Authors: Lei Yang
Abstract: We present EaaS, a cloud-native reference architecture that operationalizes AI evaluation methods as six stateless Kubernetes microservices: conformal prediction with finite-sample-corrected Adaptive Prediction Sets, calibration assessment, drift detection via RFF-approximated Maximum Mean Discrepancy, fairness monitoring with bootstrap confidence intervals, a DAG-based pipeline orchestrator, and a result storage API. We validate four key methodological concerns. First, empirical coverage is consistent with the marginal conformal guarantee across K=50 random calibration/test splits, with mean coverage within 1.4 percentage points of the nominal target. Second, all four MMLU answer tokens appear in the top-20 logprobs with 0% imputation needed, and simulated imputation at 10% produces less than 1.5% coverage impact. Third, RFF-MMD achieves 100% detection power for mild and severe drift at the median heuristic bandwidth, with Type I error between 5-8.5%. Fourth, fairness monitoring on the UCI Adult Income dataset reveals significant demographic parity disparities by race (DP gap=0.33) with stable alerts across sequential batches. Conformal prediction and calibration services achieve sub-2ms p99 latency at batch size 100; RFF-MMD requires ~500ms suited for periodic batch monitoring. A comparison with four open-source tools suggests that, to the best of our knowledge, no current platform combines conformal-prediction-as-a-service, microservice decomposition, and DAG-based orchestration.
Authors: Taegun An, Dohun kim, Haebeom Lee, Changhee Joo
Abstract: Logic Gate Networks (LGNs) implement computation through compositions of Boolean operations, yet unlike classical Boolean circuits, existing LGNs do not reliably benefit from increased depth. We identify two distinct causes: optimization collapse in deep relaxed LGNs and a topology-induced limitation that persists even when skip-biased initialization and straight-through estimation stabilize training. Thus, trainability alone is insufficient; deeper layers must also receive information that supports useful computation. We introduce Input-Anchored Logic Gate Networks (IALGNs), in which each gate combines an evolving hidden feature with a direct input anchor. This topology preserves a computational spine while conditioning every layer on the original input. We show that a depth-D path can depend on up to D+1 input bits and establish a strict path-wise depth hierarchy. Random-k anchor relaxation further improves anchor selection without relaxing the spine. Across MNIST, CIFAR-10, and CIFAR-100, IALGNs achieve consistent fixed-width depth--accuracy improvements beyond 100 layers, whereas alternative LGN topologies saturate or degrade. Layer-wise probes, topology ablations, and effective-depth analysis show that input anchoring produces progressively more informative representations and preserves longer computational paths. These results demonstrate that scalable depth in LGNs requires both stable optimization and an information-access pattern that supports input-conditioned refinement.
Authors: Tasfia Nuzhat Ornee, Elias Hossain, Ivan Garibay, Niloofar Yousef
Abstract: Masked discrete diffusion for molecular graph generation typically applies a uniform corruption schedule to all tokens in a lossless graph-to-sequence representation, implicitly treating structurally heterogeneous molecular components as equally difficult and equally important to reconstruct. However, different molecular graph token roles exhibit substantial variation in denoising difficulty and their influence on the decoded molecule, motivating role-specific corruption strategies. We introduce MotifRole-Diff, a role-aware corruption process that allocates masking rates according to empirically measured denoising difficulty and graph-level perturbation impact while preserving the model architecture, clean sequence space, and lossless molecular-graph decoder. We formulate schedule selection as the risk-optimal allocation of a fixed masking budget across token roles. Our theorem characterizes optimality for the modeled role-weighted residual risk, while downstream generation performance is evaluated empirically. Under matched architecture, training budget, and sampling compute, MotifRole-Diff improves validity on QM9 from 0.905 to 0.944 while reducing FCD from 1.701 to 1.609, and on MOSES improves validity from 0.920 to 0.938 while reducing FCD from 2.125 to 1.850. Role-wise diagnostics further show improved reconstruction across molecular graph token categories. Together, these matched-compute results indicate that structurally informed corruption is a more effective masking strategy than uniform schedules for serialized molecular graph diffusion.
Authors: Pin Qian, Su Wang, Yihang Chen, Qiaolin Yu, Xiaoyuan Wang, Zhitong Guo, Zhicheng Wang, Junxian You
Abstract: Personal agents maintain memories, learned skills, tool configurations, and policy state that evolve with each user. Existing agent benchmarks often evaluate these capabilities in isolation: tool benchmarks test invocation under fixed APIs, memory benchmarks test recall or forgetting, and safety benchmarks test static policy compliance. We argue that personal-agent evaluation requires a different protocol: replaying the same temporal intervention across different persistent user-conditioned states and measuring how failures propagate across agent components. We formalize this requirement as four conditions: explicit temporal intervention, persistent state across the intervention, induced cross-dimensional effects, and variation in user-conditioned state. A focused audit of public benchmark protocols selected by explicit inclusion criteria identifies several close cases. Under our explicitly narrow operationalization, we did not find a protocol in that audited set satisfying all four conditions. This claim is scoped as a focused gap analysis with bounded literature coverage. This position paper proposes a minimal benchmark design and candidate reporting metrics for user-conditioned adaptation. The result is a concrete design requirement for future personal-agent evaluation, with metrics used as reporting tools for that requirement.
Authors: Jie Zhang
Abstract: Synthetic tabular data is valued for preserving not only each column's marginal distribution but the dependencies between columns -- structure that carries much of the discriminative signal for minority classes in imbalanced domains such as fraud and clinical risk. Yet the metrics most commonly used to certify synthetic tabular data are, we show, largely blind to inter-column dependency: a baseline that models every column independently (and therefore destroys all dependency) is judged indistinguishable from real data by the logistic-regression C2ST, and the pairwise Trend score is only partially sensitive. We introduce a dependency-aware fidelity diagnostic that decomposes a strong classifier two-sample test (XGB-C2ST) into marginal, dependency, and numerical-categorical cross components, anchored between a worst-case fully-factorized reference (all dependency destroyed) and a best-case real-data oracle. Applying it to a state-of-the-art flow-matching generator (TabbyFlow/EF-VFM), we find a real dependency gap that standard metrics miss; destroying dependency outright collapses minority-class utility, and the generator's residual gap carries a smaller, consistent utility cost. We then ask whether this gap reflects a structural limitation of mean-field generative objectives. It does not: consistent with recent recovery results for variational flow matching, the objective is asymptotically exact. Yet the gap is stubborn -- a 16x increase in model capacity does not close it -- pointing to the absence of direct dependency supervision rather than a capacity or structural limit. Consistent with this, and because the residual gap is higher-order, no cheap intervention closes it: not an in-model dependency mechanism, not post-hoc copula correction, and not the 16x capacity increase -- a caution for a field that assumes such fixes help.
Authors: Julian G. Soltes
Abstract: This paper explores the efficacy of quasi-Monte Carlo (QMC) weight initialization for meta-reinforcement learning within modern benchmark environments. Various sampling methods are used to bound a population-based search and aggregate an optimal prior from a baseline set of tasks. The QMC meta-priors show improvements in training convergence compared to modern orthogonal (SB3) defaults when extrapolated to similar unseen continuous control environments. In dissimilar tasks, the orthogonal orientation was globally superior for an unbiased search.
Authors: Jonathan Gallagher, Roberto Guglielmi
Abstract: We present a goal-agnostic control framework for partial differential equations (PDEs) built around a joint-embedding predictive architecture (JEPA). The small 2D ViT encoder and action-conditioned latent dynamics are trained offline without a reward or downstream goal, frozen, and reused by a model-predictive path integral (MPPI) controller. We find that when available, the control objective is better applied to an explicit physical observable (provided injectivity) than to minimizing raw Euclidean distance ($L^2$) in the learned latent space. For a learned linear kinetic-energy (KE) probe on frozen latent rollouts we can reproduce held-out trajectories with $R^2=0.989$, while requiring no change to the underlying world model. On the PDE Control Gym 2D Navier--Stokes benchmark, using KE-probe planning improves the matched 50-episode native reward from $-12.08\pm0.86$ for latent-$L^2$ planning to $-10.90\pm0.91$ (95\% CI), while lowering last-quarter velocity-field RMSE from $0.0765$ to $0.0692$. Across three intentionally withheld, dissimilar, aperiodic targets, KE planning lowers late field RMSE by $53\%$ relative to latent-$L^2$ planning ($0.0220$ versus $0.0469$), winning all 30 paired episodes. The same frozen model also supports controls targeting stabilization around a steady configuration via direct regulation of KE achieving $2.7\%$ mean relative error. While the latent probe is brittle to measurement noise and missing pixels, we believe the results support the claim that latent dynamics can remain both dynamic and goal-agnostic while calibrated observables (granted they guarantee unique continuation) may be a better objective for state control
Authors: Kavya Bhand, Aadi Joshi
Abstract: Multi-horizon latent consistency is a common training knob in video predictors and world models, but practitioners rarely know what it does to transition geometry. We treat lambda, the weight on multi-step latent agreement, as a diagnostic control and measure an empirical expansion proxy L20,q95 together with horizon-20 prediction error E20. On Moving-MNIST (n=6 seeds at the critical pair), raising lambda from 0 to 0.8 cuts L20 from 4.96 +/- 2.01 to 1.01 +/- 0.06 (paired t p=0.005, Wilcoxon p=0.031) and halves E20 (0.365 to 0.177, paired t p=1.1e-13). Four of six seeds cross L<1 at lambda=0.8. The same loss does not produce population L<1 on action-conditioned Pendulum-v1 or CartPole-v1, nor on KTH Actions video, even when E20 improves. An associational mediation analysis on MMNIST gives r-hat=0.94 (95% CI [0.88, 1.00], n=27, B=2000); lambda was not randomized. Defensive checks (architectural baselines, exogenous stress, WorldTest, MPC, scaling) mostly support a narrow claim: soft consistency can push passive video toward a near-contractive band, and that band is domain-limited. A stochastic-forcing law L20 ~ 1.23 + 1.82 eta at lambda=0.8 (bootstrap slope CI [1.73, 1.92], R^2=0.96) unifies control domains on the same curve via calibrated eta_eff. Complete joint slices at lambda in {0.4, 1.2} (30/30 cells, 5 eta x 3 seeds) show comparable linear L20(eta) slopes (~1.69 and ~2.00); we do not fit a continuous (lambda, eta) surface. We do not report DreamerV3 or TD-MPC2 returns.
Authors: Timothy Tomashevskiy
Abstract: Ensuring safety in reinforcement learning under nonstationarity requires determining whether a learning system can safely adapt to forecasted environmental change within the required recovery horizon. Existing safe reinforcement learning methods typically assume stationary environments and do not explicitly consider adaptation speed as a safety concern. However, when environments evolve over time, delayed adaptation may result in transient unsafe behavior. This paper proposes adjustment speed as a safety constraint for nonstationary reinforcement learning. The central idea is to define safety in terms of adaptation feasibility: future states or regions may become unsafe when the adaptation required to remain safe exceeds the learning system's calibrated recovery capacity. The proposed framework uses learned context representations and short-horizon context forecasts to estimate adaptation demand and compare it with the agent's achievable adaptation capacity. When predicted adaptation demand exceeds the calibrated recovery capacity, the framework proactively tightens the admissible action set and activates an action-level shield to reduce unsafe behavior before violations occur. Experiments in a nonstationary driving environment show that the proposed approach primarily reduces safety violations in short-horizon windows aligned with context changes. Ablation studies further show that shielding is more conservative for peak- and tail-risk suppression, while optimization-level adjustment provides additional reductions in short-horizon switch-conditioned violations. These results support adaptation feasibility as a practical safety principle for reinforcement learning under nonstationarity and demonstrate that proactive intervention can improve safety during periods of environmental change.
Authors: Shanika Iroshi Nanayakkara, Shiva Raj Pokhrel
Abstract: Quantum federated learning enables distributed clients to train quantum neural networks without sharing local data, making it promising for privacy-aware intelligent services. Intelligent services in this context refer to privacy-sensitive distributed decision systems, such as fraud detection and genomic classification, where reliable and fair client-level learning is as important as the accuracy of the aggregate model. However, heterogeneous client data and noisy quantum optimization often cause unstable local updates, client drift, and unfair performance between clients. This paper proposes DUQFL-Prox, a drift-stable quantum federated learning framework based on deep-unfolded local optimization. Instead of using a fixed local optimizer, each client performs adaptive unfolded SPSA updates, while a proximal term keeps the local model close to the global model. A lightweight controller learns step-specific optimization parameters to improve post-aggregation performance. Experiments on financial fraud and genomic classification tasks show that DUQFL-Prox improves stability, generalization, and client fairness compared with standard QFL baselines. The results suggest that deep-unfolded quantum federated learning can support more reliable and fair intelligent services in heterogeneous distributed environments.
Authors: Kilian Rue{\ss}, Gennadiy Averkov, Florestan Brunck, Moritz Grillo, Christoph Hertrich, Georg Loho, Jack Stade, Moritz Stargalla, Matthew Sun, Martin Winter
Abstract: We prove that the maximum of $n$ real numbers is exactly representable by a ReLU network with two hidden layers for every $n\le 10$. The constructions are obtained by reducing the problem to exact rational linear algebra: after a symmetry reduction, the necessary cancellations are encoded in finite linear systems over $\mathbb{Q}$, which we solve and verify computationally. The representation of $\max_{10}$ has a structured first hidden layer consisting only of pairwise maxima, a feature that allows it to be recursively substituted into larger networks. We use this to show that for every $n>10$, the maximum $\max_{n}$ can be exactly represented with $\lceil{\log_5 (n / 2)\rceil}+1 < \log_5(n) +1.5694$ hidden layers. Via the generalized hinging-hyperplane representation [Wang, Sun, IEEE Trans. Inf. Theory 2005], the same depth bound holds for all continuous piecewise-linear functions on $\mathbb{R}^d$, with $d+1$ in place of $n$. In particular, every continuous piecewise-linear function on $\mathbb{R}^d$ for $d\le 9$ admits a two-hidden-layer ReLU representation. Our results improve on [Bakaev, Brunck, Hertrich, Stade, Yehudayoff, STOC'26]. In that work, the authors established a two-hidden-layer representation for $\max_{5}$ and an upper bound of $\lceil{\log_3 (n-2)\rceil}+1$ hidden layers for $\max_{n}$.
Authors: Jian Hu, Huiying Li, Hao Zhang, Binfeng Xu, Yifan Zhang, Shaokun Zhang, Hemil Desai, Michael Demoret, Pavlo Molchanov, Jan Kautz, Yi Dong
Abstract: Agentic reinforcement learning research is constant algorithm modification, new estimators, new pipeline stages, new rollout schemes, and in mainstream frameworks each change threads through layers of trainer, distributed backend, and rollout glue: the cost lands on the researcher at every iteration. Molt is a PyTorch-native training framework built to keep that cost small: a codebase compact and clean enough for a researcher to hold in their head, and for an AI coding assistant to read and reason about in its entirety, so the algorithm flow can be traced and changed end to end. The agent is an ordinary program, and one asynchronous loop trains multimodal and mixture-of-experts policies while never training on a token it did not generate, consistent in tokens, policy versions, and model semantics. Leanness does not cost performance: under a matched, fully asynchronous protocol, Molt is statistically comparable to a state-of-the-art Megatron-based stack. Molt is open source and provides recipes and containers at https://github.com/NVIDIA-NeMo/labs-molt.
