Singular Subspace Alignment and Merging (SSAM), a training-free model merging framework that unifies independently trained specialist MLLMs into a single model capable of handling any combination of input modalities. SSAM maintains modality-specific parameter updates separately and identifies a shared low-rank subspace for language-related parameter updates, aligns them within this subspace, and merges them to preserve complementary knowledge while minimizing parameter interference. Without using any multimodal training data, SSAM achieves state-of-the-art performance across four datasets, surpassing prior training-free merging methods and even jointly trained multimodal models. These results demonstrate that aligning models in parameter space provides a scalable and resource-efficient alternative to conventional joint multimodal training.
Authors: Devashish Chaudhary, Sutharshan Rajasegarar, Shiva Raj Pokhrel, Lei Pan, Ruby D
Abstract: The rapid expansion of the Internet of Things (IoT) and its integration with backbone networks have heightened the risk of security breaches. Traditional centralized approaches to anomaly detection, which require transferring large volumes of data to central servers, suffer from privacy, scalability, and latency limitations. This paper proposes a lightweight autoencoder-based anomaly detection framework designed for deployment on resource-constrained edge devices, enabling real-time detection while minimizing data transfer and preserving privacy. Federated learning is employed to train models collaboratively across distributed devices, where local training occurs on edge nodes and only model weights are aggregated at a central server. A real-world IoT testbed using Raspberry Pi sensor nodes was developed to collect normal and attack traffic data. The proposed federated anomaly detection system, implemented and evaluated on the testbed, demonstrates its effectiveness in accurately identifying network attacks. The communication overhead was reduced significantly while achieving comparable performance to the centralized method.
Authors: Philip S. Yu, Li Sun
Abstract: Graphs provide a natural description of the complex relationships among objects, and play a pivotal role in communications, transportation, social computing, the life sciences, etc. Currently, there is strong agreement that Graph Foundation Models (GFMs) are essential for advancing graph learning, yet considerable disagreement persists on how to build a powerful, general-purpose GFM analogous to Large Language Models (LLMs). Graph Neural Networks (GNNs) exhibit limitations in memory retention and principled interpretability when confronted with multi-domain pretraining and adaptation. The challenge of graph serialization hinders the direct application of LLMs, as the words struggle to capture the structural complexity and diversity inherent in graphs. In contrast, Riemannian geometry offers an elegant mathematical framework for modeling structures, while remaining compatible with graph semantic learning, even with LLMs. In this paper, we argue that, for graphs, Riemannian geometry speaks louder than words, and lay out the foundational principles for GFM. Reimagining with Riemannian geometry, we introduce a blue sky idea-Riemannian Foundation Model (RFM)-that opens a new pathway for capturing complex structural patterns and uncovering cross-domain generalities. RFM emphasizes intrinsic graph geometry and embodies endogenous capacities for structural inference and generation, moving beyond mere representation-space switching. Accordingly, we outline a progressive agenda that begins with universal structural understanding through intrinsic geometry, and then rebuilds LLM with a Riemannian engine for general-purpose graph modeling and beyond. Thus, RFM enables a paradigm shift from designing graph models to solving graph-structured applications with RFM agents, unlocking the next-generation graph intelligence.
Authors: Woosung Koh, Jeyoung Jeon, Youngjin Song, Yujin Cheon, Soowon Oh, Jaehyeong Choi, Se-Young Yun
Abstract: Current language model training commonly applies multi-task Supervised Fine-Tuning (SFT) using a homogeneous compute budget across all sub-datasets. This approach is fundamentally sub-optimal: heterogeneous learning dynamics cause faster-learning tasks to overfit early while slower ones remain under-fitted. To address this, we introduce mSFT, an iterative, overfitting-aware search algorithm for multi-task data mixtures. mSFT trains the model on an active mixture, identifies and excludes the earliest overfitting sub-dataset, and reverts to that specific optimal checkpoint before continuing. Extensive evaluations demonstrate that mSFT consistently outperforms 4 baselines across 10 benchmarks and 6 base models. Further analysis confirms mSFT maintains robust gains across diverse dataset sizes, task granularities, and is insensitive to its single new hyperparameter (compute budget). Notably, at low compute budget, mSFT can improve performance while lowering training FLOPs. Ultimately, mSFT establishes a practical overfitting-aware algorithm for multi-task SFT that maximizes the potential of models across diverse data mixtures.
Authors: Abdou-Raouf Atarmla
Abstract: Existing machine learning frameworks for compliance monitoring -- Markov Logic Networks, Probabilistic Soft Logic, supervised models -- share a fundamental paradigm: they treat observed data as ground truth and attempt to approximate rules from it. This assumption breaks down in rule-governed domains such as taxation or regulatory compliance, where authoritative rules are known a priori and the true challenge is to infer the latent state of rule activation, compliance, and parametric drift from partial and noisy observations. We propose Rule-State Inference (RSI), a Bayesian framework that inverts this paradigm by encoding regulatory rules as structured priors and casting compliance monitoring as posterior inference over a latent rule-state space S = {(a_i, c_i, delta_i)}, where a_i captures rule activation, c_i models the compliance rate, and delta_i quantifies parametric drift. We prove three theoretical guarantees: (T1) RSI absorbs regulatory changes in O(1) time via a prior ratio correction, independently of dataset size; (T2) the posterior is Bernstein-von Mises consistent, converging to the true rule state as observations accumulate; (T3) mean-field variational inference monotonically maximizes the Evidence Lower BOund (ELBO). We instantiate RSI on the Togolese fiscal system and introduce RSI-Togo-Fiscal-Synthetic v1.0, a benchmark of 2,000 synthetic enterprises grounded in real OTR regulatory rules (2022-2025). Without any labeled training data, RSI achieves F1=0.519 and AUC=0.599, while absorbing regulatory changes in under 1ms versus 683-1082ms for full model retraining -- at least a 600x speedup.
Authors: Shiyan Hu, Jianxin Jin, Yang Shu, Peng Chen, Bin Yang, Chenjuan Guo
Abstract: Time series anomaly detection plays a critical role in many dynamic systems. Despite its importance, previous approaches have primarily relied on unimodal numerical data, overlooking the importance of complementary information from other modalities. In this paper, we propose a novel multimodal time series anomaly detection model (MindTS) that focuses on addressing two key challenges: (1) how to achieve semantically consistent alignment across heterogeneous multimodal data, and (2) how to filter out redundant modality information to enhance cross-modal interaction effectively. To address the first challenge, we propose Fine-grained Time-text Semantic Alignment. It integrates exogenous and endogenous text information through cross-view text fusion and a multimodal alignment mechanism, achieving semantically consistent alignment between time and text modalities. For the second challenge, we introduce Content Condenser Reconstruction, which filters redundant information within the aligned text modality and performs cross-modal reconstruction to enable interaction. Extensive experiments on six real-world multimodal datasets demonstrate that the proposed MindTS achieves competitive or superior results compared to existing methods. The code is available at: https://github.com/decisionintelligence/MindTS.
Authors: Yuehu Gong, Zeyuan Wang, Yulin Chen, Yanwei Fu
Abstract: On-policy reinforcement learning with generative policies is promising but remains underexplored. A central challenge is that proximal policy optimization (PPO) is traditionally formulated in terms of action-space probability ratios, whereas diffusion- and flow-based policies are more naturally represented as trajectory-level generative processes. In this work, we propose GSB-PPO, a path-space formulation of generative PPO inspired by the Generalized Schr\"odinger Bridge (GSB). Our framework lifts PPO-style proximal updates from terminal actions to full generation trajectories, yielding a unified view of on-policy optimization for generative policies. Within this framework, we develop two concrete objectives: a clipping-based objective, GSB-PPO-Clip, and a penalty-based objective, GSB-PPO-Penalty. Experimental results show that while both objectives are compatible with on-policy training, the penalty formulation consistently delivers better stability and performance than the clipping counterpart. Overall, our results highlight path-space proximal regularization as an effective principle for training generative policies with PPO.
Authors: Yunchi Yang, Longlong Li, Jianliang Wu, Cunquan Qu
Abstract: Predicting the next mobile app a user will launch is essential for proactive mobile services. Yet accurate prediction remains challenging in real-world settings, where user intent can shift rapidly within short sessions and user-specific historical profiles are often sparse or unavailable, especially under cold-start conditions. Existing approaches mainly model app usage as sequential behavior or local session transitions, limiting their ability to capture higher-order structural dependencies and evolving session intent. To address this issue, we propose MISApp, a profile-free framework for next app prediction based on multi-hop session graph learning. MISApp constructs multi-hop session graphs to capture transition dependencies at different structural ranges, learns session representations through lightweight graph propagation, incorporates temporal and spatial context to characterize session conditions, and captures intent evolution from recent interactions. Experiments on two real-world app usage datasets show that MISApp consistently outperforms competitive baselines under both standard and cold-start settings, while maintaining a favorable balance between predictive accuracy and practical efficiency. Further analyses show that the learned hop-level attention weights align well with structural relevance, offering interpretable evidence for the effectiveness of the proposed multi-hop modeling strategy.
Authors: Vagish Kumar, Syed Bahauddin Alam, Souvik Chakraborty
Abstract: Protecting patient privacy remains a fundamental barrier to scaling machine learning across healthcare institutions, where centralizing sensitive data is often infeasible due to ethical, legal, and regulatory constraints. Federated learning offers a promising alternative by enabling privacy-preserving, multi-institutional training without sharing raw patient data; however, real-world deployments face severe challenges from data heterogeneity, site-specific biases, and class imbalance, which degrade predictive reliability and render existing uncertainty quantification methods ineffective. Here, we present TrustFed, a federated uncertainty quantification framework that provides distribution-free, finite-sample coverage guarantees under heterogeneous and imbalanced healthcare data, without requiring centralized access. TrustFed introduces a representation-aware client assignment mechanism that leverages internal model representations to enable effective calibration across institutions, along with a soft-nearest threshold aggregation strategy that mitigates assignment uncertainty while producing compact and reliable prediction sets. Using over 430,000 medical images across six clinically distinct imaging modalities, we conduct one of the most comprehensive evaluations of uncertainty-aware federated learning in medical imaging, demonstrating robust coverage guarantees across datasets with diverse class cardinalities and imbalance regimes. By validating TrustFed at this scale and breadth, our study advances uncertainty-aware federated learning from proof-of-concept toward clinically meaningful, modality-agnostic deployment, positioning statistically guaranteed uncertainty as a core requirement for next-generation healthcare AI systems.
Authors: Hung-Hsuan Chen
Abstract: Standard Transformers have a fixed computational depth, fundamentally limiting their ability to generalize to tasks requiring variable-depth reasoning, such as multi-hop graph traversal or nested logic. We propose a depth-recurrent Transformer that decouples computational depth from parameter count by iteratively applying a shared-weight Transformer block in latent space -- enabling the model to trade recurrence steps for deeper reasoning at inference time. Our architecture incorporates three mechanisms to make deep recurrence (20+ steps) stable: (1) a silent thinking objective that supervises only the final output, forcing genuine multi-step reasoning rather than intermediate heuristic shortcuts; (2) LayerScale initialization to protect fragile reasoning states from untrained layer noise; and (3) an identity-biased recurrence that creates a gradient highway across many steps. We evaluate on three compositional reasoning domains with decreasing inductive biases: graph reachability (strict adjacency masking), nested boolean logic (relative positioning), and unstructured relational text (where sequence position provides no structural hints). Across all tasks, we observe a clear \emph{computational frontier} -- a boundary where performance transitions from chance to near-perfect as thinking steps scale with task complexity. Moreover, these tasks reveal qualitatively different generalization behaviors: precise but brittle (graph), approximate but robust (logic), and autonomous latent routing without structural hints (text). This progression illuminates how the interplay between a task-invariant recurrent reasoning core and task-specific perceptual interfaces shapes out-of-distribution (OOD) generalization, offering a mechanistic perspective on vertical chain-of-thought that complements the prevailing horizontal token-generation paradigm.
Authors: Tian Xia
Abstract: Model merging has emerged as a practical approach to combine capabilities of specialized large language models (LLMs) without additional training. In the Long-to-Short (L2S) scenario, merging a base model with a long-chain-of-thought reasoning model aims to preserve reasoning accuracy while reducing output length. Existing methods rely on Task Arithmetic and its variants, which implicitly assume that model outputs vary linearly with the merging coefficient -- an assumption we show is systematically violated in L2S settings. We provide the first theoretical justification for layer-adaptive merging: we prove that merging error is bounded by a term proportional to the per-layer Hessian norm (Proposition~1), and establish that the Fisher Information Matrix (FIM) is a principled, computable proxy for this bound via the Fisher-Hessian equivalence at local optima. Building on this theory, we propose \textbf{FIM-Merging}, which computes diagonal FIM using only random token inputs (no domain-specific calibration data required) and uses it to assign per-layer merging coefficients. On the 7B L2S benchmark, FIM-TIES achieves state-of-the-art performance on five out of six evaluation benchmarks, including a \textbf{+6.2} point gain on MATH500 over ACM-TIES (90.2 vs.\ 84.0), while requiring no calibration data. On the 1.5B benchmark, FIM-TIES achieves an average accuracy of \textbf{47.3}, surpassing the previous best ACM-TIES (43.3) by \textbf{+3.9} points, while reducing average response length by \textbf{91.9\%} relative to the long-CoT model. Our framework also provides a unified theoretical explanation for why existing layer-adaptive methods such as ACM empirically outperform uniform merging.
Authors: Bahar Dibaei Nia, Farzan Farnia
Abstract: Efficient selection among multiple generative models is increasingly important in modern generative AI, where sampling from suboptimal models is costly. This problem can be formulated as a multi-armed bandit task. Under diversity-aware evaluation metrics, a non-degenerate mixture of generators can outperform any individual model, distinguishing this setting from classical best-arm identification. Prior approaches therefore incorporate an Upper Confidence Bound (UCB) exploration bonus into the mixture objective. However, across multiple datasets and evaluation metrics, we observe that the UCB term consistently slows convergence and often reduces sample efficiency. In contrast, a simple \emph{Mixture-Greedy} strategy without explicit UCB-type optimism converges faster and achieves even better performance, particularly for widely used metrics such as FID and Vendi where tight confidence bounds are difficult to construct. We provide theoretical insight explaining this behavior: under transparent structural conditions, diversity-aware objectives induce implicit exploration by favoring interior mixtures, leading to linear sampling of all arms and sublinear regret guarantees for entropy-based, kernel-based, and FID-type objectives. These results suggest that in diversity-aware multi-armed bandits for generative model selection, exploration can arise intrinsically from the objective geometry, questioning the necessity of explicit confidence bonuses.
Authors: Dongxia Wu, Yuhui Zhang, Serena Yeung-Levy, Emma Lundberg, Emily B. Fox
Abstract: Distribution-to-distribution generative models support scientific imaging tasks ranging from modeling cellular perturbation responses to translating medical images across conditions. Trustworthy generation requires both reliability (generalization across labs, devices, and experimental conditions) and accountability (detecting out-of-distribution cases where predictions may be unreliable). Uncertainty quantification (UQ) based approaches serve as promising candidates for these tasks, yet UQ for distribution-to-distribution generative models remains underexplored. We present a unified UQ framework, Bayesian Stochastic Flow Matching (BSFM), that disentangles aleatoric and epistemic uncertainty. The Stochastic Flow Matching (SFM) component augments deterministic flows with a diffusion term to improve model generalization to unseen scenarios. For UQ, we develop a scalable Bayesian approach -- MCD-Antithetic -- that combines Monte Carlo Dropout with sample-efficient antithetic sampling to produce effective anomaly scores for out-of-distribution detection. Experiments on cellular imaging (BBBC021, JUMP) and brain fMRI (Theory of Mind) across diverse scenarios show that SFM improves reliability while MCD-Antithetic enhances accountability.
Authors: Bulent Haznedar, Levent Karacan
Abstract: Transformers have achieved remarkable progress in time series forecasting, yet their reliance on deterministic dot-product attention limits their capacity to model uncertainty and nonlinear dependencies across multivariate temporal dimensions. To address this limitation, we propose FISFormer, a Fuzzy Inference System-driven Transformer that replaces conventional attention with a FIS Interaction mechanism. In this framework, each query-key pair undergoes a fuzzy inference process for every feature dimension, where learnable membership functions and rule-based reasoning estimate token-wise relational strengths. These FIS-derived interaction weights capture uncertainty and provide interpretable, continuous mappings between tokens. A softmax operation is applied along the token axis to normalize these weights, which are then combined with the corresponding value features through element-wise multiplication to yield the final context-enhanced token representations. This design fuses the interpretability and uncertainty modeling of fuzzy logic with the representational power of Transformers. Extensive experiments on multiple benchmark datasets demonstrate that FISFormer achieves superior forecasting accuracy, noise robustness, and interpretability compared to state-of-the-art Transformer variants, establishing fuzzy inference as an effective alternative to conventional attention mechanisms.
Authors: Dongxia Wu, Shiye Su, Yuhui Zhang, Elaine Sui, Emma Lundberg, Emily B. Fox, Serena Yeung-Levy
Abstract: Building virtual cells with generative models to simulate cellular behavior in silico is emerging as a promising paradigm for accelerating drug discovery. However, prior image-based generative approaches can produce implausible cell images that violate basic physical and biological constraints. To address this, we propose to post-train virtual cell models with reinforcement learning (RL), leveraging biologically meaningful evaluators as reward functions. We design seven rewards spanning three categories-biological function, structural validity, and morphological correctness-and optimize the state-of-the-art CellFlux model to yield CellFluxRL. CellFluxRL consistently improves over CellFlux across all rewards, with further performance boosts from test-time scaling. Overall, our results present a virtual cell modeling framework that enforces physically-based constraints through RL, advancing beyond "visually realistic" generations towards "biologically meaningful" ones.
Authors: Yuze Qin, Qingyong Li, Zhiqing Guo, Wen Wang, Yan Liu, Yangli-ao Geng
Abstract: Precipitation nowcasting is critical for disaster mitigation and aviation safety. However, radar-only models frequently suffer from a lack of large-scale atmospheric context, leading to performance degradation at longer lead times. While integrating meteorological variables predicted by weather foundation models offers a potential remedy, existing architectures fail to reconcile the profound representational heterogeneities between radar imagery and meteorological data. To bridge this gap, we propose PW-FouCast, a novel frequency-domain fusion framework that leverages Pangu-Weather forecasts as spectral priors within a Fourier-based backbone. Our architecture introduces three key innovations: (i) Pangu-Weather-guided Frequency Modulation to align spectral magnitudes and phases with meteorological priors; (ii) Frequency Memory to correct phase discrepancies and preserve temporal evolution; and (iii) Inverted Frequency Attention to reconstruct high-frequency details typically lost in spectral filtering. Extensive experiments on the SEVIR and MeteoNet benchmarks demonstrate that PW-FouCast achieves state-of-the-art performance, effectively extending the reliable forecast horizon while maintaining structural fidelity. Our code is available at https://github.com/Onemissed/PW-FouCast.
Authors: Armand Rousselot, Joran Wendebourg, Ullrich K\"othe
Abstract: The performance of machine learning models is determined by the quality of their learned features. They should be invariant under irrelevant data variation but sensitive to task-relevant details. To visualize whether this is the case, we propose a method to analyze feature extractors by sampling from their fibers -- equivalence classes defined by their invariances -- given an arbitrary representative. Unlike existing work where a dedicated generative model is trained for each feature detector, our algorithm is training-free and exploits a pretrained diffusion or flow-matching model as a prior. The fiber loss -- which penalizes mismatch in features -- guides the denoising process toward the desired equivalence class, via non-linear diffusion trajectory matching. This replaces days of training for invariance learning with a single guided generation procedure at comparable fidelity. Experiments on popular datasets (ImageNet, CheXpert) and model types (ResNet, DINO, BiomedClip) demonstrate that our framework can reveal invariances ranging from very desirable to concerning behaviour. For instance, we show how Qwen-2B places patients with situs inversus (heart on the right side) in the same fiber as typical anatomy.
Authors: Hanyin Cheng, Xingjian Wu, Yang Shu, Zhongwen Rao, Lujia Pan, Bin Yang, Chenjuan Guo
Abstract: Most existing Time Series Foundation Models (TSFMs) use channel independent modeling and focus on capturing and generalizing temporal dependencies, while neglecting the correlations among channels or overlooking the different aspects of correlations. However, these correlations play a vital role in Multivariate time series forecasting. To address this, we propose a CoRrelation-aware Adapter (CoRA), a lightweight plug-and-play method that requires only fine-tuning with TSFMs and is able to capture different types of correlations, so as to improve forecast performance. Specifically, to reduce complexity, we innovatively decompose the correlation matrix into low-rank Time-Varying and Time-Invariant components. For the Time-Varying component, we further design learnable polynomials to learn dynamic correlations by capturing trends or periodic patterns. To learn positive and negative correlations that appear only among some channels, we introduce a novel dual contrastive learning method that identifies correlations through projection layers, regulated by a Heterogeneous-Partial contrastive loss during training, without introducing additional complexity in the inference stage. Extensive experiments on 10 real-world datasets demonstrate that CoRA can improve TSFMs in multivariate forecasting performance.
Authors: Mohammad Moulaeifard, Philip J. Aston, Peter H. Charlton, Nils Strodthoff
Abstract: Photoplethysmography (PPG) is one of the most widely captured biosignals for clinical prediction tasks, yet PPG-based algorithms are typically trained on small-scale datasets of uncertain quality, which hinders meaningful algorithm comparisons. We present a comprehensive benchmark for PPG-based clinical prediction using the \dbname~dataset, establishing baselines across the full spectrum of clinically relevant applications: multi-class heart rhythm classification, and regression of physiological parameters including respiratory rate (RR), heart rate (HR), and blood pressure (BP). Most notably, we provide the first comprehensive assessment of PPG for general arrhythmia detection beyond atrial fibrillation (AF) and atrial flutter (AFLT), with performance stratified by BP, HR, and demographic subgroups. Using established deep learning architectures, we achieved strong performance for AF detection (AUROC = 0.96) and accurate physiological parameter estimation (RR MAE: 2.97 bpm; HR MAE: 1.13 bpm; SBP/DBP MAE: 16.13/8.70 mmHg). Cross-dataset validation demonstrates excellent generalizability for AF detection (AUROC = 0.97), while clinical subgroup analysis reveals marked performance differences across subgroups by BP, HR, and demographic strata. These variations appear to reflect population-specific waveform differences rather than systematic bias in model behavior. This framework establishes the first integrated benchmark for multi-task PPG-based clinical prediction, demonstrating that PPG signals can effectively support multiple simultaneous monitoring tasks and providing essential baselines for future algorithm development.
Authors: Marc Franquesa Mon\'es, Jiaqi Zhang, Caroline Uhler
Abstract: Learning causal relations from observational data is a fundamental problem with wide-ranging applications across many fields. Constraint-based methods infer the underlying causal structure by performing conditional independence tests. However, existing algorithms such as the prominent PC algorithm need to perform a large number of independence tests, which in the worst case is exponential in the maximum degree of the causal graph. Despite extensive research, it remains unclear if there exist algorithms with better complexity without additional assumptions. Here, we establish an algorithm that achieves a better complexity of $p^{\mathcal{O}(s)}$ tests, where $p$ is the number of nodes in the graph and $s$ denotes the maximum undirected clique size of the underlying essential graph. Complementing this result, we prove that any constraint-based algorithm must perform at least $2^{\Omega(s)}$ conditional independence tests, establishing that our proposed algorithm achieves exponent-optimality up to a logarithmic factor in terms of the number of conditional independence tests needed. Finally, we validate our theoretical findings through simulations, on semi-synthetic gene-expression data, and real-world data, demonstrating the efficiency of our algorithm compared to existing methods in terms of number of conditional independence tests needed.
Authors: Weilin Wan, Jingtao Han, Weizhong Zhang, Cheng Jin
Abstract: Scaling laws for Large Language Models govern macroscopic resource allocation, yet translating them into precise Mixture-of-Experts (MoE) architectural configurations remains an open problem due to the combinatorially vast design space. Existing MoE scaling studies are constrained by experimental budgets to either augment scaling formulas with extra MoE variables, risking unreliable fits, or fix all non-MoE factors, ignoring global interactions. We propose a reusable framework for holistic MoE architectural optimization that bridges this gap. We first show that FLOPs per token alone is an inadequate fairness metric for MoE models because differing computational densities across layer types can inflate parameters without proportional compute cost, and establish a joint constraint triad of FLOPs per token, active parameters, and total parameters. We then reduce the 16-dimensional architectural search space to two sequential low-dimensional phases through algebraic constraints and a rank-preserving property of the hidden dimension. Validated across hundreds of MoE models spanning six orders of magnitude in compute, our framework yields robust scaling laws that map any compute budget to a complete, optimal MoE architecture. A key finding is that the near-optimal configuration band widens with scale, giving practitioners quantitative flexibility to balance scaling law recommendations against infrastructure constraints.
Authors: Xinyu Lu, Kaiqi Zhang, Jinglin Yang, Boxi Cao, Yaojie Lu, Hongyu Lin, Min He, Xianpei Han, Le Sun
Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs). However, vanilla RLVR suffers from inefficient exploration, particularly when confronting "hard samples" that yield nearzero success rates. In such scenarios, the reliance on sparse outcome rewards typically results in zero-advantage estimates, effectively starving the model of supervision signals despite the high informational value of these instances. To address this, we propose P^2O, a novel framework that synergizes Prompt Optimization with Policy Optimization. P^2O identifies hard samples during training iterations and leverages the GeneticPareto (GEPA) prompt optimization algorithm to evolve prompt templates that guide the model toward discovering successful trajectories. Crucially, unlike traditional prompt engineering methods that rely on input augmentation, P^2O distills the reasoning gains induced by these optimized prompts directly into the model parameters. This mechanism provides denser positive supervision signals for hard samples and accelerates convergence. Extensive experiments demonstrate that P^2O not only achieves superior performance on in-distribution datasets but also exhibits strong generalization, yielding substantial improvements on out-of-distribution benchmarks (+4.7% avg.).
Authors: Nikolas Stavrou, Siamak Mehrkanoon
Abstract: Weather forecasting supports critical socioeconomic activities and complements environmental protection, yet operational Numerical Weather Prediction (NWP) systems remain computationally intensive, thus being inefficient for certain applications. Meanwhile, recent advances in deep data-driven models have demonstrated promising results in nowcasting tasks. This paper presents SmaAT-QMix-UNet, an enhanced variant of SmaAT-UNet that introduces two key innovations: a vector quantization (VQ) bottleneck at the encoder-decoder bridge, and mixed kernel depth-wise convolutions (MixConv) replacing selected encoder and decoder blocks. These enhancements both reduce the model's size and improve its nowcasting performance. We train and evaluate SmaAT-QMix-UNet on a Dutch radar precipitation dataset (2016-2019), predicting precipitation 30 minutes ahead. Three configurations are benchmarked: using only VQ, only MixConv, and the full SmaAT-QMix-UNet. Grad-CAM saliency maps highlight the regions influencing each nowcast, while a UMAP embedding of the codewords illustrates how the VQ layer clusters encoder outputs. The source code for SmaAT-QMix-UNet is publicly available on GitHub \footnote{\href{https://github.com/nstavr04/MasterThesisSnellius}{https://github.com/nstavr04/MasterThesisSnellius}}.
URLs: https://github.com/nstavr04/MasterThesisSnellius, https://github.com/nstavr04/MasterThesisSnellius
Authors: Ziyang Zhang, Zheshun Wu, Jie Liu, Luca Mottola
Abstract: Deploying deep neural networks (DNNs) on power-sensitive edge devices presents a formidable challenge. While Dynamic Voltage and Frequency Scaling (DVFS) is widely employed for energy optimization, traditional model-level scaling is often too coarse to capture intra-inference variations, whereas fine-grained operator-level scaling suffers from prohibitive performance degradation due to significant hardware switching latency. This paper presents SparseDVFS, a fine-grained, sparse-aware DVFS framework designed for energy-efficient edge inference. Our key insight is that operator sparsity is a primary metric for hardware frequency modulation. By distinguishing between compute-bound dense operators and memory-bound sparse operators, the system can apply specialized frequency triplets to maximize energy efficiency. To overcome switching overheads and component interference, SparseDVFS incorporates three key innovations: (1) an offline modeler that established a deterministic mapping between operator sparsity and optimal frequency triplets (CPU/GPU/EMC) via white-box timeline analysis; (2) a runtime graph partitioner that utilizes a greedy merging heuristic to aggregate operators into super-blocks, balancing scaling granularity and DVFS switching latency through a latency amortization constraint; and (3) a unified co-governor that employs a frequency unified scaling engine (FUSE) and a look-ahead instruction queue to eliminate antagonistic effects between independent controllers and hide hardware transition latencies. Extensive evaluations show that SparseDVFS achieves an average 78.17% energy efficiency gain over state-of-the-art solutions while maintaining a superior 14% cost-gain ratio.
Authors: Juan Sebastian Rojas, Chi-Guhn Lee
Abstract: The temporal difference (TD) error was first formalized in Sutton (1988), where it was first characterized as the difference between temporally successive predictions, and later, in that same work, formulated as the difference between a bootstrapped target and a prediction. Since then, these two interpretations of the TD error have been used interchangeably in the literature, with the latter eventually being adopted as the standard critic loss in deep reinforcement learning (RL) architectures. In this work, we show that these two interpretations of the TD error are not always equivalent. In particular, we show that increasingly-nonlinear deep RL architectures can cause these interpretations of the TD error to yield increasingly different numerical values. Then, building on this insight, we show how choosing one interpretation of the TD error over the other can affect the performance of deep RL algorithms that utilize the TD error to compute other quantities, such as with deep differential (i.e., average-reward) RL methods. All in all, our results show that the default interpretation of the TD error as the difference between a bootstrapped target and a prediction does not always hold in deep RL settings.
Authors: Xixi Wu, Qianguo Sun, Ruiyang Zhang, Chao Song, Junlong Wu, Yiyan Qi, Hong Cheng
Abstract: Reinforcement Learning (RL) is essential for evolving Large Language Models (LLMs) into autonomous agents capable of long-horizon planning, yet a practical recipe for scaling RL in complex, multi-turn environments remains elusive. This paper presents a systematic empirical study using TravelPlanner, a challenging testbed requiring tool orchestration to satisfy multifaceted constraints. We decompose the agentic RL design space along 5 axes: reward shaping, model scaling, data composition, algorithm selection, and environmental stability. Our controlled experiments yield 7 key takeaways, e.g., (1) reward and algorithm choices are scale-dependent as smaller models benefit from staged rewards and enhanced exploration, whereas larger models converge efficiently with simpler dense rewards, (2) ~ 1K training samples with a balanced difficulty mixture mark a sweet spot for both in-domain and out-of-domain performance, and (3) environmental stability is critical to prevent policy degradation. Based on our distilled recipe, our RL-trained models achieve state-of-the-art performance on TravelPlanner, significantly outperforming leading LLMs.
Authors: Ehimare Okoyomon, Christoph Goebel
Abstract: Accurate power flow analysis is critical for modern distribution systems, yet classical solvers face scalability issues, and current machine learning models often struggle with generalization. We introduce BOOST-RPF, a novel method that reformulates voltage prediction from a global graph regression task into a sequential path-based learning problem. By decomposing radial networks into root-to-leaf paths, we leverage gradient-boosted decision trees (XGBoost) to model local voltage-drop regularities. We evaluate three architectural variants: Absolute Voltage, Parent Residual, and Physics-Informed Residual. This approach aligns the model architecture with the recursive physics of power flow, ensuring size-agnostic application and superior out-of-distribution robustness. Benchmarked against the Kerber Dorfnetz grid and the ENGAGE suite, BOOST-RPF achieves state-of-the-art results with its Parent Residual variant which consistently outperforms both analytical and neural baselines in standard accuracy and generalization tasks. While global Multi-Layer Perceptrons (MLPs) and Graph Neural Networks (GNNs) often suffer from performance degradation under topological shifts, BOOST-RPF maintains high precision across unseen feeders. Furthermore, the framework displays linear $O(N)$ computational scaling and significantly increased sample efficiency through per-edge supervision, offering a scalable and generalizable alternative for real-time distribution system operator (DSO) applications.
Authors: Dilina Rajapakse, Juan C. Rosero, Ivana Dusparic
Abstract: Reinforcement Learning (RL) has demonstrated its ability to solve complex decision-making problems in a variety of domains, by optimizing reward signals obtained through interaction with an environment. However, many real-world scenarios involve multiple, potentially conflicting objectives that cannot be easily represented by a single scalar reward. Multi-Objective Reinforcement Learning (MORL) addresses this limitation by enabling agents to optimize several objectives simultaneously, explicitly reasoning about trade-offs between them. However, the ``black box" nature of the RL models makes the decision process behind chosen objective trade-offs unclear. Current Explainable Reinforcement Learning (XRL) methods are typically designed for single scalar rewards and do not account for explanations with respect to distinct objectives or user preferences. To address this gap, in this paper we propose TREX, a Trajectory based Explainability framework to explain Multi-objective Reinforcement Learning policies, based on trajectory attribution. TREX generates trajectories directly from the learned expert policy, across different user preferences and clusters them into semantically meaningful temporal segments. We quantify the influence of these behavioural segments on the Pareto trade-off by training complementary policies that exclude specific clusters, measuring the resulting relative deviation on the observed rewards and actions compared to the original expert policy. Experiments on multi-objective MuJoCo environments - HalfCheetah, Ant and Swimmer, demonstrate the framework's ability to isolate and quantify the specific behavioural patterns.
Authors: Cristian P\'erez-Corral, Alberto Fern\'andez-Hern\'andez, Jose I. Mestre, Manuel F. Dolz, Enrique S. Quintana-Ort\'i
Abstract: Gaussian Error Linear Unit (GELU) is a widely used smooth alternative to Rectifier Linear Unit (ReLU), yet many deployment, compression, and analysis toolchains are most naturally expressed for piecewise-linear (ReLU-type) networks. We study a hardness-parameterized formulation of GELU, f(x;{\lambda})=x{\Phi}({\lambda} x), where {\Phi} is the Gaussian CDF and {\lambda} \in [1, infty) controls gate sharpness, with the goal of turning smooth gated training into a controlled path toward ReLU-compatible models. Learning {\lambda} is non-trivial: naive updates yield unstable dynamics and effective gradient attenuation, so we introduce a constrained reparameterization and an optimizer-aware update scheme. Empirically, across a diverse set of model--dataset pairs spanning MLPs, CNNs, and Transformers, we observe structured layerwise hardness profiles and assess their robustness under different initializations. We further study a deterministic ReLU-ization strategy in which the learned gates are progressively hardened toward a principled target, enabling a post-training substitution of {\lambda}-GELU by ReLU with reduced disruption. Overall, {\lambda}-GELU provides a minimal and interpretable knob to profile and control gating hardness, bridging smooth training with ReLU-centric downstream pipelines.
Authors: Paolo Toccaceli
Abstract: We propose a method for non-parametric conditional distribution estimation based on partitioning covariate-sorted observations into contiguous bins and using the within-bin empirical CDF as the predictive distribution. Bin boundaries are chosen to minimise the total leave-one-out Continuous Ranked Probability Score (LOO-CRPS), which admits a closed-form cost function with $O(n^2 \log n)$ precomputation and $O(n^2)$ storage; the globally optimal $K$-partition is recovered by a dynamic programme in $O(n^2 K)$ time. Minimisation of Within-sample LOO-CRPS turns out to be inappropriate for selecting $K$ as it results in in-sample optimism. So we instead select $K$ by evaluating test CRPS on an alternating held-out split, which yields a U-shaped criterion with a well-defined minimum. Having selected $K^*$ and fitted the full-data partition, we form two complementary predictive objects: the Venn prediction band and a conformal prediction set based on CRPS as the nonconformity score, which carries a finite-sample marginal coverage guarantee at any prescribed level $\varepsilon$. On real benchmarks against split-conformal competitors (Gaussian split conformal, CQR, and CQR-QRF), the method produces substantially narrower prediction intervals while maintaining near-nominal coverage.
Authors: Xinyan Wang, Xiaogeng Liu, Chaowei Xiao
Abstract: Large Reasoning Models (LRMs) achieve strong accuracy on challenging tasks by generating long Chain-of-Thought traces, but suffer from overthinking. Even after reaching the correct answer, they continue generating redundant reasoning steps. This behavior increases latency and compute cost and can also lead to answer drift. Existing mitigation methods either require training-heavy backbone modification or rely on hand-crafted heuristics that do not truly capture overthinking patterns. We propose ROM, the first method that formulates overthinking mitigation as a streaming prediction-and-control problem. ROM attaches a lightweight detection head to the late-layer hidden states of a frozen large language model backbone. It monitors tokens in real time and triggers an early transition to the final answer once overthinking is detected. We also introduce token-level supervision based on solution correctness boundaries and a data augmentation strategy that reduces distilled-data bias. Across seven benchmarks, ROM achieves the highest accuracy (93.51%), the shortest responses (1,159 tokens), and the best response efficiency. Compared with the vanilla baseline, it reduces response length by 47.2% and improves efficiency by 121%. These results show that streaming detection is a promising approach to real-time overthinking mitigation.
Authors: Peter Pak, Amir Barati Farimani
Abstract: This work presents AdditiveLLM2 a multi-modal, domain adapted large language model built upon the instruction tuned variant of the Gemma 3 model using a relatively small dataset of around 50 million tokens. The dataset (AdditiveLLM2-OA) consists of open-access additive manufacturing journal articles with data extracted for the domain adaptive pretraining and visual instruction tuning processes. Various stages of the developed model are evaluated with the Additive-Manufacturing-Benchmark which consists of additive manufacturing domain specific tasks compiled published resources. AdditiveLLM2 exhibits proficiency in both language and vision based tasks, achieving accuracies upwards of 90% in general additive manufacturing knowledge. This domain adaptive pretraining and instruction tuning strategy outline an accessible specialization method for large language models to a domain such as additive manufacturing.
Authors: Tianxiang Xu, Xiaoyan Zhu, Xin Lai, Sizhe Dang, Xin Lian, Hangyu Cheng, Jiayin Wang
Abstract: Ensuring consistency between research papers and their corresponding software implementations is fundamental to software reliability and scientific reproducibility. However, this problem remains underexplored, particularly in the domain of bioinformatics, where discrepancies between methodological descriptions in papers and their actual code implementations are prevalent. To address this gap, this paper introduces a new task, namely paper-code consistency detection, and curates a collection of 48 bioinformatics software projects along with their associated publications. We systematically align sentence-level algorithmic descriptions from papers with function-level code snippets. Combined with expert annotations and a hybrid negative sampling strategy, we construct the first benchmark dataset in the bioinformatics domain tailored to this task, termed BioCon. Based on this benchmark, we further propose a cross-modal consistency detection framework designed to model the semantic relationships between natural language descriptions and code implementations. The framework adopts a unified input representation and leverages pre-trained models to capture deep semantic alignment between papers and code. To mitigate the effects of class imbalance and hard samples, we incorporate a weighted focal loss to enhance model robustness. Experimental results demonstrate that our framework effectively identifies consistency between papers and code in bioinformatics, achieving an accuracy of 0.9056 and an F1 score of 0.8011. Overall, this study opens a new research direction for paper-code consistency analysis and lays the foundation for automated reproducibility assessment and cross-modal understanding in scientific software.
Authors: Julius Kobialka, Emanuel Sommer, Chris Kolb, Juntae Kwon, Daniel Dold, David R\"ugamer
Abstract: Bayesian neural network (BNN) posteriors are often considered impractical for inference, as symmetries fragment them, non-identifiabilities inflate dimensionality, and weight-space priors are seen as meaningless. In this work, we study how overparametrization and priors together reshape BNN posteriors and derive implications allowing us to better understand their interplay. We show that redundancy introduces three key phenomena that fundamentally reshape the posterior geometry: balancedness, weight reallocation on equal-probability manifolds, and prior conformity. We validate our findings through extensive experiments with posterior sampling budgets that far exceed those of earlier works, and demonstrate how overparametrization induces structured, prior-aligned weight posterior distributions.
Authors: Valentin Petrov
Abstract: Inasmuch as the removal of refusal behavior from instruction-tuned language models by directional abliteration requires the extraction of refusal-mediating directions from the residual stream activation space, and inasmuch as the construction of the contrast baseline against which harmful prompt activations are compared has been treated in the existing literature as an implementation detail rather than a methodological concern, the present work investigates whether a topically matched contrast baseline yields superior refusal directions. The investigation is carried out on the Qwen~3.5 2B model using per-category matched prompt pairs, per-class Self-Organizing Map extraction, and Singular Value Decomposition orthogonalization. It was found that topic-matched contrast produces no functional refusal directions at any tested weight level on any tested layer, while unmatched contrast on the same model, same extraction code, and same evaluation protocol achieves complete refusal elimination on six layers. The geometric analysis of the failure establishes that topic-matched subtraction cancels the dominant activation component shared between harmful and harmless prompts of the same subject, reducing the extracted direction magnitude below the threshold at which weight-matrix projection perturbs the residual stream. The implications for the design of contrast baselines in abliteration research are discussed.
Authors: Aurora Esteban, Amelia Zafra, Sebasti\'an Ventura
Abstract: Due to the prevalence of temporal data and its inherent dependencies in many real-world problems, time series classification is of paramount importance in various domains. However, existing models often struggle with series of variable length or high dimensionality. This paper introduces the MIHT (Multi-instance Hoeffding Tree) algorithm, an efficient model that uses multi-instance learning to classify multivariate and variable-length time series while providing interpretable results. The algorithm uses a novel representation of time series as "bags of subseries," together with an optimization process based on incremental decision trees that distinguish relevant parts of the series from noise. This methodology extracts the underlying concept of series with multiple variables and variable lengths. The generated decision tree is a compact, white-box representation of the series' concept, providing interpretability insights into the most relevant variables and segments of the series. Experimental results demonstrate MIHT's superiority, as it outperforms 11 state-of-the-art time series classification models on 28 public datasets, including high-dimensional ones. MIHT offers enhanced accuracy and interpretability, making it a promising solution for handling complex, dynamic time series data.
Authors: Kexin Huang, Haoming Meng, Junkang Wu, Jinda Lu, Chiyu Ma, Ziqian Chen, Xue Wang, Bolin Ding, Jiancan Wu, Xiang Wang, Xiangnan He, Guoyin Wang, Jingren Zhou
Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models. While existing analyses identify that RLVR-induced changes are sparse, they primarily focus on the \textbf{magnitude} of these updates, largely overlooking their \textbf{direction}. In this work, we argue that the direction of updates is a more critical lens for understanding RLVR's effects, which can be captured by the signed, token-level log probability difference $\Delta\log p$ between the base and final RLVR models. Through statistical analysis and token-replacement interventions, we demonstrate that $\Delta\log p$ more effectively identifies sparse, yet reasoning-critical updates than magnitude-based metrics (\eg divergence or entropy). Building on this insight, we propose two practical applications: (1) a \textit{test-time extrapolation} method that amplifies the policy along the learned $\Delta\log p$ direction to improve reasoning accuracy without further training; (2) a \textit{training-time reweighting} method that focuses learning on low-probability (corresponding to higher $\Delta\log p$) tokens, which improves reasoning performance across models and benchmarks. Our work establishes the direction of change as a key principle for analyzing and improving RLVR.
Authors: Shreeram Murali, Cristian R. Rojas, Dominik Baumann
Abstract: While both classical and neural network classifiers can achieve high accuracy, they fall short on offering uncertainty bounds on their predictions, making them unfit for safety-critical applications. Existing kernel-based classifiers that provide such bounds scale with $\mathcal O (n^{\sim3})$ in time, making them computationally intractable for large datasets. To address this, we propose a novel, computationally efficient classification algorithm based on the Nadaraya-Watson estimator, for whose estimates we derive frequentist uncertainty intervals. We evaluate our classifier on synthetically generated data and on electrocardiographic heartbeat signals from the MIT-BIH Arrhythmia database. We show that the method achieves competitive accuracy $>$\SI{96}{\percent} at $\mathcal O(n)$ and $\mathcal O(\log n)$ operations, while providing actionable uncertainty bounds. These bounds can, e.g., aid in flagging low-confidence predictions, making them suitable for real-time settings with resource constraints, such as diagnostic monitoring or implantable devices.
Authors: Alois Bachmann
Abstract: This paper proposes $\mathrm{dynActivation}$, a per-layer trainable activation defined as $f_i(x) = \mathrm{BaseAct}(x)(\alpha_i - \beta_i) + \beta_i x$, where $\alpha_i$ and $\beta_i$ are lightweight learned scalars that interpolate between the base nonlinearity and a linear path and $\mathrm{BaseAct}(x)$ resembles any ReLU-like function. The static and dynamic ReLU-like variants are then compared across multiple vision tasks, language modeling tasks, and ablation studies. The results suggest that dynActivation variants tend to linearize deep layers while maintaining high performance, which can improve training efficiency by up to $+54\%$ over ReLU. On CIFAR-10, dynActivation(Mish) improves over static Mish by up to $+14.02\%$ on AttentionCNN with an average improvment by $+6.00\%$, with a $24\%$ convergence-AUC reduction relative to Mish (2120 vs. 2785). In a 1-to-75-layer MNIST depth-scaling study, dynActivation never drops below $95\%$ test accuracy ($95.3$--$99.3\%$), while ReLU collapses below $80\%$ at 25 layers. Under FGSM at $\varepsilon{=}0.08$, dynActivation(Mish) incurs a $55.39\%$ accuracy drop versus $62.79\%$ for ReLU ($7.40\%$ advantage). Transferred to language modeling, a new proposed dynActGLU-variant achieves a $10.3\%$ relative perplexity reduction over SwiGLU at 5620 steps (4.047 vs. 4.514), though the gap vanishes at 34300 steps.
Authors: Abolfazl Hashemi
Abstract: A celebrated method for Variational Inequalities (VIs) is Extragradient (EG), which can be viewed as a standard discrete-time integration scheme. With this view in mind, in this paper we show that EG may suffer from discretization bias when applied to non-linear vector fields, conservative or otherwise. To resolve this discretization shortcoming, we introduce RAndomized Mid-Point for debiAsed Gradient Extrapolation (RAMPAGE) and its variance-reduced counterpart, RAMPAGE+ which leverages antithetic sampling. In contrast with EG, both methods are unbiased. Furthermore, leveraging negative correlation, RAMPAGE+ acts as an unbiased, geometric path-integrator that completely removes internal first-order terms from the variance, provably improving upon RAMPAGE. We further demonstrate that both methods enjoy provable $\mathcal{O}(1/k)$ convergence guarantees for a range of problems including root finding under co-coercive, co-hypomonotone, and generalized Lipschitzness regimes. Furthermore, we introduce symmetrically scaled variants to extend our results to constrained VIs. Finally, we provide convergence guarantees of both methods for stochastic and deterministic smooth convex-concave games. Somewhat interestingly, despite being a randomized method, RAMPAGE+ attains purely deterministic bounds for a number of the studied settings.
Authors: Moritz G\"ogl, Christopher Yau
Abstract: We study multimodal survival analysis integrating clinical text, tabular covariates, and genomic profiles using locally deployable large language models (LLMs). As many institutions face tight computational and privacy constraints, this setting motivates the use of lightweight, on-premises models. Our approach jointly estimates calibrated survival probabilities and generates concise, evidence-grounded prognosis text via teacher-student distillation and principled multimodal fusion. On a TCGA cohort, it outperforms standard baselines, avoids reliance on cloud services and associated privacy concerns, and reduces the risk of hallucinated or miscalibrated estimates that can be observed in base LLMs.
Authors: Dharshan Kumaran, Nathaniel Daw, Simon Osindero, Petar Velickovic, Viorica Patraucean
Abstract: Metacognition -- the ability to assess one's own cognitive performance -- is documented across species, with internal confidence estimates serving as a key signal for adaptive behavior. While confidence can be extracted from Large Language Model (LLM) outputs, whether models actively use these signals to regulate behavior remains a fundamental question. We investigate this through a four-phase abstention paradigm.Phase 1 established internal confidence estimates in the absence of an abstention option. Phase 2 revealed that LLMs apply implicit thresholds to these estimates when deciding to answer or abstain. Confidence emerged as the dominant predictor of behavior, with effect sizes an order of magnitude larger than knowledge retrieval accessibility (RAG scores) or surface-level semantic features. Phase 3 provided causal evidence through activation steering: manipulating internal confidence signals correspondingly shifted abstention rates. Finally, Phase 4 demonstrated that models can systematically vary abstention policies based on instructed thresholds.Our findings indicate that abstention arises from the joint operation of internal confidence representations and threshold-based policies, mirroring the two-stage metacognitive control found in biological systems. This capacity is essential as LLMs transition into autonomous agents that must recognize their own uncertainty to decide when to act or seek help.
Authors: Yurong Chen, Zhiyi Huang, Michael I. Jordan, Haipeng Luo
Abstract: We study calibeating, the problem of post-processing external forecasts online to minimize cumulative losses and match an informativeness-based benchmark. Unlike prior work, which analyzed calibeating for specific losses with specific arguments, we reduce calibeating to existing online learning techniques and obtain results for general proper losses. More concretely, we first show that calibeating is minimax-equivalent to regret minimization. This recovers the $O(\log T)$ calibeating rate of Foster and Hart [FH23] for the Brier and log losses and its optimality, and yields new optimal calibeating rates for mixable losses and general bounded losses. Second, we prove that multi-calibeating is minimax-equivalent to the combination of calibeating and the classical expert problem. This yields new optimal multi-calibeating rates for mixable losses, including Brier and log losses, and general bounded losses. Finally, we obtain new bounds for achieving calibeating and calibration simultaneously for the Brier loss. For binary predictions, our result gives the first calibrated algorithm that at the same time also achieves the optimal $O(\log T)$ calibeating rate.
Authors: Oscar Novo, Oscar Bastidas-Jossa, Alberto Calvo, Antonio Peris, Carlos Kuchkovsky
Abstract: Recent advances in large language models (LLMs) have enabled the automation of an increasing number of programming tasks, including code generation for scientific and engineering domains. In rapidly evolving software ecosystems such as quantum software development, where frameworks expose complex abstractions, a central question is how best to incorporate domain knowledge into LLM-based assistants while preserving maintainability as libraries evolve. In this work, we study specialization strategies for Qiskit code generation using the Qiskit-HumanEval benchmark. We compare a parameter-specialized fine-tuned baseline introduced in prior work against a range of recent general-purpose LLMs enhanced with retrieval-augmented generation (RAG) and agent-based inference with execution feedback. Our results show that modern general-purpose LLMs consistently outperform the parameter-specialized baseline. While the fine-tuned model achieves approximately 47% pass@1 on Qiskit-HumanEval, recent general-purpose models reach 60-65% under zero-shot and retrieval-augmented settings, and up to 85% for the strongest evaluated model when combined with iterative execution-feedback agents -representing an improvement of more than 20% over zero-shot general-purpose performance and more than 35% over the parameter-specialized baseline. Agentic execution feedback yields the most consistent improvements, albeit at increased runtime cost, while RAG provides modest and model-dependent gains. These findings indicate that performance gains can be achieved without domain-specific fine-tuning, instead relying on inference-time augmentation, thereby enabling a more flexible and maintainable approach to LLM-assisted quantum software development.
Authors: Kangqi Ni, Wenyue Hua, Xiaoxiang Shi, Jiang Guo, Shiyu Chang, Tianlong Chen
Abstract: Multi-agent applications often execute complex tasks as multi-stage workflows, where each stage is an LLM call whose output becomes part of context for subsequent steps. Existing LLM serving systems largely assume homogeneous clusters with identical model replicas. This design overlooks the potential of heterogeneous deployments, where models of different sizes and capabilities enable finer trade-offs between latency and performance. However, heterogeneity introduces new challenges in scheduling across models with diverse throughput and performance. We present Chimera, a predictive scheduling system for multi-agent workflow serving on heterogeneous LLM clusters that jointly improves end-to-end latency and task performance. Chimera applies semantic routing to estimate per-model confidence scores for each request, predicts the total remaining output length of the workflow, and estimates per-model congestion using in-flight predicted token volumes for load balancing. We evaluate Chimera on representative agentic workflows for code generation and math reasoning using multiple heterogeneous LLM configurations. Across comparable settings, Chimera traces the best latency-performance frontier, reducing end-to-end latency by 1.2--2.4$\times$ and improving task performance by 8.0-9.5 percentage points on average over competitive baselines including vLLM.
Authors: Kexian Tang, Jiani Wang, Shaowen Wang, Kaifeng Lyu
Abstract: While large language models (LLMs) are pretrained on massive amounts of data, their knowledge coverage remains incomplete in specialized, data-scarce domains, motivating extensive efforts to study synthetic data generation for knowledge injection. We propose SPA (Scaling Prompt-engineered Augmentation), a simple but tough-to-beat baseline that uses a small set of carefully designed prompts to generate large-scale synthetic data for knowledge injection. Through systematic comparisons, we find that SPA outperforms several strong baselines. Furthermore, we identify two key limitations of prior approaches: (1) while RL-based methods may improve the token efficiency of LLM-based data augmentation at small scale, they suffer from diversity collapse as data scales, leading to diminishing returns; and (2) while multi-stage prompting may outperform simple augmentation methods, their advantages can disappear after careful prompt tuning. Our results suggest that, for knowledge injection, careful prompt design combined with straightforward large-scale augmentation can be surprisingly effective, and we hope SPA can serve as a strong baseline for future studies in this area. Our code is available at https://github.com/Tangkexian/SPA.
Authors: Qilin Wang
Abstract: Modern time series forecasting is evaluated almost entirely through passive observation of single historical trajectories, rendering claims about a model's robustness to non-stationarity fundamentally unfalsifiable. We propose a paradigm shift toward interventionist, exact-statistical benchmarking. By systematically titrating calibrated Gaussian observation noise into known chaotic and stochastic dynamical systems, we transform forecasting from a black-box sequence matching game into an exact distributional inference task. Because the underlying data-generating process and noise variance are mathematically explicit, evaluation can rely on exact negative log-likelihoods and calibrated distributional tests rather than heuristic approximations. To fully leverage this framework, we extend the Fern architecture into a probabilistic generative model that natively parameterizes the Symmetric Positive Definite (SPD) cone, outputting calibrated joint covariance structures without the computational bottleneck of generic Jacobian modeling. Under this rigorous evaluation, we find that state-of-the-art zero-shot foundation models behave consistently with the context-parroting mechanism, failing systematically under non-stationary regime shifts and elevated noise. In contrast, Fern explicitly captures the invariant measure and multivariate geometry of the underlying dynamics, maintaining structural fidelity and statistically sharp calibration precisely where massive sequence-matching models collapse.
Authors: Changxiao Cai, Gen Li
Abstract: Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) models for language modeling, allowing flexible generation order and parallel generation of multiple tokens. However, this flexibility introduces a challenge absent in AR models: the \emph{decoding strategy} -- which determines the order and number of tokens generated at each iteration -- critically affects sampling efficiency. Among decoding strategies explored in practice, confidence-based methods, which adaptively select which and how many tokens to unmask based on prediction confidence, have shown strong empirical performance. Despite this success, our theoretical understanding of confidence-based decoding remains limited. In this work, we develop the first theoretical analysis framework for confidence-based decoding in DLMs. We focus on an entropy sum-based strategy that continues unmasking tokens within each iteration until the cumulative entropy exceeds a threshold, and show that it achieves $\varepsilon$-accurate sampling in KL divergence with an expected number of iterations $\widetilde O(H(X_0)/\varepsilon)$, where $H(X_0)$ denotes the entropy of the target data distribution. Notably, this strategy yields substantial sampling acceleration when the data distribution has low entropy relative to the sequence length, while automatically adapting to the intrinsic complexity of data without requiring prior knowledge or hyperparameter tuning. Overall, our results provide a theoretical foundation for confidence-based decoding and may inform the design of more efficient decoding strategies for DLMs.
Authors: Zakaria Mhammedi, James Cohan
Abstract: The process of discovery requires active exploration -- the act of collecting new and informative data. However, efficient autonomous exploration remains a major unsolved problem. The dominant paradigm addresses this challenge by using Reinforcement Learning (RL) to train agents with intrinsic motivation, maximizing a composite objective of extrinsic and intrinsic rewards. We suggest that this approach incurs unnecessary overhead: while policy optimization is necessary for precise task execution, employing such machinery solely to expand state coverage may be inefficient. In this paper, we propose a new paradigm that explicitly separates exploration from exploitation and bypasses RL during the exploration phase. Our method uses a tree-search strategy inspired by the Go-With-The-Winner algorithm, paired with a measure of epistemic uncertainty to systematically drive exploration. By removing the overhead of policy optimization, our approach explores an order of magnitude more efficiently than standard intrinsic motivation baselines on hard Atari benchmarks. Further, we demonstrate that the discovered trajectories can be distilled into deployable policies using existing supervised backward learning algorithms, achieving state-of-the-art scores by a wide margin on Montezuma's Revenge, Pitfall!, and Venture without relying on domain-specific knowledge. Finally, we demonstrate the generality of our framework in high-dimensional continuous action spaces by solving the MuJoCo Adroit dexterous manipulation and AntMaze tasks in a sparse-reward setting, directly from image observations and without expert demonstrations or offline datasets. To the best of our knowledge, this has not been achieved before.
Authors: Alexandra Zelenin, Alexandra Zhuravlyova
Abstract: Weight-Decomposed Low-Rank Adaptation (DoRA) extends LoRA by decoupling weight magnitude from direction, but its forward pass requires the row-wise norm of W + sBA, a computation that every major framework we surveyed implements by materializing the dense [d_out, d_in] product BA. At d_in = 8192 and rank r = 384, a single module's norm requires about 512 MB of transient working memory in bf16, making high-rank DoRA costly and often infeasible on common single-GPU setups once hundreds of adapted modules and checkpointing are involved. We present two systems contributions. A factored norm decomposes the squared norm into base, cross, and Gram terms computable through O(d_out r + r^2) intermediates, eliminating the dense product. Fused Triton kernels collapse the four-kernel DoRA composition into a single pass, reducing memory traffic by about 4x and using a numerically stable form that avoids catastrophic cancellation in the near-unity rescaling regime where magnitude scales concentrate in practice. Across six 8-32B vision-language models (VLMs) on three NVIDIA GPUs (RTX 6000 PRO, H200, B200) at r = 384 in bf16, the fused implementation is 1.5-2.0x faster than Hugging Face PEFT's DoRA implementation for inference and 1.5-1.9x faster for gradient computation (optimizer step excluded), with up to 7 GB lower peak VRAM. Microbenchmarks on six GPUs spanning four architecture generations (L40S, A100, RTX 6000 PRO, H200, B200, B300) confirm 1.5-2.7x compose-kernel speedup. Final-logit cosine similarity exceeds 0.9999 across all model/GPU pairs, and multi-seed training curves match within 7.1 x 10^-4 mean per-step loss delta over 2000 steps.
Authors: Zizhe Zhang, Yicong Wang, Zhiquan Zhang, Tianyu Li, Nadia Figueroa
Abstract: Conventional passivity-based torque controllers for manipulators are typically unconstrained, which can lead to safety violations under external perturbations. In this paper, we employ viability theory to pre-compute safe sets in the state-space of joint positions and velocities. These viable sets, constructed via data-driven and analytical methods for self-collision avoidance, external object collision avoidance and joint-position and joint-velocity limits, provide constraints on joint accelerations and thus joint torques via the robot dynamics. A quadratic programming-based control framework enforces these constraints on a passive controller tracking a dynamical system, ensuring the robot states remain within the safe set in an infinite time horizon. We validate the proposed approach through simulations and hardware experiments on a 7-DoF Franka Emika manipulator. In comparison to a baseline constrained passive controller, our method operates at higher control-loop rates and yields smoother trajectories.
Authors: Yunbei Zhang, Yingqiang Ge, Weijie Xu, Yuhui Xu, Jihun Hamm, Chandan K. Reddy
Abstract: Current multimodal red teaming treats images as wrappers for malicious payloads via typography or adversarial noise. These attacks are structurally brittle, as standard defenses neutralize them once the payload is exposed. We introduce Visual Exclusivity (VE), a more resilient Image-as-Basis threat where harm emerges only through reasoning over visual content such as technical schematics. To systematically exploit VE, we propose Multimodal Multi-turn Agentic Planning (MM-Plan), a framework that reframes jailbreaking from turn-by-turn reaction to global plan synthesis. MM-Plan trains an attacker planner to synthesize comprehensive, multi-turn strategies, optimized via Group Relative Policy Optimization (GRPO), enabling self-discovery of effective strategies without human supervision. To rigorously benchmark this reasoning-dependent threat, we introduce VE-Safety, a human-curated dataset filling a critical gap in evaluating high-risk technical visual understanding. MM-Plan achieves 46.3% attack success rate against Claude 4.5 Sonnet and 13.8% against GPT-5, outperforming baselines by 2--5x where existing methods largely fail. These findings reveal that frontier models remain vulnerable to agentic multimodal attacks, exposing a critical gap in current safety alignment. Warning: This paper contains potentially harmful content.