Authors: Aubida A. Al-Hameed, Mohammed M. H. Qazzaz, Maryam Hafeez, Syed A. Zaidi
Abstract: Proactive service assurance in O-RAN requires predicting per-slice SLA violations before they occur. The prediction model must be auditable by operators and must train across base stations without pooling per-slice KPIs, which are commercially sensitive because slices are leased to individual tenants. Neural additive models (NAMs) offer auditability because each KPI contributes through a visible shape function. However, visibility alone does not guarantee physical validity. On the ColO-RAN testbed dataset, unconstrained NAMs learn effects that contradict wireless physics, for example predicting higher risk when channel quality improves. This failure appears under both local and centralized training, and non-IID federated averaging worsens it. We present Monotone FedNAM, a federated additive model in which KPIs with unambiguous physical direction are represented as monotone splines whose constraints survive FedAvg aggregation by construction, while contestable KPIs remain unconstrained. The model trains and operates as a Non-RT RIC rApp and is compact enough for deployment as a Near-RT RIC xApp. Monotone FedNAM eliminates all monotonicity violations, raises constrained shape consistency from 0.71 to 1.00, generalizes to an unseen scheduling policy, and reduces uplink traffic by 65%, at a cost of 0.04 to 0.07 AUC. These results show that physically constrained federated additive models can support auditable SLA risk inference for multi-tenant O-RAN service assurance
Authors: Idris Karel Seunda Ekwe, Patrick Tenga Shako, Ernest Parfait Fokou\'e
Abstract: Neural network compression and interpretability remain open challenges in modern deep learn- ing, where billion-parameter architectures deliver impressive accuracy at the cost of trans- parency, computational efficiency, and reliable uncertainty quantification. This paper introduces Neural Atom Prevalence (NAP), a principled Bayesian framework for structured node-level model selection in feedforward neural networks. NAP introduces the neural atom (activation unit) and functions as a hybrid method operating through a four-phase pipeline: Bayesian Lottery Ticket (BLT) identification via Iterative Magnitude Pruning (IMP), soft variational training of the Spike and Slab Independent Gaussian (SS-IG) model, Poisson-Binomial (PB) optimal layer-size selection, and Bayesian fine-tuning to produce a sparse, stable, interpretable, and accurate model. Extensive empirical validation across simulated nonlinear regression, two UCI benchmark datasets (Concrete, YearPredictionMSD), and the MNIST image classification task demonstrates that NAP achieves state-of-the-art structural sparsity, reducing active nodes to as few as 8% of the original dense architecture on MNIST, while well-calibrated probabilisti- cally: the aleatoric-epistemic uncertainty decomposition reveals that model ignorance accounts for only 3 to 4% of total predictive variance across all experiments, and regression reliability diagrams confirm a near-nominal predictive interval coverage (93.4% observed against a 95% target). These results establish NAP as a reliable, theoretically grounded, and computation- ally tractable solution to the simultaneous pursuit of sparsity, accuracy, interpretability, and uncertainty quantification in Bayesian neural networks.
Authors: Vishnu Bindu Balachandran
Abstract: Test-time adaptive out-of-distribution (OOD) detectors update a memory bank from the unlabelled stream. We show this adaptation obeys a provable dynamical law. Modelling bank impurity as a generalized P\'olya urn, we prove almost-sure convergence to a mean-field equilibrium whose slope acts as a reproduction number. Below one, impurity stays benign. Above one, the bank is fully poisoned and the detector collapses. The measured admission kernel is affine ($R^2 \ge 0.996$) with slope just below one in every encoder family (a protocol signature), so this detector class is near-critical by design, and across 96 settings the predicted threshold matches the empirical collapse, where ungated dictionaries lose up to $0.163$ AUROC. We then prove that a certified admission gate, reading only a frozen reserve, severs the feedback loop and removes the transition at every contamination rate, even adversarially, while controlling false positives label-free. For the complementary static-calibration failure under drift we give CDC, which restores nominal FPR label-free on all tested drift-affected cells. Finally we prove a two-world impossibility theorem. Drift and contamination are indistinguishable without labels, forcing a closed-form power ceiling our procedure approaches. Together these give a complete possibility/impossibility characterization of label-free adaptive OOD detection.
Authors: Takato Yasuno
Abstract: Bridge infrastructure deteriorates gradually, yet its root causes---salt intrusion, freezing, fatigue cracking, and others---remain invisible to the naked eye. Expert diagnosis relies on tacit knowledge built over years of practice. We address the challenge of automating this latent causal reasoning by proposing a Damage Cause Encoder that classifies 10-class damage causes from visible damage descriptions $S_i$ for use in autonomous bridge diagnostic agents. Our approach chains three components: (i)Knowledge Triple Extraction---a large language model extracts causal triples of the form (damage $\xrightarrow{\mathtt{caused\_by}}$ cause) from 15--35 diagnostic PDF manuals and indexes them in a FAISS vector store; (ii)Retrieval-Augmented Context---at training and inference time, relevant causal triples $\mathcal{C}_i$ are retrieved and concatenated with $S_i$, converting implicit domain knowledge into explicit Encoder context; (iii)Systematic Fine-tuning Comparison---we conduct a rigorous comparison of LoRA, QLoRA, and QA-LoRA on a fixed Golden Testset (116 stratified samples), demonstrating that QLoRA achieves the optimal trade-off: identical test accuracy (87.07%) to full-precision LoRA, 11% faster inference, 72% lower GPU memory, and superior generalization across diverse unseen inputs. A controlled Golden Testset---stratified, deduplicated, and difficulty-tagged---is introduced as a reusable benchmark contribution. QLoRA further outperforms LoRA by 13 percentage points on a 100-sample diverse evaluation spanning all 10 damage cause classes.These findings enable memory-efficient, high-accuracy diagnostic agents on consumer-grade hardware for edge deployment.
Authors: Awsaf Tausif Adib, Md. Shahria Sarker Shuvo, Md. Estehaar Ahmed Emon, Mustafa Kamal, Fuad Rahman, Shafin Rahman, Nabeel Mohammed
Abstract: Accurately modeling cross-variate dependencies remains a key challenge in multivariate time series forecasting, particularly in the presence of strong periodic patterns. Many existing approaches rely on attention-based mechanisms that incur quadratic complexity and scale poorly with increasing numbers of variates. Recent attention-free aggregation models address this issue through linear-complexity core-based interactions, but they do not explicitly leverage the global periodic structure present in the data. To overcome this limitation, we propose CARNet, a Cycle-Conditioned Core Aggregation and Redistribution framework that integrates global recurrent cycle information into efficient core based interaction modeling via Multihead Core Aggregation. Extensive experiments on multiple real-world multivariate forecasting benchmarks demonstrate that CARNet consistently outperforms strong transformer and non-attention baselines across diverse prediction horizons while preserving linear-complexity modeling of cross-variate dependencies.
Authors: Jim Allchin
Abstract: Sparse attention reduces the cost of long contexts by allowing each query to read only selected parts of the input. These selectors are often trained by distilling the attention patterns of a dense teacher, assuming that attention reveals which context the teacher actually uses. We test that assumption on retrieval tasks where the evidence for each answer is known exactly. By masking parts of the context and measuring whether the answer changes, we find that attention and causal dependence often disagree, and distilled selectors inherit the mismatch. Teachers attend to outdated facts they have learned to ignore, and their attention can vary across training runs even when they rely on the same evidence. In a two-step reference task, attention at the answer skips the intermediate step because it was resolved earlier in the forward pass: a selector trained on attention achieves 41% accuracy, while the same selector trained on causal evidence reaches 99% and matches the teacher. These evidence sets require no annotation: recovered from a frozen teacher by masking alone, they train selectors to the same accuracy. We find the same conflict in pretrained models: Qwen2.5-3B gives more attention to an outdated fact than the current one on 58% of conflicting-fact examples despite answering correctly, while Gemma-2-9B rises from 56% to 99% accuracy when restricted to the two relevant sentences. Attention shows where a model looks, not necessarily what its answer depends on; across the regimes we tested, that dependence matched or outperformed attention as a training target.
Authors: Maximilian Dax, Theo Heimel, Gilles Louppe
Abstract: Simulation-based inference (SBI) with machine learning is an increasingly important tool for solving inverse problems in science and engineering, including parameter inference and the inversion of detector effects. We provide an overview of the Bayesian and frequentist statistical frameworks, describe how machine-learning-based SBI methods, such as neural posterior estimation and neural likelihood estimation, can be used for parameter estimation within these frameworks, and show that the same methods can also be applied to Empirical Bayes or unfolding tasks. We also discuss how to validate inference results and the limitations of SBI with machine learning.
Authors: Alexandru Meterez, Pranav Ajit Nair, Depen Morwani, Cengiz Pehlevan, Sham Kakade, Alex Damian
Abstract: Due to the complexity of neural network loss landscapes, optimization theory is forced to rely on idealized models, and there is generally a tradeoff between how theoretically tractable the model is, and how accurately it describes the true optimization dynamics. In this work, we stress test the simplest possible model of optimization -- the quadratic model -- and show that it can be surprisingly predictive in an LLM setting with 150M parameters and 3B training tokens. Specifically, we show that Taylor expanding the model and the loss function at intermediate checkpoints through training can accurately predict the optimization dynamics over windows that can last up to 10\% of training. Having established this agreement, we then turn to analyzing the structure of these local quadratic optimization problems through two lenses: the Hessian spectrum and local stability. Using Lanczos quadrature with extremely deep probes, we are able to estimate the Hessian spectrum deep into the tail, and we find a surprising amount of structure in both the eigenvalues and eigenvectors, which depends on the batch size, preconditioner, and training time. We also empirically test local linear stability at intermediate checkpoints and compare it to theoretical predictions to demonstrate that optimization in LLMs typically occurs at a stochastic edge of stability, whose nature is also determined by batch size. Our results indicate the quadratic model may be a theoretically tractable proxy for pretraining optimization dynamics.
Authors: Zahra Yousefijamarani, Alaa Alameldeen
Abstract: Transformers are widely used across many domains, including natural language processing, computer vision, web search, and DNA sequence analysis. Given their broad applicability, improving the performance of transformer models is critical. However, the high volume of data movement between processing units and memory during attention operations significantly limits their efficiency. Processing-In-Memory (PIM) mitigates this issue by performing computations directly inside memory. While prior work has proposed PIM-based transformer implementations, they suffer from costly inter-bank communication, and struggle to scale due to the limited capacity of memory banks. As a result, attention-related data must be split across banks, diminishing the potential benefits of PIM. In this work, we propose RED-PIM, an algorithm-architecture co-design that reduces attention latency by minimizing inter-bank data movement from O(N^2) to O(N) and shrinking intermediate attention matrices from N x N to d x d. By reorganizing matrix operations, performing computations locally, and employing an optimized data transfer strategy, RED-PIM significantly reduces computation cost and interconnect traffic. Compared to baseline PIM implementation, RED-PIM achieves inference time reductions ranging from 16.05% to 99.99% (geometric mean of 66.42%), with the largest gains on longer sequences. On real-world datasets, RED-PIM improves performance by 99.60% for long documents and 13.44% for shorter ones, while maintaining or improving accuracy. These results demonstrate RED-PIM's effectiveness for scalable and efficient transformer inference.
Authors: Debarshi Kundu, Swaroop Ghosh, Vasant Honavar
Abstract: Data-adaptive sparse attention masks substantially outperform fixed patterns (e.g., BigBird and Longformer) and can even exceed dense attention on long sequences. Existing adaptive approaches---including SBM-Transformer, Dynamic Mask Attention, and NSA---typically require additional learnable parameters, custom gradient estimators, or specialized CUDA kernels. We show that classical data compression provides an effective masking signal with \textbf{no additional parameters}. By computing per-block gzip compression ratios, we identify non-redundant content blocks and route long-range attention selectively through them. Intuitively, blocks that gzip cannot compress contain information not predictable from local repetition, making them natural long-range attention targets. Because the compression profile is input-dependent, the resulting sparse mask adapts dynamically to content without learned parameters, auxiliary losses, or custom kernels. On PG-19 byte-level language modeling at 92M parameters with 8K context, our method achieves 1.71 bits-per-byte (BPB), outperforming dense attention (2.89), BigBird (2.34), Longformer (3.21), and a reimplemented SBM-Transformer (3.38)---the only learned-mask baseline---by up to 1.67 BPB while adding no parameters. The advantage grows with sequence length, with the gap over BigBird widening from 0.05 BPB at 4K context to 0.63 BPB at 8K, while convergence is 3.3$\times$ faster.
Authors: Aakil Caunhye, Xuefei Lu, Belen Martin-Barragan
Abstract: In this paper, we propose and study a robust variant of the smart predict-then-optimize approach that accounts for prediction shifts due to disturbance in the covariate feature space. While traditional integrated-learning-and-optimization models assume that side information is perfectly revealed, empirical data-driven features are frequently corrupted or noisy at the time of decision-making, leading to fragile operational policies. To bridge this gap, we integrate principles of robust optimization directly into the predictive-prescriptive pipeline via a smart predict-then-robustly optimize loss and establish a computationally tractable convex surrogate, designed to hedge against worst-case feature perturbations. On the theoretical front, we formalize the structural validity of this surrogate by proving its approximation error probability decays exponentially according to a sub-Gaussian concentration profile. Furthermore, we establish that under mild assumptions, the surrogate is Fisher consistent with high probability. We also prove necessary conditions under which our framework outperforms standard smart predict-then-optimize and maintain its superiority even when the standard method is equipped with regularized upstream predictions. Numerical experiments validate that our robust framework consistently yields significant performance improvements over standard methods, both in out-of-sample terms and in training stability.
Authors: Othmane Harraq, Tamer Aldwairi
Abstract: Talking-face (TF) deepfake generation synthesizes photore- alistic facial video from a static source image and an au- dio signal, producing forgeries that current image-based detectors consistently fail to identify. Unlike face-swap ma- nipulation, TF synthesis has no underlying real video from which to inherit physiological characteristics, making re- mote photoplethysmography (rPPG) a uniquely motivated detection modality for this forgery category. We propose a detection framework that extracts per-video rPPG wave- forms via RhythmFormer and trains a suite of lightweight classifiers to distinguish real from synthesized physiologi- cal signals. Evaluated on the TF subset of Celeb-DF++ un- der a strict subject-independent protocol, where test identi- ties are completely separated from training identities, our 1D ResNet achieves an AUC of 0.806 and EER of 27.8%, placing it within 2.4 points of the best published general- purpose detector (Effort, ICML 2025) while operating ex- clusively on the physiological channel. We document a con- trolled reproduction study of DeepFakesON-Phys, the rep- resentative prior rPPG detector, demonstrating degrada- tion from AUC 0.999 on legacy face-swap data to 0.622 on the TF subset of Celeb-DF++. We further show that detec- tion difficulty is strongly method-dependent: AUC ranges from 0.985 (Real3DPortrait) to 0.690 (IP-LAP) across the seven TF generators, with the ranking remaining perfectly stable across all evaluation protocols. This spread reflects an interpretable physiological property of each generator rather than evaluation noise, and constitutes the primary theoretical contribution of the work.
Authors: Jonathan Zhang, Erik Skalnes, Jacob Chen, Michael Oberst
Abstract: Predictive machine learning (ML) models are increasingly used to aid human decision-makers across various high-risk domains such as healthcare and criminal justice. There is a growing recognition of the need to evaluate the causal impact of deploying these systems on downstream outcomes, such as patient survival or crime recidivism. Randomized control trials (RCTs) can provide high-quality evidence on the impact of a deployed model, but they run into a challenge: it is often infeasible to run repeated trials when models are updated or retrained to improve predictive performance. In this work, we present a partial-identification approach to using prior RCT data to construct bounds on the causal effect of a new model. The core innovation in our approach is to leverage assumptions relating fine-grained predictive accuracy to downstream outcomes. We do so via two monotonicity assumptions: first, on individual-level `counterfactual correctness' (all else being equal, a correct prediction leads to non-inferior outcomes); and second, on the relation between subgroup predictive performance and outcomes, interpretable as an assumption regarding trust in model outputs. We demonstrate our method with a simulation study, illustrating how incorporating this information can lead to more informative bounds compared to prior work.
Authors: Sergio A. Alvarez
Abstract: We show that, up to isotropic scaling, the Gaussian RBF reproducing kernel Hilbert space (RKHS) is asymptotically isometric to Euclidean space in the large bandwidth limit. This strongly suggests that kernel-based constructions reliant on metric properties of the RKHS will yield results for Gaussian RBF kernels that similarly approach those of linear kernels for large bandwidths. The asymptotic behavior of Gaussian CKA can be understood in this light. We further consider kernel PCA, showing that Gaussian RBF eigenvalues, eigenprojections, and principal components all converge to those of classical (linear) PCA as bandwidth $\sigma \rightarrow \infty$. For a given data representation, both the RKHS feature embeddings and the orthogonal PCA eigenframes of the two kernel types differ asymptotically by a geometric similarity transformation, up to a residual of size $O \left (\frac{\rho}{\sigma} \right )^2$, where $\rho$ is a measure of geometric eccentricity of the representation, equal to the ratio of maximum to median pairwise distance between data examples. Experiments over a diverse collection of data sets demonstrate that $\rho$ provides a simple and reliable predictor of dataset-specific convergence behavior in the top principal directions.