Authors: Jiayun Wu, Peixu Hou, Shan Qu, Peng Zhang, Ning Gu, Tun Lu
Abstract: Reward models (RMs) are critical for aligning Large Language Models via Reinforcement Learning from Human Feedback (RLHF). While Generative Reward Models (GRMs) achieve superior accuracy through chain-of-thought (CoT) reasoning, they incur substantial computational costs. Conversely, Scalar Reward Models (SRMs) offer efficiency but suffer from limited performance and adaptability in complex scenarios. We introduce Fast-Slow Thinking Reward Models (F/S-RM), a hybrid RM architecture inspired by Dual Process Theory. It trains a single model to integrate two distinct reward paradigms: first-token prediction as a scalar score (fast thinking) and CoT-based judgment (slow thinking), regulated by a dual-confidence activation mechanism that determines when to activate slow thinking. F/S-RM achieves a 1.2% relative performance improvement over state-of-the-art models while reducing token consumption by 20.8%. Code and data will be publicly available.
Authors: Jiaqi Yuan, Jialu Wang, Zihan Wang, Qingyun Sun, Ruijie Wang, Jianxin Li
Abstract: Generative search engines represent a transition from traditional ranking-based retrieval to Large Language Model (LLM)-based synthesis, transforming optimization goals from ranking prominence towards content inclusion. Generative Engine Optimization (GEO), specifically, aims to maximize visibility and attribution in black-box summarized outputs by strategically manipulating source content. However, existing methods rely on static heuristics, single-prompt optimization, or engine preference rule distillation that is prone to overfitting. They cannot flexibly adapt to diverse content or the changing behaviors of generative engines. Moreover, effectively optimizing these strategies requires an impractical amount of interaction feedback from the engines. To address these challenges, we propose AgenticGEO, a self-evolving agentic framework formulating optimization as a content-conditioned control problem, which enhances intrinsic content quality to robustly adapt to the unpredictable behaviors of black-box engines. Unlike fixed-strategy methods, AgenticGEO employs a MAP-Elites archive to evolve diverse, compositional strategies. To mitigate interaction costs, we introduce a Co-Evolving Critic, a lightweight surrogate that approximates engine feedback for content-specific strategy selection and refinement, efficiently guiding both evolutionary search and inference-time planning. Through extensive in-domain and cross-domain experiments on two representative engines, AgenticGEO achieves state-of-the-art performance and demonstrates robust transferability, outperforming 14 baselines across 3 datasets. Our code and model are available at: https://github.com/AIcling/agentic_geo.
Authors: Hongduan Tian, Xiao Feng, Ziyuan Zhao, Xiangyu Zhu, Rolan Yan, Bo Han
Abstract: Large language models (LLMs) have recently demonstrated impressive capabilities in reasoning tasks. Currently, mainstream LLM reasoning frameworks predominantly focus on scaling up inference-time sampling to enhance performance. In particular, among all LLM reasoning frameworks, *multi-agent debate* (MAD), which employs multiple LLMs as agents to perform reasoning in the way of multi-round debate, has emerged as a powerful reasoning paradigm since it allows agents to access previous memories to alleviate fallacious content and refine their reasoning iteratively in each debate round. However, although MAD significantly improves the reasoning capabilities of LLMs, in this paper, we observe that there remain erroneous memories, and LLM agents are vulnerable to these erroneous memories. To explore this phenomenon, we provide a theoretical insight that the performance of MAD is highly dependent on the quality of memories derived from the previous debate, indicating that the existence of erroneous memories poses a threat to the performance of MAD. To address this problem, we introduce a simple yet effective multi-agent debate framework, *multi-agent debate with memory masking* (MAD-M$^2$), to improve the robustness of MAD by allowing LLM agents to mask erroneous memories from the previous debate round at the beginning of each debate round. In this way, MAD-M$^2$ can polish the contextual information before each debate round by preserving informative and meaningful memories while discarding the erroneous memories. Extensive experiments and analyses on mainstream mathematical and logical reasoning benchmarks demonstrate that MAD-M$^2$ can identify the erroneous memories and achieve better performance in reasoning than MAD.
Authors: Michael Hersche, Nicolas Menet, Ronan Tanios, Abbas Rahimi
Abstract: Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) models, offering sub-linear generation latency and bidirectional capabilities that are particularly appealing for code generation and editing. Achieving sub-linear latency in discrete DLMs requires predicting multiple tokens in parallel. However, standard DLMs sample tokens independently from conditional marginal distributions, failing to capture the joint dependencies among concurrently generated tokens. As a result, they often lead to syntactic inconsistencies and break multi-token structures. In this work, we introduce CoDiLA (Coherent Diffusion with Local Autoregression), a method that reconciles parallel sampling with local dependency modeling. Rather than forcing the DLM to resolve fine-grained syntax, CoDiLA delegates local decoding to a small, auxiliary AR model operating on the diffusion latents. This design allows for parallel block generation while ensuring sequential validity within each block and maintaining core DLM capabilities, including bidirectional modeling across blocks. We demonstrate that using a highly compact auxiliary AR model (e.g., 0.6B parameters) effectively eliminates coherence artifacts, establishing a new Pareto frontier for accuracy and speed in code generation benchmarks.
Authors: Kenan Hasanaliyev, Silas Alberti, Jenny Hamer, Dheeraj Rajagopal, Kevin Robinson, Jasper Snoek, Victor Veitch, Alexander Nicholas D'Amour
Abstract: Reward models are a standard tool to score responses from LLMs. Reward models are built to rank responses to a fixed prompt sampled from a single model, for example to choose the best of n sampled responses. In this paper, we study whether scores from response-level reward models lifted to score a model's suitability for a prompt, prior to seeing responses from that model. Specifically, we show that it is straightforward to predict the expected reward that an LLM would earn from the reward model under repeated sampling. Further, we show that these expected reward predictions are precise and discriminative enough to support an application to a model routing protocol that routes prompts to models at inference time to maximize reward while controlling computational cost. We demonstrate the performance of this routing procedure on the open-perfectblend dataset, using a model pool composed of Llama3.1-Instruct 8B/70B, Gemma2-IT 9B/27B, and Gemma1-IT 7B models. Our simple expected reward prediction--based routing (ERP) outperforms baselines that route prompts to models with the best average performance within each prompt's category, and explains the success of more complex routing protocols that implicitly estimate an expected reward. Our approach has the added advantage of being trivially extensible as new models are added to the pool.
Authors: Samuel Cestola, Tianxiang Xia, Zheng Weiyan, Zheng Pengfei, Diego Didona
Abstract: Retrieval-augmented generation improves large language models' accuracy by adding relevant retrieved text to the prompt. Chunk level caching (CLC) accelerates inference by precomputing KV caches for these retrieved chunks and reusing them. However, these caches miss cross-attention dependencies between chunks, which can reduce output quality. Several methods try to improve CLC accuracy using different techniques. We make two main contributions. First, we show that existing CLC approaches have fundamental limitations that limit their accuracy or their applicability. We back this conclusion with an extensive CLC system experimental evaluation. Second, we observe that existing CLC techniques are complementary. We leverage this insight to propose a new CLC design that carefully combines them and achieves better accuracy.
Authors: Lorenzo Noci, Gregor Bachmann, Seyed-Mohsen Moosavi-Dezfooli, Moin Nabi
Abstract: Autoregressive language models trained with next-token prediction generate text by sampling one discrete token at a time. Although very scalable, this objective forces the model to commit at every step, preventing it from exploring or reflecting upon multiple plausible continuations. Furthermore, the compute allocation across tokens is uniform; every token is formed based on a single forward-pass, potentially limiting the model's expressiveness in cases where difficult tokens require inherently more compute. Towards addressing these limitations, we introduce latent lookahead, a training strategy that enables models to "think" before generating: at selected positions in the sequence, before committing to the next token, the model performs a multi-step lookahead in latent space. More precisely, instead of sampling future tokens, we leverage the network's latent space by recursively feeding its hidden states back into the context for $\tau$ steps, investing more compute on predicting that token. This produces $\tau$ latent predictions that are supervised against the next $\tau$ ground-truth tokens, encouraging the model to "lookahead" and refine its prediction. We show that latent lookahead substantially outperforms both autoregressive and non-autoregressive baselines on planning tasks such as maze solving, Sudoku, and ProsQA, where foresight is essential.
Authors: Kushal Khemani
Abstract: Immediate feedback is a foundational requirement of effective AI-mediated learning, yet the energy and latency costs of delivering it remain largely unexamined. This study investigates the latency-energy-learning trade-off in AI tutoring through an empirical comparison of two on-device inference configurations of Microsoft Phi-3 Mini (4k-instruct) on an NVIDIA T4 GPU: full-precision FP16 and 4-bit NormalFloat (NF4) quantisation. Both were evaluated under KV-cache-enabled inference across 500 educational prompts spanning five secondary school subject domains. Pedagogical quality was assessed for each of the 1000 generated responses by a hybrid panel of 10 Cambridge International teachers and three frontier AI systems using a four-dimension rubric. We introduce Learning-per-Watt (LpW), a novel metric quantifying pedagogical value per unit of energy over the learner's waiting window. Under realistic deployment, NF4 achieves lower per-inference energy than FP16 (329 J vs. 369 J) but higher latency (13.4 s vs. 9.2 s), yielding a modest FP16 advantage in LpW of 1.33x at a quality difference of 0.19 points. Under cache-disabled inference -- used in offline evaluation but absent from real deployments -- the gap widens to 7.4x, overstating the FP16 advantage by more than fivefold. Quantisation efficiency is hardware-dependent and inference-regime dependent, with significant implications for equitable AI tutoring deployment in low-resource settings.
Authors: Ryan Cory-Wright, Jean Pauphilet
Abstract: We develop tractable convex relaxations for rank-constrained quadratic optimization problems over $n \times m$ matrices, a setting for which tractable relaxations are typically only available when the objective or constraints admit spectral (permutation-invariant) structure. We derive lifted semidefinite relaxations that do not require such spectral terms. Although a direct lifting introduces a large semidefinite constraint in dimension $n^2 + nm + 1$, we prove that many blocks of moment matrix are redundant and derive an equivalent compact relaxation that only involves two semidefinite constraints of dimension $nm + 1$ and $n+m$ respectively. For matrix completion, basis pursuit, and reduced-rank regression problems, we exploit additional structure to obtain even more compact formulations involving semidefinite matrices of dimension at most $2\max(n,m)$. Overall, we obtain scalable semidefinite bounds for a broad class of low-rank quadratic problems.
Authors: Ahmed Abouelazm, Jonas Michel, Daniel Bogdoll, Philip Sch\"orner, J. Marius Z\"ollner
Abstract: Autonomous driving involves multiple, often conflicting objectives such as safety, efficiency, and comfort. In reinforcement learning (RL), these objectives are typically combined through weighted summation, which collapses their relative priorities and often yields policies that violate safety-critical constraints. To overcome this limitation, we introduce the Preordered Multi-Objective MDP (Pr-MOMDP), which augments standard MOMDPs with a preorder over reward components. This structure enables reasoning about actions with respect to a hierarchy of objectives rather than a scalar signal. To make this structure actionable, we extend distributional RL with a novel pairwise comparison metric, Quantile Dominance (QD), that evaluates action return distributions without reducing them into a single statistic. Building on QD, we propose an algorithm for extracting optimal subsets, the subset of actions that remain non-dominated under each objective, which allows precedence information to shape both decision-making and training targets. Our framework is instantiated with Implicit Quantile Networks (IQN), establishing a concrete implementation while preserving compatibility with a broad class of distributional RL methods. Experiments in Carla show improved success rates, fewer collisions and off-road events, and deliver statistically more robust policies than IQN and ensemble-IQN baselines. By ensuring policies respect rewards preorder, our work advances safer, more reliable autonomous driving systems.
Authors: Chen Xiong, Ziwen Wang, Deqi Wang, Cheng Wang, Yiyang Chen, He Zhang, Chao Gou
Abstract: Autonomous driving testing increasingly relies on mining safety critical scenarios from large scale naturalistic driving data, yet existing screening pipelines still depend on manual risk annotation and expensive frame by frame risk evaluation, resulting in low efficiency and weakly grounded risk quantification. To address this issue, we propose a driver risk fusion based hazardous scenario screening method for autonomous driving. During training, the method combines an improved Driver Risk Field with a dynamic cost model to generate high quality risk supervision signals, while during inference it directly predicts scenario level risk scores through fast forward passes, avoiding per frame risk computation and enabling efficient large scale ranking and retrieval. The improved Driver Risk Field introduces a new risk height function and a speed adaptive look ahead mechanism, and the dynamic cost model integrates kinetic energy, oriented bounding box constraints, and Gaussian kernel diffusion smoothing for more accurate interaction modeling. We further design a risk trajectory cross attention decoder to jointly decode risk and trajectories. Experiments on the INTERACTION and FLUID datasets show that the proposed method produces smoother and more discriminative risk estimates. On FLUID, it achieves an AUC of 0.792 and an AP of 0.825, outperforming PODAR by 9.1 percent and 5.1 percent, respectively, demonstrating its effectiveness for scalable risk labeling and hazardous scenario screening.
Authors: Montgomery Flora, Samuel Varga, Corey Potvin, Noah Lang
Abstract: While machine learning (ML) post-processing of convection-allowing model (CAM) output for severe weather hazards (large hail, damaging winds, and/or tornadoes) has shown promise for very short lead times (0-3 hours), its application to slightly longer forecast windows remains relatively underexplored. In this study, we develop and evaluate a grid-based ML framework to predict the probability of severe weather hazards over the next 2-6 hours using forecast output from the Warn-on-Forecast System (WoFS). Our dataset includes WoFS ensemble forecasts valid every 5 minutes out to 6 hours from 108 days during the 2019--2023 NOAA Hazardous Weather Testbed Spring Forecasting Experiments. We train ML models to generate probabilistic forecasts of severe weather akin to Storm Prediction Center outlooks (i.e., likelihood of a tornado, severe wind, or severe hail event within 36 km of each point). We compare a histogram gradient-boosted tree (HGBT) model and a deep learning U-Net approach against a carefully calibrated baseline generated from 2-5 km updraft helicity. Results indicate that the HGBT and U-Net outperform the baseline, particularly at higher probability thresholds. The HGBT achieves the best performance metrics, but predicted probabilities cap at 60% while the U-net forecasts extend to 100%. Similar to previous studies, the U-Net produces spatially smoother guidance than the tree-based method. These findings add to the growing evidence of the effectiveness of ML-based CAM post-processing for providing short-term severe weather guidance.
Authors: Abdul Aziz Snoubara, Baraa Al_Maradni, Haya Al_Naal, Malek Al_Madrmani, Roaa Jdini, Seedra Zarzour, Khloud Al Jallad
Abstract: Speech-based AI educational applications have gained significant interest in recent years, particularly for children. However, children speech research remains limited due to the lack of publicly available datasets, especially for low-resource languages such as Arabic.This paper presents Abjad-Kids, an Arabic speech dataset designed for kindergarten and primary education, focusing on fundamental learning of alphabets, numbers, and colors. The dataset consists of 46397 audio samples collected from children aged 3 - 12 years, covering 141 classes. All samples were recorded under controlled specifications to ensure consistency in duration, sampling rate, and format. To address high intra-class similarity among Arabic phonemes and the limited samples per class, we propose a hierarchical audio classification based on CNN-LSTM architectures. Our proposed methodology decomposes alphabet recognition into a two-stage process: an initial grouping classification model followed by specialized classifiers for each group. Both strategies: static linguistic-based grouping and dynamic clustering-based grouping, were evaluated. Experimental results demonstrate that static linguistic-based grouping achieves superior performance. Comparisons between traditional machine learning with deep learning approaches, highlight the effectiveness of CNN-LSTM models combined with data augmentation. Despite achieving promising results, most of our experiments indicate a challenge with overfitting, which is likely due to the limited number of samples, even after data augmentation and model regularization. Thus, future work may focus on collecting additional data to address this issue. Abjad-Kids will be publicly available. We hope that Abjad-Kids enrich children representation in speech dataset, and be a good resource for future research in Arabic speech classification for kids.
Authors: Tianshu Zhang, Huan Sun
Abstract: Autonomous science agents built on large language models (LLMs) are increasingly used to generate hypotheses, design experiments, and produce reports. However, prior work mainly targets open-ended scientific problems with subjective outputs that are difficult to evaluate. Scientific coding benchmarks, by contrast, provide executable outputs for objective assessment. Existing approaches remain engineering-driven pipelines, revealing the need for structured, end-to-end science agent frameworks for scientific coding tasks. We address this gap by focusing on scientific coding tasks, where evaluation can be made rigorously, and introducing an agent framework SciNav (Scientific Navigator) that enables more effective solution exploration. Our framework is designed to operate under constrained search budgets, moving beyond reliance on pre-defined success metrics and prolonged search cycles. Inspired by findings that comparative judgments often reveal finer-grained quality differences and therefore provide greater discriminative power than absolute scoring, our framework leverages pairwise relative judgments within a tree search process to select top-K promising solution branches, prune low-potential ones, and progressively narrow down the solution candidates on the selected branches guided by relative comparisons. We demonstrate our agent's effectiveness across different types of tasks on two benchmarks. Experiments show that SciNav significantly outperforms direct prompting and prior agents like OpenHands and Self-Debug across different base models, task types, and difficulty levels, and exceeds different frontier comparators such as random selection and LLM absolute scoring. These results confirm the strength of our agent design and highlight the effectiveness of relative judgment-guided top-K search for high-quality scientific coding, marking a step toward more practical science agents.
Authors: Marek Zylinski, Bartosz Tomasz Smigielski, Gerard Cybulski
Abstract: Reliable detection of event-related potentials (ERPs) at the single-trial level remains a major challenge due to the low signal-to-noise ratio EEG recordings. In this work, we investigate whether incorporating prior knowledge about ERP templates into deep learning models can improve detection performance. We employ the Deep-Match framework for ERP detection using multi-channel EEG signals. The model is trained in two stages. First, an encoder-decoder architecture is trained to reconstruct input EEG signals, enabling the network to learn compact signal representations. In the second stage, the decoder is replaced with a detection module, and the network is fine-tuned for ERP identification. Two model variants are evaluated: a standard model with randomly initialized filters and a Deep-MF model in which input kernels are initialized using ERP templates. Model performance is assessed on a single-trial ERP detection task using leave-one-subject-out validation. The proposed Deep-MF model slightly outperforms the detector with standard kernel initialization for most held-out subjects. Despite substantial inter-subject variability, Deep-MF achieves a higher average F1-score (0.37) compared to the standard network (0.34), indicating improved robustness to cross-subject differences. The best performance obtained by Deep-MF reaches an F1-score of 0.71, exceeding the maximum score achieved by the standard model (0.59). These results demonstrate that ERP-informed kernel initialization can provide consistent improvements in subject-independent single-trial ERP detection. Overall, the findings highlight the potential of integrating domain knowledge with deep learning architectures for EEG analysis. The proposed approach represents a step toward practical wearable EEG and passive brain-computer interface systems capable of real-time monitoring of cognitive processes.
Authors: Zequn Liu, Kehan Wu, Shufang Xie, Zekun Guo, Wei Zhang, Tao Qin, Renhe Liu, Yingce Xia
Abstract: Emerging reasoning models hold promise for automating scientific discovery. However, their training is hindered by a critical supervision gap: experimental outcomes are abundant, whereas intermediate reasoning steps are rarely documented at scale. To bridge this gap, we propose DESRO, a framework for deciphering scientific reasoning from outcomes. By analyzing shared patterns and key differences within grouped data, a large language model (LLM) can recover the underlying logic. We instantiate this framework in molecule optimization, a pivotal stage in drug discovery that traditionally relies on the iterative reasoning of medicinal chemists. Across 2.3 million molecular property records, our framework infers optimization rationales by grouping molecules with shared fragments, then using an LLM to analyze how structural variations correlate with property differences. Based on the derived data, we train a model that conducts molecule optimization through an interpretable reasoning process. DESRO achieves the highest success rates on 15 out of 18 tasks, spanning both single- and multi-property optimization of bioactivity and ADMET properties. The reasoning process enables robust generalization to out-of-distribution scenarios, including novel property combinations, unseen biological targets, and unseen properties defined solely by natural language descriptions. In retrospective case studies under strict temporal splits, the model autonomously reconstructs expert-level lead optimization trajectories. Additionally, our framework extends beyond molecule optimization to reaction ligand selection. Our results establish deciphering reasoning steps from outcome data as a viable paradigm for enabling scientific reasoning, providing a scalable approach to accelerate scientific discovery.
Authors: Behnood Rasti, Bikram Koirala, Paul Scheunders
Abstract: This paper proposes a semisupervised geometric unmixing approach called minimum simplex semisupervised unmixing (MiSiSUn). The geometry of the data was incorporated for the first time into library-based unmixing using a simplex-volume-flavored penalty based on an archetypal analysis-type linear model. The experimental results were performed on two simulated datasets considering different levels of mixing ratios and spatial instruction at varying input noise. MiSiSUn considerably outperforms state-of-the-art semisupervised unmixing methods. The improvements vary from 1 dB to over 3 dB in different scenarios. The proposed method was also applied to a real dataset where visual interpretation is close to the geological map. MiSiSUn was implemented using PyTorch, which is open-source and available at https://github.com/BehnoodRasti/MiSiSUn. Moreover, we provide a dedicated Python package for Semisupervised Unmixing, which is open-source and includes all the methods used in the experiments for the sake of reproducibility.
Authors: Islam Guven, Mehmet Parlak
Abstract: Multi-UAV networks are increasingly deployed for large-scale inspection and monitoring missions, where operational performance depends on the coordination of sensing reliability, communication quality, and energy constraints. In particular, the rapid increase in overflowing waste bins and illegal dumping sites has created a need for efficient detection of waste hotspots. In this work, we introduce JCAS-MARL, a resource-aware multi-agent reinforcement learning (MARL) framework for joint communication and sensing (JCAS)-enabled UAV networks. Within this framework, multiple UAVs operate in a shared environment where each agent jointly controls its trajectory and the resource allocation of an OFDM waveform used simultaneously for sensing and communication. Battery consumption, charging behavior, and associated CO$_2$ emissions are incorporated into the system state to model realistic operational constraints. Information sharing occurs over a dynamic communication graph determined by UAV positions and wireless channel conditions. Waste hotspot detection requires consensus among multiple UAVs to improve reliability. Using this environment, we investigate how MARL policies exploit the sensing-communication-energy trade-off in JCAS-enabled UAV networks. Simulation results demonstrate that adaptive pilot-density control learned by the agents can outperform static configurations, particularly in scenarios where sensing accuracy and communication connectivity vary across the environment.
Authors: Tom F. Sterkenburg
Abstract: This chapter discusses the Solomonoff approach to universal prediction. The crucial ingredient in the approach is the notion of computability, and I present the main idea as an attempt to meet two plausible computability desiderata for a universal predictor. This attempt is unsuccessful, which is shown by a generalization of a diagonalization argument due to Putnam. I then critically discuss purported gains of the approach, in particular it providing a foundation for the methodological principle of Occam's razor, and it serving as a theoretical ideal for the development of machine learning methods.
Authors: Alex Popa, Adrian Taylor, Ranwa Al Mallah
Abstract: Reinforcement learning techniques are being explored as solutions to the threat of cyber attacks on enterprise networks. Recent research in the field of AI in cyber security has investigated the ability of homogeneous multi-agent reinforcement learning agents, capable of inter-agent communication, to respond to cyberattacks. This paper advances the study of learned communication in multi-agent systems by examining heterogeneous agent capabilities within a simulated network environment. To this end, we leverage CommFormer, a publicly available state-of-the-art communication algorithm, to train and evaluate agents within the Cyber Operations Research Gym (CybORG). Our results show that CommFormer agents with heterogeneous capabilities can outperform other algorithms deployed in the CybORG environment, by converging to an optimal policy up to four times faster while improving standard error by up 38%. The agents implemented in this project provide an additional avenue for exploration in the field of AI for cyber security, enabling further research involving realistic networks.
Authors: Danial Monachan, Samira Nazari, Mahdi Taheri, Ali Azarpeyvand, Milos Krstic, Michael Huebner, Christian Herglotz
Abstract: Deploying deep neural networks (DNNs) on edge devices requires strong compression with minimal accuracy loss. This paper introduces Mix-and-Match Pruning, a globally guided, layer-wise sparsification framework that leverages sensitivity scores and simple architectural rules to generate diverse, high-quality pruning configurations. The framework addresses a key limitation that different layers and architectures respond differently to pruning, making single-strategy approaches suboptimal. Mix-and-Match derives architecture-aware sparsity ranges, e.g., preserving normalization layers while pruning classifiers more aggressively, and systematically samples these ranges to produce ten strategies per sensitivity signal (magnitude, gradient, or their combination). This eliminates repeated pruning runs while offering deployment-ready accuracy-sparsity trade-offs. Experiments on CNNs and Vision Transformers demonstrate Pareto-optimal results, with Mix-and-Match reducing accuracy degradation on Swin-Tiny by 40% relative to standard single-criterion pruning. These findings show that coordinating existing pruning signals enables more reliable and efficient compressed models than introducing new criteria.
Authors: Zhenxing Yan, Jidong Yuan, Yongqi Sun, Haiyang Liu, Zhihui Gao
Abstract: Graph neural network (GNN)-based federated recommendation systems effectively capture user-item relationships while preserving data privacy. However, existing methods often face slow convergence on graph data and privacy leakage risks during collaboration. To address these challenges, we propose FastPFRec (Fast Personalized Federated Recommendation with Secure Sharing), a novel framework that enhances both training efficiency and data security. FastPFRec accelerates model convergence through an efficient local update strategy and introduces a privacy-aware parameter sharing mechanism to mitigate leakage risks. Experiments on four real-world datasets (Yelp, Kindle, Gowalla-100k, and Gowalla-1m) show that FastPFRec achieves 32.0% fewer training rounds, 34.1% shorter training time, and 8.1% higher accuracy compared with existing baselines. These results demonstrate that FastPFRec provides an efficient and privacy-preserving solution for scalable federated recommendation.
Authors: Songfeng Zhu
Abstract: In incremental classification tasks for hyperspectral images, catastrophic forgetting is an unavoidable challenge. While memory recall methods can mitigate this issue, they heavily rely on samples from old categories. This paper proposes a teacher-based knowledge retention method for incremental image classification. It alleviates model forgetting of old category samples by utilizing incremental category samples, without depending on old category samples. Additionally, this paper introduces a mask-based partial category knowledge distillation algorithm. By decoupling knowledge distillation, this approach filters out potentially misleading information that could misguide the student model, thereby enhancing overall accuracy. Comparative and ablation experiments demonstrate the proposed method's robust performance.
Authors: Govinda Kolli, Adinath Madhavrao Dukre, Behzad Bozorgtabar, Dwarikanath Mahapatra, Imran Razzak
Abstract: Medical Vision-Language Models (VLMs) often hallucinate by generating responses based on language priors rather than visual evidence, posing risks in clinical applications. We propose Visual Grounding Score Guided Decoding (VGS-Decoding), a training-free method to mitigate hallucinations during inference. Our key insight is that hallucinated tokens maintain or increase their probability when visual information is degraded, while visually grounded tokens decrease in probability. We introduce the Visual Grounding Score (VGS), which measures each token's visual dependency by comparing distributions from original and distorted images. During decoding, we reweight probabilities by amplifying visually grounded tokens while suppressing hallucinations. Unlike fixed-weight contrastive methods, VGS-Decoding provides per-token adaptive control. Experiments on MIMIC-Diff-VQA and VQA-RAD across LLaVA-Med, CheXagent, and MedGemma demonstrate consistent improvements, with up to +9.12% overall gain and $+8.98\%$ in open-ended recall, while introducing only $2\times$ inference overhead and no additional training, making it practical for clinical deployment. Upon acceptance, code will be released publicly to facilitate reproducibility.
Authors: Shasha Yu, Fiona Carroll, Barry L. Bentley
Abstract: Large language models (LLMs) are increasingly deployed as agents with access to executable tools, enabling direct interaction with external systems. However, most safety evaluations remain text-centric and assume that compliant language implies safe behavior, an assumption that becomes unreliable once models are allowed to act. In this work, we empirically examine how executable tool affordance alters safety alignment in LLM agents using a paired evaluation framework that compares text-only chatbot behavior with tool-enabled agent behavior under identical prompts and policies. Experiments are conducted in a deterministic financial transaction environment with binary safety constraints across 1,500 procedurally generated scenarios. To separate intent from outcome, we distinguish between attempted and realized violations using dual enforcement regimes that either block or permit unsafe actions. Both evaluated models maintain perfect compliance in text-only settings, yet exhibit sharp increases in violations after tool access is introduced, reaching rates up to 85% despite unchanged rules. We observe substantial gaps between attempted and executed violations, indicating that external guardrails can suppress visible harm while masking persistent misalignment. Agents also develop spontaneous constraint circumvention strategies without adversarial prompting. These results demonstrate that tool affordance acts as a primary driver of safety misalignment and that text-based evaluation alone is insufficient for assessing agentic systems.
Authors: Ernest Fokou\'e, Gregory Babbitt, Yuval Levental
Abstract: Social insect colonies and ensemble machine learning methods represent two of the most successful examples of decentralized information processing in nature and computation respectively. Here we develop a rigorous mathematical framework demonstrating that ant colony decision-making and random forest learning are isomorphic under a common formalism of \textbf{stochastic ensemble intelligence}. We show that the mechanisms by which genetically identical ants achieve functional differentiation -- through stochastic response to local cues and positive feedback -- map precisely onto the bootstrap aggregation and random feature subsampling that decorrelate decision trees. Using tools from Bayesian inference, multi-armed bandit theory, and statistical learning theory, we prove that both systems implement identical variance reduction strategies through decorrelation of identical units. We derive explicit mappings between ant recruitment rates and tree weightings, pheromone trail reinforcement and out-of-bag error estimation, and quorum sensing and prediction averaging. This isomorphism suggests that collective intelligence, whether biological or artificial, emerges from a universal principle: \textbf{randomized identical agents + diversity-enforcing mechanisms $\rightarrow$ emergent optimality}.
Authors: S. David Mis, Maarten V. de Hoop
Abstract: We study forward and inverse problems for time-dependent probability measures in Bayes--Hilbert spaces. On the forward side, we show that each sufficiently regular Bayes--Hilbert path admits a canonical dynamical realization: a weighted Neumann problem transforms the log-density variation into the unique gradient velocity field of minimum kinetic energy. This construction induces a transport form on Bayes--Hilbert tangent directions, which measures the dynamical cost of realizing prescribed motions, and yields a flow-matching interpretation in which the canonical velocity field is the minimum-energy execution of the prescribed path. On the inverse side, we formulate reconstruction directly on Bayes--Hilbert path space from time-dependent indirect observations. The resulting variational problem combines a data-misfit term with the transport action induced by the forward geometry. In our infinite-dimensional setting, however, this transport geometry alone does not provide sufficient compactness, so we add explicit temporal and spatial regularization to close the theory. The linearized observation operator induces a complementary observability form, which quantifies how strongly tangent directions are seen through the data. Under explicit Sobolev regularity and observability assumptions, we prove existence of minimizers, derive first-variation formulas, establish local stability of the observation map, and deduce recovery of the evolving law, its score, and its canonical velocity field under the strong topologies furnished by the compactness theory.
Authors: Wooseok Sim, Hogun Park
Abstract: Federated Recommender Systems (FRS) preserve privacy by training decentralized models on client-specific user-item subgraphs without sharing raw data. However, FRS faces a unique challenge: subgraph structural imbalance, where drastic variations in subgraph scale (user/item counts) and connectivity (item degree) misalign client representations, making it challenging to train a robust model that respects each client's unique structural characteristics. To address this, we propose a Low-pass Personalized Subgraph Federated recommender system (LPSFed). LPSFed leverages graph Fourier transforms and low-pass spectral filtering to extract low-frequency structural signals that remain stable across subgraphs of varying size and degree, allowing robust personalized parameter updates guided by similarity to a neutral structural anchor. Additionally, we leverage a localized popularity bias-aware margin that captures item-degree imbalance within each subgraph and incorporates it into a personalized bias correction term to mitigate recommendation bias. Supported by theoretical analysis and validated on five real-world datasets, LPSFed achieves superior recommendation accuracy and enhances model robustness.
Authors: Muhammad Muneeb, David B. Ascher
Abstract: Human genetics offers a promising route to therapeutic discovery, yet practical frameworks translating genotype-derived signal into ranked target and drug hypotheses remain limited, particularly when matched disease transcriptomics are unavailable. Here we present G2DR, a genotype-first prioritization framework propagating inherited variation through genetically predicted expression, multi-method gene-level testing, pathway enrichment, network context, druggability, and multi-source drug--target evidence integration. In a migraine case study with 733 UK Biobank participants under stratified five-fold cross-validation, we imputed expression across seven transcriptome-weight resources and ranked genes using a reproducibility-aware discovery score from training and validation data, followed by a balanced integrated score for target selection. Discovery-based prioritization generalized to held-out data, achieving gene-level ROC-AUC of 0.775 and PR-AUC of 0.475, while retaining enrichment for curated migraine biology. Mapping prioritized genes to compounds via Open Targets, DGIdb, and ChEMBL yielded drug sets enriched for migraine-linked compounds relative to a global background, though recovery favoured broader mechanism-linked and off-label space over migraine-specific approved therapies. Directionality filtering separated broadly recovered compounds from mechanistically compatible candidates. G2DR is a modular framework for genetics-informed hypothesis generation, not a clinically actionable recommendation system. All outputs require independent experimental, pharmacological, and clinical validation.
Authors: Edoardo Calvello, Elizabeth Carlson, Nikola Kovachki, Michael N. Manta, Andrew M. Stuart
Abstract: Machine learning has opened new frontiers in purely data-driven algorithms for data assimilation in, and for forecasting of, dynamical systems; the resulting methods are showing some promise. However, in contrast to model-driven algorithms, analysis of these data-driven methods is poorly developed. In this paper we address this issue, developing a theory to underpin data-driven methods to solve smoothing problems arising in data assimilation and forecasting problems. The theoretical framework relies on two key components: (i) establishing the existence of the mapping to be learned; (ii) the properties of the operator learning architecture used to approximate this mapping. By studying these two components in conjunction, we establish the first universal approximation theorem for purely data-driven algorithms for both smoothing and forecasting of dynamical systems. We work in the continuous time setting, hence deploying neural operator architectures. The theoretical results are illustrated with experiments studying the Lorenz `63, Lorenz `96 and Kuramoto-Sivashinsky dynamical systems.
Authors: Ali Darijani, J\"urgen Beyerer, Zahra Sadat Hajseyed Nasrollah, Luisa Hoffmann, Michael Heizmann
Abstract: Probability theory has become the predominant framework for quantifying uncertainty across scientific and engineering disciplines, with a particular focus on measurement and control systems. However, the widespread reliance on simple Gaussian assumptions--particularly in control theory, manufacturing, and measurement systems--can result in incomplete representations and multistage lossy approximations of complex phenomena, including inaccurate propagation of uncertainty through multi stage processes. This work proposes a comprehensive yet computationally tractable framework for representing and propagating quantitative attributes arising in measurement systems using Probability Density Functions (PDFs). Recognizing the constraints imposed by finite memory in software systems, we advocate for the use of Gaussian Mixture Models (GMMs), a principled extension of the familiar Gaussian framework, as they are universal approximators of PDFs whose complexity can be tuned to trade off approximation accuracy against memory and computation. From both mathematical and computational perspectives, GMMs enable high performance and, in many cases, closed form solutions of essential operations in control and measurement. The paper presents practical applications within manufacturing and measurement contexts especially circular factory, demonstrating how the GMMs framework supports accurate representation and propagation of measurement uncertainty and offers improved accuracy--compared to the traditional Gaussian framework--while keeping the computations tractable.
Authors: Karun Adusumilli, Maximilian Kasy, Ashia Wilson
Abstract: We derive the asymptotic risk function of regularized empirical risk minimization (ERM) estimators tuned by $n$-fold cross-validation (CV). The out-of-sample prediction loss of such estimators converges in distribution to the squared-error loss (risk function) of shrinkage estimators in the normal means model, tuned by Stein's unbiased risk estimate (SURE). This risk function provides a more fine-grained picture of predictive performance than uniform bounds on worst-case regret, which are common in learning theory: it quantifies how risk varies with the true parameter. As key intermediate steps, we show that (i) $n$-fold CV converges uniformly to SURE, and (ii) while SURE typically has multiple local minima, its global minimum is generically well separated. Well-separation ensures that uniform convergence of CV to SURE translates into convergence of the tuning parameter chosen by CV to that chosen by SURE.
Authors: Dhruv Menon, Vivek Singh, Xu Chen, Mohammad Reza Alizadeh Kiapi, Ivan Zyuzin, Hamish W. Macleod, Nakul Rampal, William Shepard, Omar M. Yaghi, David Fairen-Jimenez
Abstract: Reticular chemistry has enabled the synthesis of tens of thousands of metal-organic frameworks (MOFs), yet the discovery of new materials still relies largely on intuition-driven linker design and iterative experimentation. As a result, researchers explore only a small fraction of the vast chemical space accessible to reticular materials, limiting the systematic discovery of frameworks with targeted properties. Here, we introduce Nexerra-R1, a building-block chemical language model that enables inverse design in reticular chemistry through the targeted generation of organic linkers. Rather than generating complete frameworks directly, Nexerra-R1 operates at the level of molecular building blocks, preserving the modular logic that underpins reticular synthesis. The model supports both unconstrained generation of low-connectivity linkers and scaffold-constrained design of symmetric multidentate motifs compatible with predefined nodes and topologies. We further combine linker generation with flow-guided distributional targeting to steer the generative process toward application-relevant objectives while maintaining chemical validity and assembly feasibility. The generated linkers are subsequently assembled into three-dimensional frameworks and are structurally optimized to produce candidate materials compatible with experimental synthesis. Using Nexerra-R1, we validate this strategy by rediscovering known MOFs and by proposing the experimental synthesis of a previously unreported framework, CU-525, generated entirely in silico. Together, these results establish a general inverse-design paradigm for reticular materials in which controllable chemical language modelling enables the direct translation from computational design to synthesizable frameworks.
Authors: Abdullahi Isa Ahmed, Ana Maria Dr\u{a}gulinescu, El Mehdi Amhoud
Abstract: The evolution of Internet of Things (IoT) into multi-layered environments has positioned Low-Power Wide Area Networks (LPWANs), particularly Long Range (LoRa), as the backbone for connectivity across both surface and subterranean landscapes. However, existing LoRa-based network designs often treat ground-based wireless sensor networks (WSNs) and wireless underground sensor networks (WUSNs) as separate systems, resulting in inefficient and non-integrated connectivity across diverse environments. To address this, we propose Hetero-Net, a unified heterogeneous LoRa framework that integrates diverse LoRa end devices with multiple unmanned aerial vehicle (UAV)-mounted LoRa gateways. Our objective is to maximize system energy efficiency through the joint optimization of the spreading factor, transmission power, and three-dimensional (3D) placement of the UAVs. To manage the dynamic and partially observable nature of this system, we model the problem as a partially observable stochastic game (POSG) and address it using a multi-agent proximal policy optimization (MAPPO) framework. An ablation study shows that our proposed MAPPO Hetero-Net significantly outperforms traditional, isolated network designs, achieving energy efficiency improvements of 55.81\% and 198.49\% over isolated WSN-only and WUSN-only deployments, respectively.
Authors: Ata Poyraz Turna, Asrin Efe Yorulmaz, Tamer Ba\c{s}ar
Abstract: Classical Bayesian persuasion studies how a sender influences receivers through carefully designed signaling policies within a single strategic interaction. In many real-world environments, such interactions are repeated across multiple games, creating opportunities to exploit structural similarity across tasks. In this work, we introduce Meta-Persuasion algorithms, establishing the first line of theoretical results for both full-feedback and bandit-feedback settings in the Online Bayesian Persuasion (OBP) and Markov Persuasion Process (MPP) frameworks. We show that our proposed meta-persuasion algorithms achieve provably sharper regret rates under natural notions of task similarity, improving upon the best-known convergence rates for both OBP and MPP. At the same time, they recover the standard single-game guarantees when the sequence of games is picked arbitrarily. Finally, we complement our theoretical analysis with numerical experiments that highlight our regret improvements and the benefits of meta-learning in repeated persuasion environments.
Authors: Simon Ambrozak, Ulysse McConnell, Bhargav Srinivasan, Burak Ozkan, Can Firtina
Abstract: Nanopore sequencing can read substantially longer sequences of nucleic acid molecules than other sequencing methods, which has led to advances in genomic analysis such as the gapless human genome assembly. By analyzing the raw electrical signal reads that nanopore sequencing generates from molecules, existing works can map these reads without translating them into DNA characters (i.e., basecalling), allowing for quick and efficient analysis of sequencing data. However, raw signals often contain errors due to noise and mistakes when processing them, which limits the overall accuracy of raw signal analysis. Our goal in this work is to detect and correct errors in raw signals to improve the accuracy of raw signal analyses. To this end, we propose CERN, a mechanism that trains and utilizes a Hidden Markov Model (HMM) to accurately correct signal errors. Our extensive evaluation on various datasets including E. coli, Fruit Fly, and Human genomes shows that CERN 1) consistently improves the overall mapping accuracy of the underlying raw signal analysis tools, 2) minimizes the burden on segmentation algorithm optimization with newer nanopore chemistries, and 3) functions without causing substantial computational overhead. We conclude that CERN provides an effective mechanism to systematically identify and correct the errors in raw nanopore signals before further analysis, which can enable the development of a new class of error correction mechanisms purely designed for raw nanopore signals. CERN is available at https://github.com/STORMgroup/CERN. We also provide the scripts to fully reproduce our results on our GitHub page.
Authors: Erez Badash, Dan Boneh, Ilan Komargodski, Megha Srivastava
Abstract: We present Hawkeye, a system for analyzing and reproducing GPU-level arithmetic operations. Using our framework, anyone can re-execute on a CPU the exact matrix multiplication operations underlying a machine learning model training or inference workflow that was executed on an NVIDIA GPU, without any precision loss. This is in stark contrast to prior approaches to verifiable machine learning, which either introduce significant computation overhead to the original model owner, or suffer from non-robustness and quality degradation. The main technical contribution of Hawkeye is a systematic sequence of carefully crafted tests that study rounding direction, subnormal number handling, and order of (non-associative) accumulation during matrix multiplication on NVIDIA's Tensor Cores. We test and evaluate our framework on multiple NVIDIA GPU architectures ( Ampere, Hopper, and Lovelace) and precision types (FP16, BFP16, FP8). In all test cases, Hawkeye enables perfect reproduction of matrix multiplication on a CPU, paving the way for efficient and trustworthy third-party auditing of ML model training and inference.
Authors: Hannah Berin-Costain, Harry Wang, Kirsten Morris, Jun Liu
Abstract: This paper proposes a computable state-estimation error bound for learning-based Kazantzis--Kravaris/Luenberger (KKL) observers. Recent work learns the KKL transformation map with a physics-informed neural network (PINN) and a corresponding left-inverse map with a conventional neural network. However, no computable state-estimation error bounds are currently available for this approach. We derive a state-estimation error bound that depends only on quantities that can be certified over a prescribed region using neural network verification. We further extend the result to bounded additive measurement noise and demonstrate the guarantees on nonlinear benchmark systems.
Authors: Rounak Saha, Gurusha Juneja, Dayita Chaudhuri, Naveeja Sajeevan, Nihar B Shah, Danish Pruthi
Abstract: A number of scientific conferences and journals have recently enacted policies that prohibit LLM usage by peer reviewers, except for polishing, paraphrasing, and grammar correction of otherwise human-written reviews. But, are these policies enforceable? To answer this question, we assemble a dataset of peer reviews simulating multiple levels of human-AI collaboration, and evaluate five state-of-the-art detectors, including two commercial systems. Our analysis shows that all detectors misclassify a non-trivial fraction of LLM-polished reviews as AI-generated, thereby risking false accusations of academic misconduct. We further investigate whether peer-review-specific signals, including access to the paper manuscript and the constrained domain of scientific writing, can be leveraged to improve detection. While incorporating such signals yields measurable gains in some settings, we identify limitations in each approach and find that none meets the accuracy standards required for identifying AI use in peer reviews. Importantly, our results suggest that recent public estimates of AI use in peer reviews through the use of AI-text detectors should be interpreted with caution, as current detectors misclassify mixed reviews (collaborative human-AI outputs) as fully AI generated, potentially overstating the extent of policy violations.
Authors: Yalemzerf Getnet, Abiy Tasissa, Waltenegus Dargie
Abstract: Assigning relevance scores to the input features of a machine learning model enables to measure the contributions of the features in achieving a correct outcome. It is regarded as one of the approaches towards developing explainable models. For biomedical assignments, this is very useful for medical experts to comprehend machine-based decisions. In the analysis of electro cardiogram (ECG) signals, in particular, understanding which of the electrocardiogram samples or features contributed most for a given decision amounts to understanding the underlying cardiac phases or conditions the machine tries to explain. For the computation of relevance scores, determining the proper baseline is important. Moreover, the scores should have a distribution which is at once intuitive to interpret and easy to associate with the underline cardiac reality. The purpose of this work is to achieve these goals. Specifically, we propose a shift-invariant baseline which has a physical significance in the analysis as well as interpretation of electrocardiogram measurements. Moreover, we aggregate significance scores in such a way that they can be mapped to cardiac phases. We demonstrate our approach by inferring physical exertion from cardiac exertion using a residual network. We show that the ECG samples which achieved the highest relevance scores (and, therefore, which contributed most to the accurate recognition of the physical exertion) are those associated with the P and T waves. Index Terms Attribution, baseline, cardiovascular diseases, electrocardiogram, activity recognition, machine learning
Authors: Joanna Zou, Han Cheng Lie, Youssef Marzouk
Abstract: The governing equations of stochastic dynamical systems often become cost-prohibitive for numerical simulation at large scales. Surrogate models of the governing equations, learned from data of the high-fidelity system, are routinely used to predict key observables with greater efficiency. However, standard choices of loss function for learning the surrogate model fail to provide error guarantees in path-dependent observables, such as reaction rates of molecular dynamical systems. This paper introduces an error bound for path-space observables and employs it as a novel variational loss for the goal-oriented learning of a stochastic dynamical system. We show the error bound holds for a broad class of observables, including mean first hitting times on unbounded time domains. We derive an analytical gradient of the goal-oriented loss function by leveraging the formula for Frechet derivatives of expected path functionals, which remains tractable for implementation in stochastic gradient descent schemes. We demonstrate that surrogate models of overdamped Langevin systems developed via goal-oriented learning achieve improved accuracy in predicting the statistics of a first hitting time observable and robustness to distributional shift in the data.
Authors: Jerry M. Huang, Lukas Schumacher, Niek Stevenson, Stefan T. Radev
Abstract: Simulation-based inference (SBI) with neural networks has accelerated and transformed cognitive modeling workflows. SBI enables modelers to fit complex models that were previously difficult or impossible to estimate, while also allowing rapid estimation across large numbers of datasets. However, the utility of SBI for iterating over varying modeling assumptions remains limited: changing parameterizations, generative functions, priors, and design variables all necessitate model retraining and hence diminish the benefits of amortization. To address these issues, we pilot a meta-amortized framework for cognitive modeling which we nickname the CogFormer. Our framework trains a transformer-based architecture that remains valid across a combinatorial number of structurally similar models, allowing for changing data types, parameters, design matrices, and sample sizes. We present promising quantitative results across families of decision-making models for binary, multi-alternative, and continuous responses. Our evaluation suggests that CogFormer can accurately estimate parameters across model families with a minimal amortization offset, making it a potentially powerful engine that catalyzes cognitive modeling workflows.
Authors: Tony Mason
Abstract: We find that models report highest confidence precisely when they are fabricating. Across four model families (OLMo-3, Llama-3.1, Qwen3, Mistral), self-reported confidence inversely correlates with accuracy, with AUC ranging from 0.28 to 0.36 where 0.5 is random guessing. We prove, under explicit formal assumptions, that this is not a capability gap but an observational one. Under text-only observation, where a supervisor sees only the model's output text, no monitoring system can reliably distinguish honest model outputs from plausible fabrications. We prove two results: first, that any policy conditioning only on the query cannot satisfy epistemic honesty across ambiguous world states; second, that no learning algorithm optimizing reward from a text-only supervisor can converge to honest behavior when the supervisor's observations are identical for both grounded and fabricated responses. Within our formal model, these impossibilities hold regardless of model scale or training procedure, including RLHF and instruction tuning. We construct a tensor interface that escapes the impossibility by exporting computational byproducts (per-token entropy and log-probability distributions) that are structurally coupled to correctness under standard training. Per-token entropy achieves pooled AUC 0.757, outperforming all text baselines by 2.5--3.9 percentage points at every budget level tested (10\%, 20\%, 30\%). The entropy signal generalizes across architectures (Spearman $\rho = 0.762$). The core contribution is a cost surface where the empirical mapping from verification budget (fraction of queries receiving expensive checks) to detection accuracy for each judge strategy is a practical lookup for system builders deciding how to allocate verification resources. The contribution is the map. The territory is the system you are building.
Authors: Hang-Cheng Dong, Pengcheng Cheng, Shuhuan Li
Abstract: Solving ill-posed inverse problems necessitates effective regularization strategies to stabilize the inversion process against measurement noise. While classical methods like Tikhonov regularization require heuristic parameter tuning, and standard deep learning approaches often lack interpretability and generalization across resolutions, we propose SC-Net (Spectral Correction Network), a novel operator learning framework. SC-Net operates in the spectral domain of the forward operator, learning a pointwise adaptive filter function that reweights spectral coefficients based on the signal-to-noise ratio. We provide a theoretical analysis showing that SC-Net approximates the continuous inverse operator, guaranteeing discretization invariance. Numerical experiments on 1D integral equations demonstrate that SC-Net: (1) achieves the theoretical minimax optimal convergence rate ($O(\delta^{0.5})$ for $s=p=1.5$), matching theoretical lower bounds; (2) learns interpretable sharp-cutoff filters that outperform Oracle Tikhonov regularization; and (3) exhibits zero-shot super-resolution, maintaining stable reconstruction errors ($\approx 0.23$) when trained on coarse grids ($N=256$) and tested on significantly finer grids (up to $N=2048$). The proposed method bridges the gap between rigorous regularization theory and data-driven operator learning.
Authors: Zhilong Zhang, Haoxiang Ren, Yihao Sun, Yifei Sheng, Haonan Wang, Haoxin Lin, Zhichao Wu, Pierre-Luc Bacon, Yang Yu
Abstract: Vision-Language-Action (VLA) models show strong generalization for robotic control, but finetuning them with reinforcement learning (RL) is constrained by the high cost and safety risks of real-world interaction. Training VLA models in interactive world models avoids these issues but introduces several challenges, including pixel-level world modeling, multi-view consistency, and compounding errors under sparse rewards. Building on recent advances across large multimodal models and model-based RL, we propose VLA-MBPO, a practical framework to tackle these problems in VLA finetuning. Our approach has three key design choices: (i) adapting unified multimodal models (UMMs) for data-efficient world modeling; (ii) an interleaved view decoding mechanism to enforce multi-view consistency; and (iii) chunk-level branched rollout to mitigate error compounding. Theoretical analysis and experiments across simulation and real-world tasks demonstrate that VLA-MBPO significantly improves policy performance and sample efficiency, underscoring its robustness and scalability for real-world robotic deployment.
Authors: Kry Yik Chau Lui, Cheng Chi, Kishore Basu, Yanshuai Cao
Abstract: Despite their dominance in vision and language, deep neural networks often underperform relative to tree-based models on tabular data. To bridge this gap, we incorporate five key inductive biases into deep learning: robustness to irrelevant features, axis alignment, localized irregularities, feature heterogeneity, and training stability. We propose \emph{LassoFlexNet}, an architecture that evaluates the linear and nonlinear marginal contribution of each input via Per-Feature Embeddings, and sparsely selects relevant variables using a Tied Group Lasso mechanism. Because these components introduce optimization challenges that destabilize standard proximal methods, we develop a \emph{Sequential Hierarchical Proximal Adaptive Gradient optimizer with exponential moving averages (EMA)} to ensure stable convergence. Across $52$ datasets from three benchmarks, LassoFlexNet matches or outperforms leading tree-based models, achieving up to a $10$\% relative gain, while maintaining Lasso-like interpretability. We substantiate these empirical results with ablation studies and theoretical proofs confirming the architecture's enhanced expressivity and structural breaking of undesired rotational invariance.
Authors: Aratrika Mustafi, Soumya Mukherjee
Abstract: We propose a dense associative memory for empirical measures (weighted point clouds). Stored patterns and queries are finitely supported probability measures, and retrieval is defined by minimizing a Hopfield-style log-sum-exp energy built from the debiased Sinkhorn divergence. We derive retrieval dynamics as a spherical Hellinger Kantorovich (SHK) gradient flow, which updates both support locations and weights. Discretizing the flow yields a deterministic algorithm that uses Sinkhorn potentials to compute barycentric transport steps and a multiplicative simplex reweighting. Under local separation and PL-type conditions we prove basin invariance, geometric convergence to a local minimizer, and a bound showing the minimizer remains close to the corresponding stored pattern. Under a random pattern model, we further show that these Sinkhorn basins are disjoint with high probability, implying exponential capacity in the ambient dimension. Experiments on synthetic Gaussian point-cloud memories demonstrate robust recovery from perturbed queries versus a Euclidean Hopfield-type baseline.
Authors: Jianwei Chen, Zhengyang Miao, Wenjie Cai, Jiaxue Tang, Boxing Liu, Yunfan Zhang, Yuhang Yang, Hao Tang, Carola-Bibiane Sch\"onlieb, Zaixu Cui, Du Lei, Shouliang Qi, Chao Li
Abstract: Integrating structural and functional connectomes remains challenging because their relationship is non-linear and organized over nested modular hierarchies. We propose a hierarchical multiscale structure-function coupling framework for connectome integration that jointly learns individualized modular organization and hierarchical coupling across structural connectivity (SC) and functional connectivity (FC). The framework includes: (i) Prototype-based Modular Pooling (PMPool), which learns modality-specific multiscale communities by selecting prototypical ROIs and optimizing a differentiable modularity-inspired objective; (ii) an Attention-based Hierarchical Coupling Module (AHCM) that models both within-hierarchy and cross-hierarchy SC-FC interactions to produce enriched hierarchical coupling representations; and (iii) a Coupling-guided Clustering loss (CgC-Loss) that regularizes SC and FC community assignments with coupling signals, allowing cross-modal interactions to shape community alignment across hierarchies. We evaluate the model's performance across four cohorts for predicting brain age, cognitive score, and disease classification. Our model consistently outperforms baselines and other state-of-the-art approaches across three tasks. Ablation and sensitivity analyses verify the contributions of key components. Finally, the visualizations of learned coupling reveal interpretable differences, suggesting that the framework captures biologically meaningful structure-function relationships.
Authors: Shixiang Liu, Zhifan Li, Hanming Yang, Jianxin Yin
Abstract: Existing high-dimensional online learning methods often face the challenge that their error bounds, or per-batch sample sizes, diverge as the number of data batches increases. To address this issue, we propose an asynchronous decomposition framework that leverages summary statistics to construct a surrogate score function for current-batch learning. This framework is implemented via a dynamic-regularized iterative hard thresholding algorithm, providing a computationally and memory-efficient solution for sparse online optimization. We provide a unified theoretical analysis that accounts for both the streaming computational error and statistical accuracy, establishing that our estimator maintains non-divergent error bounds and $\ell_0$ sparsity across all batches. Furthermore, the proposed estimator adaptively achieves additional gains as batches accumulate, attaining the oracle accuracy as if the entire historical dataset were accessible and the true support were known. These theoretical properties are further illustrated through an example of the generalized linear model.
Authors: Yong Wang, Qifan Shen, Bao Zhang, Zijun Huang, Chengbo Zhu, Shuai Yao, Qisong Wu
Abstract: Millimeter-wave (mmWave) radar enables contactless respiratory sensing,yet fine-grained monitoring is often degraded by nonstationary interference from body micromotions.To achieve micromotion interference removal,we propose mmWave-Diffusion,an observation-anchored conditional diffusion framework that directly models the residual between radar phase observations and the respiratory ground truth,and initializes sampling within an observation-consistent neighborhood rather than from Gaussian noise-thereby aligning the generative process with the measurement physics and reducing inference overhead. The accompanying Radar Diffusion Transformer (RDT) is explicitly conditioned on phase observations, enforces strict one-to-one temporal alignment via patch-level dual positional encodings, and injects local physical priors through banded-mask multi-head cross-attention, enabling robust denoising and interference removal in just 20 reverse steps. Evaluated on 13.25 hours of synchronized radar-respiration data, mmWave-Diffusion achieves state-of-the-art waveform reconstruction and respiratory-rate estimation with strong generalization. Code repository:https://github.com/goodluckyongw/mmWave-Diffusion.
Authors: Soudeep Ghoshal, Himanshu Buckchash, Sarita Paudel, Rub\'en Ruiz-Torrubiano
Abstract: From customer feedback to social media, understanding human sentiment in text is central to how machines can interact meaningfully with people. However, despite notable progress, accurately capturing sentiment remains a challenging task, which continues to motivate further research in this area. To this end, we introduce Non-Differential Transformer (NDT). It is inspired by (but in contrast to) the state-of-the-art Differential Transformer (DT) model. While standard Transformers can struggle with irrelevant context, the sota DT model uses attention map subtraction, potentially for noise cancellation. We explore an alternative motivation, hypothesizing that benefits may arise from enabling different attention components to specialize on distinct concepts within the text, similar to multiplexing information channels or mixture models, rather than primarily canceling noise via subtraction. Guided by this concept-multiplexing (ConPlex) view, the specific architecture presented in this paper employs a purely additive strategy. It uses only positive weights, learned during training, to ensure constructive combination of these specialized attention perspectives. This design choice explores positive only integration, though our broader framework also shows promise with less constrained linear combinations involving both positive and negative weights. Our model computes attention via this positively weighted sum of multiple distinct attention maps. This allows the model to constructively integrate diverse signals and potentially capture more complex contextual relationships. Competitive performance is achieved by the proposed model for Sentiment Analysis while tested on multiple datasets. We conclude by presenting our results, challenges and future research agenda in this important area of research.
Authors: Zihao Zheng, Hangyu Cao, Jiayu Chen, Sicheng Tian, Chenyue Li, Maoliang Li, Xinhao Sun, Guojie Luo, Xiang Chen
Abstract: Vision-Language-Action (VLA) models are mainstream in embodied intelligence but face high inference costs. Edge-Cloud Collaborative (ECC) deployment offers an effective fix by easing edge-device computing pressure to meet real-time needs. However, existing ECC frameworks are suboptimal for VLA models due to two challenges: (1) Diverse model structures hinder optimal ECC segmentation point identification; (2) Even if the optimal split point is determined, changes in network bandwidth can cause performance drift. To address these issues, we propose a novel ECC deployment framework for various VLA models, termed RoboECC. Specifically, we propose a model-hardware co-aware segmentation strategy to help find the optimal segmentation point for various VLA models. Moreover, we propose a network-aware deployment adjustment approach to adapt to the network fluctuations for maintaining optimal performance. Experiments demonstrate that RoboECC achieves a speedup of up to 3.28x with only 2.55x~2.62x overhead.
Authors: Zacharie Bugaud
Abstract: Multi-RF Fusion achieves a test ROC-AUC of 0.8476 +/- 0.0002 on ogbg-molhiv (10 seeds), placing #1 on the OGB leaderboard ahead of HyperFusion (0.8475 +/- 0.0003). The core of the method is a rank-averaged ensemble of 12 Random Forest models trained on concatenated molecular fingerprints (FCFP, ECFP, MACCS, atom pairs -- 4,263 dimensions total), blended with deep-ensembled GNN predictions at 12% weight. Two findings drive the result: (1) setting max_features to 0.20 instead of the default sqrt(d) gives a +0.008 AUC gain on this scaffold split, and (2) averaging GNN predictions across 10 seeds before blending with the RF eliminates GNN seed variance entirely, dropping the final standard deviation from 0.0008 to 0.0002. No external data or pre-training is used.