Authors: Bertil Braun
Abstract: We present a traffic-signal control interface in which a shared graph neural network assigns scores to individual traffic movements. Each junction converts these scores into its own variable-sized set of legal signal phases using a deterministic incidence matrix. Directed corridor nodes provide traffic context, while movement nodes represent controlled input-to-output paths through junctions. Typed mean aggregation produces one scalar per movement; phase definitions and signal timing remain outside the learned network. This makes graph size and junction-specific action count independent of the learned parameter shapes. PPO experiments evaluate the interface on unseen synthetic grid geometries, altered signal coverage, and five heterogeneous city graphs. The policies retained performance across unseen geometries within the synthetic grid family, while changes in signal coverage exposed sensitivity to a signal-coverage distribution shift. A single trained city-policy instance executed across all five city graphs, with heterogeneous outcomes. These results provide feasibility evidence rather than a general estimate of transfer to arbitrary road networks.
Authors: Charles Brum, Edward Finkelstein
Abstract: We investigate whether symbolic regression can discover explicit neural network weight-update rules that outperform standard hand-designed optimizers on small symbolic regression benchmarks. Candidate update rules are represented as fixed-depth symbolic expressions over operands derived from common optimizers, including gradient, momentum, adaptive-gradient, and moment-estimate quantities. Across 30 benchmark/neural network combinations, the symbolic regression procedure found an update rule outperforming the best hyperparameter-tuned established optimizer in 25 cases, with an aggregate MSE reduction of 44.47\% over the improved cases. The discovered rules do not all share a single common symbolic form, but many combine adaptive normalization, momentum-like quantities, nonlinear transformations, and rational expressions. These results suggest that symbolic regression can serve as a lightweight mechanism for discovering compact optimizer variants, while also highlighting the need for larger-scale validation.
Authors: Ziran Yang, Chengshuai Shi, Raj Ghugare, Benjamin Eysenbach, Karthik Narasimhan, Chi Jin
Abstract: Modern reasoning models depend on reasoning data, today sourced from human annotations or distilled from stronger LLMs. However, a rich and largely untapped source of supervision lies in expert systems (e.g., game engines, classical planners, theorem provers), which routinely produce near-optimal actions across diverse domains. But these experts are silent: they commit to an action without writing down the chain of thought (CoT) behind it. Recovering that CoT as natural-language reasoning would distill expert knowledge into a student that generalizes beyond the demonstrated actions. We treat it as a latent variable and study how to recover it from the action alone. Our approach, LeAct (Learning to reason from Actions), optimizes this latent variable: the student samples candidate CoTs for each expert action, and we retain those that measurably improve its own probability of recovering the action. Across imperfect-information games at multiple scales and a simulated robotics benchmark, LeAct reaches the solver's numerical floor on small enumerable games. At larger scale, it is $5\times$ closer to the solver than the strongest expert-iteration baseline. At Flop Hold'em ($\sim 10^9$ infosets), LeAct wins head-to-head by $+60$ mbb/g, and on the robotics probe it is the only training recipe that improves on direct imitation. We present a principled framework and the result: expert systems become a categorically new source of reasoning teachers for foundation models.
Authors: Kaihua Ding
Abstract: Prior classical-ML learning-curve work fits power laws to tree, linear, and kernel models on tabular data, but at small scale: typically one curve, one team, a handful of cells. We present a distributed classroom-scale replication: 127 students each ran a fixed protocol on 3 assigned datasets, drawn from 18 tabular classification and regression datasets and 6 model families (Boosting, Random Forest, SVM, Linear/Logistic, Ridge, Lasso), yielding 11,536 training runs and 1,648 fitted power-law curves of the form error(N) = a N^(-b) + c. Three findings. (1) Power laws fit: R^2 > 0.8 on 77.7% of cells, with tree ensembles dominating at full data (Boosting 50% of datasets, RandomForest 33%; linear models underperform on classification). (2) Approximate shared exponents within a model family: for 5 of 6 families, a single family-level exponent predicts each family's cross-dataset curves nearly as well as per-dataset exponents (R^2 gap < 0.011), though AIC favors the unconstrained fit and curve collapse is partial (32-58% of points within +/-0.5 dex). We frame this as approximate predictive compressibility, not dataset-independent universality; Lasso fails outright (negative control) and Ridge is fragile under leave-one-dataset-out. (3) Replicator-implementation variance: with random_state=42 fixed, independent re-implementations of the same protocol still differ by mean CV(b) = 0.144 on the fitted exponent -- not seed variance, but the spread induced by unconstrained parts of the protocol (preprocessing, encoding, missing-value handling). We release the aggregated curves, per-cell fits, and a practical data-requirement table for N* to reach target error 0.15.
Authors: Sreejeet Maity, Feng Zhu, Aritra Mitra, Robert W. Heath Jr
Abstract: We investigate a decentralized reinforcement learning problem involving multiple agents that interact with the same Markov Decision Process (MDP). The agents can exchange information over a network to collectively learn the optimal state-action value function. For this setting, we introduce a novel epoch-based distributed $Q$-learning algorithm called VRDQ, where within each epoch, agents locally estimate the Bellman optimality operator and diffuse information using a consensus-based protocol. For both static and time-varying networks, we establish high-probability finite-time convergence rates for VRDQ that enjoy linear speedups from collaboration. Crucially, we prove that such speedups in sample-complexity require only $\tilde{O}(1)$ communication, substantially improving upon the communication costs in prior work.
Authors: Guoming Li, Jian Yang, Xukun Wang, Zixiao Wang, Shangsong Liang, Yifan Chen
Abstract: Coarsening-based training for graph neural networks (GNNs), i.e.\ training on coarsened graphs rather than the original large ones, has become a promising direction for scaling GNNs to massive graphs. However, prior work has been evaluated almost exclusively on \textit{homophilic} graphs, leaving the more challenging \textit{heterophilic} settings underexplored. We show, both empirically and theoretically, that existing coarsening-based training methods suffer significant performance degradation on heterophilic graphs due to inevitable loss of graph information during coarsening. To address this, we propose {\bf A}daptive {\bf C}omplementary {\bf E}nhancement, a plug-and-play, model-agnostic strategy that reintegrates the information discarded in coarsening: ACE learns a projector for re-constructing original node features and applies \textit{anisotropic structural regularization} to embed local heterophily. We further adopt \textit{homoscedastic uncertainty weighting} to adaptively balance the combined training objective of primary coarsened-graph training loss and full-graph auxiliary loss with augmented node features re-constructed by the heterophily-aware projector. Extensive experiments show that ACE drives consistent gains on heterophilic benchmarks while preserving competitive results on homophilic graphs with minimal computational overhead. Code is available at the GitHub repository: https://github.com/vasile-paskardlgm/ACE.
Authors: Mingyi Ma, Qingxiong Tan
Abstract: Clinical irregular multivariate time series are shaped not only by physiological dynamics but also by the measurement process that determines when and what to observe. In event-centric models, however, co-timestamp structure can be flattened too early: measurements acquired at the same timestamp are embedded as isolated nodes, leaving local patient-state context unavailable until later message-passing layers. We study this pre-propagation representation bottleneck and address it by restoring co-timestamp context before message passing begins. We propose MissHyper, a missingness-guided hypergraph forecasting model with pre-propagation synchronicity restoration. MissHyper augments each event with a local support-density cue, aggregates co-timestamp records to recover patient-state context, and uses a missingness-guided gate to adaptively fuse node-specific evidence with the recovered context. Across PhysioNet 2012, MIMIC-III, and MIMIC-IV, MissHyper achieves consistent gains in multi-step forecasting and outperforms a strong hypergraph baseline. These results suggest that improving event initialization can benefit sparse clinical forecasting without requiring a redesigned downstream propagation architecture. Ablations indicate that snapshot restoration, adaptive fusion, and support-density encoding all contribute, pointing to event initialization as a critical design axis for sparse clinical forecasting.
Authors: Anderson R. Santos
Abstract: Full self-attention in large language models scales as O(N^2), which limits long-context document analysis to 65,536 tokens and requires costly GPU clusters. The Reduced Interaction Sampling (RIS) inference engine addresses this constraint as a model-agnostic architecture. Without modifying weights, RIS reduces self-attention complexity to O(N log N) using sparse stochastic geometry that fits within commodity memory limits. We validate RIS on Qwen2-1.5B-Instruct across two regimes. In controlled evaluations at 32,768 tokens (where native dense attention serves as the upper bound), RIS-Stochastic at 1% density and 70 ensemble seeds achieves 75.00% accuracy, outperforming the native dense baseline (71.88%), while RIS-Stochastic at 5% density and 10 seeds matches it (71.88%). This demonstrates that sparse attention acts as a regularizer: low density (1%) over multiple seeds filters out sequence-level noise, whereas higher density (5%) reintroduces distractor noise. Under the tightest budget, RIS-Structural reaches 68.75% accuracy at 1% density with just 10 seeds, recovering 75% of the contextual gap relative to the zero-context floor (59.38%). At 65,536 tokens, where dense attention triggers out-of-memory faults, RIS yields retrieval gains of up to 14.06 percentage points over the zero-context floor (51.56%), which is confirmed as marginally significant under McNemar's paired test (p = 0.078 < 0.10). All evaluations run on commodity, unaccelerated CPU servers (16-128 GB of RAM), demonstrating that long-context LLM inference is feasible on standard academic hardware without GPU acceleration.
Authors: Shiyi Liu, Jiaqing Chen, Nicholas Hadler, Rostyslav Hnatyshyn, Michael W. Mahoney, Talita Perciano, John F. Hartwig, Gunther H. Weber, Ross Maciejewski
Abstract: Chemists and materials scientists increasingly use machine learning models, such as graph neural networks (GNNs), to predict properties of molecules and the outcomes of their reactions. Beyond predictive performance, understanding how these models organize chemical information internally in their latent spaces, i.e., the embeddings of the molecules, is critical. Analyzing latent spaces helps diagnose model behavior and assess whether the learned embeddings are organized in ways that reflect meaningful chemical relationships. Unfortunately, existing methods provide limited support for analyzing latent spaces across layers and across different model states (e.g., training epochs, model configurations, and input data), making it difficult to understand how these latent spaces evolve throughout a model or relate to chemical concepts. We present LatentFlow, a visual analytics system developed in collaboration with a domain expert for analyzing latent spaces in molecular GNNs. LatentFlow groups embeddings into clusters and supports exploration of latent spaces by tracking how these clusters change across layers and model states using a modified Sankey diagram. To support interpretation, LatentFlow links these clusters to representative molecules and their shared substructures, and it allows scientists to introduce their own domain knowledge and compare it with the patterns found in the latent spaces. We evaluate LatentFlow through two case studies. The results show that LatentFlow helps scientists understand how latent spaces evolve, identify meaningful molecular patterns, and better interpret model behavior.
Authors: Jiseok Kwak, Suhyeon Jo, Taewoo Kim, Yeongmin Kim, Byeonghu Na, Il-chul Moon
Abstract: This technical report presents our approach to Challenge Track~3: SeePhys Pro at the 3rd AI for Math Workshop, where the task is to answer college-level physics questions whose statement and figure may be given partly or entirely as an image. Visual physics problems become substantially harder for large language models when the decisive information resides in a figure rather than in the text, and this modality gap widens as more of the problem migrates into the image. We address the task with a two-stage framework: a visual information extraction stage that re-expresses figure content as solver-readable text to close the modality gap, and a reasoning stage that orchestrates three heterogeneous solvers through multi-agent debate. Our analysis yields two findings: the gain from orchestration comes from reliable answer selection rather than from additional debate, and the value of a figure aid scales with how much of the problem is locked inside the image. The resulting pipeline improves overall accuracy over a single-agent baseline from 0.643 to 0.802 on the public split, and won 1st place on both the public and the private leaderboard (private overall 0.743).
Authors: Xiangjun Shi, Chong Mu, Jinchuan Zhang, Lizong Zhang, Yuefeng He, Shang Liu
Abstract: Continual temporal knowledge graph (TKG) reasoning aims to continuously incorporate newly emerging facts while preserving previously acquired knowledge. Replay-based continual learning has achieved promising performance by revisiting historical representations. However, existing methods primarily focus on what to replay, while largely overlooking how replayed representations should be integrated with current ones. Such direct integration often gives rise to two critical forms of representation conflict: \textit{norm domination} and \textit{semantic blurring}, ultimately degrading continual reasoning performance. To address these challenges, we propose MA-DAR (Manifold-Aligned Dynamic Adaptive Routing), a lightweight plug-and-play framework for replay representation fusion. MA-DAR first aligns replayed and current representations onto a shared manifold to alleviate distribution discrepancies. It then employs a dynamic gating mechanism to learn dimension-wise fusion weights, adaptively determining the contribution of replayed and current representations to the fused representation. Furthermore, a polarization regularizer encourages more decisive routing behaviors by discouraging ambiguous gating decisions, resulting in more stable and effective knowledge integration. Extensive experiments on four public continual TKG benchmarks demonstrate that MA-DAR consistently improves the performance of representative TKG encoders while remaining effective under different replay settings. Comprehensive ablation studies and visualization analyses further verify the effectiveness of manifold alignment and dynamic adaptive routing in mitigating representation conflicts and improving continual reasoning.
Authors: Shujin Wu, Cheng Qian, Xiusi Chen, Heng Ji
Abstract: Test-time scaling through iterative self-evolution with environment feedback, as demonstrated by AlphaEvolve, shows remarkable performance gains. We hypothesize that the success of such evolution frameworks hinges on meta-skills, such as self-reflection with environment feedback, that enable effective multi-round refinement, yet are largely neglected by traditional post-training. To bridge this gap, we present MetaEvolve, a framework designed to develop these meta-skills via a data synthesis pipeline, evolution-aware reinforcement learning (RL), and inference-time evolutionary search. Concretely, we ground MetaEvolve in coding, where program execution provides natural, continuous reward signals beyond binary correctness. Building on these signals, we synthesize evolution trajectories as training data, each containing a current program, its fitness score (combining correctness and efficiency), and a history of prior attempts, and train the model via RL with verifiable rewards derived from test case execution. By training on large-scale code data, we aim to inspire generalizable domain-agnostic meta-skills that can transfer broadly to open-ended problems where such rich training signals are scarce. Across seven coding benchmarks, MetaEvolve outperforms the strongest baseline by 10.01% absolute on in-distribution tasks and 24.12% on out-of-distribution tasks. On open-ended algorithm optimization problems entirely outside the training domain, it further achieves a 46.9% relative improvement. These results demonstrate that explicitly cultivating self-evolution meta-skills offers a principled path toward more capable and autonomously self-evolving AI.
Authors: Ru Wang, Chengchang Liu, John C. S. Lui
Abstract: Low-rank adaptation (LoRA) optimizes $J(B,A)=\mathcal L(W_\mathrm{base}+sBA)$ over two adapters $B \in \mathbb{R}^{m \times r}$ and $A \in \mathbb{R}^{r \times n}$ that form a low-rank update to a frozen pretrained weight matrix $W_\mathrm{base} \in \mathbb{R}^{m \times n}$. The prior analysis shows LoRA-GD takes $\exp\{\mathcal{O}(\epsilon^{-2})\}$ oracle calls to find an $\epsilon$-stationary point such that $\|\nabla J(B,A)\|\leq \epsilon$ in the deterministic setting. We sharpen the analysis and show that $\mathcal{O}(\epsilon^{-4})$ full-gradient evaluations suffice for the same first-order criterion. We further study stochastic LoRA under unbiased gradient estimates and finite variance. We propose LoRA-NSGDM, which finds an $\epsilon$-stationary point with $\mathcal{O}(\epsilon^{-8})$ stochastic oracle complexity. Under the additional mean-square smoothness condition, we use variance reduction strategy and propose LoRA-STORM, which improves the stochastic oracle complexity to $\mathcal{O}(\epsilon^{-6})$.
Authors: Jiaxin Deng, Junbiao Pang
Abstract: Long-tailed learning couples two sources of poor generalization: head classes dominate training exposure, while under-represented classes often converge to sharper regions of the loss landscape. Conventional re-sampling addresses the former without considering geometry, whereas existing long-tailed sharpness-aware minimization (SAM) methods modify losses or perturbations only after biased mini-batches have been drawn. We introduce Sharpness-Guided Equilibrium Sampling (SGS), which treats the sampling distribution as an active control variable for optimization geometry. SGS dynamically adjusts subsequent mini-batches by increasing the sampling probability of less frequently sampled classes while suppressing classes with large SAM-induced loss changes, using only cumulative class counts and EMA sharpness estimates obtained from the standard SAM update, without class-wise perturbations or additional backward passes. We characterize this sampling process through a continuous-time stochastic differential equation and a sampling-dependent PAC-Bayes analysis, explaining how frequency-sharpness feedback can move training toward a more balanced flatness profile. On CIFAR-100 LT with an imbalance ratio of 100, SGS-SAM improves Focal-SAM by 10.85 points in tail accuracy and 3.56 points overall. On ImageNet-LT, it improves ImbSAM by 6.59 points on tail classes and 1.20 points overall. Its training time is only $1.02\times$ that of vanilla SAM. Beyond these gains, SGS establishes a sampling-side route to loss-landscape control, suggesting that future long-tailed methods can jointly regulate data exposure and optimization geometry rather than treating either as fixed.
Authors: Zhangyong Liang, Huanhuan Gao
Abstract: Energy natural gradient descent (ENGD) aligns parameter updates with the curvature of an underlying function-space energy, but existing formulations assume an unconstrained Euclidean parameter domain. We introduce \EMNGDfull{}, a manifold optimization framework for physics-informed and variational neural PDE solvers whose parameters lie on a Riemannian manifold. EMNGD restricts the energy-induced quadratic model to feasible tangent directions and uses retractions to preserve parameter constraints throughout optimization. Under coercivity, we prove that the push-forward of the undamped EMNGD direction is the best feasible approximation to the function-space Newton vector in the energy metric. We establish coordinate invariance, exact reduction to ENGD in Euclidean space, global first-order convergence with Armijo backtracking, and robustness to inexact tangent solves. For quadratic residual energies and generalized Gauss--Newton pullbacks, the Woodbury identity transfers the tangent system to sample space without changing the direction. Nystr\"om approximation provides scalable sample-space solves with controlled direction error and recovers the exact direction after iterative convergence. On the evaluated neural PDE benchmarks, EMNGD achieves higher accuracy and faster convergence than the compared state-of-the-art baselines. Woodbury preserves the EMNGD direction, while scalable-solver diagnostics quantify the accuracy--cost trade-off of preconditioning and residual subsampling.
Authors: Yuta Natsubori, Masataka Ushiku, Yuta Saito
Abstract: Off-Policy Evaluation and Learning (OPE/L) in contextual bandits is rapidly gaining popularity in real systems because new policies can be evaluated and learned securely using only historical logged data. However, existing methods in OPE/L cannot handle many challenging but prevalent scenarios such as few-shot data, deterministic logging policies, and new actions. In many applications, such as personalized medicine, content recommendations, education, and advertising, we need to evaluate and learn new policies in the presence of these challenges. Existing methods cannot evaluate and optimize effectively in these situations due to the notorious variance issue or limited exploration in the logged data. To enable OPE/L even under these unsolved challenges, we propose a new problem setup of Cross-Domain OPE/L, where we have access not only to the logged data from the target domain in which the new policy will be implemented but also to logged datasets collected from other domains. This novel formulation is widely applicable because we can often use historical data not only from the target hospital, country, device, or user segment but also from other hospitals, countries, devices, or segments. We develop a new estimator and policy gradient method to solve OPE/L by leveraging both target and source datasets, resulting in substantially enhanced OPE/L in the previously unsolved situations in our empirical evaluations.
Authors: Xiafeng Man
Abstract: Currently, most foundation models can reproduce or strongly depend on copyrighted training content, but output similarity alone is insufficient for infringement detection, because similar outputs may also arise from public-domain concepts, common stylistic conventions, or ordinary statistical generalization. In this paper, we develops a unified post-hoc detection framework that treats copyright infringement evidence as a counterfactual conditional distribution shift: a protected target is suspicious when the model's behavior under aligned conditions would change measurably if that target were included in, or removed from, the training process. We formalize this view through conditional differential privacy and introduce Dual-Branch Conditional Sensitivity (DCS), an operational statistic that measures the observable gap between two locally perturbed model states. Specifically, the proposed DCS framework creates a learning branch and an unlearning branch around the deployed model, connects their displacement to the unavailable counterfactual retraining effect through influence-function analysis, and bounds the observable sensitivity by the counterfactual privacy-budget surrogate, local curvature, training-set scale, and perturbation step size. To distinguish target-specific memorization from generic fine-tuning instability, we further define a calibrated detection statistic that subtracts the sensitivity measured under orthogonal conditions. The DCS framework is instantiated for ridge-regularized linear regression, conditional diffusion models, autoregressive language models, and multimodal models. These instantiations show how the same principle can be evaluated through prediction gaps, image-embedding divergence, token-distribution or entropy shifts, and cross-modal representation changes.
Authors: Oleksii Furman, {\L}ukasz Lenkiewicz, Marcel Musia{\l}ek, Maciej Zi\k{e}ba
Abstract: Counterfactual explanations are a prominent approach in explainable artificial intelligence (xAI), providing actionable guidance on what input changes would alter a model's prediction to a desired outcome. While early methods primarily focused on minimal feature changes, recent work incorporates additional properties such as sparsity, actionability and plausibility. Despite this progress, fair and systematic evaluation remains challenging. Existing studies often rely on different data splits, predictive models, and evaluation metrics, which limits objective comparison across methods. To fill this gap, we introduce CEL (Counterfactual Explanations Library), a unified library and benchmark for counterfactual explanations designed to support consistent implementation and evaluation. CEL includes 18 datasets of varying size and complexity and provides implementations or reimplementations of 14 widely used counterfactual methods. Using this standardized setup, we conduct a comprehensive quantitative comparison across a variety of methods on datasets that differ in size, number, and types of attributes. The evaluation protocol incorporates multiple complementary metrics capturing validity, coverage, sparsity, proximity, and distributional plausibility, including density- and outlier-based measures to assess the realism of generated counterfactuals. To the best of our knowledge, this is the first comprehensive benchmark that systematically evaluates recent counterfactual explanation methods within a unified and reproducible framework. While prior libraries and benchmarking efforts exist in the literature, many are outdated, limited in scope, or lack consistent evaluation protocols. The proposed benchmark aims to improve reproducibility, enable fair comparison, and establish a workbench for the development of future counterfactual explanation methods.
Authors: S. P. Sharmila, Aruna Tiwari
Abstract: Multiclass classification is a fundamental problem across a wide range of domains. It is still challenging due to possession of high inter-class similarity, class imbalance datasets, and variability in data distributions. Rule-based classifiers such as XGBoost often achieve stronger performance on structured features, but they are limited in capturing smooth functional relationships among variables. Similarly, neural network models can represent complex nonlinear interactions but frequently suffer from overfitting and generalization issues. To address these limitations, we propose LFS-FRAME, a Leakage-Free Stacked ensemble framework that integrates functional learning using Kolmogorov-Arnold Networks (KAN) and rule-based learning via XGBoost for robust multiclass classification. The proposed framework constructs unbiased meta-features by employing a strict out-of-fold stacking strategy to ensure complete isolation between training and validation data hence preventing performance leakage. By learning over probabilistic outputs from heterogeneous base learners, the meta-classifier effectively exploits both global functional patterns and sharp decision boundaries present in the complex data. Experimental evaluations on multi-class datasets demonstrate that LFS-FRAME improves performance metrics, and overall accuracy is 89.85% in identifying major families and 81.74% in identifying sub-families relative to strong single-model baselines. These results highlight the effectiveness of leakage-free functional and rule-based stacking for reliable and generalizable multiclass classification.
Authors: Joshua Placidi, Yuxuan Liu, Jinpei Han, Marek Rei, A. Aldo Faisal
Abstract: Autoregressive foundation models for electronic health records (EHRs) typically inherit pretraining methods from language modeling, where patient trajectories are concatenated into a single token stream and windows are sampled from that stream. In EHR data, this choice is consequential: windows may mix multiple patients, and patients with longer records contribute more optimization updates, potentially introducing bias. We propose Patient Sampling, a pretraining sequence-construction method that allows us to control how training signal is distributed across patients. We compare this method to the standard approach, which we refer to as Global Stream. We show that stochastic Patient Sampling with controllable weighting improves performance on real-world EHR data. Across downstream clinical tasks on MIMIC-IV v2.2 and v3.1, Patient Sampling improves Macro AUROC and AUPRC over the Global Stream baseline. These results identify training and validation sequence construction as important and underexplored design choices for autoregressive EHR foundation models.
Authors: Yuliang Yan, Shuo Yan, Haochun Tang, Yiqin Sun, Enyan Dai
Abstract: Molecular glue degraders have emerged as a promising strategy for targeted protein degradation by inducing ternary complex formation between an E3 ubiquitin ligase and a target protein. Despite their therapeutic potential, computational design of molecular glues remains largely unexplored. Unlike conventional structure-based drug design, molecular glue design is governed by the unknown protein-protein interface and requires the simultaneous modeling of ligand generation, protein-protein docking, and ternary complex assembly. In this work, we formulate molecular glue design as a ternary complex generation problem and propose a biology-inspired generative framework, TriGlue. Motivated by the mechanism of molecular glue action, we decompose ternary complex generation into two coupled stages: interface estimation and interface-conditioned complex generation. First, we develop an SE(3)-equivariant interface estimation module that predicts a geometrically constrained protein-protein interface from unbound monomer structures. Second, we introduce an interface-conditioned ternary flow matching network that jointly generates the molecular glue and predicts the rigid-body transformation required to assemble the ternary complex. Extensive experiments demonstrate that TriGlue generates chemically valid molecules and produces plausible ternary complexes, which highlight the potential of biology-inspired generative modeling for accelerating molecular glue discovery. Our code is available at https://anonymous.4open.science/r/molecular-glue-design-806B.
URLs: https://anonymous.4open.science/r/molecular-glue-design-806B.
Authors: L{\'e}o Nicollier (CB, ATT), Marc Pic (ATT), Pablo Mus{\'e} (CB, IFUMI), Enric Meinhardt-Llopis (CB), Gabriele Facciolo (CB)
Abstract: Despite recent advances, self-supervised learning (SSL) models and Joint-Embedding Predictive Architectures (JEPAs) remain susceptible to learning spurious biases in the dataset. These techniques rely on regularization, which prevents representation collapse by enforcing a global target distribution such as a multivariate Gaussian or a uniform distribution on the sphere. However, these global constraints are insufficient to prevent bias entanglement, as task-irrelevant features can still segregate the latent space into distinct sub-regions. While recent approaches like Entangling and Disentangling (EnD) and Fair Supervised Contrastive Learning (FSCL) empirically debias the latent space, we show that they act as partial approximations of conditional distribution matching. To enforce this matching explicitly, we propose Unbiased Open World Regularization (UOWReg), an encoder-only framework. We show that this shift from a global to a conditional objective guarantees statistical independence between the learned representations and the targeted attributes, regardless of the chosen target distribution. We empirically validate this framework across both Gaussian and spherical latent spaces, using statistical measures to enforce these target distributions. While conditional matching successfully mitigates bias with both distributions, we demonstrate that enforcing conditional uniformity on the sphere yields a lower linearprobing classification error. Empirically, UOWReg reduces Equalized Odds violations on the CelebA benchmark while maintaining competitive classification accuracy compared to existing encoder-only baselines. Furthermore, we introduce the Synthetic Engraving Task-a novel setting in which a dominant macro-structure masks a fine-grained micro-signature. We show that UOWReg effectively prevents the subpopulation collapse observed in standard SSL, successfully isolating micro-signatures even when heavily entangled with the global structure.
Authors: Lan V. Truong
Abstract: Score-based diffusion models have achieved remarkable empirical success in generative modeling, yet their approximation-theoretic foundations remain incomplete. In particular, although classical universal approximation theorems guarantee that neural networks can approximate score functions, it remains unclear whether such approximation guarantees translate into approximation of the probability distributions generated by reverse diffusion processes. In this paper, we establish a rigorous quantitative connection between these two notions. Specifically, we prove that if a neural network approximates the true score function sufficiently accurately, then the probability distribution generated by the corresponding reverse diffusion model is close to the target data distribution in Kullback-Leibler (KL) divergence, up to an irreducible mismatch between the terminal distribution of the forward diffusion process and the prior used to initialize the reverse process. More precisely, we derive an explicit upper bound on the distribution approximation error in terms of the score approximation error, the diffusion noise schedule, and the terminal prior mismatch. Our analysis combines Hornik's universal approximation theorem, Girsanov's theorem on path space, and the data processing inequality for relative entropy. Complementary to recent work that studies score approximation under finite-sample statistical settings and structural assumptions on the data distribution, our work develops an approximation-theoretic analysis based on classical neural network approximation theory. The resulting theorem provides a simple and explicit guarantee linking neural network approximation of score functions to approximation of the probability distributions generated by reverse diffusion models.
Authors: Ingvild Askim Adde, Mary M. Maleckar, Gabriel Balaban
Abstract: In this study, we introduce latent PDE mapping, a broadly applicable physics-informed learning technique designed to enable efficient geometric generalization with sparse training data. Latent PDE mapping pulls back geometry-specific PDE residuals and boundary conditions to a predefined latent geometry via the deformation gradient, thereby enabling the automated calculation of geometry-consistent shape gradients that are missing in conventional physics-informed machine learning formulations. We demonstrate the utility of latent PDE mapping in solving the anisotropic Aliev-Panfilov PDE of cardiac electrophysiology using both physics-informed neural networks and physics-informed deep operator networks. The Aliev-Panfilov PDE serves as a challenging exemplar: a nonlinear, time-dependent PDE benchmark with sharp gradients that are expensive to capture using traditional numerical solvers. To represent the limited data regime, we train the networks using just fifteen geometric samples drawn from parameterized distributions in two and three spatial dimensions. While modest improvements appear for geometries parameterized by affine and shear deformations, latent PDE mapping demonstrates significant benefits on select geometric families, achieving a factor ~4-6 reduction in mean relative L2 error. Furthermore, our results show that the computational cost of applying latent PDE mapping was modest during network training, and negligible at inference. Taken together, our study highlights how latent PDE mapping facilitates the creation of generalizable physics-informed machine learning models from limited sets of training geometries.
Authors: Hirotaka Sugawara, Yujin Taguchi, Kei Minagawa, Yusuke Hiki, Takashi Morikura, Akira Funahashi
Abstract: Bayesian optimization (BO) is an optimization method that sequentially proposes the next candidate explainable variables for optimizing target variables by balancing exploration and exploitation. BO is often used under a limited evaluation budget, such as hyperparameter tuning of deep learning. Despite its effectiveness, conventional BO may have poor convergence in practical experimental science where each evaluation is often costly and time-consuming. Recently, BO methods have been proposed that accelerate optimization by using pseudo-experimental data that simulate experimental data. However, when only a limited number of experimental data are available, the generated pseudo-experimental data may be of insufficient quality. In this study, we developed PolyBO to improve optimization time by generating high-quality pseudo-experimental data even when the number of trials is limited. PolyBO performs BO efficiently by generating pseudo-experimental data with an adaptively updated versatile parametric model. This low-capacity polynomial regression model is intended to enable efficient BO even with limited experimental data. PolyBO updates the BO surrogate model with a combined dataset consisting of experimental data and pseudo-experimental data and then performs optimization. Using synthetic benchmark functions with diverse landscapes, we found that PolyBO reduced the optimization time by a median of 42\%. For a real-world material composition optimization problem, PolyBO reduced the optimization time by a median of 96\% compared with conventional methods. Overall, PolyBO achieves efficient optimization in settings where each experiment requires a long time.