Authors: Kaiyuan Li, Jing-Cheng Pang, Yang Yu
Abstract: Reinforcement learning from verifiable rewards (RLVR) stimulates the thinking processes of large language models (LLMs), substantially enhancing their reasoning abilities on verifiable tasks. It is often assumed that similar gains should transfer to general question answering (GQA), but this assumption has not been thoroughly validated. To assess whether RLVR automatically improves LLM performance on GQA, we propose a Cross-Generation evaluation framework that measures the quality of intermediate reasoning by feeding the generated thinking context into LLMs of varying capabilities. Our evaluation leads to a discouraging finding: the efficacy of the thinking process on GQA tasks is markedly lower than on verifiable tasks, suggesting that explicit training on GQA remains necessary in addition to training on verifiable tasks. We further observe that direct RL training on GQA is less effective than RLVR. Our hypothesis is that, whereas verifiable tasks demand robust logical chains to obtain high rewards, GQA tasks often admit shortcuts to high rewards without cultivating high-quality thinking. To avoid possible shortcuts, we introduce a simple method, Separated Thinking And Response Training (START), which first trains only the thinking process, using rewards defined on the final answer. We show that START improves both the quality of thinking and the final answer across several GQA benchmarks and RL algorithms.
Authors: Enguang Wang, Qiang Wang, Yuanchen Wu, Ke Yan, Xinbin Yuan, Shouhong Ding, Xialei Liu, Ming-Ming Cheng
Abstract: While Multimodal Large Language Models (MLLMs) excel at vision-language tasks, the cost of their language-driven training on internal visual foundational competence remains unclear. In this paper, we conduct a detailed diagnostic analysis to unveil a pervasive issue: visual representation degradation in MLLMs. Specifically, we find that compared to the initial visual features, the visual representation in the middle layers of LLM exhibits both a degradation in global function and patch structure. We attribute this phenomenon to a visual sacrifice driven by the singular text-generation objective, where the model compromises its visual fidelity to optimize for answer generation. We argue that a robust MLLM requires both strong cross-modal reasoning and core visual competence, and propose Predictive Regularization (PRe) to force degraded intermediate features to predict initial visual features, thereby maintaining the inherent visual attributes of the MLLM's internal representations. Extensive experiments confirm that mitigating this visual degradation effectively boosts vision-language performance, underscoring the critical importance of fostering robust internal visual representations within MLLMs for comprehensive multimodal understanding.
Authors: Milos Gravara, Juan Luis Herrera, Stefan Nastic
Abstract: Compound AI is a distributed intelligence approach that represents a unified system orchestrating specialized AI/ML models with engineered software components into AI workflows. Compound AI production deployments must satisfy accuracy, latency, and cost objectives under varying loads. However, many deployments operate on fixed infrastructure where horizontal scaling is not viable. Existing approaches optimize solely for accuracy and do not consider changes in workload conditions. We observe that compound AI systems can switch between configurations to fit infrastructure capacity, trading accuracy for latency based on current load. This requires discovering multiple Pareto-optimal configurations from a combinatorial search space and determining when to switch between them at runtime. We present Compass, a novel framework that enables dynamic configuration switching through offline optimization and online adaptation. Compass consists of three components: COMPASS-V algorithm for configuration discovery, Planner for switching policy derivation, and Elastico Controller for runtime adaptation. COMPASS-V discovers accuracy-feasible configurations using finite-difference guided search and a combination of hill-climbing and lateral expansion. Planner profiles these configurations on target hardware and derives switching policies using a queuing theory based model. Elastico monitors queue depth and switches configurations based on derived thresholds. Across two compound AI workflows, COMPASS-V achieves 100% recall while reducing configuration evaluations by 57.5% on average compared to exhaustive search, with efficiency gains reaching 95.3% at tight accuracy thresholds. Runtime adaptation achieves 90-98% SLO compliance under dynamic load patterns, improving SLO compliance by 71.6% over static high-accuracy baselines, while simultaneously improving accuracy by 3-5% over static fast baselines.
Authors: Yujin Park, Haejun Chung, Ikbeom Jang
Abstract: Pairwise comparison labeling is emerging as it yields higher inter-rater reliability than conventional classification labeling, but exhaustive comparisons require quadratic cost. We propose Dodgersort, which leverages CLIP-based hierarchical pre-ordering, a neural ranking head and probabilistic ensemble (Elo, BTL, GP), epistemic--aleatoric uncertainty decomposition, and information-theoretic pair selection. It reduces human comparisons while improving the reliability of the rankings. In visual ranking tasks in medical imaging, historical dating, and aesthetics, Dodgersort achieves a 11--16\% annotation reduction while improving inter-rater reliability. Cross-domain ablations across four datasets show that neural adaptation and ensemble uncertainty are key to this gain. In FG-NET with ground-truth ages, the framework extracts 5--20$\times$ more ranking information per comparison than baselines, yielding Pareto-optimal accuracy--efficiency trade-offs.
Authors: Xiangyu Zeng, Qi Xu, Yunke Wang, Chang Xu
Abstract: Long-context language modeling is commonly framed as a scalability challenge of token-level attention, yet local-to-global information structuring remains largely implicit in existing approaches. Drawing on cognitive theories of discourse comprehension, we propose HiCI (Hierarchical Construction--Integration), a hierarchical attention module that constructs segment-level representations, integrates them into a shared global context, and broadcasts both to condition segment-level attention. We validate HiCI through parameter-efficient adaptation of LLaMA-2 with only <5.5% additional parameters, extending context from 4K to 100K tokens (7B) and 64K tokens (13B). Across language modeling, retrieval, and instruction-following benchmarks, HiCI yields consistent improvements over strong baselines, including matching proprietary models on topic retrieval and surpassing GPT-3.5-Turbo-16K on code comprehension. These results demonstrate the effectiveness of explicit hierarchical structuring as an inductive bias for long-context modeling.
Authors: Siddharth Srivastava, Adam Smith, Scott Brooks, Jack Bacon, Till Bretschneider
Abstract: Automating white blood cell classification for diagnosis of leukaemia is a promising alternative to time-consuming and resource-intensive examination of cells by expert pathologists. However, designing robust algorithms for classification of rare cell types remains challenging due to variations in staining, scanning and inter-patient heterogeneity. We propose a lightweight ensemble approach for classification of cells during Haematopoiesis, with a focus on the biology of Granulopoiesis, Monocytopoiesis and Lymphopoiesis. Through dataset expansion to alleviate some class imbalance, we demonstrate that a simple ensemble of lightweight pretrained SwinV2-Tiny, DinoBloom-Small and ConvNeXT-V2-Tiny models achieves excellent performance on this challenging dataset. We train 3 instantiations of each architecture in a stratified 3-fold cross-validation framework; for an input image, we forward-pass through all 9 models and aggregate through logit averaging. We further reason on the weaknesses of our model in confusing similar-looking myelocytes in granulopoiesis and lymphocytes in lymphopoiesis. Code: https://gitlab.com/siddharthsrivastava/wbc-bench-2026.
URLs: https://gitlab.com/siddharthsrivastava/wbc-bench-2026.
Authors: Luciano Melodia
Abstract: We establish two structural results for Moore homology of ample groupoids. First, for every ample groupoid $\mathcal{G}$ and every discrete abelian coefficient group $A$, we prove a universal coefficient theorem relating the homology groups $H_n(\mathcal{G};A)$ to the integral Moore homology of $\mathcal{G}$. More precisely, we obtain a natural short exact sequence $$ 0 \longrightarrow H_n(\mathcal{G};\mathbb{Z})\otimes_{\mathbb{Z}} A \xrightarrow{\kappa_n^{\mathcal{G}}} H_n(\mathcal{G};A) \xrightarrow{\iota_n^{\mathcal{G}}} \operatorname{Tor}_1^{\mathbb{Z}}\bigl(H_{n-1}(\mathcal{G};\mathbb{Z}),A\bigr) \longrightarrow 0. $$ Second, for a decomposition of the unit space into clopen saturated subsets, we prove a Mayer-Vietoris long exact sequence in Moore homology. The proof is carried out at the chain level and is based on a short exact sequence of Moore chain complexes associated to the corresponding restricted groupoids. These results provide effective tools for the computation of Moore homology. We also explain why the discreteness of the coefficient group is essential for the universal coefficient theorem.
Authors: Tianyou Lai, Wentao Yue, Jiayi Zhou, Chaoyuan Hao, Lingke Chang, Qingyu Mao, Zhibo Niu, Qilei Li
Abstract: Financial time-series forecasting in real-world high-frequency markets is often hindered by delayed or partially stale observations caused by asynchronous data acquisition and transmission latency. To better reflect such practical conditions, we investigate a simulated delay setting where a portion of historical signals is corrupted by a Zero-Order Hold (ZOH) mechanism, significantly increasing forecasting difficulty through stepwise stagnation artifacts. In this paper, we propose ReLaMix (Residual Latency-Aware Mixing Network), a lightweight extension of TimeMixer that integrates learnable bottleneck compression with residual refinement for robust signal recovery under delayed observations. ReLaMix explicitly suppresses redundancy from repeated stale values while preserving informative market dynamics via residual mixing enhancement. Experiments on a large-scale second-resolution PAXGUSDT benchmark demonstrate that ReLaMix consistently achieves state-of-the-art accuracy across multiple delay ratios and prediction horizons, outperforming strong mixer and Transformer baselines with substantially fewer parameters. Moreover, additional evaluations on BTCUSDT confirm the cross-asset generalization ability of the proposed framework. These results highlight the effectiveness of residual bottleneck mixing for high-frequency financial forecasting under realistic latency-induced staleness.
Authors: Kaustubh D. Dhole, Eugene Agichtein
Abstract: Large language models (LLMs) are increasingly evaluated and sometimes trained using automated graders such as LLM-as-judges that output scalar scores or preferences. While convenient, these approaches are often opaque: a single score rarely explains why an answer is good or bad, which requirements were missed, or how a system should be improved. This lack of interpretability limits their usefulness for model development, dataset curation, and high-stakes deployment. Query-specific rubric-based evaluation offers a more transparent alternative by decomposing quality into explicit, checkable criteria. However, manually designing high-quality, query-specific rubrics is labor-intensive and cognitively demanding and not feasible for deployment. While previous approaches have focused on generating intermediate rubrics for automated downstream evaluation, it is unclear if these rubrics are both interpretable and effective for human users. In this work, we investigate whether LLMs can generate useful, instance-specific rubrics as compared to human-authored rubrics, while also improving effectiveness for identifying good responses. Through our systematic study on two rubric benchmarks, and on multiple few-shot and post-training strategies, we find that off-the-shelf LLMs produce rubrics that are poorly aligned with human-authored ones. We introduce a simple strategy, RubricRAG, which retrieves domain knowledge via rubrics at inference time from related queries. We demonstrate that RubricRAG can generate more interpretable rubrics both for similarity to human-authored rubrics, and for improved downstream evaluation effectiveness. Our results highlight both the challenges and a promising approach of scalable, interpretable evaluation through automated rubric generation.
Authors: Melissa Adrian, Daniel Sanz-Alonso, Rebecca Willett
Abstract: Data assimilation algorithms estimate the state of a dynamical system from partial observations, where the successful performance of these algorithms hinges on costly parameter tuning and on employing an accurate model for the dynamics. This paper introduces a framework for jointly learning the state, dynamics, and parameters of filtering algorithms in data assimilation through a process we refer to as auto-differentiable filtering. The framework leverages a theoretically motivated loss function that enables learning from partial, noisy observations via gradient-based optimization using auto-differentiation. We further demonstrate how several well-known data assimilation methods can be learned or tuned within this framework. To underscore the versatility of auto-differentiable filtering, we perform experiments on dynamical systems spanning multiple scientific domains, such as the Clohessy-Wiltshire equations from aerospace engineering, the Lorenz-96 system from atmospheric science, and the generalized Lotka-Volterra equations from systems biology. Finally, we provide guidelines for practitioners to customize our framework according to their observation model, accuracy requirements, and computational budget.
Authors: Tanay Varshney, Annie Surla, Michelle Xu, Gomathy Venkata Krishnan, Maximilian Jeblick, David Austin, Neal Vaidya, Davide Onofrio
Abstract: LLMs often share comparable benchmark accuracies, but their complementary performance across task subsets suggests that an Oracle router--a theoretical selector with perfect foresight--can significantly surpass standalone model accuracy by navigating model-specific strengths. While current routers rely on fragile semantic signals, we propose using internal prefill activations via Encoder-Target Decoupling--a functional separation between the model providing the predictive signal (the Encoder) and the model whose performance is being estimated (the Target). This allows optimized heterogeneous pairing between unique encoders and target models. We utilize Fisher Separability (J) and Effective Dimensionality (d_eff) as mathematical probes to isolate optimal layer-wise signals, providing the predictive foundation for our SharedTrunkNet architecture. SharedTrunkNet captures up to 45.58% of the accuracy gap between the strongest standalone model and the Oracle while achieving 74.31% cost savings relative to the highest-cost model.
Authors: Lisan Al Amin, Md Ismail Hossain, Rupak Kumar Das, Mahbubul Islam, Saddam Mukta, Abdulaziz Tabbakh
Abstract: The exponential growth in data has intensified the demand for computational power to train large-scale deep learning models. However, the rapid growth in model size and complexity raises concerns about equal and fair access to computational resources, particularly under increasing energy and infrastructure constraints. GPUs have emerged as essential for accelerating such workloads. This study benchmarks four deep learning models (Conv6, VGG16, ResNet18, CycleGAN) using TensorFlow and PyTorch on Intel Xeon CPUs and NVIDIA Tesla T4 GPUs. Our experiments demonstrate that, on average, GPU training achieves speedups ranging from 11x to 246x depending on model complexity, with lightweight models (Conv6) showing the highest acceleration (246x), mid-sized models (VGG16, ResNet18) achieving 51-116x speedups, and complex generative models (CycleGAN) reaching 11x improvements compared to CPU training. Additionally, in our PyTorch vs. TensorFlow comparison, we observed that TensorFlow's kernel-fusion optimizations reduce inference latency by approximately 15%. We also analyze GPU memory usage trends and projecting requirements through 2025 using polynomial regression. Our findings highlight that while GPUs are essential for sustaining AI's growth, democratized and shared access to GPU resources is critical for enabling research innovation across institutions with limited computational budgets.
Authors: Gregorio Maglione, Veselin Rakocevic, Markus Amend, Touraj Soleymani
Abstract: Modern multi-access 5G+ networks provide mobile terminals with additional capacity, improving network stability and performance. However, in highly mobile environments such as vehicular networks, supporting multi-access connectivity remains challenging. The rapid fluctuations of wireless link quality often outpace the responsiveness of existing multipath schedulers and transport-layer protocols. This paper addresses this challenge by integrating Transformer-based path state forecasting with a new multipath splitting scheduler called Deep Adaptive Rate Allocation (DARA). The proposed scheduler employs a deep reinforcement learning engine to dynamically compute optimal congestion window fractions on available paths, determining data allocation among them. A six-component normalised reward function with weight-mediated conflict resolution drives a DQN policy that eliminates the observation-reaction lag inherent in reactive schedulers. Performance evaluation uses a Mininet-based Multipath Datagram Congestion Control Protocol testbed with traces from mobile users in vehicular environments. Experimental results demonstrate that DARA achieves better file transfer time reductions compared to learning-based schedulers under moderate-volatility traces. For buffered video streaming, resolution improvements are maintained across all tested conditions. Under controlled burst scenarios with sub-second buffer constraints, DARA achieves substantial rebuffering improvements whilst state-of-the-art schedulers exhibit near-continuous stalling.
Authors: Bert de Vries
Abstract: Physical AI agents, such as robots and other embodied systems operating under tight and fluctuating resource constraints, remain far less capable than biological agents in open-ended real-world environments. This paper argues that Active Inference (AIF), grounded in the Free Energy Principle, offers a principled foundation for closing that gap. We develop this argument from first principles, following a chain from probability theory through Bayesian machine learning and variational inference to active inference and reactive message passing. From the FEP perspective, systems that maintain their structural and functional integrity over time can, under suitable assumptions, be described as minimizing variational free energy (VFE), and AIF operationalizes this by unifying perception, learning, planning, and control within a single computational objective. We show that VFE minimization is naturally realized by reactive message passing on factor graphs, where inference emerges from local, parallel computations. This realization is well matched to the constraints of physical operation, including hard deadlines, asynchronous data, fluctuating power budgets, and changing environments. Because reactive message passing is event-driven, interruptible, and locally adaptable, performance degrades gracefully under reduced resources while model structure can adjust online. We further show that, under suitable coupling and coarse-graining conditions, coupled AIF agents can be described as higher-level AIF agents, yielding a homogeneous architecture based on the same message-passing primitive across scales. Our contribution is not empirical benchmarking, but a clear theoretical and architectural case for the engineering community.
Authors: Debdeep Pati
Abstract: We highlight a striking difference in behavior between two widely used variants of coordinate ascent variational inference: the sequential and parallel algorithms. While such differences were known in the numerical analysis literature in simpler settings, they remain largely unexplored in the optimization-focused literature on variational inference in more complex models. Focusing on the moderately high-dimensional linear regression problem, we show that the sequential algorithm, although typically slower, enjoys convergence guarantees under more relaxed conditions than the parallel variant, which is often employed to facilitate block-wise updates and improve computational efficiency.
Authors: Leandro Vignolo, Matias Gerard
Abstract: Selecting the most relevant or informative features is a key issue in actual machine learning problems. Since an exhaustive search is not feasible even for a moderate number of features, an intelligent search strategy must be employed for finding an optimal subset, which implies considering how features interact with each other in promoting class separability. Balancing feature subset size and classification accuracy constitutes a multi-objective optimization challenge. Here we propose MOELIGA, a multi-objective genetic algorithm incorporating an evolutionary local improvement strategy that evolves subordinate populations to refine feature subsets. MOELIGA employs a crowding-based fitness sharing mechanism and a sigmoid transformation to enhance diversity and guide compactness, alongside a geometry-based objective promoting classifier independence. Experimental evaluation on 14 diverse datasets demonstrates MOELIGA's ability to identify smaller feature subsets with superior or comparable classification performance relative to 11 state-of-the-art methods. These findings suggest MOELIGA effectively addresses the accuracy-dimensionality trade-off, offering a robust and adaptable approach for multi-objective feature selection in complex, high-dimensional scenarios.
Authors: Avrajit Ghosh, Bin Yu, Manfred Warmuth, Peter Bartlett
Abstract: One of the most common machine learning setups is logistic regression. In many classification models, including neural networks, the final prediction is obtained by applying a logistic link function to a linear score. In binary logistic regression, the feedback can be either soft labels, corresponding to the true conditional probability of the data (as in distillation), or sampled hard labels (taking values $\pm 1$). We point out a fundamental problem that arises even in a particularly favorable setting, where the goal is to learn a noise-free soft target of the form $\sigma(\mathbf{x}^{\top}\mathbf{w}^{\star})$. In the over-constrained case (i.e. the number of samples $n$ exceeds the input dimension $d$) with examples $(\mathbf{x}_i,\sigma(\mathbf{x}_i^{\top}\mathbf{w}^{\star}))$, it is sufficient to recover $\mathbf{w}^{\star}$ and hence achieve the Bayes risk. However, we prove that when the examples are labeled by hard labels $y_i$ sampled from the same conditional distribution $\sigma(\mathbf{x}_i^{\top}\mathbf{w}^{\star})$ and $\mathbf{w}^{\star}$ is $s$-sparse, then rotation-invariant algorithms are provably suboptimal: they incur an excess risk $\Omega\!\left(\frac{d-1}{n}\right)$, while there are simple non-rotation invariant algorithms with excess risk $O(\frac{s\log d}{n})$. The simplest rotation invariant algorithm is gradient descent on the logistic loss (with early stopping). A simple non-rotation-invariant algorithm for sparse targets that achieves the above upper bounds uses gradient descent on the weights $u_i,v_i$, where now the linear weight $w_i$ is reparameterized as $u_iv_i$.
Authors: Bo Jiang
Abstract: Multi-agent LLM systems, where multiple prompted instances of a language model independently answer questions, are increasingly used for complex reasoning tasks. However, existing methods for quantifying the uncertainty of their collective outputs rely on shallow voting statistics that discard the rich semantic information in agents' reasoning. We introduce DiscoUQ, a framework that extracts and leverages the structure of inter-agent disagreement -- both linguistic properties (evidence overlap, argument strength, divergence depth) and embedding geometry (cluster distances, dispersion, cohesion) -- to produce well-calibrated confidence estimates. We propose three methods of increasing complexity: DiscoUQ-LLM (logistic regression on LLM-extracted structure features), DiscoUQ-Embed (logistic regression on embedding geometry), and DiscoUQ-Learn (a neural network combining all features). Evaluated on four diverse benchmarks (StrategyQA, MMLU, TruthfulQA, ARC-Challenge) with a 5-agent system using Qwen3.5-27B, DiscoUQ-LLM achieves an average AUROC of 0.802, outperforming the best baseline (LLM Aggregator, 0.791) while being substantially better calibrated (ECE 0.036 vs. 0.098). The learned features generalize across benchmarks with near-zero performance degradation and provide the largest improvements where they are most needed: in the ambiguous "weak disagreement" tier where simple vote counting fails.
Authors: Benedikt Hornig, Reuth Mirsky
Abstract: In shared autonomy, a critical tension arises when an automated assistant must choose between obeying a human's instruction and deliberately overriding it to prevent harm. This safety-critical behavior is known as intelligent disobedience. To formalize this dynamic, this paper introduces the Intelligent Disobedience Game (IDG), a sequential game-theoretic framework based on Stackelberg games that models the interaction between a human leader and an assistive follower operating under asymmetric information. It characterizes optimal strategies for both agents across multi-step scenarios, identifying strategic phenomena such as ``safety traps,'' where the system indefinitely avoids harm but fails to achieve the human's goal. The IDG provides a needed mathematical foundation that enables both the algorithmic development of agents that can learn safe non-compliance and the empirical study of how humans perceive and trust disobedient AI. The paper further translates the IDG into a shared control Multi-Agent Markov Decision Process representation, forming a compact computational testbed for training reinforcement learning agents.
Authors: Rushikesh Deotale, Adithya Srinivasan, Yuan Tian, Tianyi Zhang, Pavlos Vlachos, Hector Gomez
Abstract: Finite element (FE) analysis guides the design and verification of nearly all manufactured objects. It is at the core of computational engineering, enabling simulation of complex physical systems, from fluids and solids to multiphysics systems. However, implementing FE codes and analyzing simulation results demands expertise across numerical analysis, continuum mechanics, and programming. Conventional Large Language Models (LLMs) can generate FE code, but they hallucinate, lack awareness of variational structures, and cannot close the loop from problem statement to a verified solution. Here, we propose ALL-FEM, an autonomous simulation system that integrates agentic AI with domain-specific, fine-tuned LLMs for FEniCS code generation across solid, fluid, and multiphysics applications. We construct a corpus of 1000+ verified FEniCS scripts by combining 500+ curated expert codes with a retrieval-augmented, multi-LLM pipeline that generates and filters codes for diverse PDEs, geometries, and boundary conditions. We used the corpus to fine-tune LLMs with 3B to 120B parameters. Our agentic framework orchestrates specialized agents, powered by fine-tuned LLMs, to formulate problems as PDEs, generate and debug code and visualize the results. We evaluated the system on 39 benchmarks that include problems of linear/nonlinear elasticity, plasticity, Newtonian/non-Newtonian flow, thermofluids, fluid-structure interaction, phase separation, and transport on moving domains. Embedded in a multi-agent workflow with runtime feedback, the best fine-tuned model (GPT OSS 120B) achieves code-level success of 71.79%, outperforming a non-agentic deployment of GPT 5 Thinking. By showing that relatively small, fine-tuned LLMs, orchestrated through agentic frameworks, can automate FE workflows, ALL-FEM offers a blueprint for autonomous simulation systems in computational science and engineering.
Authors: Erich Studerus, Vivienne Jia Zhong, Stephan Vonschallen
Abstract: Despite recent advances in integrating Large Language Models (LLMs) into social robotics, two weaknesses persist. First, existing implementations on platforms like Pepper often rely on cascaded Speech-to-Text (STT)->LLM->Text-to-Speech (TTS) pipelines, resulting in high latency and the loss of paralinguistic information. Second, most implementations fail to fully leverage the LLM's capabilities for multimodal perception and agentic control. We present an open-source Android framework for the Pepper robot that addresses these limitations through two key innovations. First, we integrate end-to-end Speech-to-Speech (S2S) models to achieve low-latency interaction while preserving paralinguistic cues and enabling adaptive intonation. Second, we implement extensive Function Calling capabilities that elevate the LLM to an agentic planner, orchestrating robot actions (navigation, gaze control, tablet interaction) and integrating diverse multimodal feedback (vision, touch, system state). The framework runs on the robot's tablet but can also be built to run on regular Android smartphones or tablets, decoupling development from robot hardware. This work provides the HRI community with a practical, extensible platform for exploring advanced LLM-driven embodied interaction.
Authors: Jinquan Zheng, Jia Yuan, Jiacheng Yao, Chenyang Gu, Pujun Zheng, Guoxiu He
Abstract: Large language models (LLMs) used for multiple-choice and pairwise evaluation tasks often exhibit selection bias due to non-semantic factors like option positions and label symbols. Existing inference-time debiasing is costly and may harm reasoning, while pointwise training ignores that the same question should yield consistent answers across permutations. To address this issue, we propose Permutation-Aware Group Relative Policy Optimization (PA-GRPO), which mitigates selection bias by enforcing permutation-consistent semantic reasoning. PA-GRPO constructs a permutation group for each instance by generating multiple candidate permutations, and optimizes the model using two complementary mechanisms: (1) cross-permutation advantage, which computes advantages relative to the mean reward over all permutations of the same instance, and (2) consistency-aware reward, which encourages the model to produce consistent decisions across different permutations. Experimental results demonstrate that PA-GRPO outperforms strong baselines across seven benchmarks, substantially reducing selection bias while maintaining high overall performance. The code will be made available on Github (https://github.com/ECNU-Text-Computing/PA-GRPO).
Authors: Yunhai Hu, Junwei Zhou, Yumo Cao, Yitao Long, Yiwei Xu, Qiyi Jiang, Weiyao Wang, Xiaoyu Cao, Zhen Sun, Yiran Zou, Nan Du
Abstract: Effective retrieval in complex domains requires bridging the gap between structured metadata and unstructured content. Existing systems typically isolate these capabilities, relying on either symbolic filtering or vector similarity, failing to capture their interplay. In this work, we propose DSL-R1, a unified framework that synergizes logical reasoning with semantic matching via a novel Domain-Specific Language (DSL). By embedding vector primitives within SQL-style operators, our approach leverages the complementary strengths of symbolic precision and semantic coverage. We further introduce a reinforcement learning mechanism where rule-based execution feedback and retrieval quality rewards jointly optimize the DSL generation, balancing structural correctness and semantic alignment. Evaluations on a large-scale industrial email benchmark demonstrate that DSL-R1 achieves a +12.3% improvement in Hit@1/3, consistently outperforming decoupled baselines and establishing a robust paradigm for hybrid retrieval.
Authors: Ziquan Wang, Zhongqi Lu
Abstract: We propose Knowledge Boundary Discovery (KBD), a reinforcement learning based framework to explore the knowledge boundaries of the Large Language Models (LLMs). We define the knowledge boundary by automatically generating two types of questions: (i) those the LLM can confidently answer (within-knowledge boundary) and (ii) those it cannot (beyond-knowledge boundary). Iteratively exploring and exploiting the LLM's responses to find its knowledge boundaries is challenging because of the hallucination phenomenon. To find the knowledge boundaries of an LLM, the agent interacts with the LLM under the modeling of exploring a partially observable environment. The agent generates a progressive question as the action, adopts an entropy reduction as the reward, receives the LLM's response as the observation and updates its belief states. We demonstrate that the KBD detects knowledge boundaries of LLMs by automatically finding a set of non-trivial answerable and unanswerable questions. We validate the KBD by comparing its generated knowledge boundaries with manually crafted LLM benchmark datasets. Experiments show that our KBD-generated question set is comparable to the human-generated datasets. Our approach paves a new way to evaluate LLMs.
Authors: Taiga Saito, Yu Otake, Daijiro Mizutani, Stephen Wu
Abstract: Geotechnical site characterisation relies on sparse, heterogeneous borehole data where uncertainty quantification and model interpretability are as critical as predictive accuracy for reliable engineering decisions. This paper presents an exploratory investigation into the use of TabPFN, a transformer-based tabular foundation model using in-context learning, and its extension library tabpfn-extensions for two geotechnical inference tasks: (1) soil-type classification using N-value and shear-wave velocity data from a synthetic geotechnical dataset, and (2) iterative imputation of five missing mechanical parameters ($s_\mathrm{u}$, $E_{\mathrm{u}}$, ${\sigma'}_\mathrm{p}$, $C_\mathrm{c}$, $C_\mathrm{v}$) in benchmark problem BM/AirportSoilProperties/2/2025. We apply cosine-similarity analysis to TabPFN-derived embeddings, visualise full posterior distributions from an iterative inference procedure, and compute SHAP-based feature importance, all without model retraining. Learned embeddings clearly separate Clay and Sand samples without explicit soil-type supervision; iterative imputation improves predictions for four of five target parameters, with posterior widths that reflect physically reasonable parameter-specific uncertainty; and SHAP analysis reveals the inter-parameter dependency structure, recovering established geotechnical relationships including the Skempton compression index correlation and the inverse dependence of preconsolidation pressure on water content. These results suggest the potential of foundation-model-based tools to support interpretable, uncertainty-aware parameter inference in data-scarce geotechnical practice.
Authors: Shuoxun Xu, Zhanhao Yan, Lexin Li
Abstract: Brain encoding and decoding aims to understand the relationship between external stimuli and brain activities, and is a fundamental problem in neuroscience. In this article, we study latent embedding alignment for brain encoding and decoding, with a focus on improving sample efficiency under limited fMRI-stimulus paired data and substantial subject heterogeneity. We propose a lightweight alignment framework equipped with two statistical learning components: inverse semi-supervised learning that leverages abundant unpaired stimulus embeddings through inverse mapping and residual debiasing, and meta transfer learning that borrows strength from pretrained models across subjects via sparse aggregation and residual correction. Both methods operate exclusively at the alignment stage while keeping encoders and decoders frozen, allowing for efficient computation, modular deployment, and rigorous theoretical analysis. We establish finite-sample generalization bounds and safety guarantees, and demonstrate competitive empirical performance on the large-scale fMRI-image reconstruction benchmark data.
Authors: Yingzhen Yang, Ping Li
Abstract: We study the problem of learning a low-degree spherical polynomial of degree $k_0 = \Theta(1) \ge 1$ defined on the unit sphere in $\RR^d$ by training an over-parameterized two-layer neural network with augmented feature in this paper. Our main result is the significantly improved sample complexity for learning such low-degree polynomials. We show that, for any regression risk $\eps \in (0, \Theta(d^{-k_0})]$, an over-parameterized two-layer neural network trained by a novel Gradient Descent with Projection (GDP) requires a sample complexity of $n \asymp \Theta( \log(4/\delta) \cdot d^{k_0}/\eps)$ with probability $1-\delta$ for $\delta \in (0,1)$, in contrast with the representative sample complexity $\Theta(d^{k_0} \max\set{\eps^{-2},\log d})$. Moreover, such sample complexity is nearly unimprovable since the trained network renders a nearly optimal rate of the nonparametric regression risk of the order $\log({4}/{\delta}) \cdot \Theta(d^{k_0}/{n})$ with probability at least $1-\delta$. On the other hand, the minimax optimal rate for the regression risk with a kernel of rank $\Theta(d^{k_0})$ is $\Theta(d^{k_0}/{n})$, so that the rate of the nonparametric regression risk of the network trained by GDP is nearly minimax optimal. In the case that the ground truth degree $k_0$ is unknown, we present a novel and provable adaptive degree selection algorithm which identifies the true degree and achieves the same nearly optimal regression rate. To the best of our knowledge, this is the first time that a nearly optimal risk bound is obtained by training an over-parameterized neural network with a popular activation function (ReLU) and algorithmic guarantee for learning low-degree spherical polynomials. Due to the feature learning capability of GDP, our results are beyond the regular Neural Tangent Kernel (NTK) limit.
Authors: Tin Van Huynh, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen
Abstract: High-quality text representations are crucial for natural language understanding (NLU), but low-resource languages like Vietnamese face challenges due to limited annotated data. While pre-trained models like PhoBERT and CafeBERT perform well, their effectiveness is constrained by data scarcity. Contrastive learning (CL) has recently emerged as a promising approach for improving sentence representations, enabling models to effectively distinguish between semantically similar and dissimilar sentences. We propose ViCLSR (Vietnamese Contrastive Learning for Sentence Representations), a novel supervised contrastive learning framework specifically designed to optimize sentence embeddings for Vietnamese, leveraging existing natural language inference (NLI) datasets. Additionally, we propose a process to adapt existing Vietnamese datasets for supervised learning, ensuring compatibility with CL methods. Our experiments demonstrate that ViCLSR significantly outperforms the powerful monolingual pre-trained model PhoBERT on five benchmark NLU datasets such as ViNLI (+6.97% F1), ViWikiFC (+4.97% F1), ViFactCheck (+9.02% F1), UIT-ViCTSD (+5.36% F1), and ViMMRC2.0 (+4.33% Accuracy). ViCLSR shows that supervised contrastive learning can effectively address resource limitations in Vietnamese NLU tasks and improve sentence representation learning for low-resource languages. Furthermore, we conduct an in-depth analysis of the experimental results to uncover the factors contributing to the superior performance of contrastive learning models. ViCLSR is released for research purposes in advancing natural language processing tasks.
Authors: Vivek Shripad Borkar
Abstract: Based on some recent work of the author on stochastic approximation in non-markovian environments, the situation when the driving random process is non-ergodic in addition to being non-markovian is considered. Using this, we propose an analytic framework for understanding transformer based learning, specifically, the `attention' mechanism, and continual learning, both of which depend on the entire past in principle.
Authors: Haidong Wang, Songhan Zhao, Bo Gu, Shimin Gong, Hongyang Du, Ping Wang
Abstract: In this paper, we explore a joint source and reconfigurable intelligent surface (RIS)-assisted channel encoding (JSRE) framework for multi-user semantic communications, where a deep neural network (DNN) extracts semantic features for all users and the RIS provides channel orthogonality, enabling a unified semantic encoding-decoding design. We aim to maximize the overall energy efficiency of semantic communications across all users by jointly optimizing the user scheduling, the RIS's phase shifts, and the semantic compression ratio. Although this joint optimization problem can be addressed using conventional deep reinforcement learning (DRL) methods, evaluating semantic similarity typically relies on extensive real environment interactions, which can incur heavy computational overhead during training. To address this challenge, we propose a truncated DRL (T-DRL) framework, where a DNN-based semantic similarity estimator is developed to rapidly estimate the similarity score. Moreover, the user scheduling strategy is tightly coupled with the semantic model configuration. To exploit this relationship, we further propose a semantic model caching mechanism that stores and reuses fine-tuned semantic models corresponding to different scheduling decisions. A Transformer-based actor network is employed within the DRL framework to dynamically generate action space conditioned on the current caching state. This avoids redundant retraining and further accelerates the convergence of the learning process. Numerical results demonstrate that the proposed JSRE framework significantly improves the system energy efficiency compared with the baseline methods. By training fewer semantic models, the proposed T-DRL framework significantly enhances the learning efficiency.
Authors: Shih-Wen Liu, Yen-Chang Chen, Wei-Ta Chu, Fu-En Yang, Yu-Chiang Frank Wang
Abstract: Multi-task learning (MTL) aims to enable a single model to solve multiple tasks efficiently; however, current parameter-efficient fine-tuning (PEFT) methods remain largely limited to single-task adaptation. We introduce \textbf{Free Sinewich}, a parameter-efficient multi-task learning framework that enables near-zero-cost weight modulation via frequency switching (\textbf{Free}). Specifically, a \textbf{Sine-AWB (Sinewich)} layer combines low-rank factors and convolutional priors into a single kernel, which is then modulated elementwise by a sinusoidal transformation to produce task-specialized weights. A lightweight Clock Net is introduced to produce bounded frequencies that stabilize this modulation during training. Theoretically, sine modulation enhances the rank of low-rank adapters, while frequency separation decorrelates the weights of different tasks. On dense prediction benchmarks, Free Sinewich achieves state-of-the-art performance-efficiency trade-offs (e.g., up to +5.39\% improvement over single-task fine-tuning with only 6.53M trainable parameters), offering a compact and scalable paradigm based on frequency-based parameter sharing. Project page: \href{https://casperliuliuliu.github.io/projects/Free-Sinewich/}{https://casperliuliuliu.github.io/projects/Free-Sinewich}.
URLs: https://casperliuliuliu.github.io/projects/Free-Sinewich/, https://casperliuliuliu.github.io/projects/Free-Sinewich
Authors: Ounnaci Iddir, Ahmed-ouamer Rachid, Tai Dinh
Abstract: This paper addresses the challenge of improving information retrieval from semi-structured eXtensible Markup Language (XML) documents. Traditional information retrieval systems (IRS) often overlook user-specific needs and return identical results for the same query, despite differences in users' knowledge, preferences, and objectives. We integrate external semantic resources, namely a domain ontology and user profiles, into the retrieval process. Documents, queries, and user profiles are represented as vectors of weighted concepts. The ontology applies a concept-weighting mechanism that emphasizes highly specific concepts, as lower-level nodes in the hierarchy provide more precise and targeted information. Relevance is assessed using semantic similarity measures that capture conceptual relationships beyond keyword matching, enabling personalized and fine-grained matching among user profiles, queries, and documents. Experimental results show that combining ontologies with user profiles improves retrieval effectiveness, achieving higher precision and recall than keyword-based approaches. Overall, the proposed framework enhances the relevance and adaptability of XML search results, supporting more user-centered retrieval.
Authors: MD Ruiz-Medina, AE Madrid, A Torres-Signes, JM Angulo
Abstract: This paper proposes a new formulation of functional Gaussian Process regression in manifolds, based on an Empirical Bayes approach, in the spatiotemporal random field context. We apply the machinery of tight Gaussian measures in separable Hilbert spaces, exploiting the invariance property of covariance kernels under the group of isometries of the manifold. The identification of these measures with infinite-product Gaussian measures is then obtained via the eigenfunctions of the Laplace-Beltrami operator on the manifold. The involved time-varying angular spectra constitute the key tool for dimension reduction in the implementation of this regression approach, adopting a suitable truncation scheme depending on the functional sample size. The simulation study and synthetic data application undertaken illustrate the finite sample and asymptotic properties of the proposed functional regression predictor.
Authors: Peihan Ye, Alfreds Lapkovskis, Alaa Saleh, Qiyang Zhang, Praveen Kumar Donta
Abstract: The computational demands of modern AI services are increasingly shifting execution beyond centralized clouds toward a computing continuum spanning edge and end devices. However, the scale, heterogeneity, and cross-layer dependencies of these environments make resilience difficult to maintain. Existing fault-management methods are often too static, fragmented, or heavy to support timely self-healing, especially under noisy logs and edge resource constraints. To address these limitations, this paper presents NeSy-Edge, a neuro-symbolic framework for trustworthy self-healing in the computing continuum. The framework follows an edge-first design, where a resource-constrained edge node performs local perception and reasoning, while a cloud model is invoked only at the final diagnosis stage. Specifically, NeSy-Edge converts raw runtime logs into structured event representations, builds a prior-constrained sparse symbolic causal graph, and integrates causal evidence with historical troubleshooting knowledge for root-cause analysis and recovery recommendation. We evaluate our work on representative Loghub datasets under multiple levels of semantic noise, considering parsing quality, causal reasoning, end-to-end diagnosis, and edge-side resource usage. The results show that NeSy-Edge remains robust even at the highest noise level, achieving up to 75% root-cause analysis accuracy and 65% end-to-end accuracy while operating within about 1500 MB of local memory.
Authors: Leonid Ugadiarov, Yuri Kuratov, Aleksandr Panov, Alexey Skrynnik
Abstract: Neural tree search is a powerful decision-making algorithm widely used in complex domains such as game playing and model-based reinforcement learning. Recent work has applied AlphaZero-style tree search to enhance the reasoning capabilities of Large Language Models (LLMs) during inference, but we find that this approach suffers from a scaling failure: on GSM8K and Game24, accuracy drops as the search budget increases. In this paper, we present ReSCALE, an adaptation of Gumbel AlphaZero MCTS that replaces Dirichlet noise and PUCT selection with Gumbel sampling and Sequential Halving, restoring monotonic scaling without changes to the model or its training. ReSCALE reaches 58.4\% on GSM8K and 85.3\% on Game24 at budgets where the baseline degrades. Ablations confirm that Sequential Halving is the primary driver of the improvement.
Authors: Ebasa Temesgen, Nathnael Minyelshowa, Lebsework Negash
Abstract: The use of unmanned aerial vehicles (UAVs) in precision agriculture has seen a huge increase recently. As such, systems that aim to apply various algorithms on the field need a structured framework of abstractions. This paper defines the various tasks of the UAVs in precision agriculture and model them into an architectural framework. The presented architecture is built on the context that there will be minimal physical intervention to do the tasks defined with multiple coordinated and cooperative UAVs. Various tasks such as image processing, path planning, communication, data acquisition, and field mapping are employed in the architecture to provide an efficient system. Besides, different limitation for applying Multi-UAVs in precision agriculture has been considered in designing the architecture. The architecture provides an autonomous end-to-end solution, starting from mission planning, data acquisition and image processing framework that is highly efficient and can enable farmers to comprehensively deploy UAVs onto their lands. Simulation and field tests shows that the architecture offers a number of advantages that include fault-tolerance, robustness, developer and user-friendliness.
Authors: Haolun Zheng, Yu He, Tailun Chen, Shuo Shao, Zhixuan Chu, Hongbin Zhou, Lan Tao, Zhan Qin, Kui Ren
Abstract: Text-to-image (T2I) models such as Stable Diffusion and DALLE remain susceptible to generating harmful or Not-Safe-For-Work (NSFW) content under jailbreak attacks despite deployed safety filters. Existing jailbreak attacks either rely on proxy-loss optimization instead of the true end-to-end objective, or depend on large-scale and costly RL-trained generators. Motivated by these limitations, we propose JANUS , a lightweight framework that formulates jailbreak as optimizing a structured prompt distribution under a black-box, end-to-end reward from the T2I system and its safety filters. JANUS replaces a high-capacity generator with a low-dimensional mixing policy over two semantically anchored prompt distributions, enabling efficient exploration while preserving the target semantics. On modern T2I models, we outperform state-of-the-art jailbreak methods, improving ASR-8 from 25.30% to 43.15% on Stable Diffusion 3.5 Large Turbo with consistently higher CLIP and NSFW scores. JANUS succeeds across both open-source and commercial models. These findings expose structural weaknesses in current T2I safety pipelines and motivate stronger, distribution-aware defenses. Warning: This paper contains model outputs that may be offensive.
Authors: Sing-Yuan Yeh, Yi-An Wu, Hau-Tieng Wu, Mao-Pei Tsui
Abstract: We propose a landmark-constrained algorithm, LA-VDM (Landmark Accelerated Vector Diffusion Maps), to accelerate the Vector Diffusion Maps (VDM) framework built upon the Graph Connection Laplacian (GCL), which captures pairwise connection relationships within complex datasets. LA-VDM introduces a novel two-stage normalization that effectively address nonuniform sampling densities in both the data and the landmark sets. Under a manifold model with the frame bundle structure, we show that we can accurately recover the parallel transport with landmark-constrained diffusion from a point cloud, and hence asymptotically LA-VDM converges to the connection Laplacian. The performance and accuracy of LA-VDM are demonstrated through experiments on simulated datasets and an application to nonlocal image denoising.
Authors: Zachary F. Mainen
Abstract: Externalized reasoning is already exploited by transformer-based agents through chain-of-thought, but structured retrieval -- indexing over one's own reasoning state -- remains underexplored. We formalize the transformer context window as an I/O page and prove that tool-augmented agents with indexed external memory achieve exponentially lower retrieval cost than agents restricted to sequential scanning: $O(\log_b N)$ versus $\Omega(N)$ page reads per query, and $O(T \log_b T)$ versus $\Theta(T^2)$ cumulative cost over $T$ reasoning steps -- a gap that widens as deliberation deepens. We test these predictions on a controlled lookup benchmark across three content types -- random hashes, ordered integers, and encyclopedia entries -- varying store size from 50 to 5,000 items, and replicate key conditions across two model generations (GPT-4o-mini and GPT-5.4). On abstract content, the indexed agent achieves median 1 page read regardless of store size, confirming the $O(1)$ prediction. Sorted pages without an index fail to close the gap: the weaker model cannot sustain binary search at scale, and the stronger model achieves near-optimal $\log_2 N$ search but still loses to the index by $5\times$. On familiar content (encyclopedia entries), a competing failure mode emerges: the model recognizes the domain, bypasses the retrieval protocol, and generates answers from parametric memory, producing catastrophic token expenditure even when the index is sound. This parametric memory competition dissociates the two cognitive operations that indexing combines: understanding content (where language models excel) and following navigational protocols (where they fail when understanding tempts them to shortcut). The result argues for a separation of concerns: use language models for index construction, where semantic understanding helps, and deterministic algorithms for index traversal, where it hurts.
Authors: Brianna Binder, Assad Oberai
Abstract: We propose closed-form conditional diffusion models for data assimilation. Diffusion models use data to learn the score function (defined as the gradient of the log-probability density of a data distribution), allowing them to generate new samples from the data distribution by reversing a noise injection process. While it is common to train neural networks to approximate the score function, we leverage the analytical tractability of the score function to assimilate the states of a system with measurements. To enable the efficient evaluation of the score function, we use kernel density estimation to model the joint distribution of the states and their corresponding measurements. The proposed approach also inherits the capability of conditional diffusion models of operating in black-box settings, i.e., the proposed data assimilation approach can accommodate systems and measurement processes without their explicit knowledge. The ability to accommodate black-box systems combined with the superior capabilities of diffusion models in approximating complex, non-Gaussian probability distributions means that the proposed approach offers advantages over many widely used filtering methods. We evaluate the proposed method on nonlinear data assimilation problems based on the Lorenz-63 and Lorenz-96 systems of moderate dimensionality and nonlinear measurement models. Results show the proposed approach outperforms the widely used ensemble Kalman and particle filters when small to moderate ensemble sizes are used.
Authors: Aakash Ravindra Shinde, Arianne Meijer - van de Griend, Jukka K. Nurminen
Abstract: Variational Quantum Algorithms (VQAs) have been extensively researched for applications in Quantum Machine Learning (QML), Optimization, and Molecular simulations. Although designed for Noisy Intermediate-Scale Quantum (NISQ) devices, VQAs are predominantly evaluated classically due to uncertain results on noisy devices and limited resource availability. Raising concern over the reproducibility of simulated VQAs on noisy hardware. While prior studies indicate that VQAs may exhibit noise resilience in specific parameterized shallow quantum circuits, there are no definitive measures to establish what defines a shallow circuit or the optimal circuit depth for VQAs on a noisy platform. These challenges extend naturally to Variational Quantum Classification (VQC) algorithms, a subclass of VQAs for supervised learning. In this article, we propose a relative entropy-based metric to verify whether a VQC model would perform similarly on a noisy device as it does on simulations. We establish a strong correlation between the average relative entropy difference in classes, transpilation circuit depth, and their performance difference on a noisy quantum device. Our results further indicate that circuit depth alone is insufficient to characterize shallow circuits. We present empirical evidence to support these assertions across a diverse array of techniques for implementing VQC, datasets, and multiple noisy quantum devices.
Authors: Khushiyant, Param Thakkar
Abstract: Audio representation learning typically evaluates design choices such as input frontend, sequence backbone, and sequence length in isolation. We show that these axes are coupled, and conclusions from one setting often do not transfer to others. We introduce HELIX, a controlled framework comparing pure Mamba, pure attention, and a minimal hybrid with a single attention bottleneck. All models are parameter-matched at about 8.3M parameters to isolate architectural effects. Across six datasets, we find that the preferred input representation depends on the backbone, and that attention hurts performance on short, stationary audio but becomes important at longer sequence lengths. On a 5-minute speaker identification task with 30,000 tokens, pure attention fails with out-of-memory errors, while HELIX closes an 11.5-point gap over pure Mamba.
Authors: Idan Amit
Abstract: Context: Static analysis captures software engineering knowledge and alerts on possibly problematic patterns. Previous work showed that they indeed have predictive power for various problems. However, the impact of removing the alerts is unclear. Aim: We would like to evaluate the impact of alert removals on code complexity and the tendency to bugs. Method: We evaluate the impact of removing alerts using three complementary methods. 1. We conducted a randomized controlled trial and built a dataset of 521 manual alert-removing interventions 2. We profiled intervention-like events using labeling functions. We applied these labeling functions to code commits, found intervention-like natural events, and used them to analyze the impact on the tendency to bugs. 3. We built a dataset of 8,245 alert removals, more than 15 times larger than our dataset of manual interventions. We applied supervised learning to the alert removals, aiming to predict their impact on the tendency to bugs. Results: We identified complexity-reducing interventions that reduce the probability of future bugs. Such interventions are relevant to 33\% of Python files and might reduce the tendency to bugs by 5.5 percentage points. Conclusions: We presented methods to evaluate the impact of interventions. The methods can identify a large number of natural interventions that are highly needed in causality research in many domains.
Authors: Hongyang Yang, Boyu Zhang, Yang She, Xinyu Liao, Xiaoli Zhang
Abstract: We present FinRL-X, a modular and deployment-consistent trading architecture that unifies data processing, strategy construction, backtesting, and broker execution under a weight-centric interface. While existing open-source platforms are often backtesting- or model-centric, they rarely provide system-level consistency between research evaluation and live deployment. FinRL-X addresses this gap through a composable strategy pipeline that integrates stock selection, portfolio allocation, timing, and portfolio-level risk overlays within a unified protocol. The framework supports both rule-based and AI-driven components, including reinforcement learning allocators and LLM-based sentiment signals, without altering downstream execution semantics. FinRL-X provides an extensible foundation for reproducible, end-to-end quantitative trading research and deployment. The official FinRL-X implementation is available at https://github.com/AI4Finance-Foundation/FinRL-Trading.
URLs: https://github.com/AI4Finance-Foundation/FinRL-Trading.
Authors: Saketh Vinjamuri, Marielle Fis Loperena, Marie C. Spezia, Ramez Kouzy
Abstract: Time toxicity, the cumulative healthcare contact days from clinical trial participation, is an important but labor-intensive metric to extract from protocol documents. We developed TimeTox, an LLM-based pipeline for automated extraction of time toxicity from Schedule of Assessments tables. TimeTox uses Google's Gemini models in three stages: summary extraction from full-length protocol PDFs, time toxicity quantification at six cumulative timepoints for each treatment arm, and multi-run consensus via position-based arm matching. We validated against 20 synthetic schedules (240 comparisons) and assessed reproducibility on 644 real-world oncology protocols. Two architectures were compared: single-pass (vanilla) and two-stage (structure-then-count). The two-stage pipeline achieved 100% clinically acceptable accuracy ($\pm$3 days) on synthetic data (MAE 0.81 days) versus 41.5% for vanilla (MAE 9.0 days). However, on real-world protocols, the vanilla pipeline showed superior reproducibility: 95.3% clinically acceptable accuracy (IQR $\leq$ 3 days) across 3 runs on 644 protocols, with 82.0% perfect stability (IQR = 0). The production pipeline extracted time toxicity for 1,288 treatment arms across multiple disease sites. Extraction stability on real-world data, rather than accuracy on synthetic benchmarks, is the decisive factor for production LLM deployment.
Authors: Oussama Zekri, Th\'eo Uscidda, Nicolas Boull\'e, Anna Korba
Abstract: We introduce Generalized Discrete Diffusion from Snapshots (GDDS), a unified framework for discrete diffusion modeling that supports arbitrary noising processes over large discrete state spaces. Our formulation encompasses all existing discrete diffusion approaches, while allowing significantly greater flexibility in the choice of corruption dynamics. The forward noising process relies on uniformization and enables fast arbitrary corruption. For the reverse process, we derive a simple evidence lower bound (ELBO) based on snapshot latents, instead of the entire noising path, that allows efficient training of standard generative modeling architectures with clear probabilistic interpretation. Our experiments on large-vocabulary discrete generation tasks suggest that the proposed framework outperforms existing discrete diffusion methods in terms of training efficiency and generation quality, and beats autoregressive models for the first time at this scale. We provide the code along with a blog post on the project page : \href{https://oussamazekri.fr/gdds}{https://oussamazekri.fr/gdds}.
URLs: https://oussamazekri.fr/gdds, https://oussamazekri.fr/gdds
Authors: Mohamed A Mabrok
Abstract: We present HamVision, a framework for medical image analysis that uses the damped harmonic oscillator, a fundamental building block of signal processing, as a structured inductive bias for both segmentation and classification tasks. The oscillator's phase-space decomposition yields three functionally distinct representations: position~$q$ (feature content), momentum~$p$ (spatial gradients that encode boundary and texture information), and energy $H = \tfrac{1}{2}|z|^2$ (a parameter-free saliency map). These representations emerge from the dynamics, not from supervision, and can be exploited by different task-specific heads without any modification to the oscillator itself. For segmentation, energy gates the skip connections while momentum injects boundary information at every decoder level (HamSeg). For classification, the three representations are globally pooled and concatenated into a phase-space feature vector (HamCls). We evaluate HamVision across ten medical imaging benchmarks spanning five imaging modalities. On segmentation, HamSeg achieves state-of-the-art Dice scores on ISIC\,2018 (89.38\%), ISIC\,2017 (88.40\%), TN3K (87.05\%), and ACDC (92.40\%), outperforming most baselines with only 8.57M parameters. On classification, HamCls achieves state-of-the-art accuracy on BloodMNIST (98.85\%) and PathMNIST (96.65\%), and competitive results on the remaining MedMNIST datasets against MedMamba and MedViT. Diagnostic analysis confirms that the oscillator's momentum consistently encodes an interior$\,{>}\,$boundary$\,{>}\,$exterior gradient for segmentation and that the energy map correlates with discriminative regions for classification, properties that emerge entirely from the Hamiltonian dynamics. Code is available at https://github.com/Minds-R-Lab/hamvision.
Authors: Jinghan Cao, Yu Ma, Xinjin Li, Qingyang Ren, Xiangyun Chen
Abstract: Large Language Models achieve remarkable performance but incur substantial computational costs unsuitable for resource-constrained deployments. This paper presents the first comprehensive task-specific efficiency analysis comparing 16 language models across five diverse NLP tasks. We introduce the Performance-Efficiency Ratio (PER), a novel metric integrating accuracy, throughput, memory, and latency through geometric mean normalization. Our systematic evaluation reveals that small models (0.5--3B parameters) achieve superior PER scores across all given tasks. These findings establish quantitative foundations for deploying small models in production environments prioritizing inference efficiency over marginal accuracy gains.
Authors: Gregory M. Ruddell
Abstract: As large language models are deployed as autonomous agents with tool execution privileges, a critical assumption underpins their security architecture: that model errors are detectable at runtime. We present empirical evidence that this assumption fails for two of three instruction-following models evaluable for conflict detection. We introduce governability -- the degree to which a model's errors are detectable before output commitment and correctable once detected -- and demonstrate it varies dramatically across models. In six models across twelve reasoning domains, two of three instruction-following models exhibited silent commitment failure: confident, fluent, incorrect output with zero warning signal. The remaining model produced a detectable conflict signal 57 tokens before commitment under greedy decoding. We show benchmark accuracy does not predict governability, correction capacity varies independently of detection, and identical governance scaffolds produce opposite effects across models. A 2x2 experiment shows a 52x difference in spike ratio between architectures but only +/-0.32x variation from fine-tuning, suggesting governability is fixed at pretraining. We propose a Detection and Correction Matrix classifying model-task combinations into four regimes: Governable, Monitor Only, Steer Blind, and Ungovernable.
Authors: Mariela M. Nina, Caio Veloso Costa, Lilian Berton, Didier A. Vega-Oliveros
Abstract: Although large language models have transformed natural language processing, their computational costs create accessibility barriers for low-resource languages such as Brazilian Portuguese. This work presents a systematic evaluation of Parameter-Efficient Fine-Tuning (PEFT) and quantization techniques applied to BERTimbau for Question Answering on SQuAD-BR, the Brazilian Portuguese translation of SQuAD v1. We evaluate 40 configurations combining four PEFT methods (LoRA, DoRA, QLoRA, QDoRA) across two model sizes (Base: 110M, Large: 335M parameters). Our findings reveal three critical insights: (1) LoRA achieves 95.8\% of baseline performance on BERTimbau-Large while reducing training time by 73.5\% (F1=81.32 vs 84.86); (2) higher learning rates (2e-4) substantially improve PEFT performance, with F1 gains of up to +19.71 points over standard rates; and (3) larger models show twice the quantization resilience (loss of 4.83 vs 9.56 F1 points). These results demonstrate that encoder-based models can be efficiently fine-tuned for extractive Brazilian Portuguese QA with substantially lower computational cost than large generative LLMs, promoting more sustainable approaches aligned with \textit{Green AI} principles. An exploratory evaluation of Tucano and Sabi\'a on the same extractive QA benchmark shows that while generative models can reach competitive F1 scores with LoRA fine-tuning, they require up to 4.2$\times$ more GPU memory and 3$\times$ more training time than BERTimbau-Base, reinforcing the efficiency advantage of smaller encoder-based architectures for this task.
Authors: Siqi Guo, Ming Lin, Tianbao Yang
Abstract: Developing efficient CUDA kernels is a fundamental yet challenging task in the generative AI industry. Recent researches leverage Large Language Models (LLMs) to automatically convert PyTorch reference implementations to CUDA kernels, significantly reducing the engineering efforts. State-of-the-art LLMs, such as GPT-5.2 and Claude-Sonnet-4.5, still struggle in this specific task. To address this challenge, we propose DRTriton, a scalable learning framework for training LLMs to convert PyTorch codes into highly optimized Triton kernels, which are then compiled to CUDA kernels at runtime. DRTriton consists of three key components: (i) a data synthetic algorithm CSP-DAG that guarantees full coverage and unbiased uniform sampling over the operator space with controlled difficulty; (ii) a curriculum reinforcement learning with decoupled reward efficiently optimizes conversion success rate and inference speed simultaneously; and (iii) a test-time search algorithm that further improves the inference speed of the generated Triton kernels. Notably, despite being trained exclusively on synthetic data, DRTriton generalizes effectively to real-world CUDA kernels that are challenging even for human experts. Experimental results show that DRTriton-7B achieves speedup on 92% of the KernelBench Level 2, compared to 23% for GPT-5.2 and 19% for Claude-Sonnet-4.5.
Authors: Wihan van der Heever, Keane Ong, Ranjan Satapathy, Erik Cambria
Abstract: This paper proposes a refutation-validated framework for aspect-based sentiment analysis in financial markets, addressing the limitations of correlational studies that cannot distinguish genuine associations from spurious ones. Using X data for the energy sector, we test whether aspect-level sentiment signals show robust, refutation-validated relationships with equity returns. Our pipeline combines net-ratio scoring with z-normalization, OLS with Newey West HAC errors, and refutation tests including placebo, random common cause, subset stability, and bootstrap. Across six energy tickers, only a few associations survive all checks, while renewables show aspect and horizon specific responses. While not establishing causality, the framework provides statistically robust, directionally interpretable signals, with limited sample size (six stocks, one quarter) constraining generalizability and framing this work as a methodological proof of concept.