Authors: Wei Zhang, Xinwu Liu, Yihang Cheng
Abstract: Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning method for large language models, but its performance depends strongly on how a fixed rank budget is distributed across Transformer modules. Existing adaptive-rank methods usually rely on local gradient statistics collected during training, which introduces extra memory and computation and overlooks task-conditioned global information flow. We propose IFCLoRA, a topology-aware rank allocation method applied before fine-tuning. Using a small calibration set and a frozen pretrained model, IFCLoRA builds a sparse task-conditioned interaction graph whose nodes represent LoRA-compatible modules. It combines a global information-flow topology prior with local gradient sensitivity to compute Information-Flow Centrality scores, which estimate each module's adaptation importance under multi-hop propagation. Ranks are then assigned once under a global budget. Across multiple models, tasks, and low-rank settings, IFCLoRA consistently outperforms LoRA, AdaLoRA, and EVA under matched training configurations and total rank budgets, while retaining training costs comparable to standard LoRA. On mathematical reasoning with LLaMA 3 8B, IFCLoRA improves over LoRA by 1.36 percent at rank 4 and 1.82 percent at rank 8. Further analysis shows task-dependent, non-uniform rank profiles, indicating that global information-flow structure provides an informative and interpretable prior for low-budget parameter-efficient fine-tuning.
Authors: Yi-Hang Zhu, Rajeev Raman, Shiqi Su, Jianyuan Sun, Xinyu Yang, Nan Xing, Huiyu Zhou
Abstract: Deep learning models using traditional softmax classifiers have achieved remarkable success in various classification tasks. However, their performance degrades significantly on imbalanced datasets. Although Balanced Softmax is widely adopted as a state-of-the-art rebalancing method, it possesses inherent limitations, such as yielding disproportionately lower testing accuracy for tail classes. To mitigate these shortcomings, we propose the Class-Balanced Softmax (CBS). Rooted in a theoretical Bayesian framework and a heuristic power-law assumption, the CBS is a simple logit adjustment that is computationally inexpensive and easily integrated into existing pipelines. Furthermore, we characterise a fundamental phenomenon in models trained on imbalanced data, termed the preference issue, wherein models exhibit higher training error and a larger generalisation gap for classes with limited data. To quantify this issue, we introduce a novel metric and demonstrate that CBS effectively mitigates the preference issue. Extensive experiments on large-scale benchmarks show that CBS is highly scalable and outperforms existing methods, including Balanced Softmax.
Authors: Yuxuan Liu, Joshua Placidi, Jinpei Han, Alfred John Balston, Marek Rei, A. Aldo Faisal
Abstract: Autoregressive foundation models trained on tokenized electronic health records (EHRs) can support zero-shot clinical prediction, yet most operate on structured event codes alone, and do not incorporate multiple modalities in a principled way. We present a framework for conditioning such models on auxiliary clinical modalities, including ECG waveforms, chest X-ray images, and clinical notes, using modality-specific latent compression and gated cross-attention with temporal alignment. We investigate two key design choices: (1) how to compress long per-modality sequences (e.g., ECG time series) before they enter the multi-modal cross-attention. This feature may be essential to reduce compute overheads and may be beneficial for generalization; (2) how the choice of pretrained encoder for each modality impacts downstream performance. Through controlled ablations on MIMIC-IV, we show that the best latent-compression configurations outperforms both uncompressed cross-attention and mean pooling. Encoder choice has a clear within-modality effect, with stronger pretrained encoders consistently outperforming weaker alternatives. We further show that merely adding auxiliary modalities does not guarantee improvement on ICU mortality prediction over an EHR-only baseline. This implies that careful design of the fusion architecture and an appropriate evaluation in the clinical context are required.
Authors: Romain Hermary, Nesryne Mejri, Djamila Aouada
Abstract: Anomaly detection is inherently characterised by severe class imbalance, making the interpretation of evaluation metrics challenging. Although metrics such as AUROC, AUPR, F1-score, and MCC are widely used, their values convey different meanings depending on the anomaly ratio. In this work, we analyse the behaviour of those four common anomaly detection metrics under varying levels of imbalance. We focus on the study of metric landscapes, visualisations that relate metric values to true positive and true negative rates, providing an intuitive view of metric preferences and stability. Our analysis offers practical guidance for interpreting and comparing anomaly detection results across datasets with different imbalance ratios.
Authors: Alessandro Sbandi, Federico Siciliano, Fabrizio Silvestri
Abstract: Graph-based recommendations are widely adopted in real-world industrial applications. However, graphs in these systems often reach a massive scale, posing notable scalability and efficiency challenges. This requires techniques that can effectively balance predictive quality with computational cost. One promising approach is graph coarsening, an adaptive graph reduction technique that offers a way to systematically construct smaller, yet structurally representative, versions of the original large-scale graphs. In this work, we propose a flexible two-stage diffusion framework that combines graph coarsening with multi-step label propagation in the telecommunications domain. Domain-specific heuristics are applied to first aggregate nodes into meaningful communities, reducing graph size while preserving essential business-relevant relationships. An initial diffusion process done by a Label Propagation Algorithm (LPA) or a Graph Neural Network (GNN) propagates labels across the coarsened graph to produce coarse-grained predictions. Finally, a second LPA within subgraphs generates the final recommendations for individual users. On a real-world telecommunications dataset, when using LPA in both stages, our method achieves up to +24% NDCG@5 over the full-graph LPA baseline. Incorporating a lightweight GNN in the first stage further boosts NDCG@5 by more than 50%, but requires substantial training and inference time. Through extensive experiments and a detailed ablation, we quantify these trade-offs and demonstrate that our coarsening-driven approach delivers an optimal balance between scalability, latency, and recommendation quality.
Authors: Roseline Polle, Owen Parsons, George Fairs, Luis Miguel San Martin Fernandez, Cole Looney, Xiaoliang Wu, Alexandra Livia Georgescu, Stefano Goria
Abstract: Synthetic data augmentation in speech is common practice for linguistic tasks like ASR, but has seen far less work for paralinguistic ones, especially clinical tasks where labelled data is expensive and some patient groups are underrepresented. Voice cloning is one such augmentation approach, but is typically evaluated on speech intelligibility (WER) or speaker similarity (SS) rather than on downstream performance, and it remains unclear whether these preserve the paralinguistic signal such tasks depend on. We benchmark eight voice cloning models on five paralinguistic tasks across public and clinical datasets, showing most preserve signal with modest degradation. We then clone English clinical speech into Japanese and find that training on cloned data outperforms raw cross-lingual transfer for depression and anxiety detection on real Japanese speech, suggesting voice cloning is a promising direction for augmenting clinical speech data in low-resource languages.
Authors: Zhangzhi Xiong, Minzhang Li, Haotian Yu, Sixian Shen, Kexin Zhang, Mingrui Li, Jie Zheng, Kewei Tu, Jingyi Yu
Abstract: Multiple Sequence Alignments (MSAs) provide protein language models with explicit evolutionary context, but their large depth makes subsampling unavoidable under limited token budgets. Existing strategies, including random selection, identity-based filtering, and diversity-driven sampling, are effective heuristics, yet provide limited control over the evolutionary signals retained in the subset. In this work, we recast MSA subsampling as an explicit optimization problem, where key evolutionary measures, including query identity and diversity, are treated as controllable objectives. Building on this view, we introduce AP-REASONER, an Affinity-Propagation-based factor-graph approach. With evolution-aware unary factors, exemplar-consistency factors, and two control knobs, AP-REASONER performs factor-graph reasoning through message passing to infer a fixed-budget MSA subset. Experiments on long-range contact prediction and conformational ensemble prediction show that AP-REASONER outperforms baseline subsamplers on structure-sensitive downstream tasks and enables controllable recovery of alternative protein conformations. These results highlight the value of modeling MSA subsampling as a controllable optimization problem, where factor-graph reasoning offers an effective alternative to heuristic selection.
Authors: Hao Wang, Kun Yuan, Wenlin Zhong, Minglei Zhang, Han Xiao, Ming Sun, Honggang Qi
Abstract: Open-weight language models from different families exhibit complementary capabilities, motivating their consolidation into a compact student through on-policy distillation (OPD). However, full-vocabulary OPD typically assumes a shared tokenizer, while existing cross-tokenizer methods may discard teacher probability mass or assign it to student tokens with unrelated content. We introduce Byte-Prefix Marginalization (BPM), which re-expresses the teacher's next-token distribution over the student vocabulary in a shared byte space. Specifically, BPM assigns each teacher token's probability to the longest student token whose byte representation is a prefix of the teacher token's bytes, aggregates mass mapped to the same student token, and places otherwise unmatched mass in an explicit residual category. This produces a vocabulary-complete, byte-aligned, and mass-preserving target for dense OPD. The target exactly recovers the teacher-induced byte-prefix marginal when the relevant prefix does not span multiple teacher tokens (a condition satisfied at more than 99% of training positions) and uses a mass-preserving, chain-factorized lower bound otherwise. Across Qwen3-32B, GLM-Z1-9B-0414, and MiniMax-M2.7 as teachers, BPM consistently outperforms current cross-tokenizer methods on six mathematics and programming benchmarks, improving six-benchmark avg@8 by 3.7-6.6 points over the strongest baselines.
Authors: Htet Yamin Ko Ko
Abstract: The development of effective urban climate adaptation strategies requires comprehensive spatial information on rooftops and buildings, since such information underpins the assessment of ecosystem services provided by green infrastructure, particularly for urban heat island (UHI) mitigation. Although green roofs are widely acknowledged as a promising measure for improving urban thermal comfort, most existing research maps either current green rooftops or rooftops with greening potential, but not both. This study presents a modified deep convolutional neural network rooftop classification framework based on Roofpedia, developed by the Urban Analytics Lab at the National University of Singapore. The proposed model combines high resolution aerial imagery with rooftop slope information derived from a digital surface model and relies entirely on publicly available Swisstopo datasets: SWISSIMAGE orthophotos, swissSURFACE3D elevation data, and swissTLM3D building footprints. Applied to Bern, Switzerland, the model labels rooftops into four categories: existing green roofs, rooftops suitable for green roof installation, rooftops with solar panels, and flat rooftops unsuitable for greening. The framework identifies realistic opportunities for green roof expansion and supplies urban planners with evidence-based information for green infrastructure deployment in Bern and other Swiss cities. Because it is fully open source, the framework is transferable to cities worldwide.
Authors: Masashi Sode, Gianmarco Pinton
Abstract: The speed of sound in tissue is a prerequisite for well-focused imaging and has diagnostic value, but recovering it from raw pulse-echo channel data is fundamentally a nonlinear inverse problem. Learned solvers are fast yet label hungry. Simulated sound-speed labels are expensive, while abundant real channel data is unlabeled. We propose IQ-JEPA to exploit both data types. An encoder is pretrained without labels to predict the latent representation of masked in-phase and quadrature (IQ) regions from visible context, then fine-tuned on simulated maps. Sound speed appears in the IQ signal as a phase difference, invariant to the constant phase offset. The encoder is a Hermitian vision transformer that operates on the complex signal directly. Its attention is equivariant to that phase and its conjugate-product feed-forward is invariant to it, so the encoder reads a quantity analogous to the one classical coherence methods use. On 79,293 Fullwave 2.5 simulations at 2.5 MHz, pretraining on the 63,435 unlabeled acquisitions reaches 15.60 m/s at 10,000 labels. This is a roughly threefold gain in label efficiency over supervised training, growing to over fourfold at 1,000 labels. It is about 2.2x below an InversionNet baseline, and 8.71 m/s at full labels. The gain still grows with more unlabeled pretraining data. Our comparisons point to self-supervision as the dominant factor. The same encoder transfers. Its frozen features expose sound speed and attenuation, and cross-distribution pretraining between layered and abdominal phantoms costs little accuracy. We see this as a first step toward a foundation model for quantitative ultrasound.
Authors: Yida Xu, Zhaofang Mao, Yuheng Miao, Jiaxin Zhang, Yiting Sun
Abstract: In recent years, the growing complexity of last-mile pickup operations has increased the need for fast and accurate decision-making on logistics platforms. This challenge is fundamentally driven by two key and tightly coupled decision-making processes: order dispatching and routing. Solving them separately overlooks their interdependence, while fully end-to-end learning can be unstable and costly on large, variable-scale instances due to sparse rewards. To solve this problem, we propose an integrated optimization framework which couples a learned routing oracle with real-time dispatching heuristics. For the routing subproblem, we develop a Dynamic-Residual Graph Attention Network encoder with a Look-Ahead Courier-Personalized decoder. For the dispatching subproblem, we develop a routing-oracle-guided dispatching heuristic with local search, where the oracle provides near-optimal solutions to select candidate couriers while retaining real-time scalability. Extensive experiments on real-world datasets from Cainiao Logistics are used to test the performance of our approach, including an offline evaluation and an online rolling-horizon simulation. The experimental results show that our approach outperforms other benchmarks regarding solution quality and solving time, indicating it can effectively support logistics companies in solving real-time and large-scale last-mile pickup problems.
Authors: Alexander Kozachinskiy, Vicente Opazo, Felipe Urrutia
Abstract: We study information bottlenecks in modern deep-learning architectures -- RNNs, softmax transformers, linear-attention transformers and state-space models -- through the lens of the indexing primitive. In this primitive, the input consists of $n$ bits and one integer $i$ from $1$ to $n$ called the index, and the output equals the value of the $i$-th bit. We introduce causal complexity for masked architectures. We show that architectures with low causal complexity cannot solve the indexing primitive in any constant number of layers when the index appears at the end of the input. In particular, this limitation applies to low-parameter RNNs, SSMs and masked linear-attention transformers. In contrast, small softmax transformers can solve it in one layer, while non-masked linear-attention transformers can solve it in 2, which separates them from their masked counterparts. In turn, when the index appears at the beginning, we show that small RNNs are capable of solving this task in 1 layer, while all the other architectures require 2. All our impossibility results are unconditional and apply even to models that employ infinite-precision real arithmetic. Moreover, experiments for up to $n=64$ qualitatively align with our theory: configurations with low-parameter theoretical solutions learn the indexing task easily, while configurations that do not admit such theoretical solutions struggle to learn as the sequence length grows.
Authors: Umberto Biccari, Qian Huang, Enrique Zuazua
Abstract: Feature-attribution methods assign scores relating input variables to a model's output, but do not by themselves characterize how explicitly defined interaction operators compose across its intermediate layers. We introduce \emph{interior interpretability}, a propagation-based perspective on internal model organization, and instantiate it for tabular Transformers using attention rollout. We interpret rollout as a row-stochastic operator encoding attention-mediated propagation between feature tokens. By applying classical Doeblin--Dobrushin contraction theory, we show that a rollout operator with a small Dobrushin coefficient is quantitatively close to a rank-one stochastic matrix whose common row is determined by its normalized column sums. This result gives a structural interpretation to the corresponding rollout propagation profile. In Transformers trained for metabolomic age prediction, the measured rollout contraction strengthens with depth. Trained and randomly initialized models also exhibit different propagation profiles, although the present experiments do not establish the predictive relevance of individual rollout-ranked variables. Exploratory comparisons with PCA and GradientExplainer approximations to SHAP reveal localized agreement among highly ranked variables but weak agreement across complete rankings. Attention rollout is therefore used here as a diagnostic of attention-mediated propagation, not as a causal explanation or faithful attribution of the complete Transformer.
Authors: Rachid Caich, Yassine Abbahaddou
Abstract: Curvature notions on graphs, particularly Ollivier-Ricci and Forman, have emerged as powerful tools for addressing fundamental issues in Graph Neural Networks (GNNs) such as oversmoothing and oversquashing, but rely almost exclusively on local edge-level comparisons and therefore fail to certify how information actually propagates over long distances. We introduce Entropic Curvature, a global, transport-based curvature obtained by extending the Lott-Sturm-Villani framework to graphs through the displacement convexity of entropy along Wasserstein geodesics. We define a tractable Weak Entropic Curvature proxy that lower-bounds the global entropic curvature, and from it derive (i) a Poincare-type inequality controlling oversmoothing, (ii) a transport-entropy generalization bound, and (iii) an expansion paradox proving that sparsity, strong spectral expansion, and positive entropic curvature cannot coexist in large graphs, unifying oversmoothing and oversquashing as opposite ends of a single curvature spectrum. We translate the theory into three practical mechanisms, the E-Gate aggregator, the ENT structural encoding, and Midpoint-Completion Rewiring (MCR), and benchmark them against SDRF, FoSR, BORF, LCP, and Graph Ricci Flow on six node-classification benchmarks, and graph-classification.