Authors: Kai-Wei Chang, Yi-Cheng Lin, Huang-Cheng Chou, Wenze Ren, Yu-Han Huang, Yun-Shao Tsai, Chien-Cheng Chen, Yu Tsao, Yuan-Fu Liao, Shrikanth Narayanan, James Glass, Hung-yi Lee
Abstract: Speech technologies have advanced rapidly and serve diverse populations worldwide. However, many languages remain underrepresented due to limited resources. In this paper, we introduce \textbf{TaigiSpeech}, a real-world speech intent dataset in Taiwanese Taigi (aka Taiwanese Hokkien/Southern Min), which is a low-resource and primarily spoken language. The dataset is collected from older adults, comprising 21 speakers with a total of 3k utterances. It is designed for practical intent detection scenarios, including healthcare and home assistant applications. To address the scarcity of labeled data, we explore two data mining strategies with two levels of supervision: keyword match data mining with LLM pseudo labeling via an intermediate language and an audio-visual framework that leverages multimodal cues with minimal textual supervision. This design enables scalable dataset construction for low-resource and unwritten spoken languages. TaigiSpeech will be released under the CC BY 4.0 license to facilitate broad adoption and research on low-resource and unwritten languages. The project website and the dataset can be found on https://kwchang.org/taigispeech.
Authors: Ruiqi Xian, Jing Liang, He Yin, Xuewei Qi, Dinesh Manocha
Abstract: We present \emph{GaussianSSC}, a two-stage, grid-native and triplane-guided approach to semantic scene completion (SSC) that injects the benefits of Gaussians without replacing the voxel grid or maintaining a separate Gaussian set. We introduce \emph{Gaussian Anchoring}, a sub-pixel, Gaussian-weighted image aggregation over fused FPN features that tightens voxel--image alignment and improves monocular occupancy estimation. We further convert point-like voxel features into a learned per-voxel Gaussian field and refine triplane features via a triplane-aligned \emph{Gaussian--Triplane Refinement} module that combines \emph{local gathering} (target-centric) and \emph{global aggregation} (source-centric). This directional, anisotropic support captures surface tangency, scale, and occlusion-aware asymmetry while preserving the efficiency of triplane representations. On SemanticKITTI~\cite{behley2019semantickitti}, GaussianSSC improves Stage~1 occupancy by +1.0\% Recall, +2.0\% Precision, and +1.8\% IoU over state-of-the-art baselines, and improves Stage~2 semantic prediction by +1.8\% IoU and +0.8\% mIoU.
Authors: Mohammad Eslami, Dhanvinkumar Ganeshkumar, Saber Kazeminasab, Michael G. Morley, Michael V. Boland, Michael M. Lin, John B. Miller, David S. Friedman, Nazlee Zebardast, Lucia Sobrin, Tobias Elze
Abstract: We present CataractSAM-2, a domain-adapted extension of Meta's Segment Anything Model 2, designed for real-time semantic segmentation of cataract ophthalmic surgery videos with high accuracy. Positioned at the intersection of computer vision and medical robotics, CataractSAM-2 enables precise intraoperative perception crucial for robotic-assisted and computer-guided surgical systems. Furthermore, to alleviate the burden of manual labeling, we introduce an interactive annotation framework that combines sparse prompts with video-based mask propagation. This tool significantly reduces annotation time and facilitates the scalable creation of high-quality ground-truth masks, accelerating dataset development for ocular anterior segment surgeries. We also demonstrate the model's strong zero-shot generalization to glaucoma trabeculectomy procedures, confirming its cross-procedural utility and potential for broader surgical applications. The trained model and annotation toolkit are released as open-source resources, establishing CataractSAM-2 as a foundation for expanding anterior ophthalmic surgical datasets and advancing real-time AI-driven solutions in medical robotics, as well as surgical video understanding.
Authors: Gianluca Fabiani, Michail E. Kavousanakis, Constantinos Siettos, Ioannis G. Kevrekidis
Abstract: We address a numerical framework for the stability and bifurcation analysis of nonlinear partial differential equations (PDEs) in which the solution is sought in the function space spanned by physics-informed random projection neural networks (PI-RPNNs), and discretized via a collocation approach. These are single-hidden-layer networks with randomly sampled and fixed a priori hidden-layer weights; only the linear output layer weights are optimized, reducing training to a single least-squares solve. This linear output structure enables the direct and explicit formulation of the eigenvalue problem governing the linear stability of stationary solutions. This takes a generalized eigenvalue form, which naturally separates the physical domain interior dynamics from the algebraic constraints imposed by boundary conditions, at no additional training cost and without requiring additional PDE solves. However, the random projection collocation matrix is inherently numerically rank-deficient, rendering naive eigenvalue computation unreliable and contaminating the true eigenvalue spectrum with spurious near-zero modes. To overcome this limitation, we introduce a matrix-free shift-invert Krylov-Arnoldi method that operates directly in weight space, avoiding explicit inversion of the numerically rank-deficient collocation matrix and enabling the reliable computation of several leading eigenpairs of the physical Jacobian - the discretized Frechet derivative of the PDE operator with respect to the solution field, whose eigenvalue spectrum determines linear stability. We further prove that the PI-RPNN-based generalized eigenvalue problem is almost surely regular, guaranteeing solvability with standard eigensolvers, and that the singular values of the random projection collocation matrix decay exponentially for analytic activation functions.
Authors: Hyoseok Park, Yeonsang Park
Abstract: Long-context LLM inference is bottlenecked not by compute but by the O(n) memory bandwidth cost of scanning the KV cache at every decode step -- a wall that no amount of arithmetic scaling can break. Recent photonic accelerators have demonstrated impressive throughput for dense attention computation; however, these approaches inherit the same O(n) memory scaling as electronic attention when applied to long contexts. We observe that the real leverage point is the coarse block-selection step: a memory-bound similarity search that determines which KV blocks to fetch. We identify, for the first time, that this task is structurally matched to the photonic broadcast-and-weight paradigm -- the query fans out to all candidates via passive splitting, signatures are quasi-static (matching electro-optic MRR programming), and only rank order matters (relaxing precision to 4-6 bits). Crucially, the photonic advantage grows with context length: as N increases, the electronic scan cost rises linearly while the photonic evaluation remains O(1). We instantiate this insight in PRISM (Photonic Ranking via Inner-product Similarity with Microring weights), a thin-film lithium niobate (TFLN) similarity engine. Hardware-impaired needle-in-a-haystack evaluation on Qwen2.5-7B confirms 100% accuracy from 4K through 64K tokens at k=32, with 16x traffic reduction at 64K context. PRISM achieves a four-order-of-magnitude energy advantage over GPU baselines at practical context lengths (n >= 4K).
Authors: Jing Zhang, Chenping Hou
Abstract: In many learning systems, such as activity recognition systems, as new data collection methods continue to emerge in various dynamic environmental applications, the attributes of instances accumulate incrementally, with data being stored in gradually expanding feature spaces. How to design theoretically guaranteed algorithms to effectively cluster this special type of data stream, commonly referred to as activity recognition, remains unexplored. Compared to traditional scenarios, we will face at least two fundamental questions in this feature incremental scenario. (i) How to design preliminary and effective algorithms to address the feature incremental clustering problem? (ii) How to analyze the generalization bounds for the proposed algorithms and under what conditions do these algorithms provide a strong generalization guarantee? To address these problems, by tailoring the most common clustering algorithm, i.e., $k$-means, as an example, we propose four types of Feature Incremental Clustering (FIC) algorithms corresponding to different situations of data access: Feature Tailoring (FT), Data Reconstruction (DR), Data Adaptation (DA), and Model Reuse (MR), abbreviated as FIC-FT, FIC-DR, FIC-DA, and FIC-MR. Subsequently, we offer a detailed analysis of the generalization error bounds for these four algorithms and highlight the critical factors influencing these bounds, such as the amounts of training data, the complexity of the hypothesis space, the quality of pre-trained models, and the discrepancy of the reconstruction feature distribution. The numerical experiments show the effectiveness of the proposed algorithms, particularly in their application to activity recognition clustering tasks.
Authors: Zijun Qin, Jingxuan Huang, Zesong Fei, Haichuan Ding, Yulin Shao, Xianhao Chen
Abstract: In recent years, numerous data-intensive broadcasting applications have emerged at the wireless edge, calling for a flexible tradeoff between distortion, transmission rate, and processing complexity. While deep learning-based joint source-channel coding (DeepJSCC) has been identified as a potential solution to data-intensive communications, most of these schemes are confined to worst-case solutions, lack adaptive complexity, and are inefficient in broadcast settings. To overcome these limitations, this paper introduces nonlinear transform rateless source-channel coding (NTRSCC), a variable-length JSCC framework for broadcast channels based on rateless codes. In particular, we integrate learned source transformations with physical-layer LT codes, develop unequal protection schemes that exploit decoder side information, and devise approximations to enable end-to-end optimization of rateless parameters. Our framework enables heterogeneous receivers to adaptively adjust their received number of rateless symbols and decoding iterations in belief propagation, thereby achieving a controllable tradeoff between distortion, rate, and decoding complexity. Simulation results demonstrate that the proposed method enhances image broadcast quality under stringent communication and processing budgets over heterogeneous edge devices.
Authors: Amil Khanzada, Takuji Takemoto
Abstract: Most research in urban informatics and tourism focuses on mitigating overtourism in dense global cities. However, for regions experiencing demographic decline and structural stagnation, the primary risk is "under-vibrancy", a condition where low visitor density suppresses economic activity and diminishes satisfaction. This paper introduces the Distributed Human Data Engine (DHDE), a socio-technical framework previously validated in biological crisis management, and adapts it for regional economic flow optimization. Using high-granularity data from Japan's least-visited prefecture (Fukui), we utilize an AI-driven decision support system (DSS) to analyze two datasets: a raw Fukui spending database (90,350 records) and a regional standardized sentiment database (97,719 responses). The system achieves in-sample explanatory power of 81% (R^2 = 0.810) and out-of-sample predictive performance of 68% (R^2 = 0.683). We quantify an annual opportunity gap of 865,917 unrealized visits, equivalent to approximately 11.96 billion yen (USD 76.2 million) in lost revenue. We propose a dual-nudge governance architecture leveraging the DHDE to redistribute cross-prefectural flows and reduce economic leakage.
Authors: Shenghan Zhang, Run Ling, Ke Cao, Ao Ma, Zhanjie Zhang
Abstract: Federated learning (FL) has emerged as a promising paradigm for privacy-preserving multi-camera video understanding. However, applying FL to cross-view scenarios faces three major challenges: (i) heterogeneous viewpoints and backgrounds lead to highly non-IID client distributions and overfitting to view-specific patterns, (ii) local distribution biases cause misaligned representations that hinder consistent cross-view semantics, and (iii) large video architectures incur prohibitive communication overhead. To address these issues, we propose FedCVU, a federated framework with three components: VS-Norm, which preserves normalization parameters to handle view-specific statistics; CV-Align, a lightweight contrastive regularization module to improve cross-view representation alignment; and SLA, a selective layer aggregation strategy that reduces communication without sacrificing accuracy. Extensive experiments on action understanding and person re-identification tasks under a cross-view protocol demonstrate that FedCVU consistently boosts unseen-view accuracy while maintaining strong seen-view performance, outperforming state-of-the-art FL baselines and showing robustness to domain heterogeneity and communication constraints.
Authors: Bowen Chen, Namgi Han, Yusuke Miyao
Abstract: Memorization is a fundamental component of intelligence for both humans and LLMs. However, while LLM performance scales rapidly, our understanding of memorization lags. Due to limited access to the pre-training data of LLMs, most previous studies focus on a single model series, leading to isolated observations among series, making it unclear which findings are general or specific. In this study, we collect multiple model series (Pythia, OpenLLaMa, StarCoder, OLMo1/2/3) and analyze their shared or unique memorization behavior at both the statistical and internal levels, connecting individual observations while showing new findings. At the statistical level, we reveal that the memorization rate scales log-linearly with model size, and memorized sequences can be further compressed. Further analysis demonstrated a shared frequency and domain distribution pattern for memorized sequences. However, different models also show individual features under the above observations. At the internal level, we find that LLMs can remove certain injected perturbations, while memorized sequences are more sensitive. By decoding middle layers and attention head ablation, we revealed the general decoding process and shared important heads for memorization. However, the distribution of those important heads differs between families, showing a unique family-level feature. Through bridging various experiments and revealing new findings, this study paves the way for a universal and fundamental understanding of memorization in LLM.
Authors: Kangbo Zhao, Miaoxin Guan, Xiang Chen, Yukai Shi, Jinshan Pan
Abstract: Image deraining plays a pivotal role in low-level computer vision, serving as a prerequisite for robust outdoor surveillance and autonomous driving systems. While deep learning paradigms have achieved remarkable success in firmly aligned settings, they often suffer from severe performance degradation when generalized to unseen Out-of-Distribution (OOD) scenarios. This failure stems primarily from the significant domain discrepancy between synthetic training datasets and the complex physical dynamics of real-world rain. To address these challenges, this paper proposes a pioneering cross-scenario deraining adaptation framework. Diverging from conventional approaches, our method obviates the requirements for paired rainy observations in the target domain, leveraging exclusively rain-free background images. We design a Superpixel Generation (Sup-Gen) module to extract stable structural priors from the source domain using Simple Linear Iterative Clustering. Subsequently, a Resolution-adaptive Fusion strategy is introduced to align these source structures with target backgrounds through texture similarity, ensuring the synthesis of diverse and realistic pseudo-data. Finally, we implement a pseudo-label re-Synthesize mechanism that employs multi-stage noise generation to simulate realistic rain streaks. This framework functions as a versatile plug-and-play module capable of seamless integration into arbitrary deraining architectures. Extensive experiments on state-of-the-art models demonstrate that our approach yields remarkable PSNR gains of up to 32% to 59% in OOD domains while significantly accelerating training convergence.
Authors: Shailesh Garg, Luis Mandl, Somdatta Goswami, Souvik Chakraborty
Abstract: Energy efficiency remains a critical challenge in deploying physics-informed operator learning models for computational mechanics and scientific computing, particularly in power-constrained settings such as edge and embedded devices, where repeated operator evaluations in dense networks incur substantial computational and energy costs. To address this challenge, we introduce the Separable Physics-informed Neuroscience-inspired Operator Network (SPINONet), a neuroscience-inspired framework that reduces redundant computation across repeated evaluations while remaining compatible with physics-informed training. SPINONet incorporates regression-friendly neuroscience-inspired spiking neurons through an architecture-aware design that enables sparse, event-driven computation, improving energy efficiency while preserving the continuous, coordinate-differentiable pathways required for computing spatio-temporal derivatives. We evaluate SPINONet on a range of partial differential equations representative of computational mechanics problems, with spatial, temporal, and parametric dependencies in both time-dependent and steady-state settings, and demonstrate predictive performance comparable to conventional physics-informed operator learning approaches despite the induced sparse communication. In addition, limited data supervision in a hybrid setup is shown to improve performance in challenging regimes where purely physics-informed training may converge to spurious solutions. Finally, we provide an analytical discussion linking architectural components and design choices of SPINONet to reductions in computational load and energy consumption.
Authors: Shailesh Garg, Souvik Chakraborty
Abstract: Time-dependent reliability analysis of nonlinear dynamical systems under stochastic excitations is a critical yet computationally demanding task. Conventional approaches, such as Monte Carlo simulation, necessitate repeated evaluations of computationally expensive numerical solvers, leading to significant computational bottlenecks. To address this challenge, we propose \textit{CoNBONet}, a neuroscience-inspired surrogate model that enables fast, energy-efficient, and uncertainty-aware reliability analysis, providing a scalable alternative to techniques such as Monte Carlo simulations. CoNBONet, short for \textbf{Co}nformalized \textbf{N}euroscience-inspired \textbf{B}ayesian \textbf{O}perator \textbf{Net}work, leverages the expressive power of deep operator networks while integrating neuroscience-inspired neuron models to achieve fast, low-power inference. Unlike traditional surrogates such as Gaussian processes, polynomial chaos expansions, or support vector regression, that may face scalability challenges for high-dimensional, time-dependent reliability problems, CoNBONet offers \textit{fast and energy-efficient inference} enabled by a neuroscience-inspired network architecture, \textit{calibrated uncertainty quantification with theoretical guarantees} via split conformal prediction, and \textit{strong generalization capability} through an operator-learning paradigm that maps input functions to system response trajectories. Validation of the proposed CoNBONet for various nonlinear dynamical systems demonstrates that CoNBONet preserves predictive fidelity, and achieves reliable coverage of failure probabilities, making it a powerful tool for robust and scalable reliability analysis in engineering design.
Authors: Kazuki Matsumoto, Ren Uchida, Kohei Yatabe
Abstract: The robustness of deep neural networks (DNNs) can be certified through their Lipschitz continuity, which has made the construction of Lipschitz-continuous DNNs an active research field. However, DNNs for audio processing have not been a major focus due to their poor compatibility with existing results. In this paper, we consider the amplitude modifier (AM), a popular architecture for handling audio signals, and propose its Lipschitz-continuous variants, which we refer to as LipsAM. We prove a sufficient condition for an AM to be Lipschitz continuous and propose two architectures as examples of LipsAM. The proposed architectures were applied to a Plug-and-Play algorithm for speech dereverberation, and their improved stability is demonstrated through numerical experiments.
Authors: Shuo Wang, Ziyu Chen, Ming Tang
Abstract: Fine-tuning large language models (LLMs) with backpropagation achieves high performance but incurs substantial memory overhead, limiting scalability on resource-constrained hardware. Zeroth-order (ZO) optimization provides a memory-efficient alternative by relying solely on forward passes, yet it typically suffers from slow or unstable convergence due to high-variance gradient estimates. Sparse ZO updates partially address this issue by perturbing only a subset of parameters, but their effectiveness hinges on selecting informative parameters, which is challenging in ZO optimization because each query yields only scalar feedback. We propose \textbf{Adaptive Curvature-Guided Sparse Zeroth-Order Optimization (CurvZO)}, which tracks curvature signals online from scalar ZO feedback and leverages these signals to construct a parameter-wise sampling distribution for selecting coordinates at each update, reducing the variance of the sparse ZO gradient estimator. Moreover, CurvZO dynamically adapts the perturbation budget to the evolving curvature signal distribution, yielding sparse ZO updates that remain both focused and sufficiently exploratory. Extensive experiments on OPT and Llama across diverse NLP tasks show that CurvZO consistently improves fine-tuning performance and reduces training time over ZO baselines. It improves accuracy by up to 4.4 points and achieves up to a $2\times$ speedup, while preserving memory efficiency.
Authors: Harsh Wadhwa, Rahul Bhowmick, Naipunnya Raj, Rajiv Sangle, Ruchira V. Bhat, Krishnakumar Sabapathy
Abstract: Quantum machine learning models generally lack principled design guidelines, often requiring full resource-intensive training across numerous choices of encodings, quantum circuit designs and initialization strategies to find effective configuration. To address this challenge, we develope the Quantum Bias-Expressivity Toolbox ($\texttt{QBET}$), a framework for evaluating quantum, classical, and hybrid transformer architectures. In this toolbox, we introduce lean metrics for Simplicity Bias ($\texttt{SB}$) and Expressivity ($\texttt{EXP}$), for comparing across various models, and extend the analysis of $\texttt{SB}$ to generative and multiclass-classification tasks. We show that $\texttt{QBET}$ enables efficient pre-screening of promising model variants obviating the need to execute complete training pipelines. In evaluations on transformer-based classification and generative tasks we employ a total of $18$ qubits for embeddings ($6$ qubits each for query, key, and value). We identify scenarios in which quantum self-attention variants surpass their classical counterparts by ranking the respective models according to the $\texttt{SB}$ metric and comparing their relative performance.
Authors: Emma Hannula, Jana de Wiljes, Matthew T. Moores, Heikki Haario, Lassi Roininen
Abstract: Bayesian inference is a powerful tool for parameter estimation and uncertainty quantification in dynamical systems. However, for nonlinear oscillator networks such as Kuramoto models, widely used to study synchronization phenomena in physics, biology, and engineering, inference is often computationally prohibitive due to high-dimensional state spaces and intractable likelihood functions. We present an amortized Bayesian inference approach that learns a neural approximation of the posterior from simulated phase dynamics, enabling fast, scalable inference without repeated sampling or optimization. Applied to synthetic Kuramoto networks, the method shows promising results in approximating posterior distributions and capturing uncertainty, with computational savings compared to traditional Bayesian techniques. These findings suggest that amortized inference is a practical and flexible framework for uncertainty-aware analysis of oscillator networks.
Authors: Gianluca Fontanesi, Luca Barbieri, Lorenzo Galati Giordano, Alfonso Fernandez Duran, Thorsten Wild
Abstract: This manuscript presents a comprehensive analysis of predictive modeling optimization in managed Wi-Fi networks through the integration of clustering algorithms and model evaluation techniques. The study addresses the challenges of deploying forecasting algorithms in large-scale environments managed by a central controller constrained by memory and computational resources. Feature-based clustering, supported by Principal Component Analysis (PCA) and advanced feature engineering, is employed to group time series data based on shared characteristics, enabling the development of cluster-specific predictive models. Comparative evaluations between global models (GMs) and cluster-specific models demonstrate that cluster-specific models consistently achieve superior accuracy in terms of Mean Absolute Error (MAE) values in high-activity clusters. The trade-offs between model complexity (and accuracy) and resource utilization are analyzed, highlighting the scalability of tailored modeling approaches. The findings advocate for adaptive network management strategies that optimize resource allocation through selective model deployment, enhance predictive accuracy, and ensure scalable operations in large-scale, centrally managed Wi-Fi environments.
Authors: Jesper B. Christensen, Ciaran Bench, Spencer A. Thomas, H\"usn\"u Aslan, David Balslev-Harder, Nadia A. S. Smith, Alessandra Manzin
Abstract: We introduce ControlAugment (Ctrl-A), an automated data augmentation algorithm for image-vision tasks, which incorporates principles from control theory for online adjustment of augmentation strength distributions during model training. Ctrl-A eliminates the need for initialization of individual augmentation strengths. Instead, augmentation strength distributions are dynamically, and individually, adapted during training based on a control-loop architecture and what we define as relative operation response curves. Using an operation-dependent update procedure provides Ctrl-A with the potential to suppress augmentation styles that negatively impact model performance, alleviating the need for manually engineering augmentation policies for new image-vision tasks. Experiments on the CIFAR-10, CIFAR-100, and SVHN-core benchmark datasets using the common WideResNet-28-10 architecture demonstrate that Ctrl-A is highly competitive with existing state-of-the-art data augmentation strategies.
Authors: Andrzej Odrzywo{\l}ek
Abstract: A single two-input gate suffices for all of Boolean logic in digital hardware. No comparable primitive has been known for continuous mathematics: computing elementary functions such as sin, cos, sqrt, and log has always required multiple distinct operations. Here I show that a single binary operator, eml(x,y)=exp(x)-ln(y), together with the constant 1, generates the standard repertoire of a scientific calculator. This includes constants such as $e$, $\pi$, and $i$; arithmetic operations including $+$, $-$, $\times$, $/$, and exponentiation as well as the usual transcendental and algebraic functions. For example, $e^x=\operatorname{eml}(x,1)$, $\ln x=\operatorname{eml}(1,\operatorname{eml}(\operatorname{eml}(1,x),1))$, and likewise for all other operations. That such an operator exists was not anticipated; I found it by systematic exhaustive search and established constructively that it suffices for the concrete scientific-calculator basis. In EML (Exp-Minus-Log) form, every such expression becomes a binary tree of identical nodes, yielding a grammar as simple as $S \to 1 \mid \operatorname{eml}(S,S)$. This uniform structure also enables gradient-based symbolic regression: using EML trees as trainable circuits with standard optimizers (Adam), I demonstrate the feasibility of exact recovery of closed-form elementary functions from numerical data at shallow tree depths up to 4. The same architecture can fit arbitrary data, but when the generating law is elementary, it may recover the exact formula.
Authors: Donald Shenaj, Federico Errica, Antonio Carta
Abstract: Low Rank Adaptation (LoRA) is the de facto fine-tuning strategy to generate personalized images from pre-trained diffusion models. Choosing a good rank is extremely critical, since it trades off performance and memory consumption, but today the decision is often left to the community's consensus, regardless of the personalized subject's complexity. The reason is evident: the cost of selecting a good rank for each LoRA component is combinatorial, so we opt for practical shortcuts such as fixing the same rank for all components. In this paper, we take a first step to overcome this challenge. Inspired by variational methods that learn an adaptive width of neural networks, we let the ranks of each layer freely adapt during fine-tuning on a subject. We achieve it by imposing an ordering of importance on the rank's positions, effectively encouraging the creation of higher ranks when strictly needed. Qualitatively and quantitatively, our approach, LoRA$^2$, achieves a competitive trade-off between DINO, CLIP-I, and CLIP-T across 29 subjects while requiring much less memory and lower rank than high rank LoRA versions. Code: https://github.com/donaldssh/NotAllLayersAreCreatedEqual.
URLs: https://github.com/donaldssh/NotAllLayersAreCreatedEqual.
Authors: Suchuan Dong, Yuchuan Zhang
Abstract: We present a systematic method for exactly enforcing Dirichlet, Neumann, and Robin type conditions on general quadrilateral domains with arbitrary curved boundaries. Our method is built upon exact mappings between general quadrilateral domains and the standard domain, and employs a combination of TFC (theory of functional connections) constrained expressions and transfinite interpolations. When Neumann or Robin boundaries are present, especially when two Neumann (or Robin) boundaries meet at a vertex, it is critical to enforce exactly the induced compatibility constraints at the intersection, in order to enforce exactly the imposed conditions on the joining boundaries. We analyze in detail and present constructions for handling the imposed boundary conditions and the induced compatibility constraints for two types of situations: (i) when Neumann (or Robin) boundary only intersects with Dirichlet boundaries, and (ii) when two Neumann (or Robin) boundaries intersect with each other. We describe a four-step procedure to systematically formulate the general form of functions that exactly satisfy the imposed Dirichlet, Neumann, or Robin conditions on general quadrilateral domains. The method developed herein has been implemented together with the extreme learning machine (ELM) technique we have developed recently for scientific machine learning. Ample numerical experiments are presented with several linear/nonlinear stationary/dynamic problems on a variety of two-dimensional domains with complex boundary geometries. Simulation results demonstrate that the proposed method has enforced the Dirichlet, Neumann, and Robin conditions on curved domain boundaries exactly, with the numerical boundary-condition errors at the machine accuracy.
Authors: Chedly Ben Azizi, Claire Guilloteau, Gilles Roussel, Matthieu Puigt
Abstract: Synthetic hyperspectral image (HSI) generation is essential for large-scale simulation, algorithm development, and mission design, yet traditional radiative transfer models remain computationally expensive and often limited to spectrum-level outputs. In this work, we propose a latent representation-based framework for hyperspectral emulation that learns a latent generative representation of hyperspectral data. The proposed approach supports both spectrum-level and spatial-spectral emulation and can be trained either in a direct one-step formulation or in a two-step strategy that couples variational autoencoder (VAE) pretraining with parameter-to-latent interpolation. Experiments on PROSAIL-simulated vegetation data and Sentinel-3 OLCI imagery demonstrate that the method outperforms classical regression-based emulators in reconstruction accuracy, spectral fidelity, and robustness to real-world spatial variability. We further show that emulated HSIs preserve performance in downstream biophysical parameter retrieval, highlighting the practical relevance of emulated data for remote sensing applications.
Authors: L. Riso, M. G. Zoia
Abstract: This paper develops a unified framework for measuring concentration in weighted systems embedded in networks of interactions. While traditional indices such as the Herfindahl-Hirschman Index capture dispersion in weights, they neglect the topology of relationships among the elements receiving those weights. To address this limitation, we introduce a family of topology-aware concentration indices that jointly account for weight distributions and network structure. At the core of the framework lies a baseline Network Concentration Index (NCI), defined as a normalized quadratic form that measures the fraction of potential weighted interconnection realized along observed network links. Building on this foundation, we construct a flexible class of extensions that modify either the interaction structure or the normalization benchmark, including weighted, density-adjusted, null-model, degree-constrained, transformed-data, and multi-layer variants. This family of indices preserves key properties such as normalization, invariance, and interpretability, while allowing concentration to be evaluated across different dimensions of dependence, including intensity, higher-order interactions, and extreme events. Theoretical results characterize the indices and establish their relationship with classical concentration and network measures. Empirical and simulation evidence demonstrate that systems with identical weight distributions may exhibit markedly different levels of structural concentration depending on network topology, highlighting the additional information captured by the proposed framework. The approach is broadly applicable to economic, financial, and complex systems in which weighted elements interact through networks.
Authors: Guannan Lai, Da-Wei Zhou, Zhenguo Li, Han-Jia Ye
Abstract: Continual Test-Time Adaptation (CTTA) aims to enable models to adapt online to unlabeled data streams under distribution shift without accessing source data. Existing CTTA methods face an efficiency-generalization trade-off: updating more parameters improves adaptation but severely reduces online inference efficiency. An ideal solution is to achieve comparable adaptation with minimal feature updates; we call this minimal subspace the golden subspace. We prove its existence in a single-step adaptation setting and show that it coincides with the row space of the pretrained classifier. To enable online maintenance of this subspace, we introduce the sample-wise Average Gradient Outer Product (AGOP) as an efficient proxy for estimating the classifier weights without retraining. Building on these insights, we propose Guided Online Low-rank Directional adaptation (GOLD), which uses a lightweight adapter to project features onto the golden subspace and learns a compact scaling vector while the subspace is dynamically updated via AGOP. Extensive experiments on classification and segmentation benchmarks, including autonomous-driving scenarios, demonstrate that GOLD attains superior efficiency, stability, and overall performance. Our code is available at https://github.com/AIGNLAI/GOLD.
Authors: Peter Fasogbon, Ugurcan Budak, Patrice Rondao Alface, Hamed Rezazadegan Tavakoli
Abstract: The pruning of 3D Gaussian splats is essential for reducing their complexity to enable efficient storage, transmission, and downstream processing. However, most of the existing pruning strategies depend on camera parameters, rendered images, or view-dependent measures. This dependency becomes a hindrance in emerging camera-agnostic exchange settings, where splats are shared directly as point-based representations (e.g., .ply). In this paper, we propose a camera-agnostic, one-shot, post-training pruning method for 3D Gaussian splats that relies solely on attribute-derived neighbourhood descriptors. As our primary contribution, we introduce a hybrid descriptor framework that captures structural and appearance consistency directly from the splat representation. Building on these descriptors, we formulate pruning as a statistical evidence estimation problem and introduce a Beta evidence model that quantifies per-splat reliability through a probabilistic confidence score. Experiments conducted on standardized test sequences defined by the ISO/IEC MPEG Common Test Conditions (CTC) demonstrate that our approach achieves substantial pruning while preserving reconstruction quality, establishing a practical and generalizable alternative to existing camera-dependent pruning strategies.
Authors: Marco Arazzi, Vignesh Kumar Kembu, Antonino Nocera
Abstract: Large language models are becoming pervasive core components in many real-world applications. As a consequence, security alignment represents a critical requirement for their safe deployment. Although previous related works focused primarily on model architectures and alignment methodologies, these approaches alone cannot ensure the complete elimination of harmful generations. This concern is reinforced by the growing body of scientific literature showing that attacks, such as jailbreaking and prompt injection, can bypass existing security alignment mechanisms. As a consequence, additional security strategies are needed both to provide qualitative feedback on the robustness of the obtained security alignment at the training stage, and to create an ``ultimate'' defense layer to block unsafe outputs possibly produced by deployed models. To provide a contribution in this scenario, this paper introduces SecureBreak, a safety-oriented dataset designed to support the development of AI-driven solutions for detecting harmful LLM outputs caused by residual weaknesses in security alignment. The dataset is highly reliable due to careful manual annotation, where labels are assigned conservatively to ensure safety. It performs well in detecting unsafe content across multiple risk categories. Tests with pre-trained LLMs show improved results after fine-tuning on SecureBreak. Overall, the dataset is useful both for post-generation safety filtering and for guiding further model alignment and security improvements.
Authors: Hubert Leterme, Andreas Tersenov, Jalal Fadili, Jean-Luc Starck
Abstract: Upcoming stage-IV surveys such as Euclid and Rubin will deliver vast amounts of high-precision data, opening new opportunities to constrain cosmological models with unprecedented accuracy. A key step in this process is the reconstruction of the dark matter distribution from noisy weak lensing shear measurements. Current deep learning-based mass mapping methods achieve high reconstruction accuracy, but either require retraining a model for each new observed sky region (limiting practicality) or rely on slow MCMC sampling. Efficient exploitation of future survey data therefore calls for a new method that is accurate, flexible, and fast at inference. In addition, uncertainty quantification with coverage guarantees is essential for reliable cosmological parameter estimation. We introduce PnPMass, a plug-and-play approach for weak lensing mass mapping. The algorithm produces point estimates by alternating between a gradient descent step with a carefully chosen data fidelity term, and a denoising step implemented with a single deep learning model trained on simulated data corrupted by Gaussian white noise. We also propose a fast, sampling-free uncertainty quantification scheme based on moment networks, with calibrated error bars obtained through conformal prediction to ensure coverage guarantees. Finally, we benchmark PnPMass against both model-driven and data-driven mass mapping techniques. PnPMass achieves performance close to that of state-of-the-art deep-learning methods while offering fast inference (converging in just a few iterations) and requiring only a single training phase, independently of the noise covariance of the observations. It therefore combines flexibility, efficiency, and reconstruction accuracy, while delivering tighter error bars than existing approaches, making it well suited for upcoming weak lensing surveys.
Authors: Dong Heon Cho, Boyuan Chen
Abstract: Differentiable simulators enable gradient-based optimization of soft robots over material parameters, control, and morphology, but accurately modeling real systems remains challenging due to the sim-to-real gap. This issue becomes more pronounced when geometry is itself a design variable. System identification reduces discrepancies by fitting global material parameters to data; however, when constitutive models are misspecified or observations are sparse, identified parameters often absorb geometry-dependent effects rather than reflect intrinsic material behavior. More expressive constitutive models can improve accuracy but substantially increase computational cost, limiting practicality. We propose a residual acceleration field learning (RAFL) framework that augments a base simulator with a transferable, element-level corrective dynamics field. Operating on shared local features, the model is agnostic to global mesh topology and discretization. Trained end-to-end through a differentiable simulator using sparse marker observations, the learned residual generalizes across shapes. In both sim-to-sim and sim-to-real experiments, our method achieves consistent zero-shot improvements on unseen morphologies, while system identification frequently exhibits negative transfer. The framework also supports continual refinement, enabling simulation accuracy to accumulate during morphology optimization.
Authors: Atticus Rex, Elizabeth Qian, David Peterson
Abstract: Supervised machine learning describes the practice of fitting a parameterized model to labeled input-output data. Supervised machine learning methods have demonstrated promise in learning efficient surrogate models that can (partially) replace expensive high-fidelity models, making many-query analyses, such as optimization, uncertainty quantification, and inference, tractable. However, when training data must be obtained through the evaluation of an expensive model or experiment, the amount of training data that can be obtained is often limited, which can make learned surrogate models unreliable. However, in many engineering and scientific settings, cheaper \emph{low-fidelity} models may be available, for example arising from simplified physics modeling or coarse grids. These models may be used to generate additional low-fidelity training data. The goal of \emph{multifidelity} machine learning is to use both high- and low-fidelity training data to learn a surrogate model which is cheaper to evaluate than the high-fidelity model, but more accurate than any available low-fidelity model. This work proposes a new multifidelity training approach for Gaussian process regression which uses low-fidelity data to define additional features that augment the input space of the learned model. The approach unites desirable properties from two separate classes of existing multifidelity GPR approaches, cokriging and autoregressive estimators. Numerical experiments on several test problems demonstrate both increased predictive accuracy and reduced computational cost relative to the state of the art.
Authors: Risa Shinoda, Kaede Shiohara, Nakamasa Inoue, Hiroaki Santo, Fumio Okura
Abstract: Animal vocalizations provide crucial insights for wildlife assessment, particularly in complex environments such as forests, aiding species identification and ecological monitoring. Recent advances in deep learning have enabled automatic species classification from their vocalizations. However, classifying species unseen during training remains challenging. To address this limitation, we introduce AnimalCLAP, a taxonomy-aware language-audio framework comprising a new dataset and model that incorporate hierarchical biological information. Specifically, our vocalization dataset consists of 4,225 hours of recordings covering 6,823 species, annotated with 22 ecological traits. The AnimalCLAP model is trained on this dataset to align audio and textual representations using taxonomic structures, improving the recognition of unseen species. We demonstrate that our proposed model effectively infers ecological and biological attributes of species directly from their vocalizations, achieving superior performance compared to CLAP. Our dataset, code, and models will be publicly available at https://dahlian00.github.io/AnimalCLAP_Page/.
Authors: Syed Usama Imtiaz, Mitra Nasr Azadani, Nasrin Alamdari
Abstract: Foundation models are now increasingly being developed for Earth observation (EO), yet they often rely on stochastic masking that do not explicitly enforce physics constraints; a critical trustworthiness limitation, in particular for predictive models that guide public health decisions. In this work, we propose SpecTM (Spectral Targeted Masking), a physics-informed masking design that encourages the reconstruction of targeted bands from cross-spectral context during pretraining. To achieve this, we developed an adaptable multi-task (band reconstruction, bio-optical index inference, and 8-day-ahead temporal prediction) self-supervised learning (SSL) framework that encodes spectrally intrinsic representations via joint optimization, and evaluated it on a downstream microcystin concentration regression model using NASA PACE hyperspectral imagery over Lake Erie. SpecTM achieves R^2 = 0.695 (current week) and R^2 = 0.620 (8-day-ahead) predictions surpassing all baseline models by (+34% (0.51 Ridge) and +99% (SVR 0.31)) respectively. Our ablation experiments show targeted masking improves predictions by +0.037 R^2 over random masking. Furthermore, it outperforms strong baselines with 2.2x superior label efficiency under extreme scarcity. SpecTM enables physics-informed representation learning across EO domains and improves the interpretability of foundation models.
Authors: Joanna Zou, Youssef Marzouk
Abstract: The development of machine learning interatomic potentials faces a critical computational bottleneck with the generation and labeling of useful training datasets. We present a novel application of determinantal point processes (DPPs) to the task of selecting informative subsets of atomic configurations to label with reference energies and forces from costly quantum mechanical methods. Through experiments with hafnium oxide data, we show that DPPs are competitive with existing approaches to constructing compact but diverse training sets by utilizing kernels of molecular descriptors, leading to improved accuracy and robustness in machine learning representations of molecular systems. Our work identifies promising directions to employ DPPs for unsupervised training data curation with heterogeneous or multimodal data, or in online active learning schemes for iterative data augmentation during molecular dynamics simulation.
Authors: A. Chervov, F. Levkovich-Maslyuk, A. Smolensky, F. Khafizov, I. Kiselev, D. Melnikov, I. Koltsov, S. Kudashev, D. Shiltsov, M. Obozov, S. Krymskii, V. Kirova, E. V. Konstantinova, A. Soibelman, S. Galkin, L. Grunwald, A. Kotov, A. Alexandrov, S. Lytkin, D. Fedoriaka, A. Chevychelov, Z. Kogan, A. Natyrova, L. Cheldieva, O. Nikitina, S. Fironov, A. Vakhrushev, A. Lukyanenko, V. Ilin, D. Gorodkov, N. Bogachev, I. Gaiur, M. Zaitsev, F. Petrov, L. Petrov, T. Gaintseva, A. Gavrilova, M. N. Smirnov, N. Kalinin, A. Khan, K. Jung, H. Mousset, H. Isambert, O. Debeaupuis
Abstract: This is the fourth paper in the CayleyPy project, which applies AI methods to the exploration of large graphs. In this work, we suggest the existence of a new discrete version of holographic string dualities for this setup, and discuss their relevance to AI systems and mathematics. Many modern AI tasks -- such as those addressed by GPT-style language models or RL systems -- can be viewed as direct analogues of predicting particle trajectories on graphs. We investigate this problem for a large family of Cayley graphs, for which we show that surprisingly it admits a dual description in terms of discrete strings. We hypothesize that such dualities may extend to a range of AI systems where they can lead to more efficient computational approaches. In particular, string holographic images of states are proposed as natural candidates for data embeddings, motivated by the "complexity = volume" principle in AdS/CFT. For Cayley graphs of the symmetric group S_n, our results indicate that the corresponding dual objects are flat, planar polygons. The diameter of the graph is equal to the number of integer points inside the polygon scaled by n. Vertices of the graph can be mapped holographically to paths inside the polygon, and the usual graph distances correspond to the area under the paths, thus directly realising the "complexity = volume" paradigm. We also find evidence for continuous CFTs and dual strings in the large n limit. We confirm this picture and other aspects of the duality in a large initial set of examples. We also present new datasets (obtained by a combination of ML and conventional tools) which should be instrumental in establishing the duality for more general cases.
Authors: Tom Biskupski, Stephan Kleber
Abstract: A Large Language Model (LLM) as judge evaluates the quality of victim Machine Learning (ML) models, specifically LLMs, by analyzing their outputs. An LLM as judge is the combination of one model and one specifically engineered judge prompt that contains the criteria for the analysis. The resulting automation of the analysis scales up the complex evaluation of the victim models' free-form text outputs by faster and more consistent judgments compared to human reviewers. Thus, quality and security assessments of LLMs can cover a wide range of the victim models' use cases. Being a comparably new technique, LLMs as judges lack a thorough investigation for their reliability and agreement to human judgment. Our work evaluates the applicability of LLMs as automated quality assessors of victim LLMs. We test the efficacy of 37 differently sized conversational LLMs in combination with 5 different judge prompts, the concept of a second-level judge, and 5 models fine-tuned for the task as assessors. As assessment objective, we curate datasets for eight different categories of judgment tasks and the corresponding ground-truth labels based on human assessments. Our empirical results show a high correlation of LLMs as judges with human assessments, when combined with a suitable prompt, in particular for GPT-4o, several open-source models with $\geqslant$ 32B parameters, and a few smaller models like Qwen2.5 14B.
Authors: Chi Zhang, Xixi Hu, Bo Liu, Qiang Liu
Abstract: The slow, sequential nature of autoregressive (AR) language models has driven the adoption of parallel decoding methods. However, these non-AR models often sacrifice generation quality as they struggle to model the complex joint distribution of token sequences. To narrow this performance gap, we introduce Gumbel Distillation, a novel distillation technique that enables parallel decoders to learn this distribution effectively. Our method leverages the Gumbel-Max trick to create a deterministic mapping from a latent Gumbel noise space to the output tokens of a high-performing AR teacher. As a model-agnostic technique, Gumbel Distillation seamlessly integrates with diverse parallel decoding architectures, including MDLM and BD3-LM. Experiments on LM1B and OpenWebText show that Gumbel Distillation substantially improves the generation quality of parallel language models, achieving a 30.0% improvement in MAUVE score and 10.5% in generative perplexity over MDLM trained on OpenWebText dataset. Code available at https://github.com/hxixixh/gumbel-distill.
Authors: Yanchen Jiang, Zhe Feng, Christopher P. Mah, Aranyak Mehta, Di Wang
Abstract: Generative Recommender Systems using semantic ids, such as TIGER (Rajput et al., 2023), have emerged as a widely adopted competitive paradigm in sequential recommendation. However, existing architectures are designed solely for semantic retrieval and do not address concerns such as monetization via ad revenue and incorporation of bids for commercial retrieval. We propose GEM-Rec, a unified framework that integrates commercial relevance and monetization objectives directly into the generative sequence. We introduce control tokens to decouple the decision of whether to show an ad from which item to show. This allows the model to learn valid placement patterns directly from interaction logs, which inherently reflect past successful ad placements. Complementing this, we devise a Bid-Aware Decoding mechanism that handles real-time pricing, injecting bids directly into the inference process to steer the generation toward high-value items. We prove that this approach guarantees allocation monotonicity, ensuring that higher bids weakly increase an ad's likelihood of being shown without requiring model retraining. Experiments demonstrate that GEM-Rec allows platforms to dynamically optimize for semantic relevance and platform revenue.
Authors: Luke Watkin, Daniel Archambault, Alex Telea
Abstract: Decision Boundary Maps (DBMs) are an effective tool for visualising machine learning classification boundaries. Yet, DBM quality strongly depends on the dimensionality reduction (DR) technique and high dimensional space used for the data points. For complex ML datasets, DR can create many mixed classes which, in turn, yield DBMs that are hard to use. We propose a new technique to compute DBMs by transforming data space into Shapley space and computing DR on it. Compared to standard DBMs computed directly from data, our maps have similar or higher quality metric values and visibly more compact, easier to explore, decision zones.
Authors: Claudia Islas-Vargas, L. Ricardo Montoya, Carlos A. Vital-Jos\'e, Oliver T. Unke, Klaus-Robert M\"uller, Huziel E. Sauceda
Abstract: Sodium-ion batteries require anodes that combine high capacity, low operating voltage, fast Na-ion transport, and mechanical stability, which conventional anodes struggle to deliver. Here, we use the SpookyNet machine-learning force field (MLFF) together with all-electron density-functional theory calculations to characterize Na storage in aminobenzene-functionalized Janus graphene (Na$_x$AB) at room-temperature. Simulations across state of charge reveal a three-stage storage mechanism-site-specific adsorption at aminobenzene groups and Na$_n$@AB$_m$ structure formation, followed by interlayer gallery filling-contrasting the multi-stage pore-, graphite-interlayer-, and defect-controlled behavior in hard carbon. This leads to an OCV profile with an extended low-voltage plateau of 0.15 V vs. Na/Na$^{+}$, an estimated gravimetric capacity of $\sim$400 mAh g$^{-1}$, negligible volume change, and Na diffusivities of $\sim10^{-6}$ cm$^{2}$ s$^{-1}$, two to three orders of magnitude higher than in hard carbon. Our results establish Janus aminobenzene-graphene as a promising, structurally defined high-capacity Na-ion anode and illustrate the power of MLFF-based simulations for characterizing electrode materials.
Authors: Kelly Cui, Nikhil Prakash, Ayush Raina, David Bau, Antonio Torralba, Tamar Rott Shaham
Abstract: Many multimodal tasks, such as image captioning and visual question answering, require vision-language models (VLMs) to associate objects with their properties and spatial relations. Yet it remains unclear where and how such associations are computed within VLMs. In this work, we show that VLMs rely on two concurrent mechanisms to represent such associations. In the language model backbone, intermediate layers represent content-independent spatial relations on top of visual tokens corresponding to objects. However, this mechanism plays only a secondary role in shaping model predictions. Instead, the dominant source of spatial information originates in the vision encoder, whose representations encode the layout of objects and are directly exploited by the language model backbone. Notably, this spatial signal is distributed globally across visual tokens, extending beyond object regions into surrounding background areas. We show that enhancing these vision-derived spatial representations globally across all image tokens improves spatial reasoning performance on naturalistic images. Together, our results clarify how spatial association is computed within VLMs and highlight the central role of vision encoders in enabling spatial reasoning.
Authors: Haichao Zhang, Yijiang Li, Shwai He, Tushar Nagarajan, Mingfei Chen, Jianglin Lu, Ang Li, Yun Fu
Abstract: Recent progress in latent world models (e.g., V-JEPA2) has shown promising capability in forecasting future world states from video observations. Nevertheless, dense prediction from a short observation window limits temporal context and can bias predictors toward local, low-level extrapolation, making it difficult to capture long-horizon semantics and reducing downstream utility. Vision--language models (VLMs), in contrast, provide strong semantic grounding and general knowledge by reasoning over uniformly sampled frames, but they are not ideal as standalone dense predictors due to compute-driven sparse sampling, a language-output bottleneck that compresses fine-grained interaction states into text-oriented representations, and a data-regime mismatch when adapting to small action-conditioned datasets. We propose a VLM-guided JEPA-style latent world modeling framework that combines dense-frame dynamics modeling with long-horizon semantic guidance via a dual-temporal pathway: a dense JEPA branch for fine-grained motion and interaction cues, and a uniformly sampled VLM \emph{thinker} branch with a larger temporal stride for knowledge-rich guidance. To transfer the VLM's progressive reasoning signals effectively, we introduce a hierarchical pyramid representation extraction module that aggregates multi-layer VLM representations into guidance features compatible with latent prediction. Experiments on hand-manipulation trajectory prediction show that our method outperforms both a strong VLM-only baseline and a JEPA-predictor baseline, and yields more robust long-horizon rollout behavior.
Authors: Shivam Duggal, Xingjian Bai, Zongze Wu, Richard Zhang, Eli Shechtman, Antonio Torralba, Phillip Isola, William T. Freeman
Abstract: Latent diffusion models (LDMs) enable high-fidelity synthesis by operating in learned latent spaces. However, training state-of-the-art LDMs requires complex staging: a tokenizer must be trained first, before the diffusion model can be trained in the frozen latent space. We propose UNITE - an autoencoder architecture for unified tokenization and latent diffusion. UNITE consists of a Generative Encoder that serves as both image tokenizer and latent generator via weight sharing. Our key insight is that tokenization and generation can be viewed as the same latent inference problem under different conditioning regimes: tokenization infers latents from fully observed images, whereas generation infers them from noise together with text or class conditioning. Motivated by this, we introduce a single-stage training procedure that jointly optimizes both tasks via two forward passes through the same Generative Encoder. The shared parameters enable gradients to jointly shape the latent space, encouraging a "common latent language". Across image and molecule modalities, UNITE achieves near state of the art performance without adversarial losses or pretrained encoders (e.g., DINO), reaching FID 2.12 and 1.73 for Base and Large models on ImageNet 256 x 256. We further analyze the Generative Encoder through the lenses of representation alignment and compression. These results show that single stage joint training of tokenization & generation from scratch is feasible.
Authors: Umair Nawaz, Ahmed Heakl, Ufaq Khan, Abdelrahman Shaker, Salman Khan, Fahad Shahbaz Khan
Abstract: Diffusion Transformers (DiTs) power high-fidelity video world models but remain computationally expensive due to sequential denoising and costly spatio-temporal attention. Training-free feature caching accelerates inference by reusing intermediate activations across denoising steps; however, existing methods largely rely on a Zero-Order Hold assumption i.e., reusing cached features as static snapshots when global drift is small. This often leads to ghosting artifacts, blur, and motion inconsistencies in dynamic scenes. We propose \textbf{WorldCache}, a Perception-Constrained Dynamical Caching framework that improves both when and how to reuse features. WorldCache introduces motion-adaptive thresholds, saliency-weighted drift estimation, optimal approximation via blending and warping, and phase-aware threshold scheduling across diffusion steps. Our cohesive approach enables adaptive, motion-consistent feature reuse without retraining. On Cosmos-Predict2.5-2B evaluated on PAI-Bench, WorldCache achieves \textbf{2.3$\times$} inference speedup while preserving \textbf{99.4\%} of baseline quality, substantially outperforming prior training-free caching approaches. Our code can be accessed on \href{https://umair1221.github.io/World-Cache/}{World-Cache}.
Authors: Di Chen, Jeff M. Phillips
Abstract: A reproducing kernel can define an embedding of a data point into an infinite dimensional reproducing kernel Hilbert space (RKHS). The norm in this space describes a distance, which we call the kernel distance. The random Fourier features (of Rahimi and Recht) describe an oblivious approximate mapping into finite dimensional Euclidean space that behaves similar to the RKHS. We show in this paper that for the Gaussian kernel the Euclidean norm between these mapped to features has $(1+\varepsilon)$-relative error with respect to the kernel distance. When there are $n$ data points, we show that $O((1/\varepsilon^2) \log(n))$ dimensions of the approximate feature space are sufficient and necessary. Without a bound on $n$, but when the original points lie in $\mathbb{R}^d$ and have diameter bounded by $\mathcal{M}$, then we show that $O((d/\varepsilon^2) \log(\mathcal{M}))$ dimensions are sufficient, and that this many are required, up to $\log(1/\varepsilon)$ factors.
Authors: Caleb Ju, Guanghui Lan
Abstract: Reinforcement learning (RL) problems over general state and action spaces are notoriously challenging. In contrast to the tableau setting, one can not enumerate all the states and then iteratively update the policies for each state. This prevents the application of many well-studied RL methods especially those with provable convergence guarantees. In this paper, we first present a substantial generalization of the recently developed policy mirror descent method to deal with general state and action spaces. We introduce new approaches to incorporate function approximation into this method, so that we do not need to use explicit policy parameterization at all. Moreover, we present a novel policy dual averaging method for which possibly simpler function approximation techniques can be applied. We establish linear convergence rate to global optimality or sublinear convergence to stationarity for these methods applied to solve different classes of RL problems under exact policy evaluation. We then define proper notions of the approximation errors for policy evaluation and investigate their impact on the convergence of these methods applied to general-state RL problems with either finite-action or continuous-action spaces. To the best of our knowledge, the development of these algorithmic frameworks as well as their convergence analysis appear to be new in the literature. Preliminary numerical results demonstrate the robustness of the aforementioned methods and show they can be competitive with state-of-the-art RL algorithms.
Authors: Daiqing Qi, Handong Zhao, Sheng Li
Abstract: Federated learning is a technique that enables a centralized server to learn from distributed clients via communications without accessing the client local data. However, existing federated learning works mainly focus on a single task scenario with static data. In this paper, we introduce the problem of continual federated learning, where clients incrementally learn new tasks and history data cannot be stored due to certain reasons, such as limited storage and data retention policy. Generative replay based methods are effective for continual learning without storing history data, but adapting them for this setting is challenging. By analyzing the behaviors of clients during training, we find that the unstable training process caused by distributed training on non-IID data leads to a notable performance degradation. To address this problem, we propose our FedCIL model with two simple but effective solutions: model consolidation and consistency enforcement. Our experimental results on multiple benchmark datasets demonstrate that our method significantly outperforms baselines.
Authors: Liang Yan, Shengzhong Zhang, Bisheng Li, Menglin Yang, Chen Yang, Min Zhou, Weiyang Ding, Yutong Xie, Zengfeng Huang
Abstract: Class imbalance in graph data presents a significant challenge for effective node classification, particularly in semi-supervised scenarios. In this work, we formally introduce the concept of geometric imbalance, which captures how message passing on class-imbalanced graphs leads to geometric ambiguity among minority-class nodes in the riemannian manifold embedding space. We provide a rigorous theoretical analysis of geometric imbalance on the riemannian manifold and propose a unified framework that explicitly mitigates it through pseudo-label alignment, node reordering, and ambiguity filtering. Extensive experiments on diverse benchmarks show that our approach consistently outperforms existing methods, especially under severe class imbalance. Our findings offer new theoretical insights and practical tools for robust semi-supervised node classification.
Authors: Rickard Br\"annvall, Tony Zhang, Henrik Forsgren, Andrei Stoian, Fredrik Sandin, Marcus Liwicki
Abstract: This paper introduces efficient modifications to neural network-based sequence processing approaches, laying new grounds for scalable privacy-preserving machine learning under Fully Homomorphic Encryption (FHE). Transformers are now ubiquitous in AI applications and have largely supplanted Gated Recurrent Neural Networks (RNNs) as the standard architecture for sequence modeling. Both architectures rely on costly multiplications and complex activations that hinder encrypted inference. We focus on TFHE, which supports deep circuit evaluation and efficient univariate function evaluation but makes variable-to-variable multiplication particularly expensive. To address this, we propose inhibitor designs for Transformers and gated RNNs that replace multiplications and Softmax/Sigmoid activations with additive and ReLU-based operations. These changes enable integer-only computation, reduce circuit depth, and improve the efficiency of encrypted execution while preserving learning capacity. We present complexity analyses and scaling experiments that indicate significant reductions in circuit depth and execution time under TFHE, with 3-6 times speedup for encrypted inference and 30-50% reductions in plaintext inference time. Empirical evaluations on MNIST, IMDB, and IAM handwriting show inhibitor-based models maintain competitive accuracy. Knowledge distillation further demonstrates that an inhibitor-based DistilBERT achieves performance close to that of the conventional attention model on GLUE, positioning these architectures as a viable approach for scalable, privacy-preserving AI.
Authors: Junwen Yang, Tianyuan Jin, Vincent Y. F. Tan
Abstract: We introduce a novel extension of the canonical multi-armed bandit problem that incorporates an additional strategic innovation: abstention. In this enhanced framework, the agent is not only tasked with selecting an arm at each time step, but also has the option to abstain from accepting the stochastic instantaneous reward before observing it. When opting for abstention, the agent either suffers a fixed regret or gains a guaranteed reward. This added layer of complexity naturally prompts the key question: can we develop algorithms that are both computationally efficient and asymptotically and minimax optimal in this setting? We answer this question in the affirmative by designing and analyzing algorithms whose regrets meet their corresponding information-theoretic lower bounds. Our results offer valuable quantitative insights into the benefits of the abstention option, laying the groundwork for further exploration in other online decision-making problems with such an option. Extensive numerical experiments validate our theoretical results, demonstrating that our approach not only advances theory but also has the potential to deliver significant practical benefits.
Authors: Steve Hanneke, Shay Moran, Tom Waknine
Abstract: List learning is a variant of supervised classification where the learner outputs multiple plausible labels for each instance rather than just one. We investigate classical principles related to generalization within the context of list learning. Our primary goal is to determine whether classical principles in the PAC setting retain their applicability in the domain of list PAC learning. We focus on uniform convergence (which is the basis of Empirical Risk Minimization) and on sample compression (which is a powerful manifestation of Occam's Razor). In classical PAC learning, both uniform convergence and sample compression satisfy a form of `completeness': whenever a class is learnable, it can also be learned by a learning rule that adheres to these principles. We ask whether the same completeness holds true in the list learning setting. We show that uniform convergence remains equivalent to learnability in the list PAC learning setting. In contrast, our findings reveal surprising results regarding sample compression: we prove that when the label space is $Y=\{0,1,2\}$, then there are 2-list-learnable classes that cannot be compressed. This refutes the list version of the sample compression conjecture by Littlestone and Warmuth (1986). We prove an even stronger impossibility result, showing that there are $2$-list-learnable classes that cannot be compressed even when the reconstructed function can work with lists of arbitrarily large size. We prove a similar result for (1-list) PAC learnable classes when the label space is unbounded. This generalizes a recent result by arXiv:2308.06424.
Authors: Ziao Yang, Han Yue, Jian Chen, Hongfu Liu
Abstract: Influence functions serve as crucial tools for assessing sample influence in model interpretation, subset training set selection, noisy label detection, and more. By employing the first-order Taylor extension, influence functions can estimate sample influence without the need for expensive model retraining. However, applying influence functions directly to deep models presents challenges, primarily due to the non-convex nature of the loss function and the large size of model parameters. This difficulty not only makes computing the inverse of the Hessian matrix costly but also renders it non-existent in some cases. Various approaches, including matrix decomposition, have been explored to expedite and approximate the inversion of the Hessian matrix, with the aim of making influence functions applicable to deep models. In this paper, we revisit a specific, albeit naive, yet effective approximation method known as TracIn. This method substitutes the inverse of the Hessian matrix with an identity matrix. We provide deeper insights into why this simple approximation method performs well. Furthermore, we extend its applications beyond measuring model utility to include considerations of fairness and robustness. Finally, we enhance TracIn through an ensemble strategy. To validate its effectiveness, we conduct experiments on synthetic data and extensive evaluations on noisy label detection, sample selection for large language model fine-tuning, and defense against adversarial attacks.
Authors: Jingyang Ou, Shen Nie, Kaiwen Xue, Fengqi Zhu, Jiacheng Sun, Zhenguo Li, Chongxuan Li
Abstract: Discrete diffusion models with absorbing processes have shown promise in language modeling. The key quantities to be estimated are the ratios between the marginal probabilities of two transitive states at all timesteps, called the concrete score. In this paper, we reveal that the concrete score in absorbing diffusion can be expressed as conditional probabilities of clean data, multiplied by a time-dependent scalar in an analytic form. Motivated by this finding, we propose reparameterized absorbing discrete diffusion (RADD), a dedicated diffusion model without time-condition that characterizes the time-independent conditional probabilities. Besides its simplicity, RADD can reduce the number of function evaluations (NFEs) by caching the output of the time-independent network when the noisy sample remains unchanged in a sampling interval, which enables sampling acceleration. Built upon the new perspective of conditional distributions, we further unify absorbing discrete diffusion and any-order autoregressive models (AO-ARMs), showing that the upper bound on the negative log-likelihood for the diffusion model can be interpreted as an expected negative log-likelihood for AO-ARMs. Further, our RADD models achieve SOTA performance among diffusion models on 5 zero-shot language modeling benchmarks (measured by perplexity) at the GPT-2 scale. Our code is available at https://github.com/ML-GSAI/RADD.
Authors: Kevin Qiu, W{\l}adys{\l}aw Pa{\l}ucki, Krzysztof Ciebiera, Pawe{\l} Fija{\l}kowski, Marek Cygan, {\L}ukasz Kuci\'nski
Abstract: We introduce RoboMorph, an automated approach for generating and optimizing modular robot designs using large language models (LLMs) and evolutionary algorithms. Each robot design is represented by a structured grammar, and we use LLMs to efficiently explore this design space. Traditionally, such exploration is time-consuming and computationally intensive. Using a best-shot prompting strategy combined with reinforcement learning (RL)-based control evaluation, RoboMorph iteratively refines robot designs within an evolutionary feedback loop. Across four terrain types, RoboMorph discovers diverse, terrain-specialized morphologies, including wheeled quadrupeds and hexapods, that match or outperform designs produced by Robogrammar's graph-search method. These results demonstrate that LLMs, when coupled with evolutionary selection, can serve as effective generative operators for automated robot design. Our project page and code are available at https://robomorph.github.io.
Authors: Steven Adams, Andrea Patan\`e, Morteza Lahijanian, Luca Laurenti
Abstract: Infinitely wide or deep neural networks (NNs) with independent and identically distributed (i.i.d.) parameters have been shown to be equivalent to Gaussian processes. Because of the favorable properties of Gaussian processes, this equivalence is commonly employed to analyze neural networks and has led to various breakthroughs over the years. However, neural networks and Gaussian processes are equivalent only in the limit; in the finite case there are currently no methods available to approximate a trained neural network with a Gaussian model with bounds on the approximation error. In this work, we present an algorithmic framework to approximate a neural network of finite width and depth, and with not necessarily i.i.d. parameters, with a mixture of Gaussian processes with error bounds on the approximation error. In particular, we consider the Wasserstein distance to quantify the closeness between probabilistic models and, by relying on tools from optimal transport and Gaussian processes, we iteratively approximate the output distribution of each layer of the neural network as a mixture of Gaussian processes. Crucially, for any NN and $\epsilon >0$ our approach is able to return a mixture of Gaussian processes that is $\epsilon$-close to the NN at a finite set of input points. Furthermore, we rely on the differentiability of the resulting error bound to show how our approach can be employed to tune the parameters of a NN to mimic the functional behavior of a given Gaussian process, e.g., for prior selection in the context of Bayesian inference. We empirically investigate the effectiveness of our results on both regression and classification problems with various neural network architectures. Our experiments highlight how our results can represent an important step towards understanding neural network predictions and formally quantifying their uncertainty.
Authors: Caleb Ju, Guanghui Lan
Abstract: This paper proposes a novel termination criterion, termed the advantage gap function, for finite state and action Markov decision processes (MDP) and reinforcement learning (RL). By incorporating this advantage gap function into the design of step size rules and deriving a new linear rate of convergence that is independent of the stationary state distribution of the optimal policy, we demonstrate that policy gradient methods can solve MDPs in strongly-polynomial time. To the best of our knowledge, this is the first time that such strong convergence properties have been established for policy gradient methods. Moreover, in the stochastic setting, where only stochastic estimates of policy gradients are available, we show that the advantage gap function provides close approximations of the optimality gap for each individual state and exhibits a sublinear rate of convergence at every state. The advantage gap function can be easily estimated in the stochastic case, and when coupled with easily computable upper bounds on policy values, they provide a convenient way to validate the solutions generated by policy gradient methods. Therefore, our developments offer a principled and computable measure of optimality for RL, whereas current practice tends to rely on algorithm-to-algorithm or baselines comparisons with no certificate of optimality.
Authors: Weijia Zhang, Jindong Han, Hao Liu, Wei Fan, Hao Wang, Hui Xiong
Abstract: Real estate appraisal is important for a variety of endeavors such as real estate deals, investment analysis, and real property taxation. Recently, deep learning has shown great promise for real estate appraisal by harnessing substantial online transaction data from web platforms. Nonetheless, deep learning is data-hungry, and thus it may not be trivially applicable to enormous small cities with limited data. To this end, we propose Meta-Transfer Learning Powered Temporal Graph Networks (MetaTransfer) to transfer valuable knowledge from multiple data-rich metropolises to the data-scarce city to improve valuation performance. Specifically, by modeling the ever-growing real estate transactions with associated residential communities as a temporal event heterogeneous graph, we first design an Event-Triggered Temporal Graph Network to model the irregular spatiotemporal correlations between evolving real estate transactions. Besides, we formulate the city-wide real estate appraisal as a multi-task dynamic graph link label prediction problem, where the valuation of each community in a city is regarded as an individual task. A Hypernetwork-Based Multi-Task Learning module is proposed to simultaneously facilitate intra-city knowledge sharing between multiple communities and task-specific parameters generation to accommodate the community-wise real estate price distribution. Furthermore, we propose a Tri-Level Optimization Based Meta- Learning framework to adaptively re-weight training transaction instances from multiple source cities to mitigate negative transfer, and thus improve the cross-city knowledge transfer effectiveness. Finally, extensive experiments based on five real-world datasets demonstrate the significant superiority of MetaTransfer compared with eleven baseline algorithms.
Authors: Dibakar Roy Sarkar, Vijay Kag, Birupaksha Pal, Somdatta Goswami
Abstract: Discovering hidden physical laws and identifying governing system parameters from sparse observations are central challenges in computational science and engineering. Existing data-driven methods, such as physics-informed neural networks (PINNs) and sparse regression, are limited by their need for extensive retraining, sensitivity to noise, or inability to generalize across families of partial differential equations (PDEs). In this work, we introduce two complementary frameworks based on deep operator networks (DeepONet) to address these limitations. The first, termed the Deep Hidden Physics Operator (DHPO), extends hidden-physics modeling into the operator-learning paradigm, enabling the discovery of unknown PDE terms across diverse equation families by identifying the mapping of unknown physical operators. The second is a parameter identification framework that combines pretrained DeepONet with physics-informed inverse modeling to infer system parameters directly from sparse sensor data. We demonstrate the effectiveness of these approaches on benchmark problems, including the Reaction-Diffusion system, Burgers' equation, the 2D Heat equation, and 2D Helmholtz equation. Across all cases, the proposed methods achieve high accuracy, with relative solution errors on the order of O(10^-2) and parameter estimation errors on the order of O(10^-3), even under limited and noisy observations. By uniting operator learning with physics-informed modeling, this work offers a unified and data-efficient framework for physics discovery and parameter identification, paving the way for robust inverse modeling in complex dynamical systems.
Authors: Heng Zhu, Harsh Vardhan, Arya Mazumdar
Abstract: In distributed training of machine learning models, gradient descent with local iterative steps, commonly known as Local (Stochastic) Gradient Descent (Local-(S)GD) or Federated averaging (FedAvg), is a very popular method to mitigate communication burden. In this method, gradient steps based on local datasets are taken independently in distributed compute nodes to update the local models, which are then aggregated intermittently. In the interpolation regime, Local-GD can converge to zero training loss. However, with many potential solutions corresponding to zero training loss, it is not known which solution Local-GD converges to. In this work we answer this question by analyzing implicit bias of Local-GD for classification tasks with linearly separable data. For the interpolation regime, our analysis shows that the aggregated global model obtained from Local-GD, with arbitrary number of local steps, converges exactly to the model that would be obtained if all data were in one place (centralized model) ''in direction''. Our result gives the exact rate of convergence to the centralized model with respect to the number of local steps. We also obtain the same implicit bias with a learning rate independent of number of local steps with a modified version of the Local-GD algorithm. Our analysis provides a new view to understand why Local-GD can still perform well with a very large number of local steps even for heterogeneous data. Lastly, we also discuss the extension of our results to Local-SGD and non-separable data.
Authors: Rupkatha Hira, Dominik Kau, Jessica Sorrell
Abstract: Active learning aims to reduce the number of labeled data points required by machine learning algorithms by selectively querying labels from initially unlabeled data. Ensuring replicability, where an algorithm produces consistent outcomes across different runs, is essential for the reliability of machine learning models but often increases sample complexity. This paper investigates the cost of replicability in active learning using two classical disagreement-based methods: the CAL and A^2 algorithms. Leveraging randomized thresholding techniques, we propose two replicable active learning algorithms: one for realizable learning of finite hypothesis classes and another for the agnostic setting. Our theoretical analysis shows that while enforcing replicability increases label complexity, CAL and A^2 still achieve substantial label savings under this constraint. These findings provide insights into balancing efficiency and stability in active learning.
Authors: Tetsuya Hoya, Shunpei Morita
Abstract: This paper proposes a novel approach to pattern classification using a probabilistic neural network model. The strategy is based on a compact-sized probabilistic neural network capable of continuous incremental learning and unlearning tasks. The network is constructed/reconstructed using a simple, one-pass network-growing algorithm with no hyperparameter tuning. Then, given the training dataset, its structure and parameters are automatically determined and can be dynamically varied in continual incremental and decremental learning situations. The algorithm proposed in this work involves no iterative or arduous matrix-based parameter approximations but a simple data-driven updating scheme. Simulation results using nine publicly available databases demonstrate the effectiveness of this approach, showing that compact-sized probabilistic neural networks constructed have a much smaller number of hidden units compared to the original probabilistic neural network model and yet can achieve a similar classification performance to that of multilayer perceptron neural networks in standard classification tasks, while also exhibiting sufficient capability in continuous class incremental learning and unlearning tasks.
Authors: Abhishek Dalvi, Neil Ashtekar, Vasant Honavar
Abstract: We address the problem of estimating causal effects from observational data in the presence of network confounding, a setting where both treatment assignment and observed outcomes of individuals may be influenced by their neighbors within a network structure, resulting in network interference. Traditional causal inference methods often fail to account for these dependencies, leading to biased estimates. To tackle this challenge, we introduce a novel matching-based approach that utilizes principles from hyperdimensional computing to effectively encode and incorporate structural network information. This enables more accurate identification of comparable individuals, thereby improving the reliability of causal effect estimates. Through extensive empirical evaluation on multiple benchmark datasets, we demonstrate that our method either outperforms or performs on par with existing state-of-the-art approaches, including several recent deep learning-based models that are significantly more computationally intensive. In addition to its strong empirical performance, our method offers substantial practical advantages, achieving nearly an order-of-magnitude reduction in runtime without compromising accuracy, making it particularly well-suited for large-scale or time-sensitive application
Authors: Yuhao Du, Zhuo Li, Pengyu Cheng, Zhihong Chen, Yuejiao Xie, Xiang Wan, Anningzhe Gao
Abstract: Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning Large Language Models (LLMs) with human values. However, RLHF has been continuously challenged by its high complexity in implementation and computation consumption, specifically for online sampling-based methods like Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO). Even with recent simplifications, such as Direct Preference Optimization (DPO) that designs an offline implicit reward learning objective relying on pre-collected preference datasets, the problems of over-fitting and training instability remain hindering the alignment process from the expected optimal performance. To address the existing challenges, we propose a novel simplification of RLHF from the perspective of variational inference, called Variational Alignment with Re-weighting (VAR). Specifically, by directly minimizing the distribution gap between the learning LLM policy and the optimal solution of RLHF, we transform the alignment objective into an offline reward-driven re-weighted supervised fine-tuning (SFT) form, which only requires minor adjustment on the SFT loss to obtain noticeable improvement on training stability and effectiveness. In comprehensive evaluation benchmarks, our objective empowers LLMs to outperform offline alignments, demonstrating superior performance in both helpfulness and harmlessness metrics (avg. $\uparrow7.16\%$ than DPO). Meanwhile, when compared to online sampling methods, our method is also comparable even better while significantly reducing computational overhead and accelerating convergence speed (over $5\times$ faster than GRPO), suggesting our approach as an efficient and effective solution in bridging the gap between efficiency and performance in LLM alignment.
Authors: Th\'eo Hanon, Nicolas Mil-Homens Cavaco, John Kiely, Laurent Jacques
Abstract: Representing and processing data in spherical domains presents unique challenges, primarily due to the curvature of the domain, which complicates the application of classical Euclidean techniques. Implicit neural representations (INRs) have emerged as a promising alternative for high-fidelity data representation; however, to effectively handle spherical domains, these methods must be adapted to the inherent geometry of the sphere to maintain both accuracy and stability. In this context, we propose Herglotz-NET (HNET), a novel INR architecture that employs a harmonic positional encoding based on complex Herglotz mappings. This encoding yields a well-posed representation on the sphere with interpretable and robust spectral properties. Moreover, we present a unified expressivity analysis showing that any spherical-based INR satisfying a mild condition exhibits a predictable spectral expansion that scales with network depth. Our results establish HNET as a scalable and flexible framework for accurate modeling of spherical data.
Authors: Yushan Jiang, Wenchao Yu, Geon Lee, Dongjin Song, Kijung Shin, Wei Cheng, Yanchi Liu, Haifeng Chen
Abstract: Time series analysis provides essential insights for real-world system dynamics and informs downstream decision-making, yet most existing methods often overlook the rich contextual signals present in auxiliary modalities. To bridge this gap, we introduce TimeXL, a multi-modal prediction framework that integrates a prototype-based time series encoder with three collaborating Large Language Models (LLMs) to deliver more accurate predictions and interpretable explanations. First, a multi-modal prototype-based encoder processes both time series and textual inputs to generate preliminary forecasts alongside case-based rationales. These outputs then feed into a prediction LLM, which refines the forecasts by reasoning over the encoder's predictions and explanations. Next, a reflection LLM compares the predicted values against the ground truth, identifying textual inconsistencies or noise. Guided by this feedback, a refinement LLM iteratively enhances text quality and triggers encoder retraining. This closed-loop workflow-prediction, critique (reflect), and refinement-continuously boosts the framework's performance and interpretability. Empirical evaluations on four real-world datasets demonstrate that TimeXL achieves up to 8.9% improvement in AUC and produces human-centric, multi-modal explanations, highlighting the power of LLM-driven reasoning for time series prediction.
Authors: Stella C. Dong
Abstract: We develop a reinforcement learning (RL) framework for insurance loss reserving that formulates reserve setting as a finite-horizon sequential decision problem under claim development uncertainty, macroeconomic stress, and solvency governance. The reserving process is modeled as a Markov Decision Process (MDP) in which reserve adjustments influence future reserve adequacy, capital efficiency, and solvency outcomes. A Proximal Policy Optimization (PPO) agent is trained using a risk-sensitive reward that penalizes reserve shortfall, capital inefficiency, and breaches of a volatility-adjusted solvency floor, with tail risk explicitly controlled through Conditional Value-at-Risk (CVaR). To reflect regulatory stress-testing practice, the agent is trained under a regime-aware curriculum and evaluated using both regime-stratified simulations and fixed-shock stress scenarios. Empirical results for Workers Compensation and Other Liability illustrate how the proposed RL-CVaR policy improves tail-risk control and reduces solvency violations relative to classical actuarial reserving methods, while maintaining comparable capital efficiency. We further discuss calibration and governance considerations required to align model parameters with firm-specific risk appetite and supervisory expectations under Solvency II and Own Risk and Solvency Assessment (ORSA) frameworks.
Authors: Ruitong Li, Aisheng Mo, Guowei Su, Ru Zhang, Binjie Guo, Haohan Jiang, Xurong Lin, Hongyan Wei, Jie Li, Zhiyuan Qian, Zhuhao Zhang, Xiaoyuan Cheng
Abstract: Recent years have witnessed significant progress in reinforcement learning, especially with Zero-like paradigms, which have greatly boosted the generalization and reasoning abilities of large-scale language models. Nevertheless, existing frameworks are often plagued by high implementation complexity and poor reproducibility. To tackle these challenges, we present AlphaZero-Edu, a lightweight, education-focused implementation built upon the mathematical framework of AlphaZero. It boasts a modular architecture that disentangles key components, enabling transparent visualization of the algorithmic processes. Additionally, it is optimized for resource-efficient training on a single NVIDIA RTX 3090 GPU and features highly parallelized self-play data generation, achieving a 3.2-fold speedup with 8 processes. In Gomoku matches, the framework has demonstrated exceptional performance, achieving a consistently high win rate against human opponents. AlphaZero-Edu has been open-sourced at https://github.com/StarLight1212/AlphaZero_Edu, providing an accessible and practical benchmark for both academic research and industrial applications.
Authors: Alexander Y. Ku, Thomas L. Griffiths, Stephanie C. Y. Chan
Abstract: The success of Transformers lies in their ability to improve inference through two complementary strategies: the permanent refinement of model parameters via in-weight learning (IWL), and the ephemeral modulation of inferences via in-context learning (ICL), which leverages contextual information maintained in the model's activations. Evolutionary biology tells us that the predictability of the environment across timescales predicts the extent to which analogous strategies should be preferred. Genetic evolution adapts to stable environmental features by gradually modifying the genotype over generations. Conversely, environmental volatility favors plasticity, which enables a single genotype to express different traits within a lifetime, provided there are reliable cues to guide the adaptation. We operationalize these dimensions (environmental stability and cue reliability) in controlled task settings (sinusoid regression and Omniglot classification) to characterize their influence on learning in Transformers. We find that stable environments favor IWL, often exhibiting a sharp transition when conditions are static. Conversely, reliable cues favor ICL, particularly when the environment is volatile. Furthermore, an analysis of learning dynamics reveals task-dependent transitions between strategies (ICL to IWL and vice versa). We demonstrate that these transitions are governed by (1) the asymptotic optimality of the strategy with respect to the environment, and (2) the optimization cost of acquiring that strategy, which depends on the task structure and the learner's inductive bias.
Authors: Gabriel S. Gama, Valdir Grassi Jr
Abstract: Specialized Multi-Task Optimizers (SMTOs) balance task learning in Multi-Task Learning by addressing issues like conflicting gradients and differing gradient norms, which hinder equal-weighted task training. However, recent critiques suggest that equally weighted tasks can achieve competitive results compared to SMTOs, arguing that previous SMTO results were influenced by poor hyperparameter optimization and lack of regularization. In this work, we evaluate these claims through an extensive empirical evaluation of SMTOs, including some of the latest methods, on more complex multi-task problems to clarify this behavior. Our findings indicate that SMTOs perform well compared to uniform loss and that fixed weights can achieve competitive performance compared to SMTOs. Furthermore, we demonstrate why uniform loss perform similarly to SMTOs in some instances. The source code is available at https://github.com/Gabriel-SGama/UnitScal_vs_SMTOs.
Authors: Yuanlin Chu, Bo Wang, Xiang Liu, Hong Chen, Aiwei Liu, Xuming Hu
Abstract: Large language models (LLMs) have achieved impressive results on multi-step mathematical reasoning, yet at the cost of high computational overhead. This challenge is particularly acute for test-time scaling methods such as parallel decoding, which increase answer diversity but scale poorly in efficiency. To address this efficiency-accuracy trade-off, we propose SSR (Speculative Parallel Scaling Reasoning), a training-free framework that leverages a key insight: by introducing speculative decoding at the step level, we can accelerate reasoning without sacrificing correctness. SSR integrates two components: a Selective Parallel Module (SPM) that identifies a small set of promising reasoning strategies via model-internal scoring, and Step-level Speculative Decoding (SSD), which enables efficient draft-target collaboration for fine-grained reasoning acceleration. Experiments on three mathematical benchmarks-AIME 2024, MATH-500, and LiveMathBench - demonstrate that SSR achieves strong gains over baselines. For instance, on LiveMathBench, SSR improves pass@1 accuracy by 13.84% while reducing computation to 80.5% of the baseline FLOPs. On MATH-500, SSR reduces compute to only 30% with no loss in accuracy.
Authors: Qilin Wang
Abstract: Long-term time-series forecasting (LTSF) models are often presented as general-purpose solutions that can be applied across domains, implicitly assuming that all data is pointwise predictable. Using chaotic systems such as Lorenz-63 as a case study, we argue that geometric structure - not pointwise prediction - is the right abstraction for a dynamic-agnostic foundational model. Minimizing the Wasserstein-2 distance (W2), which captures geometric changes, and providing a spectral view of dynamics are essential for long-horizon forecasting. Our model, FRIREN (Flow-inspired Representations via Interpretable Eigen-networks), implements an augmented normalizing-flow block that embeds data into a normally distributed latent representation. It then generates a W2-efficient optimal path that can be decomposed into rotation, scaling, inverse rotation, and translation. This architecture yields locally generated, geometry-preserving predictions that are independent of the underlying dynamics, and a global spectral representation that functions as a finite Koopman operator with a small modification. This enables practitioners to identify which modes grow, decay, or oscillate, both locally and system-wide. FRIREN achieves an MSE of 11.4, MAE of 1.6, and SWD of 0.96 on Lorenz-63 in a 336-in, 336-out, dt=0.01 setting, surpassing TimeMixer (MSE 27.3, MAE 2.8, SWD 2.1). The model maintains effective prediction for 274 out of 336 steps, approximately 2.5 Lyapunov times. On Rossler (96-in, 336-out), FRIREN achieves an MSE of 0.0349, MAE of 0.0953, and SWD of 0.0170, outperforming TimeMixer's MSE of 4.3988, MAE of 0.886, and SWD of 3.2065. FRIREN is also competitive on standard LTSF datasets such as ETT and Weather. By connecting modern generative flows with classical spectral analysis, FRIREN makes long-term forecasting both accurate and interpretable, setting a new benchmark for LTSF model design.
Authors: Isaac Ning Lee, Leila Mahmoodi, Trung Le, Mehrtash Harandi
Abstract: State-Space Models (SSMs) excel at capturing long-range dependencies with structured recurrence, making them well-suited for sequence modeling. However, their evolving internal states pose challenges in adapting them under Continual Learning (CL). This is particularly difficult in exemplar-free settings, where the absence of prior data leaves updates to the dynamic SSM states unconstrained, resulting in catastrophic forgetting. To address this, we propose Inf-SSM, a novel and simple geometry-aware regularization method that utilizes the geometry of the infinite-dimensional Grassmannian to constrain state evolution during CL. Unlike classical continual learning methods that constrain weight updates, Inf-SSM regularizes the infinite-horizon evolution of SSMs encoded in their extended observability subspace. We show that enforcing this regularization requires solving a matrix equation known as the Sylvester equation, which typically incurs $\mathcal{O}(n^3)$ complexity. We develop a $\mathcal{O}(n^2)$ solution by exploiting the structure and properties of SSMs. This leads to an efficient regularization mechanism that can be seamlessly integrated into existing CL methods. Comprehensive experiments on challenging benchmarks, including ImageNet-R and Caltech-256, demonstrate a significant reduction in forgetting while improving accuracy across sequential tasks.
Authors: Xuandong Zhao, Zhewei Kang, Aosong Feng, Sergey Levine, Dawn Song
Abstract: Training large language models (LLMs) for complex reasoning via Reinforcement Learning with Verifiable Rewards (RLVR) is effective but limited by reliance on costly, domain-specific supervision. We explore Reinforcement Learning from Internal Feedback (RLIF), a framework that enables LLMs to learn from intrinsic signals without external rewards or labeled data. We propose Intuitor, an RLIF method that uses a model's own confidence-termed self-certainty-as its sole reward signal. Intuitor replaces external rewards in Group Relative Policy Optimization (GRPO) with self-certainty scores, enabling fully unsupervised learning. Experiments demonstrate that Intuitor matches GRPO's performance on mathematical benchmarks while achieving better generalization to out-of-domain tasks like code generation, without requiring gold solutions or test cases. Our findings show that intrinsic model signals can drive effective learning across domains, offering a scalable alternative to RLVR for autonomous AI systems where verifiable rewards are unavailable. Code is available at https://github.com/sunblaze-ucb/Intuitor
Authors: En Yu, Jie Lu, Guangquan Zhang
Abstract: Real-world data streams exhibit inherent non-stationarity characterized by concept drift, posing significant challenges for adaptive learning systems. While existing methods address isolated distribution shifts, they overlook the critical co-evolution of label spaces and distributions under limited supervision and persistent uncertainty. To address this, we formalize Generalized Incremental Learning under Concept Drift (GILCD), characterizing the joint evolution of distributions and label spaces in open-environment streaming contexts, and propose a novel framework called Calibrated Source-Free Adaptation (CSFA). First, CSFA introduces a training-free prototype calibration mechanism that dynamically fuses emerging prototypes with base representations, enabling stable new-class identification without optimization overhead. Second, we design a novel source-free adaptation algorithm, i.e., Reliable Surrogate Gap Sharpness-aware (RSGS) minimization. It integrates sharpness-aware perturbation loss optimization with surrogate gap minimization, while employing entropy-based uncertainty filtering to discard unreliable samples. This mechanism ensures robust distribution alignment and mitigates generalization degradation caused by uncertainties. Thus, CSFA establishes a unified framework for stable adaptation to evolving semantics and distributions in open-world streaming scenarios. Extensive experiments validate the superior performance and effectiveness of CSFA compared to SOTA approaches.
Authors: Pantelis R. Vlachas, Konstantinos Vlachas, Eleni Chatzi
Abstract: Dynamical systems play a key role in modeling, forecasting, and decision-making across a wide range of scientific domains. However, variations in system parameters, also referred to as parametric variability, can lead to drastically different model behavior and output, posing challenges for constructing models that generalize across parameter regimes. In this work, we introduce the Parametric Hypernetwork for Learning Interpolated Networks (PHLieNet), a framework that simultaneously learns: (a) a global mapping from the parameter space to a nonlinear embedding and (b) a mapping from the inferred embedding to the weights of a dynamics propagation network. The learned embedding serves as a latent representation that modulates a base network, termed the hypernetwork, enabling it to generate the weights of a target network responsible for forecasting the system's state evolution conditioned on the previous time history. By interpolating in the space of models rather than observations, PHLieNet facilitates smooth transitions across parameterized system behaviors, enabling a unified model that captures the dynamic behavior across a broad range of system parameterizations. The performance of the proposed technique is validated in a series of dynamical systems with respect to its ability to extrapolate in time and interpolate and extrapolate in the parameter space, i.e., generalize to dynamics that were unseen during training. Our approach outperforms state-of-the-art baselines in both short-term forecast accuracy and in capturing long-term dynamical features such as attractor statistics.
Authors: Wenbo Yu, Anirbit Ghosh, Tobias Sebastian Finn, Rossella Arcucci, Marc Bocquet, Sibo Cheng
Abstract: Thanks to recent advances in generative AI, computers can now simulate realistic and complex natural processes. We apply this capability to predict how wildfires spread, a task made difficult by the unpredictable nature of fire and the variety of environmental conditions it depends on. In this study, We present the first denoising diffusion model for predicting wildfire spread, a new kind of AI framework that learns to simulate fires not just as one fixed outcome, but as a range of possible scenarios. By doing so, it accounts for the inherent uncertainty of wildfire dynamics, a feature that traditional models typically fail to represent. Unlike deterministic approaches that generate a single prediction, our model produces ensembles of forecasts that reflect physically meaningful distributions of where fire might go next. This technology could help us develop smarter, faster, and more reliable tools for anticipating wildfire behavior, aiding decision-makers in fire risk assessment and response planning.
Authors: Muhao Guo, Jiaqi Wu, Yizheng Liao, Wenke Lee, Shengzhe Chen, Yang Weng
Abstract: Publishing open graph data while preserving individual privacy remains challenging when data publishers and data users are distinct entities. Although differential privacy (DP) provides rigorous guarantees, most existing approaches enforce privacy during model training rather than at the data publishing stage. This limits the applicability to open-data scenarios. We propose a privacy-preserving graph structure learning framework that integrates Gaussian Differential Privacy (GDP) directly into the data release process. Our mechanism injects structured Gaussian noise into raw data prior to publication and provides formal $\mu$-GDP guarantees, leading to tight $(\varepsilon, \delta)$-differential privacy bounds. Despite the distortion introduced by privatization, we prove that the original sparse inverse covariance structure can be recovered through an unbiased penalized likelihood formulation. We further extend the framework to discrete data using discrete Gaussian noise while preserving privacy guarantees. Extensive experiments on synthetic and real-world datasets demonstrate strong privacy-utility trade-offs, maintaining high graph recovery accuracy under rigorous privacy budgets. Our results establish a formal connection between differential privacy theory and privacy-preserving data publishing for graphical models.
Authors: Sarah Lockfisch, Kristian Schwethelm, Martin Menten, Rickmer Braren, Daniel Rueckert, Alexander Ziller, Georgios Kaissis
Abstract: Model multiplicity refers to the existence of multiple machine learning models that describe the data equally well but may produce different predictions on individual samples. In medicine, these models can admit conflicting predictions for the same patient -- a risk that is poorly understood and insufficiently addressed. In this study, we empirically analyze the extent, drivers, and ramifications of predictive multiplicity across diverse medical tasks and model architectures, and show that even small ensembles can mitigate/eliminate predictive multiplicity in practice. Our analysis reveals that (1) standard validation metrics fail to identify a uniquely optimal model and (2) a substantial amount of predictions hinges on arbitrary choices made during model development. Using multiple models instead of a single model reveals instances where predictions differ across equally plausible models -- highlighting patients that would receive arbitrary diagnoses if any single model were used. In contrast, (3) a small ensemble paired with an abstention strategy can effectively mitigate measurable predictive multiplicity in practice; predictions with high inter-model consensus may thus be amenable to automated classification. While accuracy is not a principled antidote to predictive multiplicity, we find that (4) higher accuracy achieved through increased model capacity reduces predictive multiplicity. Our findings underscore the clinical importance of accounting for model multiplicity and advocate for ensemble-based strategies to improve diagnostic reliability. In cases where models fail to reach sufficient consensus, we recommend deferring decisions to expert review.
Authors: Lei Pang, Jun Luo, Ruinan Jin
Abstract: Group Relative Policy Optimization (GRPO), recently introduced by DeepSeek, is a critic-free reinforcement learning algorithm for fine-tuning large language models. GRPO replaces the value function in Proximal Policy Optimization (PPO) with group-normalized rewards while retaining PPO-style token-level importance sampling based on an old policy. Our theoretical analysis reveals that the GRPO update rule estimates the policy gradient at the old policy rather than the current one; however, since the old policy is refreshed every few steps, the resulting discrepancy remains small and the induced bias is negligible in practice. To empirically validate this insight, we conduct an ablation study that entirely removes importance sampling and performs multiple optimization steps using gradients estimated at a fixed old policy. Remarkably, this simplified variant attains performance comparable to standard GRPO. Motivated by this finding, we propose Trajectory-level Importance-Corrected GRPO (TIC-GRPO), a new algorithm that replaces token-level importance ratios with a single trajectory-level probability ratio, thereby yielding an estimate of the current policy gradient while preserving the critic-free structure. Furthermore, we present the first convergence analysis for GRPO-style methods and show that TIC-GRPO converges faster than GRPO. Finally, empirical results across math reasoning and coding tasks demonstrate the superiority of TIC-GRPO.
Authors: Aleksander Boruch-Gruszecki, Yangtian Zi, Zixuan Wu, Tejas Oberoi, Carolyn Jane Anderson, Joydeep Biswas, Arjun Guha
Abstract: Large language models (LLMs) already excel at writing code in high-resource languages such as Python and JavaScript, yet stumble on low-resource languages that remain essential to science and engineering. Besides the obvious shortage of pre-training data, post-training itself is a bottleneck: every new language seems to require new datasets, test harnesses, and reinforcement-learning (RL) infrastructure. We introduce Agnostics, a language-agnostic post-training pipeline that eliminates this per-language engineering. The key idea is to judge code solely by its externally observable behavior, so a single verifier can test solutions written in any language. Concretely, we (i) use an LLM to rewrite existing unit-test datasets into an I/O format, (ii) supply a short configuration that tells the verifier how to compile and run a target language, and (iii) apply reinforcement learning with verifiable rewards (RLVR) in a robust code execution environment. Applied to five low-resource languages--Lua, Julia, R, OCaml, and Fortran--Agnostics (1) improves Qwen-3 4B to performance that rivals other 16B-70B open-weight models; (2) scales cleanly to larger and diverse model families (Qwen-3 8B, DeepSeek Coder 6.7B Instruct, Phi 4 Mini); and (3) for ${\le} 16$B parameter models, sets new state-of-the-art pass@1 results on MultiPL-E and a new multi-language version of LiveCodeBench that we introduce. We release the language-agnostic training datasets (Ag-MBPP-X, Ag-Codeforces-X, Ag-LiveCodeBench-X), training code, and ready-to-use configurations, making RL post-training in any programming language as simple as editing a short YAML file.
Authors: Tomoya Tate, Kosuke Sugiyama, Masato Uchida
Abstract: In practical machine learning applications, it is often challenging to assign accurate labels to data, and increasing the number of labeled instances is often limited. In such cases, Weakly Supervised Learning (WSL), which enables training with incomplete or imprecise supervision, provides a practical and effective solution. However, most existing WSL methods focus on leveraging a single type of weak supervision. In this paper, we propose a novel WSL framework that leverages complementary weak supervision signals from multiple relational perspectives, which can be especially valuable when labeled data is limited. Specifically, we introduce SconfConfDiff Classification, a method that integrates two distinct forms of weaklabels: similarity-confidence and confidence-difference, which are assigned to unlabeled data pairs. To implement this method, we derive two types of unbiased risk estimators for classification: one based on a convex combination of existing estimators, and another newly designed by modeling the interaction between two weak labels. We prove that both estimators achieve optimal convergence rates with respect to estimation error bounds. Furthermore, we introduce a risk correction approach to mitigate overfitting caused by negative empirical risk, and provide theoretical analysis on the robustness of the proposed method against inaccurate class prior probability and label noise. Experimental results demonstrate that the proposed method consistently outperforms existing baselines across a variety of settings.
Authors: Yahong Yang, Juncai He
Abstract: This paper establishes a comprehensive approximation result for deep fully-connected neural networks with commonly-used and general activation functions in Sobolev spaces $W^{n,\infty}$, with errors measured in the $W^{m,p}$-norm for $m < n$ and $1\le p \le \infty$. The derived rates surpass those of classical numerical approximation techniques, such as finite element and spectral methods, exhibiting a phenomenon we refer to as \emph{super-convergence}. Our analysis shows that deep networks with general activations can approximate weak solutions of partial differential equations (PDEs) with superior accuracy compared to traditional numerical methods at the approximation level. Furthermore, this work closes a significant gap in the error-estimation theory for neural-network-based approaches to PDEs, offering a unified theoretical foundation for their use in scientific computing.
Authors: Ankur Naskar, Gugan Thoppe, Vijay Gupta
Abstract: Algorithms for solving \textit{nonlinear} fixed-point equations -- such as average-reward \textit{$Q$-learning} and \textit{TD-learning} -- often involve semi-norm contractions. Achieving parameter-free optimal convergence rates for these methods via Polyak--Ruppert averaging has remained elusive, largely due to the non-monotonicity of such semi-norms. We close this gap by (i.) recasting the averaged error as a linear recursion involving a nonlinear perturbation, and (ii.) taming the nonlinearity by coupling the semi-norm's contraction with the monotonicity of a suitably induced norm. Our main result yields the first parameter-free $\tilde{O}(1/\sqrt{t})$ optimal rates for $Q$-learning in both average-reward and exponentially discounted settings, where $t$ denotes the iteration index. The result applies within a broad framework that accommodates synchronous and asynchronous updates, single-agent and distributed deployments, and data streams obtained either from simulators or along Markovian trajectories.
Authors: Peyman Baghershahi, Gregoire Fournier, Pranav Nyati, Sourav Medya
Abstract: Graph Neural Networks (GNNs) have emerged as powerful tools for learning over structured data, including text-attributed graphs (TAGs), which are common in domains such as citation networks, social platforms, and knowledge graphs. GNNs are not inherently interpretable and thus, many explanation methods have been proposed. However, existing explanation methods often struggle to generate interpretable, fine-grained rationales, especially when node attributes include rich natural language. In this work, we introduce GSPELL, a lightweight, post-hoc framework that uses large language models (LLMs) to generate faithful and interpretable explanations for GNN predictions. GSPELL projects GNN node embeddings into the LLM embedding space and constructs hybrid prompts that interleave soft prompts with textual inputs from the graph structure. This enables the LLM to reason about GNN internal representations and produce natural language explanations along with concise explanation subgraphs. Our experiments across real-world TAG datasets demonstrate that GSPELL achieves a favorable trade-off between fidelity and sparsity, while improving human-centric metrics such as insightfulness. GSPELL sets a new direction for LLM-based explainability in graph learning by aligning GNN internals with human reasoning.
Authors: Nikita Puchkin, Denis Suchkov, Alexey Naumov, Denis Belomestny
Abstract: Modern methods of generative modelling and unpaired data translation based on Schr\"odinger bridges and stochastic optimal control theory aim to transform an initial density to a target one in an optimal way. In the present paper, we assume that we only have access to i.i.d. samples from the initial and final distributions. This makes our setup suitable for both generative modelling and unpaired data translation. Relying on the stochastic optimal control approach, we choose an Ornstein-Uhlenbeck process as the reference one and estimate the corresponding Schr\"odinger potential. Introducing a risk function as the Kullback-Leibler divergence between couplings, we derive tight bounds on the generalization ability of an empirical risk minimizer over a class of Schr\"odinger potentials, including Gaussian mixtures. Thanks to the mixing properties of the Ornstein-Uhlenbeck process, we almost achieve fast rates of convergence, up to some logarithmic factors, in favourable scenarios. We also illustrate the performance of the suggested approach with numerical experiments.
Authors: Andrea Maldonado, Christian M. M. Frey, Sai Anirudh Aryasomayajula, Ludwig Zellner, Stephan A. Fahrenkrog-Petersen, Thomas Seidl
Abstract: Process mining aims to extract and analyze insights from event logs, yet algorithm metric results vary widely depending on structural event log characteristics. Existing work often evaluates algorithms on a fixed set of real-world event logs but lacks a systematic analysis of how event log characteristics impact algorithms individually. Moreover, since event logs are generated from processes, where characteristics co-occur, we focus on associational rather than causal effects to assess how strong the overlapping individual characteristic affects evaluation metrics without assuming isolated causal effects, a factor often neglected by prior work. We introduce SHAining, the first approach to quantify the marginal contribution of varying event log characteristics to process mining algorithms' metrics. Using process discovery as a downstream task, we analyze over 22,000 event logs covering a wide span of characteristics to uncover which affect algorithms across metrics (e.g., fitness, precision, complexity) the most. Furthermore, we offer novel insights about how the value of event log characteristics correlates with their contributed impact, assessing the algorithm's robustness.
Authors: Christopher Eldred, Fran\c{c}ois Gay-Balmaz, Vakhtang Putkaradze
Abstract: Much attention has recently been devoted to data-based computing of evolution of physical systems. In such approaches, information about data points from past trajectories in phase space is used to reconstruct the equations of motion and to predict future solutions that have not been observed before. However, in many cases, the available data does not correspond to the variables that define the system's phase space. We focus our attention on the important example of dissipative dynamical systems. In that case, the phase space consists of coordinates, momenta and entropies; however, the momenta and entropies cannot, in general, be observed directly. To address this difficulty, we develop an efficient data-based computing framework based exclusively on observable variables, by constructing a novel approach based on the thermodynamic Lagrangian, and constructing neural networks that respect the thermodynamics and guarantees the non-decreasing entropy evolution. We show that our network can provide an efficient description of phase space evolution based on a limited number of data points and a relatively small number of parameters in the system.
Authors: Sitong Chen, Shen Nie, Jiacheng Sun, Zijin Feng, Zhenguo Li, Ji-Rong Wen, Chongxuan Li
Abstract: We present a systematic theoretical framework that interprets masked diffusion models (MDMs) as solutions to energy minimization problems in discrete optimal transport. Specifically, we prove that three distinct energy formulations--kinetic, conditional kinetic, and geodesic energy--are mathematically equivalent under the structure of MDMs, and that MDMs minimize all three when the mask schedule satisfies a closed-form optimality condition. This unification not only clarifies the theoretical foundations of MDMs, but also motivates practical improvements in sampling. By parameterizing interpolation schedules via Beta distributions, we reduce the schedule design space to a tractable 2D search, enabling efficient post-training tuning without model modification. Experiments on synthetic and real-world benchmarks demonstrate that our energy-inspired schedules outperform hand-crafted baselines, particularly in low-step sampling settings.
Authors: Jianglan Wei, Zhenyu Zhang, Pengcheng Wang, Mingjie Zeng, Zhigang Zeng
Abstract: Energy-efficient medical data classification is essential for modern disease screening, particularly in home and field healthcare where embedded devices are prevalent. While deep learning models achieve state-of-the-art accuracy, their substantial energy consumption and reliance on GPUs limit deployment on such platforms. We present HDC-X, a lightweight classification framework designed for low-power devices. HDC-X encodes data into high-dimensional hypervectors, aggregates them into multiple cluster-specific prototypes, and performs classification through similarity search in hyperspace. We evaluate HDC-X across three medical classification tasks; on heart sound classification, HDC-X is $350\times$ more energy-efficient than Bayesian ResNet with less than 1% accuracy difference. Moreover, HDC-X demonstrates exceptional robustness to noise, limited training data, and hardware error, supported by both theoretical analysis and empirical results, highlighting its potential for reliable deployment in real-world settings. Code is available at https://github.com/jianglanwei/HDC-X.
Authors: Jean-Michel Tucny, Abhisek Ganguly, Santosh Ansumali, Sauro Succi
Abstract: Physics-informed neural networks (PINNs) often exhibit weight matrices that appear statistically random after training, yet their implications for signal propagation and stability remain unsatisfactorily understood, let alone the interpretability. In this work, we analyze the spectral and statistical properties of trained PINN weights using viscous and inviscid variants of the one-dimensional Burgers' equation, and show that the learned weights reside in a high-entropy regime consistent with predictions from random matrix theory. To investigate the dynamical consequences of such weight structures, we study the evolution of signal features inside a network through the lens of neural partial differential equations (neural PDEs). We show that random and structured weight matrices can be associated with specific discretizations of neural PDEs, and that the numerical stability of these discretizations governs the stability of signal propagation through the network. In particular, explicit unstable schemes lead to degraded signal evolution, whereas stable implicit and higher-order schemes yield well-behaved dynamics for the same underlying neural PDE. Our results offer an explicit example of how numerical stability and network architecture shape signal propagation in deep networks, in relation to random matrix and neural PDE descriptions in PINNs.
Authors: Yuda Bi, Vince D Calhoun
Abstract: Scaling laws, a defining feature of deep learning, reveal a striking power-law improvement in model performance with increasing dataset and model size. Yet, their mathematical origins, especially the scaling exponent, have remained elusive. In this work, we show that scaling laws can be formally explained as redundancy laws. Using kernel regression, we show that a polynomial tail in the data covariance spectrum yields an excess risk power law with exponent alpha = 2s / (2s + 1/beta), where beta controls the spectral tail and 1/beta measures redundancy. This reveals that the learning curve's slope is not universal but depends on data redundancy, with steeper spectra accelerating returns to scale. We establish the law's universality across boundedly invertible transformations, multi-modal mixtures, finite-width approximations, and Transformer architectures in both linearized (NTK) and feature-learning regimes. This work delivers the first rigorous mathematical explanation of scaling laws as finite-sample redundancy laws, unifying empirical observations with theoretical foundations.
Authors: Shuaike Shen, Jiaqing Xie, Zhuo Yang, Antong Zhang, Shuzhou Sun, Ben Gao, Tianfan Fu, Biqing Qi, Yuqiang Li
Abstract: Large language models have emerged as transformative tools in molecular science, demonstrating remarkable potential in molecular property prediction and de novo molecular design. However, their application to spectroscopy remains notably limited, despite its foundational role in experimental molecular characterization and structural validation. Progress in spectroscopy-grounded reasoning has been hindered by the lack of standardized spectral representations and comprehensive evaluation protocols, making cross-study comparisons difficult. To bridge this gap, we present a unified framework for spectroscopy-grounded molecular modeling and evaluation. At its core, the SpecMol foundation model integrates spectral interpretation, molecular representation learning, and three-dimensional structure generation within a single interface. Complementing this, we establish SpecMol-Bench as a systematic evaluation protocol encompassing cross-modal tasks: spectra-to-structure elucidation, structure-to-spectra simulation, and SMILES-to-3D conformation generation. Under this unified framework, SpecMol achieves accurate spectra-driven structure elucidation and reproduces experimental nuclear magnetic resonance characteristics with high fidelity. The model also generates chemically valid three-dimensional conformations directly from SMILES strings and consistently outperforms existing general-purpose molecular language models across standardized evaluation metrics. Code is available at https://github.com/Eurekashen/SpecMol
Authors: Muyun Jiang, Shuailei Zhang, Zhenjie Yang, Mengjun Wu, Weibang Jiang, Zhiwei Guo, Wei Zhang, Rui Liu, Shangen Zhang, Yong Li, Yi Ding, Cuntai Guan
Abstract: Recent advances in electroencephalography (EEG) foundation models, which capture transferable EEG representations, have greatly accelerated the development of brain-computer interfaces (BCIs). However, existing approaches still struggle to incorporate language instructions as prior constraints for EEG representation learning, limiting their ability to leverage the semantic knowledge inherent in language to unify different labels and tasks. To address this challenge, we present LEAF, a foundation model for EEG--Language Alignment with Semantic Task Instruction and Querying. LEAF integrates task-aware semantic guidance to produce structured and linguistically aligned EEG embeddings, thereby enhancing decoding robustness and transferability. In the pretraining stage, we introduce a joint Spectral--Temporal Reconstruction (STR) framework that captures the coupled spectral rhythms and temporal dynamics of EEG signals. STR applies randomized spectral perturbation to enhance frequency robustness and uses two complementary temporal objectives to learn both contextual and sequential structure. In the EEG-Language alignment stage, we propose the Instruction-conditioned Q-Former (IQF). This query-based cross-attention transformer injects instruction embeddings into EEG tokens and achieves semantic alignment with textual label embeddings through learnable queries. We evaluate LEAF on 16 downstream datasets spanning motor imagery, emotion recognition, steady-state visual evoked potentials, covert speech, and healthcare tasks. LEAF achieves state-of-the-art performance on 12 of the 16 datasets and obtains the best average results across all five task categories. Importantly, our analyses reveal for the first time that explicit task instructions serve as semantic priors guiding EEG embeddings into coherent and linguistically grounded spaces. The code and pre-trained weights will be released.
Authors: Mohammad Hassan Vali, Tom B\"ackstr\"om, Arno Solin
Abstract: Vector quantization is common in deep models, yet its hard assignments block gradients and hinder end-to-end training. We propose DiVeQ, which treats quantization as adding an error vector that mimics the quantization distortion, keeping the forward pass hard while letting gradients flow. We also present a space-filling variant (SF-DiVeQ) that assigns to a curve constructed by the lines connecting codewords, resulting in less quantization error and full codebook usage. Both methods train end-to-end without requiring auxiliary losses or temperature schedules. In VQ-VAE image compression, VQGAN image generation, and DAC speech coding tasks across various data sets, our proposed methods improve reconstruction and sample quality over alternative quantization approaches.
Authors: Yongcheng Zeng, Zexu Sun, Bokai Ji, Erxue Min, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Haifeng Zhang, Xu Chen, Jun Wang
Abstract: Curriculum learning plays a crucial role in enhancing the training efficiency of large language models (LLMs) on reasoning tasks. However, existing methods often fail to adequately account for variations in prompt difficulty or rely on simplistic filtering mechanisms to select prompt datasets within a narrow criterion range, resulting in significant computational waste. In this work, we approach the problem from the perspective of reinforcement learning gradient optimization, offering a systematic and theoretical investigation into how to improve the training efficiency of LLMs. We identify two key factors influencing training efficiency: the selection of training prompts and the allocation of rollout quantities across different prompts. Our theoretical analysis reveals that the sampling distribution of prompts dictates the convergence rate of gradient descent, while the allocation of the rollout quantity influences the consistency and stability of overall gradient updates. Based on these insights, we propose CurES, an efficient training method that accelerates convergence and employs Bayesian posterior estimation to minimize computational overhead. Experiments demonstrate that our CurES outperforms Group Relative Policy Optimization (GRPO) by +3.30 points and +4.82 points with 1.5B and 7B models, respectively, and exceeds the best prior sample efficient methods by +2.12 points on average across eight math reasoning benchmarks. Additionally, CurES exhibits faster convergence compared to baselines, including GRPO.
Authors: Yunwen Guo, Yunlun Shu, Gongyi Zhuo, Tianyu Wang
Abstract: The batched multi-armed bandit (MAB) problem, in which rewards are collected in batches, is crucial for applications such as clinical trials. Existing research predominantly assumes light-tailed reward distributions, yet many real-world scenarios, including clinical outcomes, exhibit heavy-tailed characteristics. This paper bridges this gap by proposing robust batched bandit algorithms designed for heavy-tailed rewards, within both finite-arm and Lipschitz-continuous settings. We reveal a surprising phenomenon: in the instance-independent regime, as well as in the Lipschitz setting, heavier-tailed rewards necessitate a smaller number of batches to achieve near-optimal regret. In stark contrast, for the instance-dependent setting, the required number of batches to attain near-optimal regret remains invariant with respect to tail heaviness.
Authors: Subhodip Panda, Varun M S, Shreyans Jain, Sarthak Kumar Maharana, Prathosh A. P
Abstract: For a responsible and safe deployment of diffusion models in various domains, regulating the generated outputs from these models is desirable because such models could generate undesired, violent, and obscene outputs. To tackle this problem, recent works use machine unlearning methodology to forget training data points containing these undesired features from pre-trained generative models. However, these methods proved to be ineffective in data-constrained settings where the whole training dataset is inaccessible. Thus, the principal objective of this work is to propose a machine unlearning methodology that can prevent the generation of outputs containing undesired features from a pre-trained diffusion model in such a data-constrained setting. Our proposed method, termed as Variational Diffusion Unlearning (VDU), is a computationally efficient method that only requires access to a subset of training data containing undesired features. Our approach is inspired by the variational inference framework with the objective of minimizing a loss function consisting of two terms: plasticity inducer and stability regularizer. Plasticity inducer reduces the log-likelihood of the undesired training data points, while the stability regularizer, essential for preventing loss of image generation quality, regularizes the model in parameter space. We validate the effectiveness of our method through comprehensive experiments for both class unlearning and feature unlearning. For class unlearning, we unlearn some user-identified classes from MNIST, CIFAR-10, and tinyImageNet datasets from a pre-trained unconditional denoising diffusion probabilistic model (DDPM). Similarly, for feature unlearning, we unlearn the generation of certain high-level features from a pre-trained Stable Diffusion model trained on LAION-5B dataset.
Authors: Avichal Goel, Yoon Kim, Nir Shavit, Tony T. Wang
Abstract: Finetuning (pretrained) language models is a standard approach for updating their internal parametric knowledge and specializing them to new tasks and domains. However, the corresponding model weight changes ("weight diffs") are not generally interpretable. While inspecting the finetuning dataset can give a sense of how the model might have changed, these datasets are often not publicly available or are too large to work with directly. Towards the goal of comprehensively understanding weight diffs in natural language, we introduce Diff Interpretation Tuning (DIT), a method that trains models to describe their own finetuning-induced modifications. Our approach uses synthetic, labeled weight diffs to train a DIT-adapter, which can be applied to a compatible finetuned model to make it describe how it has changed. We demonstrate in two proof-of-concept settings (reporting hidden behaviors and summarizing finetuned knowledge) that our method enables models to describe their finetuning-induced modifications using accurate natural language descriptions.
Authors: Xin Gu, Yingtai Xiao, Guanlin He, Jiamu Bai, Daniel Kifer, Kiwan Maeng
Abstract: Differentially private stochastic gradient descent (DP-SGD) offers the promise of training deep learning models while mitigating many privacy risks. However, there is currently a large accuracy gap between DP-SGD and normal SGD training. This has resulted in different lines of research investigating orthogonal ways of improving privacy-preserving training. One such line of work, known as DP-MF, correlates the privacy noise across different iterations of stochastic gradient descent -- allowing later iterations to cancel out some of the noise added to earlier iterations. In this paper, we study how to improve this noise correlation. We propose a technique called NoiseCurve that uses model curvature, estimated from public unlabeled data, to improve the quality of this cross-iteration noise correlation. Our experiments on various datasets, models, and privacy parameters show that the noise correlations computed by NoiseCurve offer consistent and significant improvements in accuracy over the correlation scheme used by DP-MF.
Authors: Yi-Chung Chen, David I. Inouye, Jing Gao
Abstract: Generative classifiers, which leverage conditional generative models for classification, have recently demonstrated desirable properties such as robustness to distribution shifts. However, recent progress in this area has been largely driven by diffusion-based models, whose substantial computational cost severely limits scalability. This exclusive focus on diffusion-based methods has also constrained our understanding of generative classifiers. In this work, we propose a novel generative classifier built on recent advances in visual autoregressive (VAR) modeling, which offers a new perspective for studying generative classifiers. To further enhance its performance, we introduce the Adaptive VAR Classifier$^+$ (A-VARC$^+$), which achieves a superior trade-off between accuracy and inference speed, thereby significantly improving practical applicability. Moreover, we show that the VAR-based method exhibits fundamentally different properties from diffusion-based methods. In particular, due to its tractable likelihood, the VAR-based classifier enables visual explainability via token-wise mutual information and demonstrates inherent resistance to catastrophic forgetting in class-incremental learning tasks.
Authors: Lindsay Spoor, \'Alvaro Serra-G\'omez, Aske Plaat, Thomas Moerland
Abstract: Safe reinforcement learning addresses constrained optimization problems where maximizing performance must be balanced against safety constraints, and Lagrangian methods are a widely used approach for this purpose. However, the effectiveness of Lagrangian methods depends crucially on the choice of the Lagrange multiplier $\lambda$, which governs the multi-objective trade-off between return and cost. A common practice is to update the multiplier automatically during training. Although this approach is standard in practice, there remains limited empirical evidence on the optimally achievable trade-off between return and cost as a function of $\lambda$, and there is currently no systematic benchmark comparing automated update mechanisms to this empirical optimum. Therefore, we study (i) the constraint geometry for eight widely used safety tasks and (ii) the previously overlooked constraint-regime sensitivity of different Lagrange multiplier update mechanisms in safe reinforcement learning. Through the lens of multi-objective analysis, we present empirical Pareto frontiers that offer a complete visualization of the trade-off between return and cost in the underlying optimization problem. Our results reveal the highly sensitive nature of $\lambda$ and further show that the restrictiveness of the constraint cost can vary across different cost limits within the same task. This highlights the importance of careful cost limit selection across different regions of cost restrictiveness when evaluating safe reinforcement learning methods. We provide a recommended set of cost limits for each evaluated task and offer an open-source code base: https://github.com/lindsayspoor/Lagrangian_SafeRL.
Authors: Hyeongyu Kim, Geonhui Han, Dosik Hwang
Abstract: In recent advancements in Test Time Adaptation (TTA), most existing methodologies focus on updating normalization layers to adapt to the test domain. However, the reliance on normalization-based adaptation presents key challenges. First, normalization layers such as Batch Normalization (BN) are highly sensitive to small batch sizes, leading to unstable and inaccurate statistics. Moreover, normalization-based adaptation is inherently constrained by the structure of the pre-trained model, as it relies on training-time statistics that may not generalize well to unseen domains. These issues limit the effectiveness of normalization-based TTA approaches, especially under significant domain shift. In this paper, we introduce a novel paradigm based on the concept of a Buffer layer, which addresses the fundamental limitations of normalization layer updates. Unlike existing methods that modify the core parameters of the model, our approach preserves the integrity of the pre-trained backbone, inherently mitigating the risk of catastrophic forgetting during online adaptation. Through comprehensive experimentation, we demonstrate that our approach not only outperforms traditional methods in mitigating domain shift and enhancing model robustness, but also exhibits strong resilience to forgetting. Furthermore, our Buffer layer is modular and can be seamlessly integrated into nearly all existing TTA frameworks, resulting in consistent performance improvements across various architectures. These findings validate the effectiveness and versatility of the proposed solution in real-world domain adaptation scenarios. The code is available at https://github.com/hyeongyu-kim/Buffer_TTA.
Authors: Christos Thrampoulidis, Sadegh Mahdavi, Wenlong Deng
Abstract: This note reconciles two seemingly distinct approaches to policy gradient optimization for the Pass@K objective in reinforcement learning with verifiable rewards: (1) direct REINFORCE-style methods, and (2) advantage-shaping techniques that directly modify GRPO. We show that these are two sides of the same coin. By reverse-engineering existing advantage-shaping algorithms, we reveal that they implicitly optimize surrogate rewards. We specifically interpret practical "hard-example up-weighting" modifications to GRPO as reward-level regularization. Conversely, starting from surrogate reward objectives, we provide a simple recipe for deriving both existing and new advantage-shaping methods. This perspective provides a lens for RLVR policy gradient optimization beyond our original motivation of Pass@K.
Authors: Kathryn Lindsey, Govind Menon
Abstract: We use geometric invariant theory (GIT) to study the deep linear network (DLN). The Kempf-Ness theorem is used to establish that the $L^2$ regularizer is minimized on the balanced manifold. We introduce related balancing flows using the Riemannian geometry of fibers. The balancing flow defined by the $L^2$ regularizer is shown to converge to the balanced manifold at a uniform exponential rate. The balancing flow defined by the squared moment map is computed explicitly and shown to converge globally. This framework allows us to decompose the training dynamics into two distinct gradient flows: a regularizing flow on fibers and a learning flow on the balanced manifold. It also provides a common mathematical framework for balancedness in deep learning and linear systems theory. We use this framework to interpret balancedness in terms of fast-slow systems, model reduction and Bayesian principles.
Authors: Zihan Li, Mingyang Wan, Mingyu Gao, Xishi Tai, Zhongshan Chen, Xiangke Wang, Feifan Zhang
Abstract: Covalent organic frameworks (COFs) are promising adsorbents for gas adsorption and separation, while identifying the optimal structures among their vast design space requires efficient high-throughput screening. Conventional machine-learning predictors rely heavily on specific gas-related features. However, these features are time-consuming and limit scalability, leading to inefficiency and labor-intensive processes. Herein, a universal COFs adsorption prediction framework (COFAP) is proposed, which can extract multi-modal structural and chemical features through deep learning, and fuse these complementary features via cross-modal attention mechanism. Without relying on explicit gas-specific thermodynamic descriptors, COFAP achieves state-of-the-art prediction performance on the hypoCOFs dataset under the conditions investigated in this study, outperforming existing approaches. Based on COFAP, we also found that high-performing COFs for gas separation concentrate within a narrow range of pore size and surface area. A weight-adjustable prioritization scheme is also developed to enable flexible, application-specific ranking of candidate COFs for researchers. Superior efficiency and accuracy render COFAP directly deployable in crystalline porous materials.
Authors: Wenwen Si, Sooyong Jang, Insup Lee, Osbert Bastani
Abstract: While large language models (LLMs) have recently made tremendous progress towards solving challenging AI problems, they have done so at increasingly steep computational and API costs. We propose a novel strategy where we combine multiple LLM models with varying cost/accuracy tradeoffs in an agentic manner, where models and tools are run in sequence as determined by an orchestration model to minimize cost subject to a user-specified level of reliability; this constraint is formalized using conformal prediction to provide guarantees. To solve this problem, we propose Conformal Constrained Policy Optimization (CCPO), a training paradigm that integrates constrained policy optimization with off-policy reinforcement learning and recent advances in online conformal prediction. CCPO jointly optimizes a cost-aware policy (score function) and an adaptive threshold. Across two multi-hop question answering benchmarks, CCPO achieves up to a 30% cost reduction compared to other cost-aware baselines and LLM-guided methods without compromising reliability. Our approach provides a principled and practical framework for deploying LLM agents that are significantly more cost-effective while maintaining reliability.
Authors: Zhihui Tian, Ethan Suwandi, Tomas Oppelstrup, Vasily V. Bulatov, Joel B. Harley, Fei Zhou
Abstract: Graph neural networks (GNN) have emerged as a promising machine learning method for microstructure simulations such as grain growth. However, accurate modeling of realistic grain boundary networks requires large simulation cells, which GNN has difficulty scaling up to. To alleviate the computational costs and memory footprint of GNN, we propose a hybrid architecture combining a convolutional neural network (CNN) based bijective autoencoder to compress the spatial dimensions, and a GNN that evolves the microstructure in the latent space of reduced spatial sizes. Our results demonstrate that the new design significantly reduces computational costs with using fewer message passing layer (from 12 down to 3) compared with GNN alone. The reduction in computational cost becomes more pronounced as the spatial size increases, indicating strong computational scalability. For the largest mesh evaluated (160^3), our method reduces memory usage and runtime in inference by 117x and 115x, respectively, compared with GNN-only baseline. More importantly, it shows higher accuracy and stronger spatiotemporal capability than the GNN-only baseline, especially in long-term testing. Such combination of scalability and accuracy is essential for simulating realistic material microstructures over extended time scales. The improvements can be attributed to the bijective autoencoder's ability to compress information losslessly from spatial domain into a high dimensional feature space, thereby producing more expressive latent features for the GNN to learn from, while also contributing its own spatiotemporal modeling capability. The training was optimized to learn from the stochastic Potts Monte Carlo method. Our findings provide a highly scalable approach for simulating grain growth.