Authors: Marc Girona-Mata, Jakob Gawlikowski, Sumit Goski, Gautier Bardi de Fourtou, Valentin T. Bickel, Ben Moseley, Abigail Calzada-Diaz, Sylvester Kaczmarek, Ra\'ul Ramos-Poll\'an
Abstract: The renewed global focus on lunar exploration, driven by the prospect of in-situ resource utilization and a sustained human presence on the Moon, has created growing demand for accurate, large-scale characterization of the lunar surface. Although vast quantities of orbital remote-sensing data have been collected, scientific analysis and resource mapping remain fragmented by heterogeneous multiinstrument observations, sparse labels, and bespoke task-specific modelling workflows. Here we introduce LunarFM, a multimodal foundation model that learns a general representation of the lunar surface from diverse orbital measurements. LunarFM assimilates observations from six instruments across three lunar missions, mapping 18 input channels to a shared embedding space. We demonstrate that this embedding space supports a diverse range of downstream applications, including similarity search, few-shot resource mapping, mineral abundance regression, and geological unit classification, enabling efficient scientific investigation and resource-oriented analysis. We provide a machine-learning-ready dataset of co-registered multimodal observations spanning latitudes from 70{\deg}S to 70{\deg}N, a pretrained multimodal masked autoencoder, and a companion embedding dataset providing a joint 768-dimensional representation of lunar surface properties. All code and data are available at https://lunarfm.trillium.tech/
Authors: Xiangteng Zhang, Yang Guan, Bo Zhang, Ya-Qin Zhang, Shengbo Eben Li
Abstract: Learning world models that infer environment dynamics from high-dimensional observations and predict outcomes under candidate actions is central to planning and control. Joint-Embedding Predictive Architectures (JEPAs) provide a compelling framework for learning such models in representation space. Recent action-conditioned extensions perform promisingly in visual control and latent-space planning, but leave a fundamental question unresolved: when does controlled latent prediction identify both the underlying state and the controlled dynamics? This is challenging under nonlinear observations and behavior policies with limited conditional action variation, where state-dependent evolution and action effects can be statistically confounded. We establish a joint identifiability theory for controlled world models with Gaussian latent states under state-dependent Gaussian behavior policies. We identify two policy-dependent conditions: spectral separation of the predictable signal governs representation identifiability, while non-degenerate conditional action variation governs transition identifiability. We prove that when both conditions hold, every global minimizer of the JEPA objective identifies the latent state and controlled transition up to an orthogonal transformation. We further derive quantitative bounds on representation and transition identifiability under approximate optimization. Finally, we construct predictor perturbations along weakly excited action directions whose counterfactual-to-on-policy error ratio is the inverse transition-identifiability margin, revealing the cost of limited action coverage. Experiments across nonlinear observation maps and behavior policies corroborate the theory and demonstrate implications for transition identifiability, counterfactual prediction, and goal-conditioned latent planning.
Authors: Yihao Xiao, Jialong Sun, Zitian Gao, Zeming Wei, Chutian Wang, Ran Tao, Jiaye Teng, Bryan Dai
Abstract: For scale-invariant deep networks, Hyperball-style optimizers have shown strong performance in large-scale training by fixing the norms of matrix-valued parameters and normalizing updates. However, the source of their advantage remains unclear. Starting from the angular displacement between consecutive parameter states, we derive an angular effective learning rate that accounts for the parameter-update angle, parameter norm, and update norm. We also show that the conventional norm-based measure is a special case under parameter-update orthogonality. We then decompose optimizer updates into radial and tangential components and analyze how radial updates affect one-step angular displacement. Under the training configurations considered, numerical results show that the radial component has only a limited direct effect on the angular effective learning rate. It therefore cannot explain why MuonH converges more slowly than MuonWD early in training but overtakes it later. To further isolate the underlying mechanism, we devise a heuristic experiment that modifies only the learning-rate schedule so that the dynamics of each optimizer reproduce those of the other. The results suggest that their main difference stems from the evolution of the effective step size rather than an intrinsically superior update direction induced by Hyperball. Our pretraining experiments further show that more aggressive learning-rate decay can accelerate MuonH early in training but may impair its later performance. Thus, maintaining a constant angular velocity does not eliminate the learning-rate-scheduling problem; careful scheduling remains essential to realizing the potential of Hyperball-style optimizers. Our code is publicly available at https://github.com/mangocrazz/hyperball-may-not-be-a-free-lunch.
URLs: https://github.com/mangocrazz/hyperball-may-not-be-a-free-lunch.
Authors: V\'ictor Rinc\'on Yepes
Abstract: Do learned audio embeddings encode structure that nobody told them to encode? We probe four large pretrained audio models (AST, CLAP, BEATs-bio and BirdNET) with a downstream task none of them saw during training: recovering phylogenetic distance from species vocalizations. If the geometry of the embedding space tracks the tree of life, the representation is picking up something deeper than the labels the model was optimized for. We run Mantel tests across two independent radiations. In 32 marine mammal species (1,754 recordings from the Watkins Marine Mammal Sound Database) the foundation models recover strong phylogenetic signal within the 26 cetaceans (CLAP r=0.82, BEATs-bio r=0.82, AST r=0.74; all p<0.001), among the highest acoustic-phylogenetic correlations reported for any taxon. Hand-crafted MFCC features (105d) find nothing (r=0.040, p=0.338). The gap survives after PCA-projecting every embedding down to 105 dimensions, so it is not an artefact of representation size. It also survives a partial Mantel test controlling for dominant frequency (partial Mantel r=0.404, keeping 97% of the variance explained), so it is not just pitch in disguise. We repeat the analysis on 20 bird species using the Jetz et al. (2012) phylogeny, and this time add BirdNET, a classifier trained end-to-end on around 6,000 bird species. The general-purpose foundation models recover the signal again (AST r=0.55, CLAP r=0.52). The unexpected result is that neither BirdNET nor the bioacoustic BEATs-bio beat them (r around 0.32 to 0.36). Matching the training domain to the target taxon does not, by itself, help. Pretrained audio embeddings carry evolutionary information across two independent radiations, and domain-specific pretraining is not required for it to emerge.
Authors: Anjian Li, Ryne Beeson
Abstract: Data scarcity poses a fundamental challenge in training generative models to produce initial guesses for parametric optimization problems that are otherwise numerically expensive to solve. We therefore study a $k$-neighborhood data collection strategy that augments datasets of converged solutions with intermediate solver iterates, increasing the amount of training data without additional solver runs. To understand the benefits of this approach, we derive a generalization bound based on Rademacher complexity that reveals the role of the $k$-neighborhoods and related parameters. To achieve this result, we focus on one-sided box-constrained quadratic programs solved by projected gradient descent. We illustrate the behavior of this solver on two examples. The approach proposed in this paper enables a more capable DDDAS paradigm by improving the efficiency of the data-model-optimization loop. We finish by discussing two views of learning solver-iterate data and connect our analysis with GLENS, a new data-efficient global search method.
Authors: Peng Zhao
Abstract: In overparameterized linear regression, many weak spectral directions act like a ridge penalty on the signal-bearing spectrum; negative ridge is the natural correction, pushing filters above one. The stable negative-ridge endpoint, however, is structurally limited: its pole must stay below the smallest nonzero empirical eigenvalue, and it anti-shrinks smaller eigenvalues more than larger ones. Early-stopped negative-shifted gradient descent escapes this constraint. Its filter is smooth at the would-be pole and mixed-sign-capable: above-ridgeless directions form a leading prefix, with lower directions shrunk or exposure-controlled while stopping sets the crossover. In a Gaussian spike-plus-flat model we discover a Marchenko-Pastur barrier: the shift that cancels the implicit penalty lies a bulk width above the smallest empirical eigenvalue, and the stopped path improves on every admissible endpoint by a polynomial factor in risk under explicit conditions. Our main theorem permits a general high-effective-rank tail: its trace sets the implicit floor, its squared spectrum controls exposure, and the floor-critical path recovers all head scales at once, beyond positive shrinkage and, once scales separate, every uniform rescaling of ridgeless. Handling the noncontractive shifted dynamics is the central technical challenge; localized Duhamel integrals control them. A finite-grid hold-out inequality transfers the separations to the validation-selected algorithm.
Authors: Jianghui Wang, Silong Yong, Francesco Orabona, Marco Canini, Katia P. Sycara, Yaqi Xie
Abstract: Low-Rank Adaptation (LoRA) has become a widely adopted technique for efficient neural network fine-tuning, decomposing model updates into low-rank matrices. However, LoRA remains computationally costly because it updates all matrices uniformly, regardless of their actual contribution to adaptation. This cost is especially prohibitive for large-scale models with billions of parameters and for resource-constrained settings such as edge deployment and on-device fine-tuning. We show for the first time that not all LoRA matrices are equally worth tuning: matrices with smaller condition numbers (the ratio of largest to smallest singular value) are already well-balanced across directions and contribute only marginally to adaptation, whereas matrices with larger condition numbers contain underdeveloped directions that span richer subspaces and drive most of the performance gains. This observation itself is a key contribution of our work, and it motivates a more selective approach to fine-tuning. Building on this insight, we propose \k{appa}-LoRA, a method that optimizes LoRA by focusing updates on the matrices with the largest condition numbers, which capture the most informative directions of change. By restricting LoRA updates to the top 50% of weight matrices ranked by condition number, \k{appa}-LoRA halves the trainable parameter count and correspondingly reduces compute and memory cost. Extensive experiments across multiple benchmarks show that this design cuts fine-tuning time by 16.2% on average while matching the accuracy of standard LoRA and reducing memory cost by 4.5%. Further analysis reveals that the condition numbers of the selected matrices consistently decrease over training, suggesting that \k{appa}-LoRA's effectiveness stems from targeted spectral rebalancing rather than parameter selection alone.
Authors: Aliaksei Kaliutau
Abstract: Volatility forecasting is dominated by persistence and measurement noise, leaving limited residual structure for nonlinear models to exploit. We introduce Susceptible Architectures (SUSA), a reservoir-design principle for volatility forecasting, and its two concrete implementations, based on complex-valued open-chain and periodic reservoirs and regime-conditioned experts to interpret reservoir features across calm, onset, recovery, and persistent-stress states. We also implement open-system $q$-qubit counterparts in Qiskit while retaining a common AR-Ridge anchor and a bounded residual correction trained under QLIKE. We evaluate models on 16 U.S. equity and exchange-traded-fund series using three disjoint chronological training, validation, and test folds, a 12-observation input window, and a five-observation forecast horizon. The proposed models perform competitively with GARCH, achieving statistically significant QLIKE improvements for specific assets (IWM, XLP). Also models' forecasts complement HARQ-style predictions: a stacked ensemble improves mean QLIKE by 0.0116 over its strongest constituent and wins in 75% of test scenarios.
Authors: Athanasios Papastathopoulos-Katsaros, Steven T. Lee, Lin Yao, Ajay Thomas, Junseok Park, Matthew J. McGinley, Zhandong Liu
Abstract: Electroencephalography (EEG) is widely used to diagnose neurological conditions, but its analysis usually relies on either predefined spectral features or deep neural networks. Predefined features carry a strong bias, since they fix in advance what counts as informative, while deep neural networks and foundation models are hard to interpret and need large amounts of data and compute. We present bag-of-waves, an interpretable framework that learns a small dictionary of recurring EEG waveform templates, called atoms, using shift-invariant k-means without labels. The continuous EEG is then turned into a sequence of atom tokens, whose counts feed a simple downstream classifier or clustering step. We extend this representation in two ways: we add atom-to-atom transitions, which we call n- grams, to capture temporal structure, and we move from single-channel atoms to regional and cross-channel spatial atoms for the multichannel case. We test the method on three complementary datasets, each probing a different aspect: single-channel mouse genotype clustering with only sixteen animals (the low-data and temporal case), resting-state dementia classification (the spatial case), and the TUEV benchmark, a six-way classification of clinical EEG events (a high-data comparison against strong deep and foundation baselines). Across all three datasets, bag-of-waves achieves performance competitive with state-of-the-art deep and foundation models. Yet, it operates with a fraction of the parameter count and provides full interpretability: because every atom corresponds to an inspectable waveform, the method explicitly recovers known clinical morphologies that a neurophysiologist can directly validate. Its main advantage is that it works in the low-data regime where heavier models are a poor fit.
Authors: Siyuan Zhao, Eric Ababio Anyimadu, Zachary G. Brumm, Yue Ma, Clifton David Fuller, Xinhua Zhang, G. Elisabeta Marai, Guadalupe Canahuate
Abstract: Dysphagia is a debilitating late effect of head and neck cancer (HNC) treatment, yet timely identification of at-risk patients remains challenging in survivorship care. Definitive assessment relies on videofluoroscopic imaging, as captured by the Dynamic Imaging Grade of Swallowing Toxicity (CTCAE-DIGEST), which, while validated, requires specialized equipment, trained personnel, and significant patient burden, limiting its routine use in surveillance. Patient-reported outcomes (PROs), by contrast, are low-cost, scalable, and easily collected at any clinical encounter, making them an attractive alternative signal for identifying patients who may warrant further evaluation. However, a clear clinical framework for translating PRO responses into actionable interventions is still evolving. In particular, uncertainty remains regarding when a patient's self-reported symptom burden should prompt escalation of care. This study addresses this gap by formulating a single-visit PRO-clinical prediction framework and introducing a clinically interpretable two-stage stacking model to predict swallowing impairment risk using PRO responses and structured clinical variables, without requiring videofluoroscopic imaging. The proposed framework quantifies the independent contributions of patient-reported symptoms and clinical factors within a unified and interpretable risk assessment model. Our findings demonstrate that individual MDADI responses contain predictive information beyond that captured by composite or global summary scores, while interpretability analyses reveal symptom patterns and clinical risk factors associated with swallowing impairment. Together, these results support the use of structured PRO-clinical integration as a practical, imaging-free approach for dysphagia risk stratification in HNC survivorship.
Authors: Pamela Kirui, Cho Hyuk, Qingzhong Liu, Haodi Jiang
Abstract: Deepfake generation has raised growing concerns regarding digital media authenticity, misinformation, identity fraud, and public trust. Recent studies show that combining spatial and frequency features leads to stronger detection results than using independently. This paper presents MSCA-FFT, a Fast Fourier Transform (FFT)-based multi-scale cross-attention framework for image-level deepfake detection. The model combines a partially fine-tuned Xception spatial branch with an FFT-based frequency branch. The frequency branch processes the log-scaled FFT magnitude spectrum through shallow convolutional layers, avoiding inverse frequency-to-image reconstruction used in DCT-based pipelines. The spatial and frequency representations are refined by transformer encoders, fused through cross-attention, and passed to an MLP classifier for real/fake prediction. Experimental results show that MSCA-FFT achieves consistently higher performance than the DCT-based state-of-the-art spatial-frequency fusion method and the compared baseline models. The ablation study further indicates that the FFT-based frequency branch provides complementary spectral cues when fused with spatial features. In addition, FFT-based frequency analysis and Grad-CAM/LIME explanations show consistent evidence around manipulation-sensitive facial regions, including the eyes, mouth, nose, and facial boundaries.
Authors: Guillermo Rubi\~nos Rodr\'iguez, Mart\'in Ottavianelli, Mateo Alonso, Gonzalo Bl\'azquez Gil, Boris-Stephan Rauchmann, Pablo D\'iez-Valle, Sergio Altares-L\'opez
Abstract: Numerous studies have analyzed the use of hybrid quantum-classical convolutional neural networks as a promising alternative to classical deep learning. However, network components on quantum hardware impose fundamental limitations, while the scalability of quantum circuits leads to trainability issues. In this work, we investigate whether small, classically-emulated quantum circuit components can play a meaningful role within complex models, offering an alternative to purely classical convolutional architectures. To this end, we present a systematic study of the effectiveness of a Hybrid Quantum-inspired Convolutional Neural Network (HQiCNN) compared with a parameter-matched classical Convolutional Neural Network (CNN) that differs only in an intermediate dense neural layer. Both models are evaluated on two real-world medical datasets while systematically varying the different hyperparameters, ensuring a fair model comparison that is both dataset and hyperparameter independent. The results show that no architecture consistently dominates the other: the HQiCNN achieves its largest gains in intermediate-data regimes, whereas the CNN reaches the highest accuracies for the largest training sets in both datasets. Furthermore, removing entanglement produces comparable performance while enabling substantially better scalability of quantum simulations, and richer observable sets become beneficial only when sufficient training data are available. Finally, we propose two SHAP-based explainability tools for comparing the predictions between both models, $|SHAP|$IoU and $EMD_{pos}$ metric, to demonstrate that both architectures consistently attend to anatomically plausible regions. Thus, we provide a comprehensive benchmark showing that, under certain conditions, hybrid quantum-inspired models are an alternative that can offer benefits in practical tasks such as medical image classification.