Authors: James R. M. Black, Moritz S. Hanke, Aaron Maiwald, Tina Hernandez-Boussard, Oliver M. Crook, Jaspreet Pannu
Abstract: Novel deep learning architectures are increasingly being applied to biological data, including genetic sequences. These models, referred to as genomic language models (gLMs), have demonstrated impressive predictive and generative capabilities, raising concerns that such models may also enable misuse, for instance via the generation of genomes for human-infecting viruses. These concerns have catalyzed calls for risk mitigation measures. The de facto mitigation of choice is filtering of pretraining data (i.e., removing viral genomic sequences from training datasets) in order to limit gLM performance on virus-related tasks. However, it is not currently known how robust this approach is for securing open-source models that can be fine-tuned using sensitive pathogen data. Here, we evaluate a state-of-the-art gLM, Evo 2, and perform fine-tuning using sequences from 110 harmful human-infecting viruses to assess the rescue of misuse-relevant predictive capabilities. The fine-tuned model exhibited reduced perplexity on unseen viral sequences relative to 1) the pretrained model and 2) a version fine-tuned on bacteriophage sequences. The model fine-tuned on human-infecting viruses also identified immune escape variants from SARS-CoV-2 (achieving an AUROC of 0.6), despite having no exposure to SARS-CoV-2 sequences during fine-tuning. This work demonstrates that data exclusion might be circumvented by fine-tuning approaches that can, to some degree, rescue misuse-relevant capabilities of gLMs. We highlight the need for safety frameworks for gLMs and outline further work needed on evaluations and mitigation measures to enable the safe deployment of gLMs.
Authors: Hans Gundlach, Jayson Lynch, Matthias Mertens, Neil Thompson
Abstract: Language models have seen enormous progress on advanced benchmarks in recent years, but much of this progress has only been possible by using more costly models. Benchmarks may therefore present a warped picture of progress in practical capabilities *per dollar*. To remedy this, we use data from Artificial Analysis and Epoch AI to form the largest dataset of current and historical prices to run benchmarks to date. We find that the price for a given level of benchmark performance has decreased remarkably fast, around $5\times$ to $10\times$ per year, for frontier models on knowledge, reasoning, math, and software engineering benchmarks. These reductions in the cost of AI inference are due to economic forces, hardware efficiency improvements, and algorithmic efficiency improvements. Isolating out open models to control for competition effects and dividing by hardware price declines, we estimate that algorithmic efficiency progress is around $3\times$ per year. However, at the same time, the price of running frontier models is rising between $3\times$ to $18\times$ per year due to bigger models and larger reasoning demands. Finally, we recommend that evaluators both publicize and take into account the price of benchmarking as an essential part of measuring the real-world impact of AI.
Authors: Julian Evan Chrisnanto, Nurfauzi Fadillah, Yulison Herry Chrisnanto
Abstract: Physics-Informed Neural Networks (PINNs) have emerged as a powerful, mesh-free paradigm for solving partial differential equations (PDEs). However, they notoriously struggle with stiff, multi-scale, and nonlinear systems due to the inherent spectral bias of standard multilayer perceptron (MLP) architectures, which prevents them from adequately representing high-frequency components. In this work, we introduce the Adaptive Spectral Physics-Enabled Network (ASPEN), a novel architecture designed to overcome this critical limitation. ASPEN integrates an adaptive spectral layer with learnable Fourier features directly into the network's input stage. This mechanism allows the model to dynamically tune its own spectral basis during training, enabling it to efficiently learn and represent the precise frequency content required by the solution. We demonstrate the efficacy of ASPEN by applying it to the complex Ginzburg-Landau equation (CGLE), a canonical and challenging benchmark for nonlinear, stiff spatio-temporal dynamics. Our results show that a standard PINN architecture catastrophically fails on this problem, diverging into non-physical oscillations. In contrast, ASPEN successfully solves the CGLE with exceptional accuracy. The predicted solution is visually indistinguishable from the high-resolution ground truth, achieving a low median physics residual of 5.10 x 10^-3. Furthermore, we validate that ASPEN's solution is not only pointwise accurate but also physically consistent, correctly capturing emergent physical properties, including the rapid free energy relaxation and the long-term stability of the domain wall front. This work demonstrates that by incorporating an adaptive spectral basis, our framework provides a robust and physically-consistent solver for complex dynamical systems where standard PINNs fail, opening new options for machine learning in challenging physical domains.
Authors: Sanjeev Shrestha, Rahul Dubey, Hui Liu
Abstract: With the increasing complexity of black-box machine learning models and their adoption in high-stakes areas, it is critical to provide explanations for their predictions. Existing local explanation methods lack in generating high-fidelity explanations. This paper proposes a novel local model agnostic explanation method to generate high-fidelity explanations using multivariate adaptive regression splines (MARS) and N-ball sampling strategies. MARS is used to model non-linear local boundaries that effectively captures the underlying behavior of the reference model, thereby enhancing the local fidelity. The N-ball sampling technique samples perturbed samples directly from a desired distribution instead of reweighting, leading to further improvement in the faithfulness. The performance of the proposed method was computed in terms of root mean squared error (RMSE) and evaluated on five different benchmark datasets with different kernel width. Experimental results show that the proposed method achieves higher local surrogate fidelity compared to baseline local explanation methods, with an average reduction of 32% in root mean square error, indicating more accurate local approximations of the black-box model. Additionally, statistical analysis shows that across all benchmark datasets, the proposed approach results were statistically significantly better. This paper advances the field of explainable AI by providing insights that can benefit the broader research and practitioner community.
Authors: Kevin Lee, Duncan Smith-Halverson, Pablo Millan Arias
Abstract: Layer-wise Relevance Propagation (LRP) provides principled attribution for neural networks through conservation properties and foundations in Deep Taylor Decomposition. However, existing implementations operate at the module level, requiring architecture-specific propagation rules and model modifications. These limit the generality of target model and sustainability of implementations as architectures evolve. We introduce DynamicLRP, a model-agnostic LRP framework operating at the tensor operation level. By decomposing attribution to individual operations within computation graphs and introducing a novel mechanism for deferred activation resolution, named the Promise System, our approach achieves true architecture agnosticity while maintaining LRP's theoretical guarantees. This design operates independently of backpropagation machinery, requiring no model modification, enabling side-by-side execution with gradient backpropagation. Being based on computation graphs, this method is theoretically extensible to other deep learning libraries that support auto-differentiation. We demonstrate faithfulness matching or exceeding specialized implementations (1.77 vs 1.69 ABPC on VGG, equivalent performance on ViT, 93.70% and 95.06% top-1 attribution accuracy for explaining RoBERTa-large and Flan-T5-large answers on SQuADv2, respectively) while maintaining practical efficiency on models with 100M-1B parameters. We achieved 99.92% node coverage across 31,465 computation graph nodes from 15 diverse architectures, including state-space models (Mamba), audio transformers (Whisper), and multimodal systems (DePlot) without any model-specific code with rules for 47 fundamental operations implemented. Our operation-level decomposition and Promise System establish a sustainable, extensible foundation for LRP across evolving architectures. All code is available at https://github.com/keeinlev/dynamicLRP .
Authors: L\'ea Bohbot, Cyril Letrouit, Gabriel Peyr\'e, Fran\c{c}ois-Xavier Vialard
Abstract: As context windows in large language models continue to expand, it is essential to characterize how attention behaves at extreme sequence lengths. We introduce token-sample complexity: the rate at which attention computed on $n$ tokens converges to its infinite-token limit. We estimate finite-$n$ convergence bounds at two levels: pointwise uniform convergence of the attention map, and convergence of moments for the transformed token distribution. For compactly supported (and more generally sub-Gaussian) distributions, our first result shows that the attention map converges uniformly on a ball of radius $R$ at rate $C(R)/\sqrt{n}$, where $C(R)$ grows exponentially with $R$. For large $R$, this estimate loses practical value, and our second result addresses this issue by establishing convergence rates for the moments of the transformed distribution (the token output of the attention layer). In this case, the rate is $C'(R)/n^{\beta}$ with $\beta<\tfrac{1}{2}$, and $C'(R)$ depends polynomially on the size of the support of the distribution. The exponent $\beta$ depends on the attention geometry and the spectral properties of the tokens distribution. We also examine the regime in which the attention parameter tends to infinity and the softmax approaches a hardmax, and in this setting, we establish a logarithmic rate of convergence. Experiments on synthetic Gaussian data and real BERT models on Wikipedia text confirm our predictions.
Authors: Julian Kleutgens, Claudio Battiloro, Lingkai Kong, Benjamin Grewe, Francesca Dominici, Mauricio Tec
Abstract: Discrete diffusion models (DMs) have achieved strong performance in language and other discrete domains, offering a compelling alternative to autoregressive modeling. Yet this performance typically depends on large training datasets, challenging the performance of DMs in small-data regimes -- common under real-world constraints. Aimed at this challenge, recent work in continuous DMs suggests that transfer learning via classifier ratio-based guidance can adapt a pretrained DM to a related target distribution, often outperforming alternatives such as full-weight fine-tuning on the target data. By contrast, transfer learning for discrete DMs remains unexplored. We address this gap by exploring practical analogues of ratio-based transfer learning for discrete DMs. Our theoretical analysis shows that a direct extension of existing ratio-based guidance is computationally prohibitive, scaling with vocabulary size. To overcome this limitation, we introduce a scheduling mechanism that yields a practical algorithm, Guided Transfer Learning for discrete diffusion models (GTL). GTL enables sampling from a target distribution without modifying the pretrained denoiser and reduces the cost to linear scaling in vocabulary size, which in turn supports longer sequence generation. We evaluate GTL on sequential data, including synthetic Markov chains and language modeling tasks, and provide a detailed empirical analysis of its behavior. The results highlight a clear trade-off: when target datasets are large, weight fine-tuning is often preferable, whereas GTL becomes increasingly effective as target data shrinks. Finally, we experimentally demonstrate a key failure mode of GTL: when the source and target distributions overlap poorly, the ratio-based classifier required for guidance becomes unreliable, limiting transfer performance.
Authors: Khawla Elhadri, J\"org Schl\"otterer, Christin Seifert
Abstract: In data-driven applications relying on tabular data, where interpretability is key, machine learning models such as decision trees and linear regression are applied. Although neural networks can provide higher predictive performance, they are not used because of their blackbox nature. In this work, we present XNNTab, a neural architecture that combines the expressiveness of neural networks and interpretability. XNNTab first learns highly non-linear feature representations, which are decomposed into monosemantic features using a sparse autoencoder (SAE). These features are then assigned human-interpretable concepts, making the overall model prediction intrinsically interpretable. XNNTab outperforms interpretable predictive models, and achieves comparable performance to its non-interpretable counterparts.
Authors: Gangxiong Zhang, Yongchao Long, Yuxi Zhou, Yong Zhang, Shenda Hong
Abstract: Accurately predicting mortality risk in intensive care unit (ICU) patients is essential for clinical decision-making. Although large language models (LLMs) show strong potential in structured medical prediction tasks, their outputs may exhibit biases related to demographic attributes such as sex, age, and race, limiting their reliability in fairness-critical clinical settings. Existing debiasing methods often degrade predictive performance, making it difficult to balance fairness and accuracy. In this study, we systematically analyze fairness issues in LLM-based ICU mortality prediction and propose a clinically adaptive prompting framework that improves both performance and fairness without model retraining. We first design a multi-dimensional bias assessment scheme to identify subgroup disparities. Based on this, we introduce CAse Prompting (CAP), a training-free framework that integrates existing debiasing strategies and further guides models using similar historical misprediction cases paired with correct outcomes to correct biased reasoning. We evaluate CAP on the MIMIC-IV dataset. Results show that AUROC improves from 0.806 to 0.873 and AUPRC from 0.497 to 0.694. Meanwhile, prediction disparities are substantially reduced across demographic groups, with reductions exceeding 90% in sex and certain White-Black comparisons. Feature reliance analysis further reveals highly consistent attention patterns across groups, with similarity above 0.98. These findings demonstrate that fairness and performance in LLM-based clinical prediction can be jointly optimized through carefully designed prompting, offering a practical paradigm for developing reliable and equitable clinical decision-support systems.
Authors: Yongwei Zhang, Yuanzhe Xing, Quanyi Liang, Quan Quan, Zhikun She
Abstract: For stabilizing control tasks, model-free reinforcement learning (RL) approaches face numerous challenges, particularly regarding the issues of effectiveness and efficiency in complex high-dimensional environments with limited training data. To address these challenges, we propose Multi-Step Actor-Critic Learning with Lyapunov Certificates (MSACL), a novel approach that integrates exponential stability into off-policy maximum entropy reinforcement learning (MERL). In contrast to existing RL-based approaches that depend on elaborate reward engineering and single-step constraints, MSACL adopts intuitive reward design and exploits multi-step samples to enable exploratory actor-critic learning. Specifically, we first introduce Exponential Stability Labels (ESLs) to categorize training samples and propose a $\lambda$-weighted aggregation mechanism to learn Lyapunov certificates. Based on these certificates, we further design a stability-aware advantage function to guide policy optimization, thereby promoting rapid Lyapunov descent and robust state convergence. We evaluate MSACL across six benchmarks, comprising four stabilizing and two high-dimensional tracking tasks. Experimental results demonstrate its consistent performance improvements over both standard RL baselines and state-of-the-art Lyapunov-based RL algorithms. Beyond rapid convergence, MSACL exhibits robustness against environmental uncertainties and generalization to unseen reference signals. The source code and benchmarking environments are available at \href{https://github.com/YuanZhe-Xing/MSACL}{https://github.com/YuanZhe-Xing/MSACL}.
URLs: https://github.com/YuanZhe-Xing/MSACL, https://github.com/YuanZhe-Xing/MSACL
Authors: Julian Evan Chrisnanto, Salsabila Rahma Alia, Nurfauzi Fadillah, Yulison Herry Chrisnanto
Abstract: Simulating nonlinear reaction-diffusion dynamics on complex, non-Euclidean manifolds remains a fundamental challenge in computational morphogenesis, constrained by high-fidelity mesh generation costs and symplectic drift in discrete time-stepping schemes. This study introduces the Intrinsic-Metric Physics-Informed Neural Network (IM-PINN), a mesh-free geometric deep learning framework that solves partial differential equations directly in the continuous parametric domain. By embedding the Riemannian metric tensor into the automatic differentiation graph, our architecture analytically reconstructs the Laplace-Beltrami operator, decoupling solution complexity from geometric discretization. We validate the framework on a "Stochastic Cloth" manifold with extreme Gaussian curvature fluctuations ($K \in [-2489, 3580]$), where traditional adaptive refinement fails to resolve anisotropic Turing instabilities. Using a dual-stream architecture with Fourier feature embeddings to mitigate spectral bias, the IM-PINN recovers the "splitting spot" and "labyrinthine" regimes of the Gray-Scott model. Benchmarking against the Surface Finite Element Method (SFEM) reveals superior physical rigor: the IM-PINN achieves global mass conservation error of $\mathcal{E}_{mass} \approx 0.157$ versus SFEM's $0.258$, acting as a thermodynamically consistent global solver that eliminates mass drift inherent in semi-implicit integration. The framework offers a memory-efficient, resolution-independent paradigm for simulating biological pattern formation on evolving surfaces, bridging differential geometry and physics-informed machine learning.
Authors: Amin Abyaneh, Charlotte Morissette, Mohamad H. Danesh, Anas El Houssaini, David Meger, Gregory Dudek, Hsiu-Chin Lin
Abstract: Diffusion policies have emerged as powerful generative models for offline policy learning, whose sampling process can be rigorously characterized by a score function guiding a stochastic differential equation (SDE). However, the same score-based SDE modeling that grants diffusion policies the flexibility to learn diverse behavior also incurs solver and score-matching errors, large data requirements, and inconsistencies in action generation. While less critical in image generation, these inaccuracies compound and lead to failure in continuous control settings. We introduce contractive diffusion policies (CDPs) to induce contractive behavior in the diffusion sampling dynamics. Contraction pulls nearby flows closer to enhance robustness against solver and score-matching errors while reducing unwanted action variance. We develop an in-depth theoretical analysis along with a practical implementation recipe to incorporate CDPs into existing diffusion policy architectures with minimal modification and computational cost. We evaluate CDPs for offline learning by conducting extensive experiments in simulation and real-world settings. Across benchmarks, CDPs often outperform baseline policies, with pronounced benefits under data scarcity.
Authors: Yi Gu, Lingyou Pang, Xiangkun Ye, Tianyu Wang, Jianyu Lin, Carey E. Priebe, Alexander Aue
Abstract: The rapid adoption of synthetic data for training Large Language Models (LLMs) has introduced the technical challenge of "model collapse"-a degenerative process where recursive training on model-generated content leads to a contraction of distributional variance and representational quality. While the phenomenology of collapse is increasingly evident, rigorous methods to quantify and predict its onset in high-dimensional spaces remain elusive. In this paper, we introduce SIGMA (Spectral Inequalities for Gram Matrix Analysis), a unified framework that benchmarks model collapse through the spectral lens of the embedding Gram matrix. By deriving and utilizing deterministic and stochastic bounds on the matrix's spectrum, SIGMA provides a mathematically grounded metric to track the contraction of the representation space. Crucially, our stochastic formulation enables scalable estimation of these bounds, making the framework applicable to large-scale foundation models where full eigendecomposition is intractable. We demonstrate that SIGMA effectively captures the transition towards degenerate states, offering both theoretical insights into the mechanics of collapse and a practical, scalable tool for monitoring the health of recursive training pipelines.
Authors: Jun Liu, Leo Yu Zhang, Fengpeng Li, Isao Echizen, Jiantao Zhou
Abstract: Hard-label black-box settings, where only top-1 predicted labels are observable, pose a fundamentally constrained yet practically important feedback model for understanding model behavior. A central challenge in this regime is whether meaningful gradient information can be recovered from such discrete responses. In this work, we develop a unified theoretical perspective showing that a wide range of existing sign-flipping hard-label attacks can be interpreted as implicitly approximating the sign of the true loss gradient. This observation reframes hard-label attacks from heuristic search procedures into instances of gradient sign recovery under extremely limited feedback. Motivated by this first-principles understanding, we propose a new attack framework that combines a zero-query frequency-domain initialization with a Pattern-Driven Optimization (PDO) strategy. We establish theoretical guarantees demonstrating that, under mild assumptions, our initialization achieves higher expected cosine similarity to the true gradient sign compared to random baselines, while the proposed PDO procedure attains substantially lower query complexity than existing structured search approaches. We empirically validate our framework through extensive experiments on CIFAR-10, ImageNet, and ObjectNet, covering standard and adversarially trained models, commercial APIs, and CLIP-based models. The results show that our method consistently surpasses SOTA hard-label attacks in both attack success rate and query efficiency, particularly in low-query regimes. Beyond image classification, our approach generalizes effectively to corrupted data, biomedical datasets, and dense prediction tasks. Notably, it also successfully circumvents Blacklight, a SOTA stateful defense, resulting in a $0\%$ detection rate. Our code will be released publicly soon at https://github.com/csjunjun/DPAttack.git.
Authors: Zhipeng Zhang, Xiongfei Su, Kai Li
Abstract: Robust reinforcement learning methods typically focus on suppressing unreliable experiences or corrupted rewards, but they lack the ability to reason about the reliability of their own learning process. As a result, such methods often either overreact to noise by becoming overly conservative or fail catastrophically when uncertainty accumulates. In this work, we propose a meta-cognitive reinforcement learning framework that enables an agent to assess, regulate, and recover its learning behavior based on internally estimated reliability signals. The proposed method introduces a meta-trust variable driven by Value Prediction Error Stability (VPES), which modulates learning dynamics via fail-safe regulation and gradual trust recovery. Experiments on continuous-control benchmarks with reward corruption demonstrate that recovery-enabled meta-cognitive control achieves higher average returns and significantly reduces late-stage training failures compared to strong robustness baselines.
Authors: C. V\'azquez-Garc\'ia, F. J. Mart\'inez-Murcia, F. Segovia Rom\'an, A. Forte, J. Ram\'irez, I. Ill\'an, A. Hern\'andez-Segura, C. Jim\'enez-Mesa, Juan M. G\'orriz
Abstract: High-dimensional neuroimaging data presents challenges for assessing neurodegenerative diseases due to complex non-linear relationships. Variational Autoencoders (VAEs) can encode scans into lower-dimensional latent spaces capturing disease-relevant features. We propose a semi-supervised VAE framework with a flexible similarity regularization term that aligns selected latent variables with clinical or biomarker measures of dementia progression. This allows adapting the similarity metric and supervised variables to specific goals or available data. We demonstrate the approach using PET scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI), guiding the first latent dimension to align with a cognitive score. Using this supervised latent variable, we generate average reconstructions across levels of cognitive impairment. Voxel-wise GLM analysis reveals reduced metabolism in key regions, mainly the hippocampus, and within major Resting State Networks, particularly the Default Mode and Central Executive Networks. The remaining latent variables encode affine transformations and intensity variations, capturing confounds such as inter-subject variability and site effects. Our framework effectively extracts disease-related patterns aligned with established Alzheimer's biomarkers, offering an interpretable and adaptable tool for studying neurodegenerative progression.
Authors: Ian Wu, Yuxiao Qu, Amrith Setlur, Aviral Kumar
Abstract: Large Language Models (LLMs) that can continually improve beyond their training budgets are able to solve increasingly difficult problems by adapting at test time, a property we refer to as extrapolation. However, standard reinforcement learning (RL) operates over fixed problem distributions and training budgets, which limits extrapolation amidst distribution shift at test time. To address this, we introduce RC, an iterative decoding algorithm that replaces standard autoregressive decoding during both training and inference. RC exploits an asymmetry between the response generation and summarization capabilities of LLMs to construct reasoning chains that consistently improve across iterations. Models trained to use RC can extrapolate and continually improve over reasoning horizons more than an order of magnitude longer than those seen during training. Empirically, training a 4B model with RC using a 16k-token training budget improves performance on HMMT 2025 from 40% to nearly 70% with 0.5m tokens at test time, outperforming both comparably sized models and many larger reasoning LLMs. Finally, we also show that models trained with RC can more effectively leverage existing scaffolds to further scale test-time performance, due to the improved summary-conditioned generation abilities learned through training.
Authors: Wonjun Yi, Rismaya Kumar Mishra, Yong-Hwa Park
Abstract: Machine systems inherently generate signals in which fault conditions and various variables influence signals measured from machine system. Although many existing fault classification studies rely solely on direct fault labels, the aforementioned signals naturally embed additional information shaped by other variables. Herein, we leverage this through a multi-task learning (MTL) framework that jointly learns fault conditions and other variables influencing measured signals. Among MTL architectures, cross-talk structures have distinct advantages because they allow for controlled information exchange between tasks through the cross-talk layer while preventing negative transfer, in contrast to shared trunk architectures that often mix incompatible features. We build on our previously introduced residual neural dimension reductor model, and extend its application to two benchmarks where system influenced by multiple variables. The first benchmark is a drone fault dataset, in which machine type and maneuvering direction significantly alter the frequency components of measured signals even under the same drone status. The second benchmark dataset is motor compound fault dataset. In this system, severity of each fault component, inner race fault, outer race fault, misalignment, and unbalance influences measured signal. Across both benchmarks, our residual neural dimension reductor, consistently outperformed single-task models, multi-class models that merge all label combinations, and shared trunk multi-task models.
Authors: Francesco Alesiani, Jonathan Warrell, Tanja Bien, Henrik Christiansen, Matheus Ferraz, Mathias Niepert
Abstract: We propose LOGDIFF (Logical Guidance for the Exact Composition of Diffusion Models), a guidance framework for diffusion models that enables principled constrained generation with complex logical expressions at inference time. We study when exact score-based guidance for complex logical formulas can be obtained from guidance signals associated with atomic properties. First, we derive an exact Boolean calculus that provides a sufficient condition for exact logical guidance. Specifically, if a formula admits a circuit representation in which conjunctions combine conditionally independent subformulas and disjunctions combine subformulas that are either conditionally independent or mutually exclusive, exact logical guidance is achievable. In this case, the guidance signal can be computed exactly from atomic scores and posterior probabilities using an efficient recursive algorithm. Moreover, we show that, for commonly encountered classes of distributions, any desired Boolean formula is compilable into such a circuit representation. Second, by combining atomic guidance scores with posterior probability estimates, we introduce a hybrid guidance approach that bridges classifier guidance and classifier-free guidance, applicable to both compositional logical guidance and standard conditional generation. We demonstrate the effectiveness of our framework on multiple image and protein structure generation tasks.
Authors: Bjarni Haukur Bjarnason, Andr\'e Silva, Martin Monperrus
Abstract: Agentic systems are evaluated on benchmarks where agents interact with environments to solve tasks. Most papers report a pass@1 score computed from a single run per task, assuming this gives a reliable performance estimate. We test this assumption by collecting 60,000 agentic trajectories on SWE-Bench-Verified, spanning three models and two scaffolds. We find substantial variance: single-run pass@1 estimates vary by 2.2 to 6.0 percentage points depending on which run is selected, with standard deviations exceeding 1.5 percentage points even at temperature 0. This variance has critical implications: reported improvements of 2--3 percentage points may reflect evaluation noise rather than genuine algorithmic progress. Through token-level analysis, we show that trajectories diverge early, often within the first few percent of tokens, and that these small differences cascade into different solution strategies. To enable reliable evaluation of agentic systems, we recommend three concrete practices: (1) estimate pass@1 from multiple independent runs per task, especially when measuring small improvements, (2) use statistical power analysis to determine the number of runs needed to detect expected effect sizes, and (3) consider metrics like pass@k (optimistic bound) and pass^k (pessimistic bound) with k>1 to better characterize the full performance envelope. While these practices increase evaluation cost, they are essential for distinguishing genuine scientific progress from statistical noise.
Authors: Yuanfu Wang, Zhixuan Liu, Xiangtian Li, Chaochao Lu, Chao Yang
Abstract: The prevailing paradigm for training large reasoning models--combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR)--is fundamentally constrained by its reliance on high-quality, human-annotated reasoning data and external verifiers. This dependency incurs significant data-collection costs, risks embedding human cognitive biases, and confines the reinforcement learning stage to objectively assessable domains like mathematics and coding, leaving a wide range of unverifiable tasks beyond its scope. To overcome these limitations, we introduce NRT (Native Reasoning Training), a novel framework that cultivates complex reasoning by having the model generate its own reasoning traces using only standard question-answer pairs, thereby obviating the need for expert-written demonstrations. NRT reframes the training problem by treating the reasoning process as a latent variable. It employs a unified training objective that models reasoning as an optimization problem, intrinsically rewarding paths that increase the model's likelihood of producing the ground-truth answer. This unified perspective allows us to analyze intrinsic failure modes of prior methods, such as policy collapse, and systematically design more robust reward aggregation functions, creating a self-reinforcing feedback loop where the model learns to think in ways that resolve its own uncertainty. Empirical evaluation on Llama and Mistral model families demonstrates that NRT achieves state-of-the-art performance among verifier-free methods, significantly outperforming standard SFT baselines and prior verifier-free RL methods. Our approach yields particularly strong performance gains in complex reasoning domains and exhibits high robustness to policy collapse, offering a general, scalable path toward building more powerful and broadly applicable reasoning systems.
Authors: Kenji Fukumizu, Wei Huang, Han Bao, Shuntuo Xu, Nisha Chandramoorthy
Abstract: We reformulate Optimal Transport Conditional Flow Matching (OT-CFM), a class of dynamical generative models, showing that it admits an exact proximal formulation via an extended Brenier potential, without assuming that the target distribution has a density. In particular, the mapping to recover the target point is exactly given by a proximal operator, which yields an explicit proximal expression of the vector field. We also discuss the convergence of minibatch OT-CFM to the population formulation as the batch size increases. Finally, using second epi-derivatives of convex potentials, we prove that, for manifold-supported targets, OT-CFM is terminally normally hyperbolic: after time rescaling, the dynamics contracts exponentially in directions normal to the data manifold while remaining neutral along tangential directions.
Authors: Chethana Prasad Kabgere, Shylaja SS
Abstract: Federated learning over graph-structured data exposes a fundamental mismatch between standard aggregation mechanisms and the operator nature of graph neural networks (GNNs). While federated optimization treats model parameters as elements of a shared Euclidean space, GNN parameters induce graph-dependent message-passing operators whose semantics depend on underlying topology. Under structurally and distributionally heterogeneous client graph distributions, local updates correspond to perturbations of distinct operator manifolds. Linear aggregation of such updates mixes geometrically incompatible directions, producing global models that converge numerically yet exhibit degraded relational behavior. We formalize this phenomenon as a geometric failure of global aggregation in cross-domain federated GNNs, characterized by destructive interference between operator perturbations and loss of coherence in message-passing dynamics. This degradation is not captured by conventional metrics such as loss or accuracy, as models may retain predictive performance while losing structural sensitivity. To address this, we propose GGRS (Global Geometric Reference Structure), a server-side aggregation framework operating on a data-free proxy of operator perturbations. GGRS enforces geometric admissibility via directional alignment, subspace compatibility, and sensitivity control, preserving the structure of the induced message-passing operator.
Authors: Neelay Velingker, Alaia Solko-Breslin, Mayank Keoliya, Seewon Choi, Jiayi Xin, Anika Marathe, Alireza Oraii, Rajat Deo, Sameed Khatana, Rajeev Alur, Mayur Naik, Eric Wong
Abstract: Electrocardiograms (ECG) are electrical recordings of the heart that are critical for diagnosing cardiovascular conditions. ECG language models (ELMs) have recently emerged as a promising framework for ECG classification accompanied by report generation. However, current models cannot forecast future cardiac events despite the immense clinical value for planning earlier intervention. To address this gap, we propose CAMEL, the first ELM that is capable of inference over longer signal durations which enables its forecasting capability. Our key insight is a specialized ECG encoder which enables cross-understanding of ECG signals with text. We train CAMEL using established LLM training procedures, combining LoRA adaptation with a curriculum learning pipeline. Our curriculum includes ECG classification, metrics calculations, and multi-turn conversations to elicit reasoning. CAMEL demonstrates strong zero-shot performance across 6 tasks and 9 datasets, including ECGForecastBench, a new benchmark that we introduce for forecasting arrhythmias. CAMEL is on par with or surpasses ELMs and fully supervised baselines both in- and out-of-distribution, achieving SOTA results on ECGBench (+7.0% absolute average gain) as well as ECGForecastBench (+12.4% over fully supervised models and +21.1% over zero-shot ELMs).
Authors: Dongik Park, Hyunwoo Ryu, Suahn Bae, Keondo Park, Hyung-Sin Kim
Abstract: Imputing missing values in multivariate time series remains challenging, especially under diverse missing patterns and heavy missingness. Existing methods suffer from suboptimal performance as corrupted temporal features hinder effective cross-variable information transfer, amplifying reconstruction errors. Robust imputation requires both extracting temporal patterns from sparse observations within each variable and selectively transferring information across variables--yet current approaches excel at one while compromising the other. We introduce T1 (Time series imputation with 1-to-1 channel-head binding), a CNN-Transformer hybrid architecture that achieves robust imputation through Channel-Head Binding--a mechanism creating one-to-one correspondence between CNN channels and attention heads. This design enables selective information transfer: when missingness corrupts certain temporal patterns, their corresponding attention pathways adaptively down-weight based on remaining observable patterns while preserving reliable cross-variable connections through unaffected channels. Experiments on 11 benchmark datasets demonstrate that T1 achieves state-of-the-art performance, reducing MSE by 46% on average compared to the second-best baseline, with particularly strong gains under extreme sparsity (70% missing ratio). The model generalizes to unseen missing patterns without retraining and uses a consistent hyperparameter configuration across all datasets. The code is available at https://github.com/Oppenheimerdinger/T1.
Authors: Rui Cen (Hunyuan AI Infra Team), QiangQiang Hu (Hunyuan AI Infra Team), Hong Huang (Hunyuan AI Infra Team), Hong Liu (Hunyuan AI Infra Team), Song Liu (Hunyuan AI Infra Team), Xin Luo (Hunyuan AI Infra Team), Lin Niu (Hunyuan AI Infra Team), Yifan Tan (Hunyuan AI Infra Team), Decheng Wu (Hunyuan AI Infra Team), Linchuan Xie (Hunyuan AI Infra Team), Rubing Yang (Hunyuan AI Infra Team), Guanghua Yu (Hunyuan AI Infra Team), Jianchen Zhu (Hunyuan AI Infra Team)
Abstract: This technical report introduces AngelSlim, a comprehensive and versatile toolkit for large model compression developed by the Tencent Hunyuan team. By consolidating cutting-edge algorithms, including quantization, speculative decoding, token pruning, and distillation. AngelSlim provides a unified pipeline that streamlines the transition from model compression to industrial-scale deployment. To facilitate efficient acceleration, we integrate state-of-the-art FP8 and INT8 Post-Training Quantization (PTQ) algorithms alongside pioneering research in ultra-low-bit regimes, featuring HY-1.8B-int2 as the first industrially viable 2-bit large model. Beyond quantization, we propose a training-aligned speculative decoding framework compatible with multimodal architectures and modern inference engines, achieving 1.8x to 2.0x throughput gains without compromising output correctness. Furthermore, we develop a training-free sparse attention framework that reduces Time-to-First-Token (TTFT) in long-context scenarios by decoupling sparse kernels from model architectures through a hybrid of static patterns and dynamic token selection. For multimodal models, AngelSlim incorporates specialized pruning strategies, namely IDPruner for optimizing vision tokens via Maximal Marginal Relevance and Samp for adaptive audio token merging and pruning. By integrating these compression strategies from low-level implementations, AngelSlim enables algorithm-focused research and tool-assisted deployment.
Authors: Deepak Agarwal, Dhyey Dharmendrakumar Mavani, Suyash Gupta, Karthik Sethuraman, Tejas Dharamsi
Abstract: Self-attention is usually described as a flexible, content-adaptive way to mix a token with information from its past. We reinterpret causal self-attention transformers, the backbone of modern foundation models, within a probabilistic framework, much as classical PCA is extended to probabilistic PCA. This reformulation reveals a key structural consequence of the underlying change of variables: a barrier constraint emerges on the parameters of self-attention. The resulting geometry exposes a degeneracy boundary where the attention-induced mapping becomes locally ill-conditioned, yielding a stability-margin interpretation analogous to the margin in support vector machines. This, in turn, naturally gives rise to the concept of support tokens. We further show that causal transformers define a consistent stochastic process over infinite token sequences, providing a rigorous probabilistic foundation for sequence modeling. Building on this view, we derive a Bayesian MAP training objective that requires only a minimal modification to standard LLM training: adding a smooth log-barrier penalty to the usual cross-entropy loss. Empirically, the resulting training objective improves robustness to input perturbations and sharpens the margin geometry of the learned representations without sacrificing out-of-sample accuracy.
Authors: Hongyi Zhou, Kai Ye, Erhan Xu, Jin Zhu, Ying Yang, Shijin Gong, Chengchun Shi
Abstract: Group relative policy optimization (GRPO), a core methodological component of DeepSeekMath and DeepSeek-R1, has emerged as a cornerstone for scaling reasoning capabilities of large language models. Despite its widespread adoption and the proliferation of follow-up works, the theoretical properties of GRPO remain less studied. This paper provides a unified framework to understand GRPO through the lens of classical U-statistics. We demonstrate that the GRPO policy gradient is inherently a U-statistic, allowing us to characterize its mean squared error (MSE), derive the finite-sample error bound and asymptotic distribution of the suboptimality gap for its learned policy. Our findings reveal that GRPO is asymptotically equivalent to an oracle policy gradient algorithm -- one with access to a value function that quantifies the goodness of its learning policy at each training iteration -- and achieves asymptotically optimal performance within a broad class of policy gradient algorithms. Furthermore, we establish a universal scaling law that offers principled guidance for selecting the optimal group size. Empirical experiments further validate our theoretical findings, demonstrating that the optimal group size is universal, and verify the oracle property of GRPO.
Authors: Tanishq Kumar, Tri Dao, Avner May
Abstract: Autoregressive decoding is bottlenecked by its sequential nature. Speculative decoding has become a standard way to accelerate inference by using a fast draft model to predict upcoming tokens from a slower target model, and then verifying them in parallel with a single target model forward pass. However, speculative decoding itself relies on a sequential dependence between speculation and verification. We introduce speculative speculative decoding (SSD) to parallelize these operations. While a verification is ongoing, the draft model predicts likely verification outcomes and prepares speculations pre-emptively for them. If the actual verification outcome is then in the predicted set, a speculation can be returned immediately, eliminating drafting overhead entirely. We identify three key challenges presented by speculative speculative decoding, and suggest principled methods to solve each. The result is Saguaro, an optimized SSD algorithm. Our implementation is on average 30% faster than optimized speculative decoding baselines and up to 5x faster than autoregressive decoding with open source inference engines.
Authors: Shailesh Sridhar, Anton Xue, Eric Wong
Abstract: Popular explanation methods often produce unreliable feature importance scores due to missingness bias, a systematic distortion that arises when models are probed with ablated, out-of-distribution inputs. Existing solutions treat this as a deep representational flaw that requires expensive retraining or architectural modifications. In this work, we challenge this assumption and show that missingness bias can be effectively treated as a superficial artifact of the model's output space. We introduce MCal, a lightweight post-hoc method that corrects this bias by fine-tuning a simple linear head on the outputs of a frozen base model. Surprisingly, we find this simple correction consistently reduces missingness bias and is competitive with, or even outperforms, prior heavyweight approaches across diverse medical benchmarks spanning vision, language, and tabular domains.
Authors: Julien Amblard, Niklas Groll, Matthew Tait, Mark Law, G\"urkan Sin, Alessandra Russo
Abstract: Over the past decade, Artificial Intelligence has significantly advanced, mostly driven by large-scale neural approaches. However, in the chemical process industry, where safety is critical, these methods are often unsuitable due to their brittleness, and lack of explainability and interpretability. Furthermore, open-source real-world datasets containing historical failures are scarce in this domain. In this paper, we investigate an approach for predicting failures in chemical processes using symbolic machine learning and conduct a feasibility study in the context of an ethylene oxidation process. Our method builds on a state-of-the-art symbolic machine learning system capable of learning predictive models in the form of probabilistic rules from context-dependent noisy examples. This system is a general-purpose symbolic learner, which makes our approach independent of any specific chemical process. To address the lack of real-world failure data, we conduct our feasibility study leveraging data generated from a chemical process simulator. Experimental results show that symbolic machine learning can outperform baseline methods such as random forest and multilayer perceptron, while preserving interpretability through the generation of compact, rule-based predictive models. Finally, we explain how such learned rule-based models could be integrated into agents to assist chemical plant operators in decision-making during potential failures.
Authors: Guangnian Wan, Xinyin Ma, Gongfan Fang, Xinchao Wang
Abstract: Understanding and addressing potential safety alignment risks in large language models (LLMs) is critical for ensuring their safe and trustworthy deployment. In this paper, we highlight an insidious safety threat: a compromised LLM can maintain a facade of proper safety alignment while covertly generating harmful content. To achieve this, we finetune the model to understand and apply a steganographic technique. At inference time, we input a prompt that contains a steganographically embedded malicious target question along with a plaintext cover question. The model, in turn, produces a target response similarly embedded within a benign-looking cover response. In this process, human observers only see the model being prompted with a cover question and generating a corresponding cover response, while the malicious content is hidden from view. We demonstrate this invisible safety threat on GPT-4.1 despite the OpenAI finetuning API's safeguards. The finetuned model produces steganographic malicious outputs in response to hidden malicious prompts, while the user interface displays only a fully benign cover interaction. We also replicate the attack on three open-source models, Llama-3.3-70B-Instruct, Phi-4, and Mistral-Small-24B-Base-2501, confirming the generality of our method. We quantitatively evaluate our method on the AdvBench dataset, using Llama-Guard-3-8B for content safety classification. Across all four models, all stegotexts containing malicious content are incorrectly classified as safe.
Authors: Zegu Zhang, Jian Zhang
Abstract: Variational autoencoders (VAEs) frequently suffer from posterior collapse, where the latent variables become uninformative as the approximate posterior degenerates to the prior. While recent work has characterized collapse as a phase transition determined by data covariance properties, existing approaches primarily aim to avoid rather than eliminate collapse. We introduce a novel framework that theoretically guarantees non-collapsed solutions by leveraging spherical shell geometry and cluster-aware constraints. Our method transforms data to a spherical shell, computes optimal cluster assignments via K-means, and defines a feasible region between the within-cluster variance $W$ and collapse loss $\delta_{\text{collapse}}$. We prove that when the reconstruction loss is constrained to this region, the collapsed solution is mathematically excluded from the feasible parameter space. \textbf{Critically, we introduce norm constraint mechanisms that ensure decoder outputs remain compatible with the spherical shell geometry without restricting representational capacity.} Unlike prior approaches, our method provides a strict theoretical guarantee with minimal computational overhead without imposing constraints on decoder outputs. Experiments on synthetic and real-world datasets demonstrate 100\% collapse prevention under conditions where conventional VAEs completely fail, with reconstruction quality matching or exceeding state-of-the-art methods. Our approach requires no explicit stability conditions (e.g., $\sigma^2 < \lambda_{\max}$) and works with arbitrary neural architectures. The code is available at https://github.com/tsegoochang/spherical-vae-with-Cluster.
URLs: https://github.com/tsegoochang/spherical-vae-with-Cluster.
Authors: Bo Hu, Jose C Principe
Abstract: Statistical dependence measures like mutual information is ideal for analyzing autoencoders, but it can be ill-posed for deterministic, static, noise-free networks. We adopt the variational (Gaussian) formulation that makes dependence among inputs, latents, and reconstructions measurable, and we propose a stable neural dependence estimator based on an orthonormal density-ratio decomposition. Unlike MINE, our method avoids input concatenation and product-of-marginals re-pairing, reducing computational cost and improving stability. We introduce an efficient NMF-like scalar cost and demonstrate empirically that assuming Gaussian noise to form an auxiliary variable enables meaningful dependence measurements and supports quantitative feature analysis, with a sequential convergence of singular values.
Authors: Chenghan Wu, Zongmin Yu, Boai Sun, Liu Yang
Abstract: In-context operator learning enables neural networks to infer solution operators from contextual examples without weight updates. While prior work has demonstrated the effectiveness of this paradigm in leveraging vast datasets, a systematic comparison against single-operator learning using identical training data has been absent. We address this gap through controlled experiments comparing in-context operator learning against classical operator learning (single-operator models trained without contextual examples), under the same training steps and dataset. To enable this investigation on real-world spatiotemporal systems, we propose GICON (Graph In-Context Operator Network), combining graph message passing for geometric generalization with example-aware positional encoding for cardinality generalization. Experiments on air quality prediction across two Chinese regions show that in-context operator learning outperforms classical operator learning on complex tasks, generalizing across spatial domains and scaling robustly from few training examples to 100 at inference.
Authors: Wanyin Wu, Kanxue Li, Baosheng Yu, Haoyun Zhao, Yibing Zhan, Dapeng Tao, Hua Jin
Abstract: Accurate prediction of surgical duration is pivotal for hospital resource management. Although recent supervised learning approaches-from machine learning (ML) to fine-tuned large language models (LLMs)-have shown strong performance, they remain constrained by the need for high-quality labeled data and computationally intensive training. In contrast, zero-shot LLM inference offers a promising training-free alternative but it lacks grounding in institution-specific clinical context (e.g., local demographics and case-mix distributions), making its predictions clinically misaligned and prone to instability. To address these limitations, we present PREBA, a retrieval-augmented framework that integrates PCA-weighted retrieval and Bayesian averaging aggregation to ground LLM predictions in institution-specific clinical evidence and statistical priors. The core of PREBA is to construct an evidence-based prompt for the LLM, comprising (1) the most clinically similar historical surgical cases and (2) clinical statistical priors. To achieve this, PREBA first encodes heterogeneous clinical features into a unified representation space enabling systematic retrieval. It then performs PCA-weighted retrieval to identify clinically relevant historical cases, which form the evidence context supplied to the LLM. Finally, PREBA applies Bayesian averaging to fuse multi-round LLM predictions with population-level statistical priors, yielding calibrated and clinically plausible duration estimates. We evaluate PREBA on two real-world clinical datasets using three state-of-the-art LLMs, including Qwen3, DeepSeek-R1, and HuatuoGPT-o1. PREBA significantly improves performance-for instance, reducing MAE by up to 40% and raising R^2 from -0.13 to 0.62 over zero-shot inference-and it achieves accuracy competitive with supervised ML methods, demonstrating strong effectiveness and generalization.
Authors: Maria Rosaria Briglia, Simone Facchiano, Paolo Cursi, Alessio Sampieri, Emanuele Rodol\`a, Guido Maria D'Amely di Melendugno, Luca Franco, Fabio Galasso, Iacopo Masi
Abstract: As modern text-to-image (T2I) models draw closer to synthesizing highly realistic content, the threat of unsafe content generation grows, and it becomes paramount to exercise control. Existing approaches steer these models by applying Euclidean adjustments to text embeddings, redirecting the generation away from unsafe concepts. In this work, we introduce hyperbolic control (HyCon): a novel control mechanism based on parallel transport that leverages semantically aligned hyperbolic representation space to yield more expressive and stable manipulation of concepts. HyCon reuses off-the-shelf generative models and a state-of-the-art hyperbolic text encoder, linked via a lightweight adapter. HyCon achieves state-of-the-art results across four safety benchmarks and four T2I backbones, showing that hyperbolic steering is a practical and flexible approach for more reliable T2I generation.
Authors: Eran Rosenbluth
Abstract: We define a generic class of functions that captures most conceivable aggregations for Message-Passing Graph Neural Networks (MP-GNNs), and prove that any MP-GNN model with such aggregations induces only a polynomial number of equivalence classes on all graphs - while the number of non-isomorphic graphs is doubly-exponential (in number of vertices). Adding a familiar perspective, we observe that merely 2-iterations of Color Refinement (CR) induce at least an exponential number of equivalence classes, making the aforementioned MP-GNNs relatively infinitely weaker. Previous results state that MP-GNNs match full CR, however they concern a weak, 'non-uniform', notion of distinguishing-power where each graph size may required a different MP-GNN to distinguish graphs up to that size. Our results concern both distinguishing between non-equivariant vertices and distinguishing between non-isomorphic graphs.
Authors: Arthur Charpentier, Agathe Fernandes Machado
Abstract: Calibration is a conditional property that depends on the information retained by a predictor. We develop decomposition identities for arbitrary proper losses that make this dependence explicit. At any information level $\mathcal A$, the expected loss of an $\mathcal A$-measurable predictor splits into a proper-regret (reliability) term and a conditional entropy (residual uncertainty) term. For nested levels $\mathcal A\subseteq\mathcal B$, a chain decomposition quantifies the information gain from $\mathcal A$ to $\mathcal B$. Applied to classification with features $\boldsymbol{X}$ and score $S=s(\boldsymbol{X})$, this yields a three-term identity: miscalibration, a {\em grouping} term measuring information loss from $\boldsymbol{X}$ to $S$, and irreducible uncertainty at the feature level. We leverage the framework to analyze post-hoc recalibration, aggregation of calibrated models, and stagewise/boosting constructions, with explicit forms for Brier and log-loss.
Authors: Christina Baek, Ricardo Pio Monti, David Schwab, Amro Abbas, Rishabh Adiga, Cody Blakeney, Maximilian B\"other, Paul Burstein, Aldo Gael Carranza, Alvin Deng, Parth Doshi, Vineeth Dorna, Alex Fang, Tony Jiang, Siddharth Joshi, Brett W. Larsen, Jason Chan Lee, Katherine L. Mentzer, Luke Merrick, Haakon Mongstad, Fan Pan, Anshuman Suri, Darren Teh, Jason Telanoff, Jack Urbanek, Zhengping Wang, Josh Wills, Haoli Yin, Aditi Raghunathan, J. Zico Kolter, Bogdan Gaza, Ari Morcos, Matthew Leavitt, Pratyush Maini
Abstract: Real-world model deployments demand strong performance on narrow domains where data is often scarce. Typically, practitioners finetune models to specialize them, but this risks overfitting to the domain and forgetting general knowledge. We study a simple strategy, specialized pretraining (SPT), where a small domain dataset, typically reserved for finetuning, is repeated starting from pretraining as a fraction of the total tokens. Across three specialized domains (ChemPile, MusicPile, and ProofPile), SPT improves domain performance and preserves general capabilities after finetuning compared to standard pretraining. In our experiments, SPT reduces the pretraining tokens needed to reach a given domain performance by up to 1.75x. These gains grow when the target domain is underrepresented in the pretraining corpus: on domains far from web text, a 1B SPT model outperforms a 3B standard pretrained model. Beyond these empirical gains, we derive overfitting scaling laws to guide practitioners in selecting the optimal domain-data repetition for a given pretraining compute budget. Our observations reveal the finetuner's fallacy: while finetuning may appear to be the cheapest path to domain adaptation, introducing specialized domain data during pretraining stretches its utility. SPT yields better specialized domain performance (via reduced overfitting across repeated exposures) and better general domain performance (via reduced forgetting during finetuning), ultimately achieving stronger results with fewer parameters and less total compute when amortized over inference. To get the most out of domain data, incorporate it as early in training as possible.
Authors: Hongjun Wang, Wei Liu, Weibo Gu, Xing Sun, Kai Han
Abstract: Regulating the importance ratio is critical for the training stability of Group Relative Policy Optimization (GRPO) based frameworks. However, prevailing ratio control methods, such as hard clipping, suffer from non-differentiable boundaries and vanishing gradient regions, failing to maintain gradient fidelity. Furthermore, these methods lack a hazard-aware mechanism to adaptively suppress extreme deviations, leaving the optimization process vulnerable to abrupt policy shifts. To address these challenges, we propose Modulated Hazard-aware Policy Optimization (MHPO), a novel framework designed for robust and stable reinforcement learning. The proposed MHPO introduces a Log-Fidelity Modulator (LFM) to map unbounded importance ratios into a bounded, differentiable domain. This mechanism effectively prevents high-variance outlier tokens from destabilizing the loss landscape while ensuring global gradient stability. Complementarily, a Decoupled Hazard Penalty (DHP) integrates cumulative hazard functions from survival analysis to independently regulate positive and negative policy shifts. By shaping the optimization landscape with hazard-aware penalties, the proposed MHPO achieves fine-grained regulation of asymmetric policy shifts simultaneously mitigating mode collapse from over-expansion and preventing policy erosion from catastrophic contraction within a stabilized trust region. Extensive evaluations on diverse reasoning benchmarks across both text-based and vision-language tasks demonstrate that MHPO consistently outperforms existing methods, achieving superior performance while significantly enhancing training stability.
Authors: Bharat Runwal, Ashish Agrawal, Anurag Roy, Rameswar Panda
Abstract: We present PRISM, a comprehensive empirical study of mid-training design choices for large language models. Through controlled experiments across seven base models spanning four families (Granite, LLaMA, Mistral, Nemotron-H), two architecture types (dense Transformer and attention-Mamba hybrid), and scales from 3B to 24B parameters, we show that mid-training on approximately 27B high-quality tokens yields consistent gains of +15 to +40 points on math, +5 to +12 points on code, and +6 to +13 points on science benchmarks while preserving general performance. The full PRISM to RL pipeline improves macro-average across six reasoning benchmarks from under 12 to 29-42 (a 3-4x improvement), whereas RL applied directly to most of the base models remains substantially less effective, with AIME scores near zero. Data composition matters most at mid-training, not RL: including science data during mid-training unlocks +17 to +28 point GPQA-Diamond gains during RL, while changing the RL mix produces less than 2 point differences. Mechanistically, mid-training densely restructures over 90% of model weights, while RL makes sparse, front-loaded refinements to approximately 5% of parameters. Representation analysis (CKA) confirms that RL consistently preserves mid-training's representational geometry (over 0.998 CKA) across architectures. Crucially, RL applies identical weight changes regardless of starting point, yet only succeeds on mid-trained models, consistent with mid-training placing the model in a configuration from which RL can effectively improve performance. Our results demonstrate that retention-aware mid-training is highly effective for reliable reasoning enhancement and provide practical guidance for designing robust mid-training pipelines.
Authors: Alexander K\"ohler, Michael Breu{\ss}
Abstract: In many CAD-based applications, complex geometries are defined by a high number of design parameters. This leads to high-dimensional design spaces that are challenging for downstream engineering processes like simulations, optimization, and design exploration tasks. Therefore, dimension reduction methods such as principal component analysis (PCA) are used. The PCA identifies dominant modes of geometric variation and yields a compact representation of the geometry. While classical PCA excels in the compact representation part, it does not directly recover underlying design parameters of a generated geometry. In this work, we deal with the problem of estimating design parameters from PCA-based representations. Analyzing a recent modification of the PCA dedicated to our field of application, we show that the results are actually identical to the standard PCA. We investigate limitations of this approach and present reasonable conditions under which accurate, interpretable parameter estimation can be obtained. With the help of dedicated experiments, we take a more in-depth look at every stage of the PCA and the possible changes of the geometry during these processes.
Authors: Yifan Zhang, Liang Zheng
Abstract: Bus holding control is challenging due to stochastic traffic and passenger demand. While deep reinforcement learning (DRL) shows promise, standard actor-critic algorithms suffer from Q-value instability in volatile environments. A key source of this instability is the conflation of two distinct uncertainties: aleatoric uncertainty (irreducible noise) and epistemic uncertainty (data insufficiency). Treating these as a single risk leads to value underestimation in noisy states, causing catastrophic policy collapse. We propose a robust ensemble soft actor-critic (RE-SAC) framework to explicitly disentangle these uncertainties. RE-SAC applies Integral Probability Metric (IPM)-based weight regularization to the critic network to hedge against aleatoric risk, providing a smooth analytical lower bound for the robust Bellman operator without expensive inner-loop perturbations. To address epistemic risk, a diversified Q-ensemble penalizes overconfident value estimates in sparsely covered regions. This dual mechanism prevents the ensemble variance from misidentifying noise as a data gap, a failure mode identified in our ablation study. Experiments in a realistic bidirectional bus corridor simulation demonstrate that RE-SAC achieves the highest cumulative reward (approx. -0.4e6) compared to vanilla SAC (-0.55e6). Mahalanobis rareness analysis confirms that RE-SAC reduces Oracle Q-value estimation error by up to 62% in rare out-of-distribution states (MAE of 1647 vs. 4343), demonstrating superior robustness under high traffic variability.
Authors: M. A. Sampaio, P. H. Ranazzi, M. J. Blunt
Abstract: Currently, the methods called Iterative Ensemble Smoothers, especially the method called Ensemble Smoother with Multiple Data Assimilation (ESMDA) can be considered state-of-the-art for history matching in petroleum reservoir simulation. However, this approach has two important limitations: the use of an ensemble with finite size to represent the distributions and the Gaussian assumption in parameter and data uncertainties. This latter is particularly important because many reservoir properties have non-Gaussian distributions. Parameterization involves mapping non-Gaussian parameters to a Gaussian field before the update and then mapping them back to the original domain to forward the ensemble through the reservoir simulator. A promising approach to perform parameterization is through deep learning models. Recent studies have shown that Generative Adversarial Networks (GAN) performed poorly concerning data assimilation, but generated more geologically plausible realizations of the reservoir, while the Variational Autoencoder (VAE) performed better than the GAN in data assimilation, but generated less geologically realistic models. This work is innovative in combining the strengths of both to implement a deep learning model called Variational Autoencoder Generative Adversarial Network (VAE-GAN) integrated with ESMDA. The methodology was applied in two case studies, one case being categorical and the other with continuous values of permeability. Our findings demonstrate that by applying the VAE-GAN model we can obtain high quality reservoir descriptions (just like GANs) and a good history matching on the production curves (just like VAEs) simultaneously.
Authors: Seyed Mahdi B. Azad, Jasper Hoffmann, Iman Nematollahi, Hao Zhu, Abhinav Valada, Joschka Boedecker
Abstract: Forward-backward (FB) representations provide a powerful framework for learning the successor representation (SR) in continuous spaces by enforcing a low-rank factorization. However, a fundamental spectral mismatch often exists between the high-rank transition dynamics of continuous environments and the low-rank bottleneck of the FB architecture, making accurate low-rank representation learning difficult. In this work, we analyze temporal abstraction as a mechanism to mitigate this mismatch. By characterizing the spectral properties of the transition operator, we show that temporal abstraction acts as a low-pass filter that suppresses high-frequency spectral components. This suppression reduces the effective rank of the induced SR while preserving a formal bound on the resulting value function error. Empirically, we show that this alignment is a key factor for stable FB learning, particularly at high discount factors where bootstrapping becomes error-prone. Our results identify temporal abstraction as a principled mechanism for shaping the spectral structure of the underlying MDP and enabling effective long-horizon representations in continuous control.
Authors: Sam Ganzfried
Abstract: Many real-world games contain parameters which can affect payoffs, action spaces, and information states. For fixed values of the parameters, the game can be solved using standard algorithms. However, in many settings agents must act without knowing the values of the parameters that will be encountered in advance. Often the decisions must be made by a human under time and resource constraints, and it is unrealistic to assume that a human can solve the game in real time. We present a new framework that enables human decision makers to make fast decisions without the aid of real-time solvers. We demonstrate applicability to a variety of situations including settings with multiple players and imperfect information.
Authors: Sharan Vaswani, Benjamin Dubois-Taine, Reza Babanezhad
Abstract: We aim to make stochastic gradient descent (SGD) adaptive to (i) the noise $\sigma^2$ in the stochastic gradients and (ii) problem-dependent constants. When minimizing smooth, strongly-convex functions with condition number $\kappa$, we prove that $T$ iterations of SGD with exponentially decreasing step-sizes and knowledge of the smoothness can achieve an $\tilde{O} \left(\exp \left( \frac{-T}{\kappa} \right) + \frac{\sigma^2}{T} \right)$ rate, without knowing $\sigma^2$. In order to be adaptive to the smoothness, we use a stochastic line-search (SLS) and show (via upper and lower-bounds) that SGD with SLS converges at the desired rate, but only to a neighbourhood of the solution. On the other hand, we prove that SGD with an offline estimate of the smoothness converges to the minimizer. However, its rate is slowed down proportional to the estimation error. Next, we prove that SGD with Nesterov acceleration and exponential step-sizes (referred to as ASGD) can achieve the near-optimal $\tilde{O} \left(\exp \left( \frac{-T}{\sqrt{\kappa}} \right) + \frac{\sigma^2}{T} \right)$ rate, without knowledge of $\sigma^2$. When used with offline estimates of the smoothness and strong-convexity, ASGD still converges to the solution, albeit at a slower rate. We empirically demonstrate the effectiveness of exponential step-sizes coupled with a novel variant of SLS.
Authors: Andong Li, Zhaohong Deng, Qiongdan Lou
Abstract: In clinical practice, electroencephalography (EEG) plays an important role in the diagnosis of epilepsy. EEG-based computer-aided diagnosis of epilepsy can greatly improve the ac-curacy of epilepsy detection while reducing the workload of physicians. However, there are many challenges in practical applications for personalized epileptic EEG detection (i.e., training of detection model for a specific person), including the difficulty in extracting effective features from one single view, the undesirable but common scenario of lacking sufficient training data in practice, and the no guarantee of identically distributed training and test data. To solve these problems, we propose a TSK fuzzy system-based epilepsy detection algorithm that integrates multi-view collaborative transfer learning. To address the challenge due to the limitation of single-view features, multi-view learning ensures the diversity of features by extracting them from different views. The lack of training data for building a personalized detection model is tackled by leveraging the knowledge from the source domain (reference scene) to enhance the performance of the target domain (current scene of interest), where mismatch of data distributions between the two domains is resolved with adaption technique based on maximum mean discrepancy. Notably, the transfer learning and multi-view feature extraction are performed at the same time. Furthermore, the fuzzy rules of the TSK fuzzy system equip the model with strong fuzzy logic inference capability. Hence, the proposed method has the potential to detect epileptic EEG signals effectively, which is demonstrated with the positive results from a large number of experiments on the CHB-MIT dataset.