Authors: Ranjan Veerabhadraswamy, Ajith Jubilson Emerson
Abstract: Graph Neural Networks propagate information through local message passing, but the graph topologies themselves can silently prevent any amount of training from solving long-range tasks. When we deploy GNNs on new graphs, there is currently no inexpensive way to know, before training begins, whether the graphs' structures will allow information to travel far enough between distant nodes. We address this gap by proposing Spectral Flow Certificates (SFCs), single scalars computed from the graphs' normalised Laplacians in seconds, requiring no model training and no labelled data. An SFC fuses a graph's algebraic connectivity with the chosen message-passing depth into one number that measures how much of the critical spectral bottleneck can be traversed within the available depth budget. Unlike raw spectral gaps, which are static and depth-agnostic, SFCs adapt as the number of layers increases and therefore carry strictly more diagnostic information when depths vary. Compared with classical structural statistics such as average effective resistance and graph diameter, SFCs explain more than twice as much variance in trained GNN long-range accuracy. Across twenty-five synthetic graph families spanning paths, cycles, grids, regular graphs, and random graphs, SFCs predict trained accuracy before any gradients are computed, achieving explanatory power above ninety percent at all tested depths. The same predictive relationships hold on one hundred fifty real molecular graph topologies drawn from three independent benchmark datasets, confirming that the findings are not artefacts of their synthetic construction. Taken together, these results show that a single eigenvalue computation is sufficient to flag topology-limited graphs before committing to expensive training pipelines, providing a principled first filter for GNN deployments.
Authors: Miaobo Hu, Xiaobo Guo, Shuhao Hu, Bokun Wang, Rui Chen, Xin Wang, Daren Zha, Jun Xiao
Abstract: Schema graphs are an upstream bottleneck of schema-grounded information extraction and knowledge graph construction, yet most extraction systems assume the schema is already available. We introduce SCOPE (Schema Construction and Ontology-induction Pipeline Evaluation), a train-text-only benchmark for corpus-to-schema induction and optional schema fusion from raw text, built from 24 public information extraction sources (15 RE and 9 EE) normalized into evaluation-only gold schema graphs; its core event-extraction target covers event types and within-event argument roles, with inter-event links reported separately. We present SCION (Schema Construction and Induction with Ontology Normalization), an auditable reference pipeline rather than a new extraction architecture; it constructs candidate spaces from train text and restricts naming, merging, filtering, validation, and conservative fusion to candidate-linked evidence under strict JSON contracts. On the SCOPE core suite, SCION-lite attains the highest F1 among released source-schema references, Text2Onto-style, LLM-only, and matched extract-then-aggregate baselines under Literal, Fuzzy, Continuous, and Graph schema-graph metrics, while the compact open-model SCION-RL variant reduces reliance on proprietary LLM schema engineers. These results are reported against normalized typed-edge targets rather than as claims that induced schemas surpass human ontology design; the release includes evidence-linked outputs, parse/fallback logs, candidate retention/merging logs, run manifests, code, and benchmark packages at https://github.com/wandugu/paper_scion.
Authors: Simon Dennis, Kevin Shabahang, Hao Guo, Rivaan Patil
Abstract: Parameter-efficient fine-tuning methods like LoRA have become the default for adapting large language models, succeeding across instruction following, style transfer, and factual adaptation. We show that for procedural knowledge--the ability to follow multi-step procedures with conditional branching through to terminal states--LoRA fails to match full fine-tuning at the ranks where it retains its efficiency advantage. In a systematic ablation (r = 16--128) on a procedural travel booking task (14 nodes), all LoRA configurations fail uniformly (task success <= 2.54 vs. 4.11 for full fine-tuning, all p < 0.001), with scores decreasing at higher ranks--despite maintaining 95--99% conversation completion rates. Cross-domain replication on Zoom support (14 nodes) and insurance claims (55 nodes) at 8B confirms the failure generalizes: LoRA underperforms full fine-tuning by 0.8--2.2 points on average at both r = 32 and r = 128, with the largest gap on the most complex procedure. Quadrupling rank from 32 to 128 provides marginal improvement but does not close the gap. SVD analysis of the weight changes produced by full fine-tuning explains why: across three domains at both 3B and 8B, the mean effective rank of the update ranges from 761 to 1,026, and rank 128 captures only 43--51% of the squared Frobenius norm. Together, these findings establish that for procedural tasks LoRA falls well short of full fine-tuning--a fundamental limitation for agentic applications.
Authors: Theodoros Aivalis, Iraklis A. Klampanos, Antonis Troumpoukis, Joemon M. Jose
Abstract: The rapid deployment of generative AI has amplified the critical need for Training Data Attribution to ensure transparency and accountability. However, current parametric approaches require computationally prohibitive access to model weights, while similarity-based methods ignore deep structural context. We propose a novel probabilistic framework that operates entirely in a black-box setting. Our method fuses continuous feature similarities with discrete, domain-specific Knowledge Graphs (KGs). This approach ensures the attribution is grounded in structural reality, explicitly rewarding highly specific historical samples while preventing generic background data from dominating the results. We evaluate our framework across two distinct domains where linking outputs to data and domain context is inherently complex: abstract artistic image synthesis and high-dimensional physical weather forecasting. Extensive benchmarking demonstrates the robust efficacy of our approach. In the artistic domain, it achieves a strong Linear Datamodeling Score that exceeds standard black-box similarity baselines, while closing much of the gap to gradient-based estimators. We additionally present a cross-domain feasibility case study in environmental forecasting, where we use domain KGs to retrieve physically consistent historical analogs for regional flood forecasts, improving geographic localisation over a latent-only baseline. Operating entirely without internal model access, our approach provides an efficient, interpretable mechanism for post-hoc influence analysis and domain-grounded retrieval.
Authors: Martin Andrews
Abstract: We prove that two canonical local synaptic learning rules, the potentiation arm of spike-timing-dependent plasticity (STDP$^+$) and homeostatic plasticity (instantiated here via flashlight granule-cell-like neurons), together can implement the exact gradient of a SIGReg-like self-supervised learning objective. The equivalence requires no gradient calculations, no global error signals, no weight transport, and no label information: the only inputs are pre- and post-synaptic firing rates, local firing statistics, and the temporal contiguity of natural sensory streams. On a synthetic clustering task designed to probe whether class structure can be recovered from temporal ordering of inputs alone, ordered presentation raised cluster separation (CSR) to 2.49 while random ordering left it near baseline (0.83), a roughly threefold ($\approx 3.5\sigma$) separation attributable solely to input ordering. On temporally ordered MNIST, a two-layer network trained entirely with these rules achieved 87.3% linear-probe accuracy, showing that the mechanism functions end-to-end.
Authors: Kahou Tam, Wei Niu, Yu Bao, Xiaomin Ouyang, Chengzhong Xu, Li Li
Abstract: Transformer-based models have enabled unprecedented capabilities across language, vision, and multimodal tasks. On-device fine-tuning of transformer models offers a privacy-preserving path to personalized AI, yet remains inefficient on mobile GPUs due to severe memory constraints and frequent layout transformations in attention mechanism during training. Existing mobile training frameworks either use unified layouts for forward and backward passes -- leading to fragmented memory access and poor GPU utilization during backpropagation -- or rely on explicit layout conversions, which introduce significant transformation overhead. To overcome this, we propose FBLayout, a layout-aware framework that co-designs tensor organization with mobile GPU platforms. FBLayout introduces: (1) a unified R-Tile layout for multi-dimensional reductions across forward/backward passes; (2) tile-based index transformation to eliminate physical data movement; and (3) activation-guided layout selection to propagate efficient layouts globally. Evaluations on seven transformer models across different mobile phones (including ARM Mali and Qualcomm Adreno GPUs) show that FBLayout achieves 2.2-5.7x speedup over MNN, TFLite, and TVM, while significantly improving cache efficiency and reducing memory footprint, enabling practical on-device large model fine-tuning.
Authors: Xiaoyang Cao, Siddarth Srinivasan, Michiel A. Bakker
Abstract: End-to-end reinforcement learning can improve the accuracy of compound LLM systems, but it does not constrain how modules divide labor internally. We identify Role Drift, a failure mode in which modules preserve or improve end-task performance while deviating from their assigned roles through role-violating shortcuts that remain invisible to system-level evaluation. To make role drift observable and controllable, we propose Role Anchor, a regularizer that modulates how much each module deviates from its assigned role during end-to-end training. The key idea is to preserve how the role prompt shifts the module's next-token predictions relative to a neutral prompt, which serves as a proxy for the role's intended effect during training. Experiments on two compound LLM pipelines reveal role drift that accuracy alone fails to detect: a decomposer meant to split a question into sub-questions for a separate solver instead plants the answer in them, and a reader meant to answer from retrieved passages instead falls back on parametric memory. In fact, on the decomposer pipeline this shortcut drives most of the apparent RL gain: 86% of it vanishes once the decomposer is held to its role, indicating that terminal accuracy alone can badly overstate how much a compound system has genuinely learned. Across both pipelines, Role Anchor mitigates role drift at a tunable accuracy cost that varies by pipeline and anchor strength. Additional gradient analysis suggests that the regularizer reduces alignment with the role-drift direction rather than simply suppressing learning.
Authors: Zag ElSayed, Nathan Suer, Grace Westerkamp, Jack Yanchen Liu, Makoto Miyakoshi, Craig Erickson, Ernest Pedapati
Abstract: The electroencephalogram (EEG) is a valuable and widely applied tool for investigating brain disorders and behavioral changes. It offers a minimally restrictive and non-invasive method. However, challenges in using EEG for cognitive development studies include temporal resolution, signal source localization, and EEG artifacts. Careful consideration of these factors is essential for informed application of EEG technology. Independent component analysis (ICA) effectively isolates source generator processes from signals recorded by multiple, adjacent EEG scalp electrodes. Although ICA decomposition requires manual inspection, selection, and interpretation of independent components (ICs), this process is time consuming and demands expertise. Automated IC classification can achieve sufficient accuracy, expediting large scale EEG research and enabling near real time applications in conjunction with brain activity rejection tasks, which are crucial for medical specialists. This study introduces an automated computer vision based ICA rejection labeling tool compatible with widely used software interfaces like ICLabel and EEGLab. By automating the manual task, the proposed system reduces processing time by 7200 fold and achieves an accuracy of 89.45%.
Authors: Xianyuan Liu, Charles Anjah, Benjamin E. Jolly, Jonathon F. S. Markanday, Joshua Berry, Haolin Wang, Nicola A. Morley, Robert D. J. Oliver, Alexandra J. Ramadan, Delvin Ce Zhang, Katerina A. Christofidou, Haiping Lu
Abstract: Artificial intelligence (AI) is accelerating materials prediction and design by enabling efficient exploration of chemical and structural spaces, with particular promise for novel materials discovery. However, novelty in materials discovery encompasses chemical plausibility, structural distinctiveness, property relevance and experimental realisability, making AI-driven novelty claims difficult to substantiate. We introduce a materials property hierarchy, from intrinsic, composition-determined properties to extrinsic, processing-dependent performance, to clarify deployment constraints and distinguish structural, physical and deployment novelty. This framework motivates an evidence-based view of multimodal materials data spanning chemical composition, microstructure, processing, and testing and characterisation, showing that current evidence remains concentrated in composition and idealised structure while heterogeneous, under-represented and weakly integrated modalities limit support for physical and deployment novelty. It also highlights the limitations of benchmarks based mainly on computational labels and proxy novelty criteria. Community-wide standards for data collection, modality alignment and evidence synthesis are needed to support multimodal data construction, process-aware multimodal modelling, feasibility-first generative modelling and deployment-aware benchmarking, so that generative and multimodal AI can design experimentally realisable materials with defensible scientific and practical novelty.
Authors: Chaoqi Liu, Yue Zhao, Haonan Chen, Xiaoshen Han, Jiawei Gao, Ehsan Adeli, Yilun Du
Abstract: Action tokenization maps continuous robot action chunks to discrete tokens and has become an important interface for modern visuomotor policies. Existing approaches either rely on analytical discretization methods that produce prohibitively long token sequences or learned latent tokenizers that lack structure, limiting their compatibility with downstream policies. In this work, we identify three desiderata for action tokenization - high compression, total decodability, and an ordered token space - and introduce Ordered Action Tokenization (OAT), a learned action tokenizer that satisfies all three. OAT discretizes action chunks into an ordered sequence of tokens using a transformer with registers, finite scalar quantization, and ordering-inducing training mechanisms. By training each token prefix to decode into a valid action chunk, OAT places coarse control information in early tokens and uses later tokens to refine residual detail, yielding an anytime tradeoff between inference cost and action fidelity. We validate OAT in two prevailing uses of action tokens: autoregressive policies that generate tokens for control, and token co-training policies that use token losses to shape the vision-language model context consumed by a flow-based action expert. Across three policy backbones and more than 60 tasks spanning five simulation benchmarks and real-world settings, OAT consistently delivers strong policy performance while offering significantly greater flexibility at inference time.
Authors: Xiao Xue, Maida Wang, Mingyang Gao, Minh Chung, Peter V. Coveney
Abstract: Machine-learning surrogates of physical systems face a paradox: explainable models facing the challenge of expressivity to capture complex nonlinear flows, whereas expressive deep surrogates match high-fidelity simulations only through massive parameterisations that turn the learned dynamics into a black box. Here, we introduce quantum-compressed machine learning (QCML), which resolves this tension by compressing the latent propagator of a flow surrogate from $524{,}288$ trainable parameters to no more than $8$. This parameter reduction brings the learned dynamical law to the parameter scale of a physical constitutive relation rather than a black-box neural network, making the surrogate directly interpretable and controllable without sacrificing expressivity. The compression is realised by a structured quantum circuit whose unitary propagator constrains the latent spectrum to the unit circle exactly and by construction, replacing exponential error growth with linear accumulation over autoregressive rollouts. Classical regularisation only approximates this constraint: even a quantum-inspired classical baseline penalised towards unitarity collapses within one Lyapunov time on turbulent channel flow, whereas QCML remains stable over the full rollout. Shared phase and coupling angles parameterising the circuit correspond directly to modal frequencies and inter-mode interactions, giving the learned dynamics a physical interpretation in spectral space. On two patient-specific cardiovascular benchmarks, the structured QCML propagator matches the predictive accuracy of its classical counterpart on surface pressure spectra, pressure drop, and wall shear stress. These results establish QCML as a working component of scientific machine learning and a concrete contribution towards practical quantum advantage in real-world prediction.
Authors: Ali Siahkoohi, Sina Alemohammad
Abstract: Learned generative priors are increasingly used for ill-posed Bayesian inverse problems, their posterior uncertainty treated as earned from data. But training one requires truths, scarce in seismic and medical imaging, so the recourse is an archive of legacy reconstructions---prior laundering. Where the measurements are uninformative the posterior reverts to the prior, so the uncertainty reported there is the archive's, not the data's, and nothing in deployment reveals it: truths differing only on those directions induce identical data laws, and self-consistency checks such as simulation-based calibration pass whatever the prior believes. That belief has an exact source: averaging the legacy posterior over the measurements yields the old regularizer advanced a single expectation--maximization step---improved where the data resolve, frozen where they cannot. It is overconfident wherever the inherited belief is tighter than the truth. A single-best archive is worse, collapsing the blind credible interval to zero width. Deployed, a diffusion prior fit to the archive under-covers the operator's blind subspace, unlike a truth-trained control, and a normalizing flow does the same on a nonlinear groundwater operator. We recommend reporting which directions the measurements resolve, separating confidence the data support from belief inherited through the pipeline.