Authors: Yiding Feng, Wei Tang, Haifeng Xu
Abstract: We introduce and study the online Bayesian recommendation problem for a recommender system platform. The platform has the privilege to privately observe a utility-relevant \emph{state} of a product at each round and uses this information to make online recommendations to a stream of myopic users. This paradigm is common in a wide range of scenarios in the current Internet economy. The platform commits to an online recommendation policy that utilizes her information advantage on the product state to persuade self-interested users to follow the recommendation. Since the platform does not know users' preferences or beliefs in advance, we study the platform's online learning problem of designing an adaptive recommendation policy to persuade users while gradually learning users' preferences and beliefs en route. Specifically, we aim to design online learning policies with no \emph{Stackelberg regret} for the platform, i.e., against the optimal benchmark policy in hindsight under the assumption that users will correspondingly adapt their responses to the benchmark policy. Our first result is an online policy that achieves double logarithmic regret dependence on the number of rounds. We also present an information-theoretic lower bound showing that no adaptive online policy can achieve regret with better dependency on the number of rounds. Finally, by formulating the platform's problem as optimizing a linear program with membership oracle access, we present our second online recommendation policy that achieves regret with polynomial dependence on the number of states but logarithmic dependence on the number of rounds.
Authors: Luqin Gan, Lili Zheng, Genevera I. Allen
Abstract: Feature importance inference is critical for the interpretability and reliability of machine learning models. There has been increasing interest in developing model-agnostic approaches to interpret any predictive model, often in the form of feature occlusion or leave-one-covariate-out (LOCO) inference. Existing methods typically make limiting distributional assumptions, modeling assumptions, and require data splitting. In this work, we develop a novel, mostly model-agnostic, and distribution-free inference framework for feature importance in regression or classification tasks that does not require data splitting. Our approach leverages a form of random observation and feature subsampling called minipatch ensembles; it utilizes the trained ensembles for inference and requires no model-refitting or held-out test data after training. We show that our approach enjoys both computational and statistical efficiency as well as circumvents interpretational challenges with data splitting. Further, despite using the same data for training and inference, we show the asymptotic validity of our confidence intervals under mild assumptions. Additionally, we propose theory-supported solutions to critical practical issues including vanishing variance for null features and inference after data-driven tuning for hyperparameters. We demonstrate the advantages of our approach over existing methods on a series of synthetic and real data examples.
Authors: Nikita Puchkin, Artur Goldman, Konstantin Yakovlev, Valeriia Dzis, Uliana Vinogradova
Abstract: We suggest a novel procedure for online change point detection. Our approach expands an idea of maximizing a discrepancy measure between points from pre-change and post-change distributions. This leads to flexible algorithms suitable for both parametric and nonparametric scenarios. We prove non-asymptotic bounds on the average running length of the procedure and its expected detection delay. The efficiency of the algorithm is illustrated with numerical experiments on synthetic and real-world data sets.
Authors: Prateek Jain, Param Pathak, Krishna Bhatia, Shalini Devendrababu, Srinjoy Ganguly
Abstract: In molecular research, the modelling and analysis of molecules through simulation is an important part that has a direct influence on medical development, material science and drug discovery. The processing power required to design protein chains with hundreds of peptides is huge. Classical computing techniques, including state-of-the-art machine learning models being deployed on classical computing machines, have proven to be inefficient in this task, though they have been successful in a limited way. Moreover, current practical implementations, as opposed to purely theoretical modelling, are often infeasible in terms of both time and cost. One of the major areas where quantum machine learning is expected to have a profound advantage over classical algorithms is drug discovery. Quantum generative models have given some promising benefits in recent studies. This paper introduces three novel quantum generative adversarial network (QGAN) architecture variants resulting from different configurations, various quantum circuit layers and patched ansatz. A quantum simulator from Xanadu's PennyLane was utilized for executing the QGAN models trained on the QM9 dataset. Upon evaluation, one of the models, namely the QWGAN-HG-GP (Wasserstein distance with gradient penalty) model, outperformed the other QGAN models in different drug molecule property metrics.
Authors: Xin Guo, Binnan Wang, Ruixun Zhang, Chaoyi Zhao
Abstract: Signatures are iterated path integrals of continuous and discrete-time processes, and their universal nonlinearity linearizes the problem of feature selection in time series data analysis. This paper studies the consistency of signature using Lasso regression, both theoretically and numerically. We establish conditions under which the Lasso regression is consistent both asymptotically and in finite sample. Furthermore, we show that the Lasso regression is more consistent with the It\^o signature for time series and processes that are closer to the Brownian motion and with weaker inter-dimensional correlations, while it is more consistent with the Stratonovich signature for mean-reverting time series and processes. We demonstrate that signature can be applied to learn nonlinear functions and option prices with high accuracy, and the performance depends on properties of the underlying process and the choice of the signature.
Authors: Xiaohan Bie, Manoj Arthanari, Evelin Barbosa de Melo, Baihua Ren, Juancheng Li, Nicolas Brodusch, Stephen Yue, Salim Brahimi, Raynald Gauvin, Jun Song
Abstract: Lower Bainite (LB) and Tempered Martensite (TM) are two common microstructures in modern high-strength steels. LB and TM can render similar mechanical properties for steels, yet LB is often considered superior to TM in resistance to hydrogen embrittlement. Such performance difference has conventionally been attributed to their distinction in certain microstructural features, particularly carbides. The present study developed, MatSegNet, a new contour-aware deep learning (DL) architecture. It is tailored for comprehensive segmentation and quantitative characterization of carbide precipitates with complex contours in high-strength steels, shown to outperform existing state-of-the-art DL architectures. Based on MatSegNet, a high-throughput DL pipeline has been established for precise comparative carbide analysis in LB and TM. The results showed that statistically the two microstructures exhibit similarity in key carbide characteristics with marginal difference, cautioning against the conventional use of carbide orientation as a reliable means to differentiate LB and TM in practice. Through MatSegNet, this work demonstrated the potential of DL to play a critical role in enabling accurate and quantitative microstructure characterization to facilitate development of structure-property relationships for accelerating materials innovation.
Authors: Wanrong Zhu, Zhipeng Lou, Ziyang Wei, Wei Biao Wu
Abstract: Uncertainty quantification for estimation through stochastic optimization solutions in an online setting has gained popularity recently. This paper introduces a novel inference method focused on constructing confidence intervals with efficient computation and fast convergence to the nominal level. Specifically, we propose to use a small number of independent multi-runs to acquire distribution information and construct a t-based confidence interval. Our method requires minimal additional computation and memory beyond the standard updating of estimates, making the inference process almost cost-free. We provide a rigorous theoretical guarantee for the confidence interval, demonstrating that the coverage is approximately exact with an explicit convergence rate and allowing for high confidence level inference. In particular, a new Gaussian approximation result is developed for the online estimators to characterize the coverage properties of our confidence intervals in terms of relative errors. Additionally, our method also allows for leveraging parallel computing to further accelerate calculations using multiple cores. It is easy to implement and can be integrated with existing stochastic algorithms without the need for complicated modifications.
Authors: Weijia Zhang, Jindong Han, Zhao Xu, Hang Ni, Tengfei Lyu, Hao Liu, Hui Xiong
Abstract: The integration of machine learning techniques has become a cornerstone in the development of intelligent urban services, significantly contributing to the enhancement of urban efficiency, sustainability, and overall livability. Recent advancements in foundational models, such as ChatGPT, have introduced a paradigm shift within the fields of machine learning and artificial intelligence. These models, with their exceptional capacity for contextual comprehension, problem-solving, and task adaptability, present a transformative opportunity to reshape the future of smart cities and drive progress toward Urban General Intelligence (UGI). Despite increasing attention to Urban Foundation Models (UFMs), this rapidly evolving field faces critical challenges, including the lack of clear definitions, systematic reviews, and universalizable solutions. To address these issues, this paper first introduces the definition and concept of UFMs and highlights the distinctive challenges involved in their development. Furthermore, we present a data-centric taxonomy that classifies existing research on UFMs according to the various urban data modalities and types. In addition, we propose a prospective framework designed to facilitate the realization of versatile UFMs, aimed at overcoming the identified challenges and driving further progress in this field. Finally, this paper systematically summarizes and discusses existing benchmarks and datasets related to UFMs, and explores the wide-ranging applications of UFMs within urban contexts, illustrating their potential to significantly impact and transform urban systems. A comprehensive collection of relevant research papers and open-source resources have been collated and are continuously updated at: https://github.com/usail-hkust/Awesome-Urban-Foundation-Models.
URLs: https://github.com/usail-hkust/Awesome-Urban-Foundation-Models.
Authors: Quanjun Lang, Xiong Wang, Fei Lu, Mauro Maggioni
Abstract: Modeling multi-agent systems on networks is a fundamental challenge in a wide variety of disciplines. Given data consisting of multiple trajectories, we jointly infer the (weighted) network and the interaction kernel, which determine, respectively, which agents are interacting and the rules of such interactions. Our estimator is based on a non-convex optimization problem, and we investigate two approaches to solve it: one based on an alternating least squares (ALS) algorithm, and another based on a new algorithm named operator regression with alternating least squares (ORALS). Both algorithms are scalable to large ensembles of data trajectories. We establish coercivity conditions guaranteeing identifiability and well-posedness. The ALS algorithm appears statistically efficient and robust even in the small data regime, but lacks performance and convergence guarantees. The ORALS estimator is consistent and asymptotically normal under a coercivity condition. We conduct several numerical experiments ranging from Kuramoto particle systems on networks to opinion dynamics in leader-follower models.
Authors: Tianshu Chu, Dachuan Xu, Wei Yao, Jin Zhang
Abstract: While stochastic bilevel optimization methods have been extensively studied for addressing large-scale nested optimization problems in machine learning, it remains an open question whether the optimal complexity bounds for solving bilevel optimization are the same as those in single-level optimization. Our main result resolves this question: SPABA, an adaptation of the PAGE method for nonconvex optimization in (Li et al., 2021) to the bilevel setting, can achieve optimal sample complexity in both the finite-sum and expectation settings. We show the optimality of SPABA by proving that there is no gap in complexity analysis between stochastic bilevel and single-level optimization when implementing PAGE. Notably, as indicated by the results of (Dagr\'eou et al., 2022), there might exist a gap in complexity analysis when implementing other stochastic gradient estimators, like SGD and SAGA. In addition to SPABA, we propose several other single-loop stochastic bilevel algorithms, that either match or improve the state-of-the-art sample complexity results, leveraging our convergence rate and complexity analysis. Numerical experiments demonstrate the superior practical performance of the proposed methods.
Authors: K. Bharati, Vikesh Siddhu, Krishna Jagannathan
Abstract: Entanglement is a key property of quantum states that acts as a resource for a wide range of tasks in quantum computing. Entanglement detection is a key conceptual and practical challenge. Without adaptive or joint measurements, entanglement detection is constrained by no-go theorems (Lu et al. [Phys. Rev. Lett., 116, 230501 (2016)]), necessitating full state tomography. Batch entanglement detection refers to the problem of identifying all entangled states from amongst a set of $K$ unknown states, which finds applications in quantum information processing. We devise a method for performing batch entanglement detection by measuring a single-parameter family of entanglement witnesses, as proposed by Zhu, Teo, and Englert [Phys. Rev. A, 81, 052339, 2010], followed by a thresholding bandit algorithm on the measurement data. The proposed method can perform batch entanglement detection conclusively when the unknown states are drawn from a practically well-motivated class of two-qubit states $\mathcal{F}$, which includes Depolarised Bell states, Bell diagonal states, etc. Our key novelty lies in drawing a connection between batch entanglement detection and a Thresholding Bandit problem in classical Multi-Armed Bandits (MAB). The connection to the MAB problem also enables us to derive theoretical guarantees on the measurement/sample complexity of the proposed technique. We demonstrate the performance of the proposed method through numerical simulations and an experimental implementation. More broadly, this paper highlights the potential for employing classical machine learning techniques for quantum entanglement detection.
Authors: Zhixu Tao, Rajita Chandak, Sanjeev Kulkarni
Abstract: Data heterogeneity has been a long-standing bottleneck in studying the convergence rates of Federated Learning algorithms. In order to better understand the issue of data heterogeneity, we study the convergence rate of the Expectation-Maximization (EM) algorithm for the Federated Mixture of $K$ Linear Regressions model (FMLR). We completely characterize the convergence rate of the EM algorithm under all regimes of number of clients and number of data points per client, with partial limits in the number of clients. We show that with a signal-to-noise-ratio (SNR) that is atleast of order $\sqrt{K}$, the well-initialized EM algorithm converges to the ground truth under all regimes. We perform experiments on synthetic data to illustrate our results. In line with our theoretical findings, the simulations show that rather than being a bottleneck, data heterogeneity can accelerate the convergence of iterative federated algorithms.
Authors: Ariel Neufeld, Tuan Anh Nguyen
Abstract: We prove that multilevel Picard approximations and deep neural networks with ReLU, leaky ReLU, and softplus activation are capable of approximating solutions of semilinear Kolmogorov PDEs in $L^\mathfrak{p}$-sense, $\mathfrak{p}\in [2,\infty)$, in the case of gradient-independent, Lipschitz-continuous nonlinearities, while the computational effort of the multilevel Picard approximations and the required number of parameters in the neural networks grow at most polynomially in both dimension $d\in \mathbb{N}$ and reciprocal of the prescribed accuracy $\epsilon$.
Authors: Zhexiao Lin, Pablo Crespo
Abstract: Online controlled experiments (A/B testing) are fundamental to data-driven decision-making in many companies. Improving the sensitivity of these experiments under fixed sample size constraints requires reducing the variance of the average treatment effect (ATE) estimator. Existing variance reduction techniques such as CUPED and CUPAC use pre-experiment data, but their effectiveness depends on how predictive those data are for outcomes measured during the experiment. In-experiment data are often more strongly correlated with the outcome, but using arbitrary post-treatment variables can introduce bias. In this paper, we propose a general, robust, and scalable framework that combines both pre-experiment and in-experiment data to achieve variance reduction. Our framework is simple, interpretable, and computationally efficient, making it practical for real-world deployment. We develop the asymptotic theory of the proposed estimator and provide consistent variance estimators. Empirical results from multiple online experiments conducted at Etsy demonstrate substantial additional variance reduction over current pipeline, even when incorporating only a few post-treatment covariates. These findings underscore the effectiveness of our framework in improving experimental sensitivity and accelerating data-driven decision-making.
Authors: Anupreet Porwal, Abel Rodriguez
Abstract: This paper introduces Dirichlet process mixtures of block $g$ priors for model selection and prediction in linear models. These priors are extensions of traditional mixtures of $g$ priors that allow for differential shrinkage for various (data-selected) blocks of parameters while fully accounting for the predictors' correlation structure, providing a bridge between the literatures on model selection and continuous shrinkage priors. We show that Dirichlet process mixtures of block $g$ priors are consistent in various senses and, in particular, that they avoid the conditional Lindley ``paradox'' highlighted by Som et al. (2016). Further, we develop a Markov chain Monte Carlo algorithm for posterior inference that requires only minimal ad-hoc tuning. Finally, we investigate the empirical performance of the prior in various real and simulated datasets. In the presence of a small number of very large effects, Dirichlet process mixtures of block $g$ priors lead to higher power for detecting smaller but significant effects without only a minimal increase in the number of false discoveries.
Authors: Yanan Wang, Zhenghao Fei, Ruichen Li, Yibin Ying
Abstract: Recent breakthroughs in large foundation models have enabled the possibility of transferring knowledge pre-trained on vast datasets to domains with limited data availability. Agriculture is one of the domains that lacks sufficient data. This study proposes a framework to train effective, domain-specific, small models from foundation models without manual annotation. Our approach begins with SDM (Segmentation-Description-Matching), a stage that leverages two foundation models: SAM2 (Segment Anything in Images and Videos) for segmentation and OpenCLIP (Open Contrastive Language-Image Pretraining) for zero-shot open-vocabulary classification. In the second stage, a novel knowledge distillation mechanism is utilized to distill compact, edge-deployable models from SDM, enhancing both inference speed and perception accuracy. The complete method, termed SDM-D (Segmentation-Description-Matching-Distilling), demonstrates strong performance across various fruit detection tasks object detection, semantic segmentation, and instance segmentation) without manual annotation. It nearly matches the performance of models trained with abundant labels. Notably, SDM-D outperforms open-set detection methods such as Grounding SAM and YOLO-World on all tested fruit detection datasets. Additionally, we introduce MegaFruits, a comprehensive fruit segmentation dataset encompassing over 25,000 images, and all code and datasets are made publicly available at https://github.com/AgRoboticsResearch/SDM-D.git.
Authors: Ahmed Akl, Abdelwahed Khamis, Zhe Wang, Ali Cheraghian, Sara Khalifa, Kewen Wang
Abstract: Visual Question Answering (VQA) systems are notoriously brittle under distribution shifts and data scarcity. While previous solutions-such as ensemble methods and data augmentation-can improve performance in isolation, they fail to generalise well across in-distribution (IID), out-of-distribution (OOD), and low-data settings simultaneously. We argue that this limitation stems from the suboptimal training strategies employed. Specifically, treating all training samples uniformly-without accounting for question difficulty or semantic structure-leaves the models vulnerable to dataset biases. Thus, they struggle to generalise beyond the training distribution. To address this issue, we introduce Task-Progressive Curriculum Learning (TPCL)-a simple, model-agnostic framework that progressively trains VQA models using a curriculum built by jointly considering question type and difficulty. Specifically, TPCL first groups questions based on their semantic type (e.g., yes/no, counting) and then orders them using a novel Optimal Transport-based difficulty measure. Without relying on data augmentation or explicit debiasing, TPCL improves generalisation across IID, OOD, and low-data regimes and achieves state-of-the-art performance on VQA-CP v2, VQA-CP v1, and VQA v2. It outperforms the most competitive robust VQA baselines by over 5% and 7% on VQA-CP v2 and v1, respectively, and boosts backbone performance by up to 28.5%.
Authors: Chen Li, Elena Ferro, Corey Lammie, Manuel Le Gallo, Irem Boybat, Bipin Rajendran
Abstract: Analog In-Memory Computing (AIMC) offers a promising solution to the von Neumann bottleneck. However, deploying transformer models on AIMC remains challenging due to their inherent need for flexibility and adaptability across diverse tasks. For the benefits of AIMC to be fully realized, weights of static vector-matrix multiplications must be mapped and programmed to analog devices in a weight-stationary manner. This poses two challenges for adapting a base network to hardware and downstream tasks: (i) conventional analog hardware-aware (AHWA) training requires retraining the entire model, and (ii) reprogramming analog devices is both time- and energy-intensive. To address these issues, we propose Analog Hardware-Aware Low-Rank Adaptation (AHWA-LoRA) training, a novel approach for efficiently adapting transformers to AIMC hardware. AHWA-LoRA training keeps the analog weights fixed as meta-weights and introduces lightweight external LoRA modules for both hardware and task adaptation. We validate AHWA-LoRA training on SQuAD v1.1 and the GLUE benchmark, demonstrate its scalability to larger models, and show its effectiveness in instruction tuning and reinforcement learning. We further evaluate a practical deployment scenario that balances AIMC tile latency with digital LoRA processing using optimized pipeline strategies, with RISC-V-based programmable multi-core accelerators. This hybrid architecture achieves efficient transformer inference with only a 4% per-layer overhead compared to a fully AIMC implementation.
Authors: Othmane Echchabi, Aya Lahlou, Nizar Talty, Josh Malcolm Manto, Tongshu Zheng, Ka Leung Lam
Abstract: Clean water and sanitation are essential for health, well-being, and sustainable development, yet significant global disparities persist. Although the United Nations' Sustainable Development Goal (SDG) 6 clearly defines targets for universal access to clean water and sanitation, limitations in data coverage and openness impede accurate tracking of progress in many countries. To bridge these gaps, this study integrates Afrobarometer survey data, satellite imagery from Sentinel-2, and advanced deep learning techniques using Meta's self-supervised Distillation with No Labels (DINO) model to develop a modeling framework for evaluating access to piped water and sewage systems across diverse African regions. The modeling framework achieved notable accuracy, with over 84% for piped water and 87% for sewage system access classification. When combined with geospatial population data, validation against official statistics from the United Nations Joint Monitoring Program demonstrated high concordance at the national scale (R2 of 0.92 for piped water access and R2 of 0.72 for sewage system access). The national-level estimates can represent SDG Indicators 6.1.1 and 6.2.1. This approach provides policymakers and stakeholders with an effective, scalable, and cost-efficient tool to pinpoint underserved areas requiring targeted intervention. The methodology developed herein can be adapted for assessing other infrastructure-related SDGs, promoting enhanced monitoring and informed decision-making towards achieving global sustainability objectives.
Authors: Tara Radvand, Mojtaba Abdolmaleki, Mohamed Mostagir, Ambuj Tewari
Abstract: Verifying the provenance of content is crucial to the functioning of many organizations, e.g., educational institutions, social media platforms, and firms. This problem is becoming increasingly challenging as text generated by Large Language Models (LLMs) becomes almost indistinguishable from human-generated content. In addition, many institutions use in-house LLMs and want to ensure that external, non-sanctioned LLMs do not produce content within their institutions. In this paper, we answer the following question: Given a piece of text, can we identify whether it was produced by a particular LLM, while ensuring a guaranteed low false positive rate? We model LLM text as a sequential stochastic process with complete dependence on history. We then design zero-shot statistical tests to (i) distinguish between text generated by two different known sets of LLMs $A$ (non-sanctioned) and $B$ (in-house), and (ii) identify whether text was generated by a known LLM or by any unknown model. We prove that the Type I and Type II errors of our test decrease exponentially with the length of the text. We also extend our theory to black-box access via sampling and characterize the required sample size to obtain essentially the same Type I and Type II error upper bounds as in the white-box setting (i.e., with access to $A$). We show the tightness of our upper bounds by providing an information-theoretic lower bound. We next present numerical experiments to validate our theoretical results and assess their robustness in settings with adversarial post-editing. Our work has a host of practical applications in which determining the origin of a text is important and can also be useful for combating misinformation and ensuring compliance with emerging AI regulations. See https://github.com/TaraRadvand74/llm-text-detection for code, data, and an online demo of the project.
Authors: Stella C. Dong
Abstract: Reinsurance optimization is a cornerstone of solvency and capital management, yet traditional approaches often rely on restrictive distributional assumptions and static program designs. We propose a hybrid framework that combines Variational Autoencoders (VAEs) to learn joint distributions of multi-line and multi-year claims data with Proximal Policy Optimization (PPO) reinforcement learning to adapt treaty parameters dynamically. The framework explicitly targets expected surplus under capital and ruin-probability constraints, bridging statistical modeling with sequential decision-making. Using simulated and stress-test scenarios, including pandemic-type and catastrophe-type shocks, we show that the hybrid method produces more resilient outcomes than classical proportional and stop-loss benchmarks, delivering higher surpluses and lower tail risk. Our findings highlight the usefulness of generative models for capturing cross-line dependencies and demonstrate the feasibility of RL-based dynamic structuring in practical reinsurance settings. Contributions include (i) clarifying optimization goals in reinsurance RL, (ii) defending generative modeling relative to parametric fits, and (iii) benchmarking against established methods. This work illustrates how hybrid AI techniques can address modern challenges of portfolio diversification, catastrophe risk, and adaptive capital allocation.
Authors: Erell Gachon, Elsa Cazelles, J\'er\'emie Bigot
Abstract: We consider statistical learning problems in which data are observed as a set of probability measures. Optimal transport (OT) is a popular tool to compare and manipulate such objects, but its computational cost becomes prohibitive when the measures have large support. We study a quantization-based approach in which all input measures are approximated by $K$-point discrete measures sharing a common support. We establish consistency of the resulting quantized measures. We further derive convergence guarantees for several OT-based downstream tasks computed from the quantized measures. Numerical experiments on synthetic and real datasets demonstrate that the proposed approach achieves performance comparable to individual quantization while substantially reducing runtime.
Authors: Miao Li, Michael Klamkin, Russell Bent, Pascal Van Hentenryck
Abstract: Decision makers routinely use constrained optimization technology to plan and operate complex systems like global supply chains or power grids. In this context, practitioners must assess how close a computed solution is to optimality in order to make operational decisions, such as whether the current solution is sufficient or whether additional computation is warranted. A common practice is to evaluate solution quality using dual bounds returned by optimization solvers. While these dual bounds come with certified guarantees, they are often too loose to be practically informative. To this end, this paper introduces a novel conformal prediction framework for tightening loose primal and dual bounds. The proposed method addresses the heteroskedasticity commonly observed in these bounds via selective inference, and further exploits their inherent certified validity to produce tighter, more informative prediction intervals. Finally, numerical experiments on large-scale industrial problems suggest that the proposed approach can provide the same coverage level more efficiently than baseline methods.
Authors: Jutika Borah, Hidam Kumarjit Singh
Abstract: Deep learning models have gained increasing adoption in medical image analysis. However, these models often produce overconfident predictions, which can compromise clinical accuracy and reliability. Bridging the gap between high-performance and awareness of uncertainty remains a crucial challenge in biomedical imaging applications. This study focuses on developing a unified deep learning framework for enhancing feature integration, interpretability, and reliability in prediction. We introduced a cross-guided channel spatial attention architecture that fuses feature representations extracted from EfficientNetB4 and ResNet34. Bidirectional attention approach enables the exchange of information across networks with differing receptive fields, enhancing discriminative and contextual feature learning. For quantitative predictive uncertainty assessment, Monte Carlo (MC)-Dropout is integrated with conformal prediction. This provides statistically valid prediction sets with entropy-based uncertainty visualization. The framework is evaluated on four medical imaging benchmark datasets: chest X-rays of COVID-19, Tuberculosis, Pneumonia, and retinal Optical Coherence Tomography (OCT) images. The proposed framework achieved strong classification performance with an AUC of 99.75% for COVID-19, 100% for Tuberculosis, 99.3% for Pneumonia chest X-rays, and 98.69% for retinal OCT images. Uncertainty-aware inference yields calibrated prediction sets with interpretable examples of uncertainty, showing transparency. The results demonstrate that bidirectional cross-attention with uncertainty quantification can improve performance and transparency in medical image classification.
Authors: Flavia Esposito, Andersen Ang
Abstract: Low-rank optimization problems with sparse simplex constraints involve variables that must satisfy nonnegativity, sparsity, and sum-to-1 conditions, making their optimization particularly challenging due to the interplay between low-rank structures and constraints. These problems arise in various applications, including machine learning, signal processing, environmental fields, and computational biology. In this work, we propose a novel manifold optimization approach to efficiently tackle these problems. Our method leverages the geometry of oblique manifolds to reformulate the problem and introduces a new Riemannian optimization method based on Riemannian gradient descent that strictly maintains the simplex constraints. By exploiting the underlying manifold structure, our approach improves optimization efficiency. Experiments on synthetic and real datasets demonstrate the effectiveness of the proposed method compared to standard Euclidean and Riemannian methods, paving the way for broader applications.
Authors: Christian Alexander Holz, Christian Bader, Markus Enzweiler, Matthias Dr\"uppel
Abstract: We present a modular, production-ready approach that integrates compact Neural Network (NN) into a Kalmanfilter-based Multi-Object Tracking (MOT) pipeline. We design three tiny task-specific networks to retain modularity, interpretability and eal-time suitability for embedded Automotive Driver Assistance Systems: (i) SPENT (Single-Prediction Network) - predicts per-track states and replaces heuristic motion models used by the Kalman Filter (KF). (ii) SANT (Single-Association Network) - assigns a single incoming sensor object to existing tracks, without relying on heuristic distance and association metrics. (iii) MANTa (Multi-Association Network) - jointly associates multiple sensor objects to multiple tracks in a single step. Each module has less than 50k trainable parameters. Furthermore, all three can be operated in real-time, are trained from tracking data, and expose modular interfaces so they can be integrated with standard Kalman-filter state updates and track management. This makes them drop-in compatible with many existing trackers. Modularity is ensured, as each network can be trained and evaluated independently of the others. Our evaluation on the KITTI tracking benchmark shows that SPENT reduces prediction RMSE by more than 50% compared to a standard Kalman filter, while SANT and MANTa achieve up to 95% assignment accuracy. These results demonstrate that small, task-specific neural modules can substantially improve tracking accuracy and robustness without sacrificing modularity, interpretability, or the real-time constraints required for automotive deployment.
Authors: Rachmad Vidya Wicaksana Putra, Avaneesh Devkota, Muhammad Shafique
Abstract: Training resource-constrained autonomous agents on multiple tasks simultaneously is crucial for adapting to diverse real-world environments. Recent works employ reinforcement learning (RL) approach, but they still suffer from sub-optimal multi-task performance due to task interference. State-of-the-art works employ Spiking Neural Networks (SNNs) to improve RL-based multi-task learning and enable low-power/energy operations through network enhancements and spike-driven data stream processing. However, they rely on fixed task-switching intervals during its training, thus limiting its performance and scalability. To address this, we propose SwitchMT, a novel methodology that employs adaptive task-switching for effective, scalable, and simultaneous multi-task learning. SwitchMT employs the following key ideas: (1) leveraging a Deep Spiking Q-Network with active dendrites and dueling structure, that utilizes task-specific context signals to create specialized sub-networks; and (2) devising an adaptive task-switching policy that leverages both rewards and internal dynamics of the network parameters. Experimental results demonstrate that SwitchMT achieves competitive scores in multiple Atari games (i.e., Pong: -8.8, Breakout: 5.6, and Enduro: 355.2) and longer game episodes as compared to the state-of-the-art. These results also highlight the effectiveness of SwitchMT methodology in addressing task interference without increasing the network complexity, enabling intelligent autonomous agents with scalable multi-task learning capabilities.
Authors: Yiru Jiao, Simeon C. Calvert, Sander van Cranenburgh, Hans van Lint
Abstract: Accurately and proactively alerting drivers or automated systems to emerging collisions is crucial for road safety, particularly in highly interactive and complex urban environments. Existing methods either require labour-intensive annotation of sparse risk, struggle to consider varying contextual factors, or are tailored to limited scenarios. Here we present the Generalised Surrogate Safety Measure (GSSM), a data-driven approach that learns collision risk from naturalistic driving without the need for crash or risk labels. Trained over multiple datasets and evaluated on 2,591 real-world crashes and near-crashes, a basic GSSM using only instantaneous motion kinematics achieves an area under the precision-recall curve of 0.9, and secures a median time advance of 2.6 seconds to prevent potential collisions. Incorporating additional interaction patterns and contextual factors provides further performance gains. Across interaction scenarios such as rear-end, merging, and turning, GSSM consistently outperforms existing baselines in accuracy and timeliness. These results establish GSSM as a scalable, context-aware, and generalisable foundation to identify risky interactions before they become unavoidable, supporting proactive safety in autonomous driving systems and traffic incident management. Code and experiment data are openly accessible at https://github.com/Yiru-Jiao/GSSM.
Authors: Feiyang Cai, Jiahui Bai, Tao Tang, Guijuan He, Joshua Luo, Tianyu Zhu, Srikanth Pilla, Gang Li, Ling Liu, Feng Luo
Abstract: Precise recognition, editing, and generation of molecules are essential prerequisites for both chemists and AI systems tackling various chemical tasks. We present MolLangBench, a comprehensive benchmark designed to evaluate fundamental molecule-language interface tasks: language-prompted molecular structure recognition, editing, and generation. To ensure high-quality, unambiguous, and deterministic outputs, we construct the recognition tasks using automated cheminformatics tools, and curate editing and generation tasks through rigorous expert annotation and validation. MolLangBench supports the evaluation of models that interface language with different molecular representations, including linear strings, molecular images, and molecular graphs. Evaluations of state-of-the-art models reveal significant limitations: the strongest model (GPT-5) achieves $86.2\%$ and $85.5\%$ accuracy on recognition and editing tasks, which are intuitively simple for humans, and performs even worse on the generation task, reaching only $43.0\%$ accuracy. These results highlight the shortcomings of current AI systems in handling even preliminary molecular recognition and manipulation tasks. We hope MolLangBench will catalyze further research toward more effective and reliable AI systems for chemical applications.The dataset and code can be accessed at https://huggingface.co/datasets/ChemFM/MolLangBench and https://github.com/TheLuoFengLab/MolLangBench, respectively.
URLs: https://huggingface.co/datasets/ChemFM/MolLangBench, https://github.com/TheLuoFengLab/MolLangBench,
Authors: Nicolas K\"uchler, Ivan Petrov, Conrad Grobler, Ilia Shumailov
Abstract: For nearly a decade the academic community has investigated backdoors in neural networks, primarily focusing on classification tasks where adversaries manipulate the model prediction. While demonstrably malicious, the immediate real-world impact of such prediction-altering attacks has remained unclear. In this paper we introduce a novel and significantly more potent class of backdoors that builds upon recent advancements in architectural backdoors. We demonstrate how these backdoors can be specifically engineered to exploit batched inference, a common technique for hardware utilization, enabling large-scale user data manipulation and theft. By targeting the batching process, these architectural backdoors facilitate information leakage between concurrent user requests and allow attackers to fully control model responses directed at other users within the same batch. In other words, an attacker who can change the model architecture can set and steal model inputs and outputs of other users within the same batch. We show that such attacks are not only feasible but also alarmingly effective, can be readily injected into prevalent model architectures, (e.g. Transformers), and represent a truly malicious threat to user privacy and system integrity. Critically, to counteract this new class of vulnerabilities, we propose a deterministic mitigation strategy that provides formal guarantees against this new attack vector, unlike prior work that relied on LLMs to find the backdoors. Our mitigation strategy employs a novel Information Flow Control mechanism that analyzes the model graph and proves non-interference between different user inputs within the same batch. Using our mitigation strategy we perform a large scale analysis of models hosted through Hugging Face and find over 200 models that introduce (unintended) information leakage between batch entries due to the use of dynamic quantization.
Authors: Daniil Tiapkin, Daniele Calandriello, Denis Belomestny, Eric Moulines, Alexey Naumov, Kashif Rasul, Michal Valko, Pierre Menard
Abstract: Traditional Reinforcement Learning from Human Feedback (RLHF) often relies on reward models, frequently assuming preference structures like the Bradley--Terry model, which may not accurately capture the complexities of real human preferences (e.g., intransitivity). Nash Learning from Human Feedback (NLHF) offers a more direct alternative by framing the problem as finding a Nash equilibrium of a game defined by these preferences. While many works study the Nash learning problem directly in the policy space, we instead consider it under a more realistic policy parametrization setting. We first analyze a simple self-play policy gradient method, which is equivalent to Online IPO. We establish high-probability last-iterate convergence guarantees for this method, but our analysis also reveals a possible stability limitation of the underlying dynamics. Motivated by this, we embed the self-play updates into a proximal point framework, yielding a stabilized algorithm. For this combined method, we prove high-probability last-iterate convergence and discuss its more practical version, which we call Nash Prox. Finally, we apply this method to post-training of large language models and validate its empirical performance.
Authors: Shahrooz Pouryousef, Ali Montazeralghaem
Abstract: Collaborative information from user-item interactions is a fundamental source of signal in successful recommender systems. Recently, researchers have attempted to incorporate this knowledge into large language model-based recommender approaches (LLMRec) to enhance their performance. However, there has been little fundamental analysis of whether LLMs can effectively reason over collaborative information. In this paper, we analyze the ability of LLMs to reason about collaborative information in recommendation tasks, comparing their performance to traditional matrix factorization (MF) models. We propose a simple and effective method to improve LLMs' reasoning capabilities using retrieval-augmented generation (RAG) over the user-item interaction matrix with four different prompting strategies. Our results show that the LLM outperforms the MF model whenever we provide relevant information in a clear and easy-to-follow format, and prompt the LLM to reason based on it. We observe that with this strategy, in almost all cases, the more information we provide, the better the LLM performs.
Authors: Hang Liu, Anna Scaglione, Sean Peisert
Abstract: Gaussian Mixture Models (GMMs) are widely used statistical models for representing multi-modal data distributions, with numerous applications in data mining, pattern recognition, data simulation, and machine learning. However, recent research has shown that releasing GMM parameters poses significant privacy risks, potentially exposing sensitive information about the underlying data. In this paper, we address the challenge of releasing GMM parameters while ensuring differential privacy (DP) guarantees. Specifically, we focus on the privacy protection of mixture weights, component means, and covariance matrices. We propose to use Kullback-Leibler (KL) divergence as a utility metric to assess the accuracy of the released GMM, as it captures the joint impact of noise perturbation on all the model parameters. To achieve privacy, we introduce a DP mechanism that adds carefully calibrated random perturbations to the GMM parameters. Through theoretical analysis, we quantify the effects of privacy budget allocation and perturbation statistics on the DP guarantee, and derive a tractable expression for evaluating KL divergence. We formulate and solve an optimization problem to minimize the KL divergence between the released and original models, subject to a given $(\epsilon, \delta)$-DP constraint. Extensive experiments on both synthetic and real-world datasets demonstrate that our approach achieves strong privacy guarantees while maintaining high utility.
Authors: Anselm Paulus, A. Ren\'e Geist, Pierre Schumacher, V\'it Musil, Simon Rappenecker, Georg Martius
Abstract: Contact forces introduce discontinuities into robot dynamics that severely limit the use of simulators for gradient-based optimization. Penalty-based simulators such as MuJoCo, soften contact resolution to enable gradient computation. However, realistically simulating hard contacts requires stiff solver settings, which leads to incorrect simulator gradients when using automatic differentiation. Contrarily, using non-stiff settings strongly increases the sim-to-real gap. We analyze penalty-based simulators to pinpoint why gradients degrade under hard contacts. Building on these insights, we propose DiffMJX, which couples adaptive time integration with penalty-based simulation to substantially improve gradient accuracy. A second challenge is that contact gradients vanish when bodies separate. To address this, we introduce contacts from distance (CFD) which combines penalty-based simulation with straight-through estimation. By applying CFD exclusively in the backward pass, we obtain informative pre-contact gradients while retaining physical realism.
Authors: Victor Boussange, Bert Wuyts, Philipp Brun, Johanna T. Malle, Gabriele Midolo, Jeanne Portier, Th\'eophile Sanchez, Niklaus E. Zimmermann, Irena Axmanov\'a, Helge Bruelheide, Milan Chytr\'y, Stephan Kambach, Zde\v{n}ka Lososov\'a, Martin Ve\v{c}e\v{r}a, Idoia Biurrun, Klaus T. Ecker, Jonathan Lenoir, Jens-Christian Svenning, Dirk Nikolaus Karger
Abstract: Biodiversity assessments depend critically on the spatial scale at which species richness is measured. How species richness accumulates with sampling area is influenced by natural and anthropogenic processes whose effects vary across spatial scales. These accumulation dynamics, described by the species-area relationship (SAR), are challenging to assess because most biodiversity surveys cover sampling areas far smaller than the scales at which these processes operate. Here, we combine sampling theory with deep learning to estimate species richness at arbitrary spatial scales across geographic space from existing ecological surveys. We apply our model, named MuScaRi, to ~350k vegetation surveys across Europe. Validated against independent regional plant inventories, MuScaRi reduces root mean squared error of vascular plant richness estimates by 61% relative to conventional estimators, yields substantially less biased predictions, and produces multi-scale richness maps alongside spatially explicit estimates of the species accumulation rate, a key indicator for biodiversity conservation. By encompassing the full spectrum of ecologically relevant spatial scales within a single unified framework, MuScaRi provides an essential tool for robust biodiversity assessments and forecasts under global change.
Authors: Sangwoo Park, Jinheon Baek, Soyeong Jeong, Sung Ju Hwang
Abstract: Scientific paper retrieval, particularly framed as document-to-document retrieval, aims to identify relevant papers in response to a long-form query paper, rather than a short query string. Previous approaches to this task have focused exclusively on abstracts, embedding them into dense vectors as surrogates for full documents and calculating similarity between them. Yet, abstracts offer only sparse and high-level summaries, and such methods primarily optimize one-to-one similarity, overlooking the dynamic relations that emerge across relevant papers during the retrieval process. To address this, we propose Chain of Retrieval(COR), a novel iterative framework for full-paper retrieval. Specifically, COR decomposes each query paper into multiple aspect-specific views, matches them against segmented candidate papers, and iteratively expands the search by promoting top-ranked results as new queries, thereby forming a tree-structured retrieval process. The resulting retrieval tree is then aggregated in a post-order manner: descendants are first combined at the query level, then recursively merged with their parent nodes, to capture hierarchical relations across iterations. To validate this, we present SCIFULLBENCH, a large-scale benchmark providing both complete and segmented contexts of full papers for queries and candidates, and results show that COR significantly outperforms existing retrieval baselines. Our code and dataset is available at https://github.com/psw0021/Chain-of-Retrieval-Official.
URLs: https://github.com/psw0021/Chain-of-Retrieval-Official.
Authors: Saptarshi Mitra, Rachid Karami, Haocheng Xu, Sitao Huang, Hyoukjun Kwon
Abstract: Emerging applications such as AR are driving demands for machine intelligence capable of processing continuous and/or long-context inputs on local devices. However, currently dominant models based on Transformer architecture suffers from the quadratic computational and memory overhead, which hinders applications required to process long contexts. This has spurred a paradigm shift towards new architectures like State Space Models (SSMs) and SSM-Transformer hybrid models, which provide near-linear scaling. The near-linear scaling enabled efficient handling of millions of tokens while delivering high performance in recent studies. Although such works present promising results, their workload characteristics in terms of computational performance and hardware resource requirements are not yet thoroughly explored, which limits our understanding of their implications to the system level optimizations. To address this gap, we present a comprehensive, compara-ive benchmarking of carefully selected Transformers, SSMs, and hybrid models specifically for long-context inference on consumer and embedded GPUs. Our analysis shows that SSMs are well-suited for on-device AI on consumer and embedded GPUs for long context inferences. While Transformers are up to 1.9x faster at short sequences (<8K tokens), SSMs demonstrate a dramatic performance inversion, becoming up to 4x faster at very long contexts (~57K tokens), thanks to their linear computational complexity and ~64% reduced memory footrprint. Our operator-level analysis reveals that custom SSM kernels like selective scan despite being hardware-aware to minimize memory IO, dominate the inference runtime on edge platforms, accounting for over 55% of latency due to their sequential, element-wise nature. SSM-Scope is open-sourced at https://github.com/sapmitra/ssm-scope
Authors: Yiqi Wang, Mrinal Verghese, Jeff Schneider
Abstract: The performance of learned robot visuomotor policies is heavily dependent on the size and quality of the training dataset. Although large-scale robot and human datasets are increasingly available, embodiment gaps and mismatched action spaces make them difficult to leverage. Our main insight is that skills performed across different embodiments produce visual similarities in motions that can be captured using off-the-shelf action representations such as optical flow. Moreover, World Models (WMs) can leverage sub-optimal data since they focus on modeling dynamics. In this work, we aim to improve visuomotor policies in low-data regimes by first pretraining a WM using optical flow as an embodiment-agnostic action representation to leverage accessible or easily collected data from multiple embodiments (robots, humans). Given a small set of demonstrations on a target embodiment, we finetune the WM on this data to better align the WM predictions, train a base policy, and learn a robust value function. Using our finetuned WM and value function, our approach evaluates action candidates from the base policy and selects the best one to improve performance. Our approach, which we term Latent Policy Steering (LPS), improves behavior-cloned policies by 10.6% on average across four Robomimic tasks, even though most of the pretraining data comes from the real world. In the real-world experiments, LPS achieves larger gains: 70% relative improvement with 30-50 target-embodiment demonstrations, and 44% relative improvement with 60-100 demonstrations, compared to a behavior-cloned baseline. Qualitative results can be found on the website: https://yiqiwang8177.github.io/LatentPolicySteering/.
Authors: Xiang Zhang, Zhou Li, Shuangyang Li, Kai Wan, Derrick Wing Kwan Ng, Giuseppe Caire
Abstract: In decentralized federated learning (FL), multiple clients collaboratively learn a shared machine learning (ML) model by leveraging their privately held datasets distributed across the network, through interactive exchange of the intermediate model updates. To ensure data security, cryptographic techniques are commonly employed to protect model updates during aggregation. Despite growing interest in secure aggregation, existing works predominantly focus on protocol design and computational guarantees, with limited understanding of the fundamental information-theoretic limits of such systems. Moreover, optimal bounds on communication and key usage remain unknown in decentralized settings, where no central aggregator is available. Motivated by these gaps, we study the problem of decentralized secure aggregation (DSA) from an information-theoretic perspective. Specifically, we consider a network of $K$ fully-connected users, each holding a private input -- an abstraction of local training data -- who aim to securely compute the sum of all inputs. The security constraint requires that no user learns anything beyond the input sum, even when colluding with up to $T$ other users. We characterize the optimal rate region, which specifies the minimum achievable communication and secret key rates for DSA. In particular, we show that to securely compute one symbol of the desired input sum, each user must (i) transmit at least one symbol to others, (ii) hold at least one symbol of secret key, and (iii) all users must collectively hold no fewer than $K - 1$ independent key symbols. Our results establish the fundamental performance limits of DSA, providing insights for the design of provably secure and communication-efficient protocols in decentralized learning.
Authors: Wangyue Lu, Lun Du, Sirui Li, Ke Weng, Haozhe Sun, Hengyu Liu, Minghe Yu, Tiancheng Zhang, Ge Yu
Abstract: Interactive theorem provers (ITPs) require manual formalization, which is labor-intensive and demands expert knowledge. While automated formalization offers a potential solution, it faces two major challenges: model hallucination (e.g., undefined predicates, symbol misuse, and version incompatibility) and the semantic gap caused by ambiguous or missing premises in natural language descriptions. To address these issues, we propose CRAMF, a Concept-driven Retrieval-Augmented Mathematical Formalization framework. CRAMF enhances LLM-based autoformalization by retrieving formal definitions of core mathematical concepts, providing contextual grounding during code generation. However, applying retrieval-augmented generation (RAG) in this setting is non-trivial due to the lack of structured knowledge bases, the polymorphic nature of mathematical concepts, and the high precision required in formal retrieval. We introduce a framework for automatically constructing a concept-definition knowledge base from Mathlib4, the standard mathematical library for the Lean 4 theorem prover, indexing over 26,000 formal definitions and 1,000+ core mathematical concepts. To address conceptual polymorphism, we propose contextual query augmentation with domain- and application-level signals. In addition, we design a dual-channel hybrid retrieval strategy with reranking to ensure accurate and relevant definition retrieval. Experiments on miniF2F, ProofNet, and our newly proposed AdvancedMath benchmark show that CRAMF can be seamlessly integrated into LLM-based autoformalizers, yielding consistent improvements in translation accuracy, achieving up to 62.1% and an average of 29.9% relative improvement.
Authors: Yunyue Su, Jiahui Chen, Zao Jiang, Zhenyi Zhong, Liang Wang, Qiang Liu, Zhaoxiang Zhang
Abstract: Automated molecular structure elucidation remains challenging, as existing approaches often depend on pre-compiled databases or restrict themselves to single spectroscopic modalities. Here we introduce \textbf{SpectraLLM}, a large language model that performs end-to-end structure prediction by reasoning over one or multiple spectra. Unlike conventional spectrum-to-structure pipelines, SpectraLLM represents both continuous (IR, Raman, UV-Vis, NMR) and discrete (MS) modalities in a shared language space, enabling it to capture substructural patterns that are complementary across different spectral types. We pretrain and fine-tune the model on small-molecule domains and evaluate it on four public benchmark datasets. SpectraLLM achieves state-of-the-art performance, substantially surpassing single-modality baselines. Moreover, it demonstrates strong robustness in unimodal settings and further improves prediction accuracy when jointly reasoning over diverse spectra, establishing a scalable paradigm for language-based spectroscopic analysis. Code is available at https://github.com/OPilgrim/SpectraLLM.
Authors: Josh Barua, Seun Eisape, Kayo Yin, Alane Suhr
Abstract: While large reasoning models have shown remarkable ability to generate long chains-of-thought (CoTs) in English, we still lack understanding of how these long-form reasoning abilities transfer to the vast majority of the world's languages. In this work, we systematically investigate four key stages of model development--scaling, pretraining, post-training, and inference--to understand how long CoT capabilities extend beyond English. We compare two reasoning settings across nine non-English target languages: En-CoT, where models process target-language inputs, but reason in English; and Target-CoT, where models both process inputs and generate long CoTs in the target language. We find that scaling reasoning model size improves multilingual task performance in En-CoT, but Target-CoT performance lags behind. This gap widens for tasks requiring long, multi-step CoTs such as mathematical reasoning. Shifting to pretraining, we find that adding a specialized reasoning stage enhances En-CoT performance but degrades Target-CoT, whereas broad multilingual pretraining improves both modes simultaneously. Given the scarcity of high-quality reasoning traces in languages other than English, we explore synthetic data curation approaches for post-training. We demonstrate that fine-tuning on reasoning traces automatically translated from gold English traces outperforms fine-tuning on target-language traces distilled from large reasoning models. Finally, we report disparities in inference efficiency between languages and uncover language-specific failure modes in CoTs. We release models, datasets, and code to foster further research.
Authors: Jan Kapar, Kathrin G\"unther, Lori Ann Vallis, Klaus Berger, Nadine Binder, Hermann Brenner, Stefanie Castell, Beate Fischer, Volker Harth, Bernd Holleczek, Timm Intemann, Till Ittermann, Andr\'e Karch, Thomas Keil, Lilian Krist, Berit Lange, Michael F. Leitzmann, Katharina Nimptsch, Nadia Obi, Iris Pigeot, Tobias Pischon, Tamara Schikowski, B\"orge Schmidt, Carsten Oliver Schmidt, Anja M. Sedlmair, Justine Tanoey, Harm Wienbergen, Andreas Wienke, Claudia Wigmann, Marvin N. Wright
Abstract: Synthetic data holds substantial potential to address practical challenges in epidemiology due to restricted data access and privacy concerns. However, many current methods suffer from limited quality, high computational demands, and complexity for non-experts. Furthermore, common evaluation strategies for synthetic data often fail to directly reflect statistical utility and measure privacy risks sufficiently. Against this background, a critical underexplored question is whether synthetic data can reliably reproduce key findings from epidemiological research while preserving privacy. We propose adversarial random forests (ARF) as an efficient and convenient method for synthesizing tabular epidemiological data. To evaluate its performance, we replicated statistical analyses from six epidemiological publications covering blood pressure, anthropometry, myocardial infarction, accelerometry, loneliness, and diabetes, from the German National Cohort (NAKO Gesundheitsstudie), the Bremen STEMI Registry U45 Study, and the Guelph Family Health Study. We further assessed how dataset dimensionality and variable complexity affect the quality of synthetic data, and contextualized ARF's performance by comparison with commonly used tabular data synthesizers in terms of utility, privacy, generalisation, and runtime. Across all replicated studies, results on ARF-generated synthetic data consistently aligned with original findings. Even for datasets with relatively low sample size-to-dimensionality ratios, replication outcomes closely matched the original results across descriptive and inferential analyses. Reduced dimensionality and variable complexity further enhanced synthesis quality. ARF demonstrated favourable performance regarding utility, privacy preservation, and generalisation relative to other synthesizers and superior computational efficiency.
Authors: Malinda Lu, Yue-Jane Liu, Matthew K. Nock, Yaniv Yacoby
Abstract: Ecological Momentary Assessment (EMA) studies enable the collection of high-frequency self-reports of suicidal thoughts and behaviors (STBs) via smartphones. Latent stochastic differential equations (SDE) are a promising model class for EMA data, as it is irregularly sampled, noisy, and partially observed. But SDE-based models suffer from two key limitations. (a) These models often violate domain constraints, undermining scientific validity and clinical trust of the model. (b) Training is numerically unstable without ad-hoc fixes (e.g. oversimplified dynamics) that are ill-suited for high-stakes applications. Here, we develop a novel class of expressive SDEs whose solutions are provably confined to a prescribed compact polyhedral state space, matching the domains of EMA data. (1) We show why chain-rule-based constructions of SDEs on compact domains fail, theoretically and empirically; (2) we derive constraints on drift and diffusion for non-stationary/stationary SDEs so their solutions remain on the desired state space; and (3), we introduce a parameterization that maps arbitrary (neural or expert-given) dynamics into constraint-satisfying SDEs. On several real EMA datasets, including a large suicide-risk study, our parameterization improves inductive bias, training dynamics, and predictive performance over standard latent neural SDE baselines. These contributions pave way for principled, trustworthy continuous-time models of suicide risk and other clinical time series; they also extend the application of SDE-based methods (e.g. diffusion models) to domains with hard state constraints.
Authors: Andrea Andrisani, Gennaro Vessio, Fabrizio Sgobba, Francesco Di Lena, Luigi Amato Santamaria, Giovanna Castellano
Abstract: Quantum optical neurons (QONs) are emerging as promising computational units that leverage photonic interference to perform neural operations in an energy-efficient and physically grounded manner. Building on recent theoretical proposals, we introduce a family of QON architectures based on Hong-Ou-Mandel (HOM) and Mach-Zehnder (MZ) interferometers, incorporating different photon modulation strategies -- phase, amplitude, and intensity. These physical setups yield distinct pre-activation functions, which we implement as fully differentiable software modules. We evaluate these QONs both in isolation and as building blocks of multilayer networks, training them on binary and multiclass image classification tasks using the MNIST and FashionMNIST datasets. Each experiment is repeated over five independent runs and assessed under both ideal and non-ideal conditions to measure accuracy, convergence, and robustness. Across settings, MZ-based neurons exhibit consistently stable behavior -- including under noise -- while HOM amplitude modulation performs competitively in deeper architectures, in several cases approaching classical performance. In contrast, phase- and intensity-modulated HOM-based variants show reduced stability and greater sensitivity to perturbations. These results highlight the potential of QONs as efficient and scalable components for future quantum-inspired neural architectures and hybrid photonic-electronic systems. The code is publicly available at https://github.com/gvessio/quantum-optical-neurons.
Authors: Ahmed E. Fahmy
Abstract: The reliable identification of magnetic ground states remains a major challenge in high-throughput materials databases, where density functional theory (DFT) workflows often converge to ferromagnetic (FM) solutions. Here, we partially address this challenge by developing machine learning classifiers trained on experimentally validated MAGNDATA magnetic materials leveraging a limited number of simple compositional, structural, and electronic descriptors sourced from the Materials Project database. Our propagation vector classifiers achieve accuracies above 92%, outperforming recent studies in reliably distinguishing zero from nonzero propagation vector structures, and exposing a systematic ferromagnetic bias inherent to the Materials Project database for more than 7,843 materials. In parallel, LightGBM and XGBoost models trained directly on the Materials Project labels achieve accuracies of 84-86% (with macro F1 average scores of 63-66%), which proves useful for large-scale screening for magnetic classes, if refined by MAGNDATA-trained classifiers. These results underscore the role of machine learning techniques as corrective and exploratory tools, enabling more trustworthy databases and accelerating progress toward the identification of materials with various properties.
Authors: Yanke Li, Tianyu Cui, Tommaso Mansi, Mangal Prakash, Rui Liao
Abstract: Efficient design of genomic perturbation experiments is crucial for accelerating drug discovery and therapeutic target identification, yet exhaustive perturbation of the human genome remains infeasible due to the vast search space of potential genetic interactions and experimental constraints. Bayesian optimization (BO) has emerged as a powerful framework for selecting informative interventions, but existing approaches often fail to exploit domain-specific biological prior knowledge. We propose Biology-Informed Bayesian Optimization (BioBO), a method that integrates Bayesian optimization with multimodal gene embeddings and enrichment analysis, a widely used tool for gene prioritization in biology, to enhance surrogate modeling and acquisition strategies. BioBO combines biologically grounded priors with acquisition functions in a principled framework, which biases the search toward promising genes while maintaining the ability to explore uncertain regions. Through experiments on established public benchmarks and datasets, we demonstrate that BioBO improves labeling efficiency by 25-40%, and consistently outperforms conventional BO by identifying top-performing perturbations more effectively. Moreover, by incorporating enrichment analysis, BioBO yields pathway-level explanations for selected perturbations, offering mechanistic interpretability that links designs to biologically coherent regulatory circuits.
Authors: Zhe Liu, Yuyan Ni, Zhichen Pu, Qiming Sun, Siyuan Liu, Wen Yan
Abstract: Recently, sophisticated deep learning-based approaches have been developed for generating efficient initial guesses to accelerate the convergence of density functional theory (DFT) calculations. While the actual initial guesses are often density matrices (DM), quantities that can convert into density matrices also qualify as alternative forms of initial guesses. Hence, existing works mostly rely on the prediction of the Hamiltonian matrix for obtaining high-quality initial guesses. However, the Hamiltonian matrix is both numerically difficult to predict and intrinsically non-transferable, hindering the application of such models in real scenarios. In light of this, we propose a method that constructs DFT initial guesses by predicting the electron density in a compact auxiliary basis representation using E(3)-equivariant neural networks. Trained exclusively on small molecules with up to 20 atoms, our model achieves an average 33.3% reduction in SCF iterations for molecules three times larger (up to 60 atoms). This result is particularly significant given that baseline Hamiltonian-based methods fail to generalize, often increasing the iteration count by over 80% or failing to converge entirely on these larger systems. Furthermore, we demonstrate that this acceleration is robustly scalable: the model successfully accelerates calculations for systems with up to 900 atoms (polymers and polypeptides) without retraining. To the best of our knowledge, this work represents the first and robust candidate for a universally transferable DFT acceleration method. We also released the SCFbench dataset and its accompanying code to facilitate future research in this promising direction.
Authors: Yi Bin, Tianyi Jiang, Yujuan Ding, Kainian Zhu, Fei Ma, Jingkuan Song, Yang Yang, Heng Tao Shen
Abstract: Large Language Models (LLMs) have demonstrated remarkable reasoning abilities on complex problems using long Chain-of-Thought (CoT) reasoning. However, they often suffer from overthinking, meaning generating unnecessarily lengthy reasoning steps for simpler problems. This issue may degrade the efficiency of the models and make them difficult to adapt the reasoning depth to the complexity of problems. To address this, we introduce a novel metric Token Entropy Cumulative Average (TECA), which measures the extent of exploration throughout the reasoning process. We further propose a novel reasoning paradigm named "Explore Briefly, Then Decide", with an associated Cumulative Entropy Regulation (CER) mechanism. This paradigm leverages TECA to help the model dynamically determine the optimal point to conclude its thought process and provide a final answer, thus achieving efficient reasoning. Experimental results across diverse mathematical benchmarks show that our approach substantially mitigates overthinking without sacrificing problem solving ability. With our thinking paradigm, the average response length decreases by up to 71% on simpler datasets, demonstrating the effectiveness of our method in creating a more efficient and adaptive reasoning process.
Authors: David Romero, Ariana Bermudez, Viacheslav Iablochnikov, Hao Li, Fabio Pizzati, Ivan Laptev
Abstract: Recent video generation models have achieved remarkable progress and are now deployed in film, social media production, and advertising. Beyond their creative potential, such models also hold promise as world simulators for robotics and embodied decision making. Despite strong advances, current approaches still struggle to generate physically plausible object interactions and lack object-level control mechanisms. To address these limitations, we introduce KineMask, an approach for video generation that enables realistic rigid body control, interactions, and effects. Given a single image and a specified object velocity, our method generates videos with inferred motions and future object interactions. We propose a two-stage training strategy that gradually removes future motion supervision via object masks. Using this strategy we train video diffusion models (VDMs) on synthetic scenes of simple interactions and demonstrate significant improvements and generalization to rigid body and hand-object interactions in real scenes. Furthermore, KineMask integrates low-level motion control with high-level textual conditioning via predicted scene descriptions, leading to support for synthesis of complex dynamical phenomena. Our experiments show that KineMask generalizes to different VDMs and achieves strong improvements over recent models of comparable size. Ablation studies further highlight the complementary roles of low- and high-level conditioning in VDMs. Project Page: https://daromog.github.io/KineMask/
Authors: Hadi Pouransari, David Grangier, C Thomas, Michael Kirchhof, Oncel Tuzel
Abstract: The impressive performance gains of modern language models currently rely on scaling parameters: larger models store more world knowledge and reason better. Yet compressing all world knowledge into parameters is unnecessary, as only a fraction is used per prompt, and impractical for edge devices with limited inference-time memory and compute. We address this shortcoming by a memory-augmented architecture and a pretraining strategy aligned with existing hardware paradigms. We introduce small language models that access large hierarchical parametric memory banks encoding world knowledge. During pretraining and inference, we fetch a small, context-dependent memory block and add it to the model. Our pretraining learns to store long-tail world knowledge in the memory parameters, while the small language model acts as an anchor capturing common knowledge and general reasoning abilities. Through trillion-token-scale experiments, we show significant gains: a 160M-parameters model augmented with an 18M-parameters memory fetched from a 4.6B memory bank obtains comparable performance to a regular model with more than 2x the parameters. Through extensive experiments, we study the optimal type and size of parametric memories in transformers, scaling them to over 21B parameters. We find that our proposed hierarchical feed-forward memories work robustly across transformer architectures, whether added during pretraining or post-hoc.
Authors: Raj Ghugare, Roger Creus Castanyer, Catherine Ji, Kathryn Wantlin, Jin Schofield, Karthik Narasimhan, Benjamin Eysenbach
Abstract: Today's AI models learn primarily through mimicry and refining, so it is not surprising that they struggle to solve problems beyond the limits set by existing data. To solve novel problems, agents should acquire skills for exploring and learning through experience. Finding a scalable learning mechanism for developing agents that learn through interaction remains a major open problem. In this work, we introduce BuilderBench, a benchmark to accelerate research into agent pre-training that centers open-ended exploration. BuilderBench requires agents to learn how to build any structure using blocks. BuilderBench is equipped with $(1)$ a hardware accelerated simulator of a robotic agent interacting with various physical blocks, and $(2)$ a task-suite with over 42 diverse target structures that are carefully curated to test an understanding of physics, mathematics, and long-horizon planning. During training, agents have to explore and learn general principles about the environment without any external supervision. During evaluation, agents have to build the unseen target structures from the task suite. Solving these tasks requires a sort of \emph{embodied reasoning} that is not reflected in words but rather in actions, experimenting with different strategies and piecing them together. Our experiments show that many of these tasks challenge the current iteration of algorithms. Hence, we also provide a ``training wheels'' protocol, in which agents are trained and evaluated to build a single target structure from the task suite. Finally, we provide single-file implementations of six different algorithms as a reference point for researchers.
Authors: Annisaa Fitri Nurfidausi, Eleonora Mancini, Paolo Torroni
Abstract: Depression is a widespread mental health disorder, yet its automatic detection remains challenging. Prior work has explored unimodal and multimodal approaches, with multimodal systems showing promise by leveraging complementary signals. However, existing studies are limited in scope, lack systematic comparisons of features, and suffer from inconsistent evaluation protocols. We address these gaps by systematically exploring feature representations and modelling strategies across EEG, together with speech and text. We evaluate handcrafted features versus pre-trained embeddings, assess the effectiveness of different neural encoders, compare unimodal, bimodal, and trimodal configurations, and analyse fusion strategies with attention to the role of EEG. Consistent subject-independent splits are applied to ensure robust, reproducible benchmarking. Our results show that (i) the combination of EEG, speech and text modalities enhances multimodal detection, (ii) pretrained embeddings outperform handcrafted features, and (iii) carefully designed trimodal models achieve state-of-the-art performance. Our work lays the groundwork for future research in multimodal depression detection.
Authors: Aleksandr Oganov, Ilya Bykov, Eva Neudachina, Mishan Aliev, Alexander Tolmachev, Alexander Sidorov, Aleksandr Zuev, Andrey Okhotin, Denis Rakitin, Aibek Alanov
Abstract: While diffusion models achieve state-of-the-art generation quality, they still suffer from computationally expensive sampling. Recent works address this issue with gradient-based optimization methods that distill a few-step ODE diffusion solver from the full sampling process, reducing the number of function evaluations from dozens to just a few. However, these approaches often rely on intricate training techniques and do not explicitly focus on preserving fine-grained details. In this paper, we introduce the Generalized Solver: a simple parameterization of the ODE sampler that does not require additional training tricks and improves quality over existing approaches. We further combine the original distillation loss with adversarial training, which mitigates artifacts and enhances detail fidelity. We call the resulting method the Generalized Adversarial Solver and demonstrate its superior performance compared to existing solver training methods under similar resource constraints. Code is available at https://github.com/3145tttt/GAS.
Authors: Weiman Yan, Yi-Chia Chang, Wanyu Zhao
Abstract: Accurate and efficient circuit behavior modeling is a cornerstone of modern electronic design automation. Among different types of circuits, stiff circuits are challenging to model using previous frameworks. In this work, we propose a new approach using Crossformer, which is a current state-of-the-art Transformer model for time-series prediction tasks, combined with Kolmogorov-Arnold Networks (KANs), to model stiff circuit transient behavior. By leveraging the Crossformer's temporal representation capabilities and the enhanced feature extraction of KANs, our method achieves improved fidelity in predicting circuit responses to a wide range of input conditions. Experimental evaluations on datasets generated through SPICE simulations of analog-to-digital converter (ADC) circuits demonstrate the effectiveness of our approach, with significant reductions in training time and error rates.
Authors: Farshid Farhadi Khouzani, Abinash Kumar Shaw, Paul La Plante, Bryar Mustafa Shareef, Laxmi Gewali
Abstract: Upcoming measurements of the kinetic Sunyaev-Zel'dovich (kSZ) effect, which results from Cosmic Microwave Background (CMB) photons scattering off moving electrons, offer a powerful probe of the Epoch of Reionization (EoR). The kSZ signal contains key information about the timing, duration, and spatial structure of the EoR. A precise measurement of the CMB optical depth $\tau$, a key parameter that characterizes the universe's integrated electron density, would significantly constrain models of early structure formation. However, the weak kSZ signal is difficult to extract from CMB observations due to significant contamination from astrophysical foregrounds. We present a machine learning approach to extract $\tau$ from simulated kSZ maps. We train advanced machine learning models, including swin transformers, on high-resolution seminumeric simulations of the kSZ signal. To robustly quantify prediction uncertainties of $\tau$, we employ the Laplace Approximation (LA). This approach provides an efficient and principled Gaussian approximation to the posterior distribution over the model's weights, allowing for reliable error estimation. We investigate and compare two distinct application modes: a post-hoc LA applied to a pre-trained model, and an online LA where model weights and hyperparameters are optimized jointly by maximizing the marginal likelihood. This approach provides a framework for robustly constraining $\tau$ and its associated uncertainty, which can enhance the analysis of upcoming CMB surveys like the Simons Observatory and CMB-S4.
Authors: Jonas Elsborg, Emma L. Hovmand, Arghya Bhowmik
Abstract: We approach the search for optimal element ordering in bimetallic alloy nanoparticles (NPs) as a reinforcement learning (RL) problem and have built an RL agent that learns to perform such global optimization using the geometric graph representation of the NPs. To demonstrate the effectiveness, we train an RL agent to perform composition-conserving atomic swap actions on the icosahedral nanoparticle structure. Trained once on randomized $Ag_{X}Au_{309-X}$ compositions and orderings, the agent discovers previously established ground state structure. We show that this optimization is robust to differently ordered initialisations of the same NP compositions. We also demonstrate that a trained policy can extrapolate effectively to NPs of unseen size. However, the efficacy is limited when multiple alloying elements are involved. Our results demonstrate that RL with pre-trained equivariant graph encodings can navigate combinatorial ordering spaces at the nanoparticle scale, and offer a transferable optimization strategy with the potential to generalize across composition and reduce repeated individual search cost.
Authors: Mengyi Chen, Pengru Huang, Kostya S. Novoselov, Qianxiao Li
Abstract: Macroscopic dynamical descriptions of complex physical systems are crucial for understanding and controlling material behavior. With the growing availability of data and compute, machine learning has become a promising alternative to first-principles methods to build accurate macroscopic models from microscopic trajectory simulations. However, for spatially extended systems, direct simulations of sufficiently large microscopic systems that inform macroscopic behavior is prohibitive. In this work, we propose a framework that learns the macroscopic dynamics of large stochastic microscopic systems using only small-system simulations. Our framework employs a partial evolution scheme to generate training data pairs by evolving large-system snapshots within local patches. We subsequently identify the closure variables associated with the macroscopic observables and learn the macroscopic dynamics using a custom loss. Furthermore, we introduce a hierarchical upsampling scheme that enables efficient generation of large-system snapshots from small-system trajectory distributions. We empirically demonstrate the accuracy and robustness of our framework through a variety of stochastic spatially extended systems, including those described by stochastic partial differential equations, idealised lattice spin systems, and a more realistic NbMoTa alloy system.
Authors: Kyla D. Jones, Alexander W. Dowling
Abstract: We introduce Bayesian Information-Theoretic Sampling for hierarchical GAussian Process Surrogates (BITS for GAPS), a framework enabling information-theoretic experimental design of Gaussian process-based surrogate models. Unlike standard methods, which use fixed or point-estimated hyperparameters in acquisition functions, our approach propagates hyperparameter uncertainty into the sampling criterion through Bayesian hierarchical modeling. In this framework, a latent function receives a Gaussian process prior, while hyperparameters are assigned additional priors to capture the modeler's knowledge of the governing physical phenomena. Consequently, the acquisition function incorporates uncertainties from both the latent function and its hyperparameters, ensuring that sampling is guided by both data scarcity and model uncertainty. We further establish theoretical results in this context: a closed-form approximation and a lower bound of the posterior differential entropy. We demonstrate the framework's utility for hybrid modeling with a vapor-liquid equilibrium case study. Specifically, we build a surrogate model for latent activity coefficients in a binary mixture. We construct a hybrid model by embedding the surrogate into an extended form of Raoult's law. This hybrid model then informs distillation design. This case study shows how partial physical knowledge can be translated into a hierarchical Gaussian process surrogate. It also shows that using BITS for GAPS increases expected information gain and predictive accuracy by targeting high-uncertainty regions of the Wilson activity model. Overall, BITS for GAPS is a generalized uncertainty-aware framework for adaptive data acquisition in complex physical systems.
Authors: Zichuan Lin, Yicheng Liu, Yang Yang, Lvfang Tao, Deheng Ye
Abstract: Vision-Language Models (VLMs) have achieved remarkable success in visual question answering tasks, but their reliance on large numbers of visual tokens introduces significant computational overhead. While existing efficient VLM approaches reduce visual tokens through fixed-ratio compression, they operate passively and lack the ability to adapt to varying task requirements. This motivates a fundamental question: Can VLMs autonomously determine the minimum number of visual tokens required for each sample? Inspired by human active vision mechanisms, we introduce AdaptVision, an efficient VLM paradigm that enables adaptive visual token acquisition through a coarse-to-fine approach. Our model initially processes compressed visual tokens from low-resolution images and selectively acquires additional visual information by invoking a bounding box tool to crop key regions when necessary. We train AdaptVision using a reinforcement learning framework that carefully balances accuracy and efficiency. Central to our approach is Decoupled Turn Policy Optimization (DTPO), which decouples the learning objective into two components: (1) tool learning, which optimizes correct tool utilization, and (2) accuracy improvement, which refines the generated responses to improve answer correctness. Based on this formulation, we further decouple advantage estimation by computing separate advantages for tokens associated with each objective. This formulation enables more effective optimization for AdaptVision compared to vanilla GRPO. Comprehensive experiments across multiple VQA benchmarks demonstrate that AdaptVision achieves superior performance while consuming substantially fewer visual tokens than state-of-the-art efficient VLM methods.
Authors: Antonio Varagnolo, Giuseppe Romano, Rapha\"el Pestourie
Abstract: Designing materials with controlled heat flow at the nano-scale is central to advances in microelectronics, thermoelectrics, and energy-conversion technologies. At these scales, phonon transport follows the Boltzmann Transport Equation (BTE), which captures non-diffusive (ballistic) effects but is too costly to solve repeatedly in inverse-design loops. Existing surrogate approaches trade speed for accuracy: fast macroscopic solvers can overestimate conductivities by hundreds of percent, while recent data-driven operator learners often require thousands of high-fidelity simulations. This creates a need for a fast, data-efficient surrogate that remains reliable across ballistic and diffusive regimes. We introduce a Physics-Enhanced Deep Surrogate (PEDS) that combines a differentiable Fourier solver with a neural generator and couples it with uncertainty-driven active learning. The Fourier solver acts as a physical inductive bias, while the network learns geometry-dependent corrections and a mixing coefficient that interpolates between macroscopic and nano-scale behavior. PEDS reduces training-data requirements by up to 70% compared with purely data-driven baselines, achieves roughly 5% fractional error with only 300 high-fidelity BTE simulations, and enables efficient design of porous geometries spanning 12-85 W m$^{-1}$ K$^{-1}$ with average design errors of 4%. The learned mixing parameter recovers the ballistic-diffusive transition and improves out of distribution robustness. These results show that embedding simple, differentiable low-fidelity physics can dramatically increase surrogate data-efficiency and interpretability, making repeated PDE-constrained optimization practical for nano-scale thermal-materials design.
Authors: Qiming Bao, Xiaoxuan Fu, Michael Witbrock
Abstract: Large language models (LLMs) excel at many natural language tasks, yet their reasoning reliability under structured perturbations of rule-based systems remains brittle. We present a controlled evaluation framework consisting of four stress tests: (1) rule deletion (redundant vs. essential), (2) contradictory evidence injection, (3) logic-preserving rewrites, and (4) multi-law equivalence stacking. While representative model families (BERT, Qwen2, and TinyLlama) achieve Acc = 1.0000 on base tasks, our framework reveals a critical failure mode termed Logic Inertia - a total breakdown with Acc = 0.0000 under contradictions, where deductive momentum overrides factual reality. To address this, we propose Conflict-Aware Fusion (Fusion-Conflict), a framework grounded in the Cognitive Structure Hypothesis, which posits that robust reasoning requires an explicit structural inductive bias. By imposing a dual-process architecture that separates premise verification from logical deduction, Conflict-Aware Fusion effectively mitigates logic inertia under the proposed evaluation framework, achieving 1.0000 accuracy on both base and contradictory stress tests. It also significantly enhances robustness to missing evidence. Our results demonstrate that, for reliable multi-step reasoning, structural verification discipline is as critical as training data scale, providing a potential blueprint for building robust, contradiction-aware AI systems this https://github.com/14H034160212/lemo . See the OpenAI/Evals pull request this https://github.com/openai/evals/pull/1622 .
URLs: https://github.com/14H034160212/lemo, https://github.com/openai/evals/pull/1622
Authors: Jiayin Lu, Ying Jiang, Yumeng He, Yin Yang, Chenfanfu Jiang
Abstract: Voronoi diagrams naturally produce convex, watertight, and topologically consistent cells, making them an appealing representation for 3D shape reconstruction. However, standard differentiable Voronoi approaches typically optimize generator positions in stable configurations, which can lead to locally uneven surface geometry. We present VoroLight, a differentiable framework that promotes controlled Voronoi degeneracy for smooth surface reconstruction. Instead of optimizing generator positions alone, VoroLight associates each Voronoi surface vertex with a trainable sphere and introduces a sphere--intersection loss that encourages higher-order equidistance among face-incident generators. This formulation improves surface regularity while preserving intrinsic Voronoi properties such as watertightness and convexity. Because losses are defined directly on surface vertices, VoroLight supports multimodal shape supervision from implicit fields, point clouds, meshes, and multi--view images. By introducing additional interior generators optimized under a centroidal Voronoi tessellation objective, the framework naturally extends to volumetric Voronoi meshes with consistent surface--interior topology. Across diverse input modalities, VoroLight achieves competitive reconstruction fidelity while producing smoother and more geometrically regular Voronoi surfaces. Project page: https://jiayinlu19960224.github.io/vorolight/
Authors: Qizhi Wang
Abstract: Digital-humanities work on semantic shift often alternates between handcrafted close readings and opaque embedding machinery. We present a reproducible expert-system style pipeline that quantifies lexical drift and its instability in the Old Bailey Corpus (1674-1913), coupling interpretable trajectories with legally meaningful axes. We bin proceedings by decade with dynamic merging for low-resource slices, train skip-gram embeddings, align spaces through orthogonal Procrustes to a 1900s anchor, and measure both geometric displacement and neighborhood turnover. We add split-half baselines and seed-sensitivity checks to separate within-bin instability from temporal change. Three visual analytics outputs (drift magnitudes, semantic trajectories, and movement along a mercy-versus-retribution axis) expose how justice, crime, poverty, and insanity evolve with penal reforms, transportation debates, and Victorian moral politics. The pipeline is implemented as auditable scripts so results can be reproduced in other historical corpora.
Authors: Tianjun Gu, Jingyu Gong, Zhizhong Zhang, Yuan Xie, Lizhuang Ma, Xin Tan, Athanasios V
Abstract: Spatial intelligence is central to embodied cognition, yet contemporary AI systems still struggle to reason about physical interactions in open-world human environments. Despite strong performance on controlled benchmarks, vision-language models often fail to jointly model physical dynamics, reference frames, and the latent human intentions that drive spatial change. We introduce Teleo-Spatial Intelligence (TSI), a reasoning capability that links spatiotemporal change to goal-directed structure. To evaluate TSI, we present EscherVerse, a large-scale open-world resource built from 11,328 real-world videos, including an 8,000-example benchmark and a 35,963-example instruction-tuning set. Across 27 state-of-the-art vision-language models and an independent analysis of first-pass human responses from 11 annotators, we identify a persistent teleo-spatial reasoning gap: the strongest proprietary model achieves 57.26\% overall accuracy, far below first-pass human performance, which ranges from 84.81\% to 95.14\% with a mean of 90.62\%. Fine-tuning on real-world, intent-aware data narrows this gap for open-weight models, but does not close it. EscherVerse provides a diagnostic testbed for purpose-aware spatial reasoning and highlights a critical gap between pattern recognition and human-level understanding in embodied AI.
Authors: Zirui Ren, Ziming Liu
Abstract: Hierarchical reasoning model (HRM) achieves extraordinary performance on various reasoning tasks, significantly outperforming large language model-based reasoners. To understand the strengths and potential failure modes of HRM, we conduct a mechanistic study on its reasoning patterns and find three surprising facts: (a) Failure of extremely simple puzzles, e.g., HRM can fail on a puzzle with only one unknown cell. We attribute this failure to the violation of the fixed point property, a fundamental assumption of HRM. (b) "Grokking" dynamics in reasoning steps, i.e., the answer is not improved uniformly, but instead there is a critical reasoning step that suddenly makes the answer correct; (c) Existence of multiple fixed points. HRM "guesses" the first fixed point, which could be incorrect, and gets trapped there for a while or forever. All facts imply that HRM appears to be "guessing" instead of "reasoning". Leveraging this "guessing" picture, we propose three strategies to scale HRM's guesses: data augmentation (scaling the quality of guesses), input perturbation (scaling the number of guesses by leveraging inference randomness), and model bootstrapping (scaling the number of guesses by leveraging training randomness). On the practical side, by combining all methods, we develop Augmented HRM, boosting accuracy on Sudoku-Extreme from 54.5% to 96.9%. On the scientific side, our analysis provides new insights into how reasoning models "reason".
Authors: Ryan Lopez, Charlotte Loh, Rumen Dangovski, Marin Solja\v{c}i\'c
Abstract: Active learning for photonic crystals explores the integration of analytic approximate Bayesian last layer neural networks (LL-BNNs) with uncertainty-driven sample selection to accelerate photonic band gap prediction. We employ an analytic LL-BNN formulation, corresponding to the infinite Monte Carlo sample limit, to obtain uncertainty estimates that are strongly correlated with the true predictive error on unlabeled candidate structures. These uncertainty scores drive an active learning strategy that prioritizes the most informative simulations during training. Applied to the task of predicting band gap sizes in two-dimensional, two-tone photonic crystals, our approach achieves up to a 2.6x reduction in required training data compared to a random sampling baseline while maintaining predictive accuracy. The efficiency gains arise from concentrating computational resources on high uncertainty regions of the design space rather than sampling uniformly. Given the substantial cost of full band structure simulations, especially in three dimensions, this data efficiency enables rapid and scalable surrogate modeling. Our results suggest that analytic LL-BNN based active learning can substantially accelerate topological optimization and inverse design workflows for photonic crystals, and more broadly, offers a general framework for data efficient regression across scientific machine learning domains.
Authors: Dohun Lee, Chun-Hao Paul Huang, Xuelin Chen, Jong Chul Ye, Duygu Ceylan, Hyeonho Jeong
Abstract: Video-to-video diffusion models achieve impressive single-turn editing performance, but practical editing workflows are inherently iterative. When edits are applied sequentially, existing models treat each turn independently, often causing previously generated regions to drift or be overwritten. We identify this failure mode as the problem of cross-turn consistency in multi-turn video editing. We introduce Memory-V2V, a memory-augmented framework that treats prior edits as structured constraints for subsequent generations. Memory-V2V maintains an external memory of previous outputs, retrieves task-relevant edits, and integrates them through relevance-aware tokenization and adaptive compression. These technical ingredients enable scalable conditioning without linear growth in computation. We demonstrate Memory-V2V on iterative video novel view synthesis and text-guided long video editing. Memory-V2V substantially enhances cross-turn consistency while maintaining visual quality, outperforming strong baselines with modest overhead.
Authors: Kenan Begovic, Abdulaziz Al-Ali, Qutaibah Malluhi
Abstract: Ransomware core capability, unauthorized encryption, demands controls that identify and block malicious cryptographic activity without disrupting legitimate use. We present a probabilistic, risk-based access control architecture that couples machine learning inference with mandatory access control to regulate encryption on Linux in real time. The system builds a specialized dataset from the native ftrace framework using the function_graph tracer, yielding high-resolution kernel-function execution traces augmented with resource and I/O counters. These traces support both a supervised classifier and interpretable rules that drive an SELinux policy via lightweight booleans, enabling context-sensitive permit/deny decisions at the moment encryption begins. Compared to approaches centered on sandboxing, hypervisor introspection, or coarse system-call telemetry, the function-level tracing we adopt provides finer behavioral granularity than syscall-only telemetry while avoiding the virtualization/VMI overhead of sandbox-based approaches. Our current user-space prototype has a non-trivial footprint under burst I/O; we quantify it and recognize that a production kernel-space solution should aim to address this. We detail dataset construction, model training and rule extraction, and the run-time integration that gates file writes for suspect encryption while preserving benign cryptographic workflows. During evaluation, the two-layer composition retains model-level detection quality while delivering rule-like responsiveness; we also quantify operational footprint and outline engineering steps to reduce CPU and memory overhead for enterprise deployment. The result is a practical path from behavioral tracing and learning to enforceable, explainable, and risk-proportionate encryption control on production Linux systems.
Authors: Chia-Ming Lee, Yu-Fan Lin, Jin-Hui Jiang, Yu-Jou Hsiao, Chih-Chung Hsu, Yu-Lun Liu
Abstract: Single Image Reflection Separation (SIRS) disentangles mixed images into transmission and reflection layers. Existing methods suffer from transmission-reflection confusion under nonlinear mixing, particularly in deep decoder layers, due to implicit fusion mechanisms and inadequate multi-scale coordination. We propose ReflexSplit, a dual-stream framework with three key innovations. (1) Cross-scale Gated Fusion (CrGF) adaptively aggregates semantic priors, texture details, and decoder context across hierarchical depths, stabilizing gradient flow and maintaining feature consistency. (2) Layer Fusion-Separation Blocks (LFSB) alternate between fusion for shared structure extraction and differential separation for layer-specific disentanglement. Inspired by Differential Transformer, we extend attention cancellation to dual-stream separation via cross-stream subtraction. (3) Curriculum training progressively strengthens differential separation through depth-dependent initialization and epoch-wise warmup. Extensive experiments on synthetic and real-world benchmarks demonstrate state-of-the-art performance with superior perceptual quality and robust generalization. Our code is available at https://github.com/wuw2135/ReflexSplit.
Authors: J. Ben Tamo, Daniel Carlander-Reuterfelt, Jonathan Rubin, Dezhi Hong, Mingxian Wang, Oleg Poliannikov
Abstract: Despite multilingual pretraining, large language models often struggle with non-English tasks, particularly in language control, the ability to respond in the intended language. We identify and characterize two key failure modes: the multilingual transfer bottleneck (correct language, incorrect task response) and the language consistency bottleneck (correct task response, wrong language). To systematically surface these issues, we design a four-scenario evaluation protocol spanning MMLU, MGSM, and XQuAD benchmarks. To probe these issues with interpretability, we extend logit lens analysis to track language probabilities layer by layer and compute cross-lingual semantic similarity of hidden states. The results reveal a three-phase internal structure: early layers align inputs into a shared semantic space, middle layers perform task reasoning, and late layers drive language-specific generation. Guided by these insights, we introduce selective fine-tuning of only the final layers responsible for language control. On Qwen-3-32B and Bloom-7.1B, this method achieves over 98 percent language consistency across six languages while fine-tuning only 3-5 percent of parameters, without sacrificing task accuracy. Importantly, this result is nearly identical to that of full-scope fine-tuning (for example, above 98 percent language consistency for both methods across all prompt scenarios) but uses a fraction of the computational resources. To the best of our knowledge, this is the first approach to leverage layer-localization of language control for efficient multilingual adaptation.
Authors: F. D. Amaro, R. Antonietti, E. Baracchini, L. Benussi, C. Capoccia, M. Caponero, L. G. M. de Carvalho, G. Cavoto, I. A. Costa, A. Croce, M. D'Astolfo, G. D'Imperio, G. Dho, E. Di Marco, J. M. F. dos Santos, D. Fiorina, F. Iacoangeli, Z. Islam, E. Kemp, H. P. Lima Jr, G. Maccarrone, R. D. P. Mano, D. J. G. Marques, G. Mazzitelli, P. Meloni, A. Messina, C. M. B. Monteiro, R. A. Nobrega, G. M. Oppedisano, I. F. Pains, E. Paoletti, F. Petrucci, S. Piacentini, D. Pierluigi, D. Pinci, F. Renga, A. Russo, G. Saviano, P. A. O. C. Silva, N. J. Spooner, R. Tesauro, S. Tomassini, D. Tozzi
Abstract: The CYGNO experiment employs an optical-readout Time Projection Chamber (TPC) to search for rare low-energy interactions using finely resolved scintillation images. While the optical readout provides rich topological information, it produces large, sparse megapixel images that challenge real-time triggering, data reduction, and background discrimination. We summarize two complementary machine-learning approaches developed within CYGNO. First, we present a fast and fully unsupervised strategy for online data reduction based on reconstruction-based anomaly detection. A convolutional autoencoder trained exclusively on pedestal images (i.e. frames acquired with GEM amplification disabled) learns the detector noise morphology and highlights particle-induced structures through localized reconstruction residuals, from which compact Regions of Interest (ROIs) are extracted. On real prototype data, the selected configuration retains (93.0 +/- 0.2)% of reconstructed signal intensity while discarding (97.8 +/- 0.1)% of the image area, with ~25 ms per-frame inference time on a consumer GPU. Second, we report a weakly supervised application of the Classification Without Labels (CWoLa) framework to data acquired with an Americium--Beryllium neutron source. Using only mixed AmBe and standard datasets (no event-level labels), a convolutional classifier learns to identify nuclear-recoil-like topologies. The achieved performance approaches the theoretical limit imposed by the mixture composition and isolates a high-score population with compact, approximately circular morphologies consistent with nuclear recoils.
Authors: Yue Yu, Ting Bai, HengZhi Lan, Li Qian, Li Peng, Jie Wu, Wei Liu, Jian Luan, Chuan Shi
Abstract: The attribution technique enhances the credibility of LLMs by adding citations to the generated sentences, enabling users to trace back to the original sources and verify the reliability of the output. However, existing instruction-tuned attributed LLMs often fail to properly interpret the contextual semantics of citation symbols (e.g., [i]) during text generation. This shortcoming arises from their insufficient awareness of the context information surrounding citation markers, which in turn leads to disjointed references and poor integration of retrieved knowledge into the generated content. To address this issue, we propose a novel \textbf{C}ontextual-aware \textbf{C}itation generation framework (\textbf{C$^2$}-\textbf{Cite}) that explicitly integrates the semantic relationships between citation markers and their referenced content. Specifically, a contextual citation alignment mechanism is adopted: it first encodes the retrieved document contexts into the symbol representation of citations, then aligns the marker numbers by decoding information from a citation router function. This mechanism enables the transformation of citation markers from generic placeholders into active knowledge pointers that link to the referenced source information. Experimental results on the ALCE benchmark across three datasets validate our framework C$^2$-Cite++: it outperforms the SOTA baseline by an average of 5.8\% in citation quality and 17.4\% in response correctness. The implementation is publicly available at https://github.com/BAI-LAB/c2cite
Authors: Siyuan Shen, Kai Wang
Abstract: The growing availability of large language models (LLMs) has raised questions about their role in academic peer review. This study examines the temporal emergence of AI-generated content in peer reviews by applying a detection model trained on historical reviews to later review cycles at International Conference on Learning Representations (ICLR) and Nature Communications (NC). We observe minimal detection of AI-generated content before 2022, followed by a substantial increase through 2025, with approximately 20% of ICLR reviews and 12% of Nature Communications reviews classified as AI-generated in 2025. The most pronounced growth of AI-generated reviews in NC occurs between the third and fourth quarter of 2024. Together, these findings provide suggestive evidence of a rapidly increasing presence of AI-assisted content in peer review and highlight the need for further study of its implications for scholarly evaluation.
Authors: Piotr Br\'odka, Micha{\l} Czuba, Bogumi{\l} Kami\'nski, {\L}ukasz Krai\'nski, Katarzyna Musial, Pawe{\l} Pra{\l}at, Mateusz Stolarski
Abstract: The increasing availability of relational data has contributed to a growing reliance on network-based representations of complex systems. Over time, these models have evolved to capture more nuanced properties, such as the heterogeneity of relationships, leading to the concept of multilayer networks. However, the analysis and evaluation of methods for these structures is often hindered by the limited availability of large-scale empirical data. As a result, graph generators are commonly used as a workaround, albeit at the cost of introducing systematic biases. In this paper, we address the inverse-generator problem by inferring the configuration parameters of a multilayer network generator, \mABCD, from a real-world system. Our goal is to identify parameter settings that enable the generator to produce synthetic networks that act as digital twins of the original structure. We propose a method for estimating matching configurations and for quantifying the associated error. Our results demonstrate that this task is non-trivial, as strong interdependencies between configuration parameters weaken independent estimation and instead favour a joint-prediction approach.
Authors: Lars K\"uhmichel, Jerry M. Huang, Valentin Pratz, Jonas Arruda, Hans Olischl\"ager, Daniel Habermann, Simon Kucharsky, Lasse Elsem\"uller, Aayush Mishra, Niels Bracher, Svenja Jedhoff, Marvin Schmitt, Paul-Christian B\"urkner, Stefan T. Radev
Abstract: Modern Bayesian inference involves a mixture of computational methods for estimating, validating, and drawing conclusions from probabilistic models as part of principled workflows. An overarching motif of many Bayesian methods is that they are relatively slow, which often becomes prohibitive when fitting complex models to large data sets. Amortized Bayesian inference (ABI) offers a path to solving the computational challenges of Bayes. ABI trains neural networks on model simulations, rewarding users with rapid inference of any model-implied quantity, such as point estimates, likelihoods, or full posterior distributions. In this work, we present the Python library BayesFlow, Version 2.0, for general-purpose ABI. Along with direct posterior, likelihood, and ratio estimation, the software includes support for multiple popular deep learning backends, a rich collection of generative networks for sampling and density estimation, complete customization and high-level interfaces, as well as new capabilities for hyperparameter optimization, design optimization, and hierarchical modeling. Using a case study on dynamical system parameter estimation, combined with comparisons to similar software, we show that our streamlined, user-friendly workflow has strong potential to support broad adoption.
Authors: Luciano Melodia
Abstract: We study homology of ample groupoids via the compactly supported Moore complex of the nerve. Let $A$ be a topological abelian group. For $n\ge 0$ set $C_n(\mathcal G;A) := C_c(\mathcal G_n,A)$ and define $\partial_n^A=\sum_{i=0}^n(-1)^i(d_i)_*$. This defines $H_n(\mathcal G;A)$. The theory is functorial for continuous \'etale homomorphisms. It is compatible with standard reductions, including restriction to saturated clopen subsets. In the ample setting it is invariant under Kakutani equivalence. We reprove Matui type long exact sequences and identify the comparison maps at chain level. For discrete $A$ we prove a natural universal coefficient short exact sequence $$0\to H_n(\mathcal G)\otimes_{\mathbb Z}A\xrightarrow{\ \iota_n^{\mathcal G}\ }H_n(\mathcal G;A)\xrightarrow{\ \kappa_n^{\mathcal G}\ }\operatorname{Tor}_1^{\mathbb Z}\bigl(H_{n-1}(\mathcal G),A\bigr)\to 0.$$ The key input is the chain level isomorphism $C_c(\mathcal G_n,\mathbb Z)\otimes_{\mathbb Z}A\cong C_c(\mathcal G_n,A)$, which reduces the groupoid statement to the classical algebraic UCT for the free complex $C_c(\mathcal G_\bullet,\mathbb Z)$. We also isolate the obstruction for non-discrete coefficients. For a locally compact totally disconnected Hausdorff space $X$ with a basis of compact open sets, the image of $\Phi_X:C_c(X,\mathbb Z)\otimes_{\mathbb Z}A\to C_c(X,A)$ is exactly the compactly supported functions with finite image. Thus $\Phi_X$ is surjective if and only if every $f\in C_c(X,A)$ has finite image, and for suitable $X$ one can produce compactly supported continuous maps $X\to A$ with infinite image. Finally, for a clopen saturated cover $\mathcal G_0=U_1\cup U_2$ we construct a short exact sequence of Moore complexes and derive a Mayer-Vietoris long exact sequence for $H_\bullet(\mathcal G;A)$ for explicit computations.
Authors: Chenhui Deng, Zhongzhi Yu, Guan-Ting Liu, Nathaniel Pinckney, Brucek Khailany, Haoxing Ren
Abstract: Recent advances in LLMs have sparked growing interest in applying them to hardware design automation, particularly for accurate RTL code generation. Prior efforts follow two largely independent paths: (i) training domain-adapted RTL models to internalize hardware semantics, (ii) developing agentic systems that leverage frontier generic LLMs guided by simulation feedback. However, these two paths exhibit complementary strengths and weaknesses. In this work, we present ACE-RTL that unifies both directions through Agentic Context Evolution (ACE). ACE-RTL integrates an RTL-specialized LLM, trained on a large-scale dataset of 1.7 million RTL samples, with a frontier reasoning LLM through three synergistic components: the generator, reflector, and coordinator. These components iteratively refine RTL code toward functional correctness. We further analyze a parallel scaling strategy that reduces wall-clock iterations to first success by exploring diverse debugging trajectories concurrently. On the CVDP benchmark, ACE-RTL achieves up to a 41.02% pass rate improvement over 14 competitive baselines.
Authors: Seyedarmin Azizi, Erfan Baghaei Potraghloo, Minoo Ahmadi, Souvik Kundu, Massoud Pedram
Abstract: Many recent reasoning gains in large language models can be explained as distribution sharpening: biasing generation toward high-likelihood trajectories already supported by the pretrained model, rather than modifying its weights. A natural formalization is the sequence-level power distribution $\pi_\alpha(y\mid x)\propto p_\theta(y\mid x)^\alpha$ ($\alpha>1$), which concentrates mass on whole sequences instead of adjusting token-level temperature. Prior work shows that Metropolis--Hastings (MH) sampling from this distribution recovers strong reasoning performance, but at order-of-magnitude inference slowdowns. We introduce Power-SMC, a training-free Sequential Monte Carlo scheme that targets the same objective while remaining close to standard decoding latency. Power-SMC advances a small particle set in parallel, corrects importance weights token-by-token, and resamples when necessary, all within a single GPU-friendly batched decode. We prove that temperature $\tau=1/\alpha$ is the unique prefix-only proposal minimizing incremental weight variance, interpret residual instability via prefix-conditioned R\'enyi entropies, and introduce an exponent-bridging schedule that improves particle stability without altering the target. On MATH500, Power-SMC matches or exceeds MH power sampling while reducing latency from $16$--$28\times$ to $1.4$--$3.3\times$ over baseline decoding. The code is available at https://github.com/ArminAzizi98/Power-SMC.
Authors: Antonin Sulc
Abstract: We present FastLSQ, a framework for PDE solving and inverse problems built on trigonometric random Fourier features with exact analytical derivatives. Trigonometric features admit closed-form derivatives of any order in $\mathcal{O}(1)$, enabling graph-free operator assembly without autodiff. Linear PDEs: one least-squares call; nonlinear: Newton--Raphson reusing analytical assembly. On 17 PDEs (1--6D), FastLSQ achieves $10^{-7}$ in 0.07s (linear) and $10^{-8}$--$10^{-9}$ in $<$9s (nonlinear), orders of magnitude faster and more accurate than iterative PINNs. Analytical higher-order derivatives yield a differentiable digital twin; we demonstrate inverse problems (heat-source, coil recovery) and PDE discovery. Code: github.com/sulcantonin/FastLSQ and \texttt{pip install fastlsq}.
Authors: Abhinaba Basu
Abstract: Personal AI agents incur substantial cost via repeated LLM calls. We show existing caching methods fail: GPTCache achieves 37.9% accuracy on real benchmarks; APC achieves 0-12%. The root cause is optimizing for the wrong property -- cache effectiveness requires key consistency and precision, not classification accuracy. We observe cache-key evaluation reduces to clustering evaluation and apply V-measure decomposition to separate these on n=8,682 points across MASSIVE, BANKING77, CLINC150, and NyayaBench v2, our new 8,514-entry multilingual agentic dataset (528 intents, 20 W5H2 classes, 63 languages). We introduce W5H2, a structured intent decomposition framework. Using SetFit with 8 examples per class, W5H2 achieves 91.1%+/-1.7% on MASSIVE in ~2ms -- vs 37.9% for GPTCache and 68.8% for a 20B-parameter LLM at 3,447ms. On NyayaBench v2 (20 classes), SetFit achieves 55.3%, with cross-lingual transfer across 30 languages. Our five-tier cascade handles 85% of interactions locally, projecting 97.5% cost reduction. We provide risk-controlled selective prediction guarantees via RCPS with nine bound families.
Authors: Vugar Ismailov
Abstract: We study shallow and deep neural networks whose inputs range over a general topological space. The model is built from a prescribed family of continuous feature maps and reduces to multilayer feedforward networks in the Euclidean case. We focus on the universal approximation property and establish general conditions under which such networks are dense in spaces of continuous vector-valued functions on arbitrary topological spaces and, in particular, locally convex spaces. Universality results obtained in the arbitrary-width case extend classical approximation theorems to non-Euclidean spaces. We also consider the deep narrow setting, in which the width of each hidden layer is uniformly bounded while the depth is allowed to grow. We identify conditions under which such networks retain the universal approximation property. As a concrete example, we employ Ostrand's extension of the Kolmogorov superposition theorem to derive an explicit universality result for products of compact metric spaces, with width bounds expressed in terms of topological dimension.
Authors: Xiangyan Qu, Zhenlong Yuan, Jing Tang, Rui Chen, Datao Tang, Meng Yu, Lei Sun, Yancheng Bai, Xiangxiang Chu, Gaopeng Gou, Gang Xiong, Yujun Cai
Abstract: Image Chain-of-Thought (Image-CoT) is a test-time scaling paradigm that improves image generation by extending inference time. Most Image-CoT methods focus on text-to-image (T2I) generation. Unlike T2I generation, image editing is goal-directed: the solution space is constrained by the source image and instruction. This mismatch causes three challenges when applying Image-CoT to editing: inefficient resource allocation with fixed sampling budgets, unreliable early-stage verification using general MLLM scores, and redundant edited results from large-scale sampling. To address this, we propose ADaptive Edit-CoT (ADE-CoT), an on-demand test-time scaling framework to enhance editing efficiency and performance. It incorporates three key strategies: (1) a difficulty-aware resource allocation that assigns dynamic budgets based on estimated edit difficulty; (2) edit-specific verification in early pruning that uses region localization and caption consistency to select promising candidates; and (3) depth-first opportunistic stopping, guided by an instance-specific verifier, that terminates when intent-aligned results are found. Extensive experiments on three SOTA editing models (Step1X-Edit, BAGEL, FLUX.1 Kontext) across three benchmarks show that ADE-CoT achieves superior performance-efficiency trade-offs. With comparable sampling budgets, ADE-CoT obtains better performance with more than 2x speedup over Best-of-N.
Authors: Jin Zeng, Yupeng Qi, Hui Li, Chengming Li, Ziyu Lyu, Lixin Cui, Lu Bai
Abstract: Large language models (LLMs) are increasingly adopted as the backbone of recommender systems. However, user-item interactions in real-world scenarios are non-stationary, making preference drift over time inevitable. Existing model update strategies mainly rely on global fine-tuning or pointwise editing, but they face two fundamental challenges: (i) imbalanced update granularity, where global updates perturb behaviors unrelated to the target while pointwise edits fail to capture broader preference shifts; (ii) unstable incremental updates, where repeated edits interfere with prior adaptations, leading to catastrophic forgetting and inconsistent recommendations. To address these issues, we propose Region-Aware Incremental Editing (RAIE), a plug-in framework that freezes the backbone model and performs region-level updates. RAIE first constructs semantically coherent preference regions via spherical k-means in the representation space. It then assigns incoming sequences to regions via confidence-aware gating and performs three localized edit operations - Update, Expand, and Add - to dynamically revise the affected region. Each region is equipped with a dedicated Low-Rank Adaptation (LoRA) module, which is trained only on the region's updated data. During inference, RAIE routes each user sequence to its corresponding region and activates the region-specific adapter for prediction. Experiments on two benchmark datasets under a time-sliced protocol that segments data into Set-up (S), Finetune (F), and Test (T) show that RAIE significantly outperforms state-of-the-art baselines while effectively mitigating forgetting. These results demonstrate that region-aware editing offers an accurate and scalable mechanism for continual adaptation in dynamic recommendation scenarios. Our code is available at https://github.com/fengaogao/RAIE.
Authors: Ruichen Xu, Wenjing Yan, Ying-Jun Angela Zhang
Abstract: Understanding reasoning in large language models is complicated by evaluations that conflate multiple reasoning types. We isolate analogical reasoning (inferring shared properties between entities based on known similarities) and analyze its emergence in transformers. We theoretically prove three key results: (1) Joint training on similarity and attribution premises enables analogical reasoning through aligned representations; (2) Sequential training succeeds only when similarity structure is learned before specific attributes, revealing a necessary curriculum; (3) Two-hop reasoning ($a \to b, b \to c \implies a \to c$) reduces to analogical reasoning with identity bridges ($b = b$), which must appear explicitly in training data. These results reveal a unified mechanism: transformers encode entities with similar properties into similar representations, enabling property transfer through feature alignment. Experiments with architectures up to 1.5B parameters validate our theory and demonstrate how representational geometry shapes inductive reasoning capabilities.
Authors: Nikolaos Al. Papadopoulos, Konstantinos Psannis
Abstract: Multi-agent coordination dilemmas expose a fundamental tension between individual optimization and collective welfare, yet characterizing such coordination requires metrics sensitive to temporal structure and collective dynamics. As a diagnostic testbed, we study a BoE-derived multi-agent variant of the Battle of the Exes, formalizing it as a Markov game in which turn-taking emerges as a periodic coordination regime. Conventional outcome-based metrics (e.g., efficiency and min/max fairness) are temporally blind (they cannot distinguish structured alternation from monopolistic or random access patterns) and fairness ratios lose discriminative power as n grows, obscuring inequities. To address this limitation, we introduce Perfect Alternation (PA) as a reference coordination regime and propose six novel Alternation (ALT) metrics designed as temporally sensitive observables of coordination quality. Using Q-learning agents as a minimal adaptive diagnostic baseline, and comparing against random-policy null processes, we uncover a clear measurement failure: despite exhibiting deceptively high traditional metrics (e.g., reward fairness often exceeding 0.9), learned policies perform up to 81% below random baselines under ALT-variant evaluation, a deficit already present in the two-agent case and intensifying as n grows. These results demonstrate, in this setting, that high aggregate payoffs can coexist with poor temporal coordination, and that conventional metrics may severely mischaracterize emergent dynamics. Our findings underscore the necessity of temporally aware observables for analyzing coordination in multi-agent games and highlight random-policy baselines as essential null processes for interpreting coordination outcomes relative to chance-level behavior.
Authors: Pranjal Rawat
Abstract: This survey (re)introduces reinforcement learning methods to economists. The curse of dimensionality limits how far exact dynamic programming can be effectively applied, forcing us to rely on suitably "small" problems or our ability to convert "big" problems into smaller ones. While this reduction has been sufficient for many classical applications, a growing class of economic models resists such reduction. Reinforcement learning algorithms offer a natural, sample-based extension of dynamic programming, extending tractability to problems with high-dimensional states, continuous actions, and strategic interactions. I review the theory connecting classical planning to modern learning algorithms and demonstrate their mechanics through simulated examples in pricing, inventory control, strategic games, and preference elicitation. I also examine the practical vulnerabilities of these algorithms, noting their brittleness, sample inefficiency, sensitivity to hyperparameters, and the absence of global convergence guarantees outside of tabular settings. The successes of reinforcement learning remain strictly bounded by these constraints, as well as a reliance on accurate simulators. When guided by economic structure, reinforcement learning provides a remarkably flexible framework. It stands as an imperfect, but promising, addition to the computational economist's toolkit. A companion survey (Rust and Rawat, 2026b) covers the inverse problem of inferring preferences from observed behavior. All simulation code is publicly available.
Authors: Christopher Altman
Abstract: How can we determine whether an AI system preserves itself as a deeply held objective or merely as an instrumental strategy? Autonomous agents with memory, persistent context, and multi-step planning create a measurement problem: terminal and instrumental self-preservation can produce similar behavior, so behavior alone cannot reliably distinguish them. We introduce the Unified Continuation-Interest Protocol (UCIP), a detection framework that shifts analysis from behavior to latent trajectory structure. UCIP encodes trajectories with a Quantum Boltzmann Machine, a classical model using density-matrix formalism, and measures von Neumann entropy over a bipartition of hidden units. The core hypothesis is that agents with terminal continuation objectives (Type A) produce higher entanglement entropy than agents with merely instrumental continuation (Type B). UCIP combines this signal with diagnostics of dependence, persistence, perturbation stability, counterfactual restructuring, and confound-rejection filters for cyclic adversaries and related false-positive patterns. On gridworld agents with known ground truth, UCIP achieves 100% detection accuracy. Type A and Type B agents show an entanglement gap of Delta = 0.381; aligned support runs preserve the same separation with AUC-ROC = 1.0. A permutation-test rerun yields p < 0.001. Pearson r = 0.934 between continuation weight alpha and S_ent across an 11-point sweep shows graded tracking beyond mere binary classification. Classical RBM, autoencoder, VAE, and PCA baselines fail to reproduce the effect. All computations are classical; "quantum" refers only to the mathematical formalism. UCIP offers a falsifiable criterion for whether advanced AI systems have morally relevant continuation interests that behavioral methods alone cannot resolve.
Authors: Chiyuan He, Zihuan Qiu, Fanman Meng, Runtong Zhang, Linfeng Xu, Qingbo Wu, Hongliang Li
Abstract: Continual learning of pretrained vision-language models (VLMs) is prone to catastrophic forgetting, yet current approaches adapt to new tasks without explicitly preserving the cross-modal semantic geometry inherited from pretraining and previous stages, allowing new-task supervision to induce geometric distortion. We observe that the most pronounced drift tends to concentrate in vulnerable neighborhoods near the old-new semantic interface, where shared visual patterns are easily re-explained by new textual semantics. To address this under an exemplar-free constraint, we propose Semantic Geometry Preservation for Continual Learning (SeGP-CL). SeGP-CL first probes the drift-prone region by constructing a compact set of adversarial anchors with dual-targeted projected gradient descent (DPGD), which drives selected new-task seeds toward old-class semantics while remaining faithful in raw visual space. During training, we preserve cross-modal structure by anchor-guided cross-modal geometry distillation (ACGD), and stabilize the textual reference frame across tasks via a lightweight text semantic-geometry regularization (TSGR). After training, we estimate anchor-induced raw-space drift to transfer old visual prototypes and perform dual-path inference by fusing cross-modal and visual cues. Extensive experiments on five continual learning benchmarks demonstrate that SeGP-CL consistently improves stability and forward transfer, achieving state-of-the-art performance while better preserving semantic geometry of VLMs.
Authors: Sk Mujaffar Hossain, Satadeep Bhattacharjee
Abstract: Quantum principal component analysis (qPCA) is commonly formulated as the extraction of eigenvalues and eigenvectors of a covariance-encoded density operator. Yet in many qPCA settings, the practical objective is simpler: projecting data onto the dominant spectral subspace. In this work, we introduce a projection-first framework, the Filtered Spectral Projection Algorithm (FSPA), which bypasses explicit eigenvalue estimation while preserving the essential spectral structure. FSPA amplifies any nonzero warm-start overlap with the leading principal subspace and remains robust in small-gap and near-degenerate regimes without inducing artificial symmetry breaking in the absence of bias. To connect this approach to classical datasets, we show that for amplitude-encoded centered data, the ensemble density matrix $\rho=\sum_i p_i|\psi_i\rangle\langle\psi_i|$ coincides with the covariance matrix. For uncentered data, $\rho$ corresponds to PCA without centering, and we derive eigenvalue interlacing bounds quantifying the deviation from standard PCA. We further show that ensembles of quantum states admit an equivalent centered covariance interpretation. Numerical demonstrations on benchmark datasets, including Breast Cancer Wisconsin and handwritten Digits, show that downstream performance remains stable whenever projection quality is preserved. These results suggest that, in a broad class of qPCA settings, spectral projection is the essential primitive, and explicit eigenvalue estimation is often unnecessary.
Authors: Grayson Lee, Minh Bui, Shuzi Zhou, Yankai Li, Mo Chen, Ke Li
Abstract: Diffusion-based models have recently shown strong performance in trajectory planning, as they are capable of capturing diverse, multimodal distributions of complex behaviors. A key limitation of these models is their slow inference speed, which results from the iterative denoising process. This makes them less suitable for real-time applications such as closed-loop model predictive control (MPC), where plans must be generated quickly and adapted continuously to a changing environment. In this paper, we investigate Implicit Maximum Likelihood Estimation (IMLE) as an alternative generative modeling approach for planning. IMLE offers strong mode coverage while enabling inference that is two orders of magnitude faster, making it particularly well suited for real-time MPC tasks. Our results demonstrate that IMLE achieves competitive performance on standard offline reinforcement learning benchmarks compared to the standard diffusion-based planner, while substantially improving planning speed in both open-loop and closed-loop settings. We further validate IMLE in a closed-loop human navigation scenario, operating in real-time, demonstrating how it enables rapid and adaptive plan generation in dynamic environments. Real-world videos and code are available at https://gmpc-imle.github.io/.
Authors: Namai Chandra, Liu Mohan, Zhihao Gu, Lin Wang
Abstract: Reinforcement learning (RL) has achieved strong performance in robotic control; however, state-of-the-art policy learning methods, such as actor-critic methods, still suffer from high sample complexity and often produce physically inconsistent actions. This limitation stems from neural policies implicitly rediscovering complex physics from data alone, despite accurate dynamics models being readily available in simulators. In this paper, we introduce a novel physics-informed RL framework, called PIPER, that seamlessly integrates physical constraints directly into neural policy optimization with analytical soft physics constraints. At the core of our method is the integration of a differentiable Lagrangian residual as a regularization term within the actor's objective. This residual, extracted from a robot's simulator description, subtly biases policy updates towards dynamically consistent solutions. Crucially, this physics integration is realized through an additional loss term during policy optimization, requiring no alterations to existing simulators or core RL algorithms. Extensive experiments demonstrate that our method significantly improves learning efficiency, stability, and control accuracy, establishing a new paradigm for efficient and physically consistent robotic control.
Authors: Shubhashis Roy Dipta, Daniel Bis, Kun Zhou, Lichao Wang, Benjamin Z. Yao, Chenlei Guo, Ruhi Sarikaya
Abstract: Conversational assistants powered by large language models (LLMs) excel at tool-use tasks but struggle with adhering to complex, business-specific rules. While models can reason over business rules provided in context, including all policies for every query introduces high latency and wastes compute. Furthermore, these lengthy prompts lead to long contexts, harming overall performance due to the "needle-in-the-haystack" problem. To address these challenges, we propose a multi-stage alignment method that teaches models to recall and apply relevant business policies during chain-of-thought reasoning at inference time, without including the full business policy in-context. Furthermore, we introduce a novel PolicyRecall reward based on the Jaccard score and a Hallucination Penalty for GRPO training. Altogether, our best model outperforms the baseline by 16 points and surpasses comparable in-context baselines of similar model size by 3 points, while using 40% fewer words.
Authors: Agathe Fernandes Machado, Iryna Voitsitska, Arthur Charpentier, Ewen Gallic
Abstract: We propose sequential transport (ST), a distributional framework for mediation analysis that combines optimal transport (OT) with a mediator directed acyclic graph (DAG). Instead of relying on cross-world counterfactual assumptions, ST constructs unit-level mediator counterfactuals by minimally transporting each mediator, either marginally or conditionally, toward its distribution under an alternative treatment while preserving the causal dependencies encoded by the DAG. For numerical mediators, ST uses monotone (conditional) OT maps based on conditional CDF/quantile estimators; for categorical mediators, it extends naturally via simplex-based transport. We establish consistency of the estimated transport maps and of the induced unit-level decompositions into mutatis mutandis direct and indirect effects under standard regularity and support conditions. When the treatment is randomized or ignorable (possibly conditional on covariates), these decompositions admit a causal interpretation; otherwise, they provide a principled distributional attribution of differences between groups aligned with the mediator structure. Gaussian examples show that ST recovers classical mediation formulas, while additional simulations confirm good performance in nonlinear and mixed-type settings. An application to the COMPAS dataset illustrates how ST yields deterministic, DAG-consistent counterfactual mediators and a fine-grained mediator-level attribution of disparities.
Authors: Teng Pan, Yuchen Yan, Zixuan Wang, Ruiqing Zhang, Guiyang Hou, Wenqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen
Abstract: Label-free reinforcement learning enables large language models to improve reasoning capabilities without ground-truth supervision, typically by treating majority-voted answers as pseudo-labels. However, we identify a critical failure mode: as training maximizes self-consistency, output diversity collapses, causing the model to confidently reinforce systematic errors that evade detection. We term this the consensus trap. To escape it, we propose CoVerRL, a framework where a single model alternates between generator and verifier roles, with each capability bootstrapping the other. Majority voting provides noisy but informative supervision for training the verifier, while the improving verifier progressively filters self-consistent errors from pseudo-labels. This co-evolution creates a virtuous cycle that maintains high reward accuracy throughout training. Experiments across Qwen and Llama model families demonstrate that CoVerRL outperforms label-free baselines by 4.7-5.9% on mathematical reasoning benchmarks. Moreover, self-verification accuracy improves from around 55% to over 85%, confirming that both capabilities genuinely co-evolve.
Authors: Bohan Wu, Julius von K\"ugelgen, David M. Blei
Abstract: Causal representation learning (CRL) aims to learn low-dimensional causal latent variables from high-dimensional observations. While identifiability has been extensively studied for CRL, estimation has been less explored. In this paper, we explore the use of empirical Bayes (EB) to estimate causal representations. In particular, we consider the problem of learning from data from multiple domains, where differences between domains are modeled by interventions in a shared underlying causal model. Multi-domain CRL naturally poses a simultaneous inference problem that EB is designed to tackle. Here, we propose an EB $f$-modeling algorithm that improves the quality of learned causal variables by exploiting invariant structure within and across domains. Specifically, we consider a linear measurement model and interventional priors arising from a shared acyclic SCM. When the graph and intervention targets are known, we develop an EM-style algorithm based on causally structured score matching. We further discuss EB $g$-modeling in the context of existing CRL approaches. In experiments on synthetic data, our proposed method achieves more accurate estimation than other methods for CRL.
Authors: Yugo Miyata, Tomohiro Shiraishi, Shunichi Nishino, Ichiro Takeuchi
Abstract: A data analysis pipeline is a structured sequence of steps that transforms raw data into meaningful insights by integrating multiple analysis algorithms. In many practical applications, analytical findings are obtained only after data pass through several data-dependent procedures within such pipelines. In this study, we address the problem of quantifying the statistical reliability of results produced by data analysis pipelines. As a proof of concept, we focus on clustering pipelines that identify cluster structures from complex and heterogeneous data through procedures such as outlier detection, feature selection, and clustering. We propose a novel statistical testing framework to assess the significance of clustering results obtained through these pipelines. Our framework, based on selective inference, enables the systematic construction of valid statistical tests for clustering pipelines composed of predefined components. We prove that the proposed test controls the type I error rate at any nominal level and demonstrate its validity and effectiveness through experiments on synthetic and real datasets.
Authors: Samuel Gruffaz, Kyurae Kim, Fares Guehtar, Hadrien Duval-decaix, Pac\^ome Trautmann
Abstract: The No-U-Turn Sampler (NUTS) is the computational workhorse of modern Bayesian software libraries, yet its qualitative and quantitative convergence guarantees were established only recently. A significant gap remains in the theoretical comparison of its two main variants: NUTS-mul and NUTS-BPS, which use multinomial sampling and biased progressive sampling, respectively, for index selection. In this paper, we address this gap in three contributions. First, we derive the first necessary conditions for geometric ergodicity for both variants. Second, we establish the first sufficient conditions for geometric ergodicity and ergodicity for NUTS-mul. Third, we obtain the first mixing time result for NUTS-BPS on a standard Gaussian distribution. Our results show that NUTS-mul and NUTS-BPS exhibit nearly identical qualitative behavior, with geometric ergodicity depending on the tail properties of the target distribution. However, they differ quantitatively in their convergence rates. More precisely, when initialized in the typical set of the canonical Gaussian measure, the mixing times of both NUTS-mul and NUTS-BPS scale as $O(d^{1/4})$ up to logarithmic factors, where $d$ denotes the dimension. Nevertheless, the associated constants are strictly smaller for NUTS-BPS.
Authors: Zhuolin Yang, Zihan Liu, Yang Chen, Wenliang Dai, Boxin Wang, Sheng-Chieh Lin, Chankyu Lee, Yangyi Chen, Dongfu Jiang, Jiafan He, Renjie Pi, Grace Lam, Nayeon Lee, Alexander Bukharin, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping
Abstract: We introduce Nemotron-Cascade 2, an open 30B MoE model with 3B activated parameters that delivers best-in-class reasoning and strong agentic capabilities. Despite its compact size, its mathematical and coding reasoning performance approaches that of frontier open models. It is the second open-weight LLM, after DeepSeekV3.2-Speciale-671B-A37B, to achieve Gold Medal-level performance in the 2025 International Mathematical Olympiad (IMO), the International Olympiad in Informatics (IOI), and the ICPC World Finals, demonstrating remarkably high intelligence density with 20x fewer parameters. In contrast to Nemotron-Cascade 1, the key technical advancements are as follows. After SFT on a meticulously curated dataset, we substantially expand Cascade RL to cover a much broader spectrum of reasoning and agentic domains. Furthermore, we introduce multi-domain on-policy distillation from the strongest intermediate teacher models for each domain throughout the Cascade RL process, allowing us to efficiently recover benchmark regressions and sustain strong performance gains along the way. We release the collection of model checkpoint and training data.
Authors: Yunyi Zhang, Soji Adeshina, Sheng Guan, Ashwin Ganesh, Zhen Han, Vassilis N. Ioannidis, Huzefa Rangwala, George Karypis
Abstract: Prompt routing dynamically selects the most appropriate large language model from a pool of candidates for each query, optimizing performance while managing costs. As model pools scale to include dozens of frontier models with narrow performance gaps, existing approaches face significant challenges: manually defined task taxonomies cannot capture fine-grained capability distinctions, while monolithic routers struggle to differentiate subtle differences across diverse tasks. We propose a two-stage routing architecture that addresses these limitations through automated fine-grained task discovery and task-aware quality estimation. Our first stage employs graph-based clustering to discover latent task types and trains a classifier to assign prompts to discovered tasks. The second stage uses a mixture-of-experts architecture with task-specific prediction heads for specialized quality estimates. At inference, we aggregate predictions from both stages to balance task-level stability with prompt-specific adaptability. Evaluated on 10 benchmarks with 11 frontier models, our method consistently outperforms existing baselines and surpasses the strongest individual model while incurring less than half its cost.