Authors: Khalid El-Darymli, Christoph H. Gierull, Katerina Biron, Weimin Huang
Abstract: Radar cross-section (RCS) modeling is foundational to advancing the utility and sensitivity of spaceborne radar systems. This study introduces a deep sigma-point process (DSPP) model for predicting RCS in synthetic aperture radar (SAR) imagery using a RADARSAT-2 dataset containing 208,191 verified ships. The DSPP model not only strives for predictive accuracy but also characterizes the uncertainty inherent in the intricate relationships among radar signals, ship parameters, and environmental conditions. Unlike traditional approaches that rely on deterministic equations with static parameters, the DSPP uses a hierarchical Gaussian process framework with Bayesian inference to capture variability and uncertainty in RCS predictions. By generating predictive distributions rather than single estimates, the model accounts for the complex dynamics governing radar returns. Using a Matern kernel with automatic relevance determination, the DSPP identifies and ranks critical features across radar, operational, and environmental domains, thereby supporting transparency and interpretability. Performance evaluations demonstrate the model's superiority over linear regression baselines, with a 20.83 percent reduction in root mean squared error, a 25.89 percent increase in R-squared, and a 44.4 percent reduction in both the residual interquartile range and median absolute deviation on the test data. By providing calibrated uncertainty bounds, the DSPP enhances prediction reliability and supports robust decision-making. This work represents a shift toward probabilistic models that incorporate the inherent uncertainty of complex phenomena. By transitioning from fixed equations to distributions over outcomes, the DSPP fosters a deeper understanding of RCS behavior and enables systems to operate effectively in dynamic environments.
Authors: Denis Mayr Lima Martins, Gottfried Vossen
Abstract: Large Language Models (LLMs) are increasingly used in database-backed applications to classify tuples, filter records using semantic predicates, extract structured attributes, and enrich query results. Yet the prompt that start these computations are typically stored outside the DBMS in unstructured formats, making them invisible to query execution, metadata management, and optimization. Drawing on Stonebraker's QUEL as a Data Type and the principles of reflective programming, this paper introduces PromptDB, a database system that treats prompts as tuple-level database values. PromptDB provides a logical PROMPT datatype whose values store a template, bindings to tuple attributes, model metadata, and task metadata. Relations may contain PROMPT attributes directly in base tables, or expose them through views over joined tuples. Users query prompt-valued attributes through generated evaluation views, while the system internally renders, rewrites, optimizes, and executes prompts through an EVAL operator. Making prompts database-visible creates a new optimization space. The key idea is to bring query-optimizer thinking to prompts: just as query optimizers exploit database metadata to rewrite SQL plans, PromptDB exploits database metadata to rewrite prompts. We evaluate PromptDB on synthetic and real-world data workloads across different tasks. The results show how database-guided rewriting improves output validity and yields favorable cost-quality trade-offs compared with static, manually written prompts.
Authors: G Conant, C Terry
Abstract: We prove function-theoretic analogues of a quantitative result of Hodges on extracting the order property from a sufficiently large 2-tree coded in a binary relation. Similar analogues for functions were previously obtained by Daskalakis and Golowich and by Anderson and Benedikt. These results are from statistical learning theory, where 2-trees are captured by sequential fat-shattering dimension, and the order property is controlled by various notions of "thresholds". Our first main result (Theorem 1.11) focuses on extracting a less restrictive kind of threshold from a tree, and yields significantly better bounds compared to what can be obtained from earlier results focusing on more restrictive versions. Part of the motivation for Theorem 1.11 lies in a companion paper, where this theorem is used to obtain efficient bounds in quantitative regularity lemmas for "stable functions". Here will use Theorem 1.11 to reprove a result of Anderson and Benedikt in a stronger form and with improved bounds. We also use Theorem 1.11 to prove an at most double-exponential bound on dual sequential fat-shattering, which resolves an open problem. In our second main result (Theorem 1.14), we give a new proof of a result of Daskalakis and Golowich on extracting "tight thresholds" from large sequential fat-shattering dimension, with improved bounds. This resolves another open problem related to correcting the proof of a result claimed by Jung, Kim, and Tewari.
Authors: Jinglin Yu, Feiyang Wu, Longying Wen, Chongxian Yuan, Renjie Li, Zhaoyu Zhang
Abstract: Near 1310 nm photonic-crystal surface-emitting lasers (PCSELs) are attractive narrow-beam sources for optical communication and sensing, but their final design refinement is costly. Small geometry changes simultaneously shift the band-edge resonance, cavity leakage, far-field divergence, and the numerical stability of a high-$Q$ decay fit, while every full-wave trial requires a time-domain simulation. We couple a commercial finite-difference time-domain solver to a reliability-aware Bayesian optimization (BO) loop over eight local design variables. Each completed simulation updates the surrogate used to choose the next geometry. Candidate ranking combines wavelength and beam-quality requirements with a reliability-adjusted metric $Q_{\mathrm{eff}}$ derived from the solver-reported relative fit-error estimate $dQ/Q$. Across three 80-evaluation runs from the same reference model, BO produced 5--15 candidates per run that passed the joint filter. Designs reconstructed from fresh model copies retained $Q_{\mathrm{eff}}=4.33\times10^6$--$7.76\times10^6$, a 60--108-fold increase over the baseline metric, at 1308.23--1310.90~nm with approximately $0.84^{\circ}$ divergence. Under equal budgets, BO gave the highest mean strict-filter yield (9.0 candidates), compared with differential evolution (7.0) and Latin-hypercube sampling (1.5), although the controls occasionally matched the peak $Q_{\mathrm{eff}}$. Field maps, resonance spectra, and local perturbations further identify an index-related wavelength handle and a hole-size-related leakage handle. The resulting FDTD budget produces a pool of wavelength-compatible, narrow-beam, and reproducible high-$Q$ PCSEL candidates without trusting a single optimistic decay fit.
Authors: Rodrigo Vargas Sainz, Christian Ber\'on Curti
Abstract: Roadblocks in Bolivia are a social conflict phenomenon with devastating economic impacts, estimated at losses equivalent to 4% of the national Gross Domestic Product. Despite their recurrence and impact, there is a lack of local predictive systems to anticipate these events for logistical decision-making. This paper presents a hybrid probabilistic forecasting system that integrates time series decomposition (Prophet) with natural language processing (NLP) techniques applied to a six-year corpus of Bolivian news coverage. The methodology employs vector semantic embeddings and zero-shot classification models to capture signals of discursive escalation prior to the materialization of the roadblocks. Using an expanding walk-forward validation scheme applied over 1,762 days and seven forecasting horizons (H+1 to H+7), seven internal configurations and four external benchmarks were compared, including SARIMA and LightGBM. The results demonstrate that the hybrid configuration (Prophet + NLP, C6) consistently outperforms purely statistical models, achieving an AUC-ROC of 0.677 at H+1 and reducing the Brier Score by 10.9% relative to the baseline temporal model (0.220 vs. 0.247), maintaining a statistically significant error reduction across all evaluated horizons ($p < 0.02$). This research validates that the integration of semantic news signals allows for the detection of social tension peaks not captured by historical inertia, providing a technical tool for risk management in critical transport corridors.
Authors: William Gaudelier, Albert Cohen, Dumitru Potop Butucaru
Abstract: Previous work has shown that the simple dataflow primitives of the Lustre language allow the natural, semantically unambiguous, and compact representation of machine learning (ML) applications, including models featuring complex conditional execution and recurrent state. The Lustre clock calculus is responsible for the static determination of important properties such as liveness (absence of deadlocks) and static memory bounds. Yet existing clock calculi are tailored for embedded control applications. We show they do not cater for the representation of control patterns commonly found in training algorithms, resulting in cumbersome expressions and inefficient compilation. We propose a conservative extension of Lustre's clock calculus addressing this limitation, thereby facilitating the embedding of ML models in reactive applications.
Authors: Run Wang, Chaoyi Zhou, Xi Liu, Yi Zhu, Amir Salarpour, Pedram MohajerAnsari, Zhi-Qi Cheng, Feng Luo, Siyu Huang, Mert D. Pes\'e
Abstract: Lossless acceleration schemes, such as speculative decoding, promise significant inference speedups by relying on dynamic token-level alignment between a draft and a target model. However, this guarantee of semantic equivalence masks a severe operational vulnerability: draft-target alignment can be systematically attacked. In this paper, we introduce ADSD, which, to the best of our knowledge, is the first prompt-suffix attack that collapses verifier acceptance by pushing draft probability mass toward tokens the target is unlikely to accept. ADSD uses Soft-Collapse, a verifier-aligned surrogate derived from the asymmetric speculative acceptance rule, together with a target-preservation objective that discourages obvious task corruption. ADSD successfully generates highly effective adversarial suffixes. On the GSM8K dataset, our attack increases the mean sample time by 62.3% while preserving the task quality. We further show that this vulnerability exists across different domains, speculative decoding strategies, and model architectures.
Authors: Jakub Bielawski, Thiparat Chotibut, Fryderyk Falniowski, Micha{\l} Misiurewicz, Georgios Piliouras
Abstract: We study the long-term behavior of the Multiplicative Weights Update (MWU) algorithm in game settings where learning dynamics frequently fail to converge to Nash equilibria and instead exhibit Li-Yorke chaos. While such chaos precludes the prediction of specific long-term strategy profiles, it does not imply a lack of statistical structure. We demonstrate that natural invariant measures - a fundamental concept from ergodic theory - provide the rigorous framework necessary to find order within this chaos. Focusing on a two-strategy congestion game, we prove that these measures allow for a comprehensive statistical characterization of the dynamics. Crucially, we show that this framework extends beyond simple strategy frequencies to \emph{general observables}, enabling the precise calculation of long-term time averages for broad classes of economic metrics - including payoffs, social cost, and regret - despite chaos. Our results reveal that this simple learning algorithm captures the full spectrum of behaviors found in one-dimensional dynamical systems, from unique or multiple absolutely continuous invariant measures to complex periodic attractors as well as coexisting chaotic and stable (periodic) behaviors. By bridging game theory and dynamical systems, we show that statistical predictability is attainable even in the absence of pointwise convergence.
Authors: Yangsheng Wang, Xiaotian Dai, Haoda Fu, Guifang Fu
Abstract: Longitudinal studies often collect data at sparse, irregular, and unequally spaced time points. Such heterogeneity is often driven by subject-specific covariates, yet existing methods have been restricted to a scalar endpoint value, completely neglecting the underlying response trajectories. We propose a novel Longitudinal Random Forest (LRF) framework that leverages tree-based ensemble machine learning with adaptive node-wise longitudinal trajectory estimation. The LRF framework makes five methodological contributions. it captures each subject's individual response trajectory while simultaneously accommodating within-node correlation, between-node heterogeneity, and nonlinear and interactive covariate effects. It introduces a novel trajectory-based splitting criterion that maximizes trajectory separation while incorporating a size-weighted penalty; it provides two variants, Principal Analysis by Conditional Expectation (LRF-PACE) and adaptive linear mixed-effects models (LRF-adaptiveLMM), which employ nonparametric and semiparametric node-wise smoothers, respectively, while learning covariate effects in a data-driven manner. It provides a comprehensive interpretation of covariates using both the classical trajectory-based permutation variable importance measure (PVIM) and a newly proposed finite-way interaction frequency count, and it not only predicts entire trajectories for new subjects but also forecasts future trajectories for existing subjects. Extensive simulation studies demonstrate that LRF achieves superior performance over several competing methods, even under severe sparsity. The practical significance of the LRF framework lies in its ability to address five important clinical questions.
Authors: Daniyal Kabir Dar, Arun Ross
Abstract: Audio deepfake detectors are trained to distinguish genuine speech from synthetic speech and often perform well on standard benchmarks. Yet the same detector that achieves less than 1% error on one dataset can see its error rate increase twentyfold when evaluated on a different dataset. We argue that one contributing factor is speaker-identity reliance: standard training corpora correlate speaker identity with the genuine/synthetic label, allowing detectors to partially rely on speaker-related cues rather than synthesis artifacts alone. We propose the Identity Sensitivity Score (ISS), a per-utterance diagnostic that quantifies how much a detector's output changes across different speaker identity contexts. ISS requires no ground-truth labels at inference time and can be computed from the detector score and a pool of reference speaker examples. Across two detectors and two datasets, incorrectly classified utterances have ISS scores 29 to 52 times higher than correctly classified utterances, and ISS alone predicts misclassification with area-under-curve (AUC) up to 0.954. To test whether ISS actually captures identity-sensitive behavior rather than serving only as a proxy for prediction confidence, we apply voice conversion to 500 utterances and measure the resulting detector-score shift. Utterances flagged as identity-sensitive by ISS respond 19 to 30 times more strongly to this manipulation than utterances flagged as stable. These results position ISS as a practical inference-time diagnostic for speaker-dependent failure analysis in audio deepfake detection.
Authors: Iren Mazloomzadeh, Mohammad Mehdi Morovati, Foutse Khomh
Abstract: Recent advances in large language models and their rapid adoption across software engineering tasks have made Artificial Intelligence (AI) coding agents an integral component of modern software development workflows. While developers increasingly benefit from these coding agents, their impact on software quality remains insufficiently understood. In particular, how agentic contributions evolve across the software development lifecycle has not been thoroughly investigated. This study aims to characterize agentic pull requests (PR) in comparison to human generated PRs and to examine how their properties change across different stages of the development lifecycle. Using the AIDev dataset, we first analyze how differences in merge rates between agentic and human generated PRs vary over time. We then identify the types of development tasks where AI coding agents are predominantly applied and investigate how these task distributions evolve across development quarters. Finally, we compare a set of key characteristics of agentic and human generated PRs, focusing on their implications for software quality and their temporal dynamics. Overall, our findings provide an empirical and longitudinal perspective on the role of AI coding agents in software development, offering a more nuanced understanding of their benefits and limitations in real-world practices.
Authors: Carter Luck, Olive Franzese-McLaughlin, Elisaweta Masserova, Akira Takahashi, Antigoni Polychroniadou, Nicolas Papernot
Abstract: Privacy-preserving machine learning auditing protocols allow auditors to assess models for properties such as accuracy or fairness, without revealing their internals or training data. This makes them especially attractive for auditing models deployed in sensitive domains such as healthcare or finance. For these protocols to be meaningful in real-world audit settings, though, their guarantees must reflect how the model will behave once deployed, rather than merely certifying its behavior during an audit. Existing security definitions often miss this mark: most certify model behavior only on a fixed audit dataset, without ensuring that the same guarantees generalize to other datasets drawn from the same distribution. As we show, this gap allows a model provider to attack many cryptographic model certification (CMC) schemes built on secure zero knowledge proofs (ZKP) by carefully engineering training data, resulting in models that exhibit benign behavior during an audit, but pathological behavior in practice. For example, we empirically demonstrate that an attacker can certify that a model achieves over 99% accuracy on an audit dataset, but less than 30% accuracy on fresh samples from the same distribution. To address this gap, we formalize rigorous cryptographic security notions tailored to CMC frameworks, introduce a generic protocol template, and prove that it satisfies these requirements. Our results thus offer both cautionary evidence about existing approaches and constructive guidance for designing secure, privacy-preserving ML auditing protocols.
Authors: Fathima Ameen, Christopher G. Healey
Abstract: Research on political polarization on social media depends on the ability to reliably measure partisanship in user-generated content. However, existing approaches are typically tailored to platform-specific properties, such as structural affordances or linguistic conventions, which hurts generalizability across platforms. This limitation is increasingly consequential as the social media ecosystem fragments and fringe, alt-tech platforms emerge alongside mainstream ones. We propose a text-based, platform-portable methodology for measuring political partisanship in social media posts, anchored by an external news-credibility signal. Posts are embedded using a transformer-based sentence encoder and clustered into topic groups, which are labeled using the aggregated AllSides media bias scores of cited news outlets. A partisanship axis is then constructed in the embedding space as the difference between centroids of oppositely labeled clusters, and individual posts are scored by projection onto this axis. We apply the method to a corpus of approximately 1.3 million posts collected from Bluesky and Truth Social during the six months preceding the 2024 U.S. presidential election, providing the first cross-platform comparison of partisanship distributions on these two ideologically asymmetric platforms. The resulting partisanship scores correlate significantly with held-out AllSides media bias scores both in-distribution and out-of-distribution on an independent Twitter corpus, and recover within-platform partisan dynamics that platform identity alone cannot explain.
Authors: Xinwei Shen, Diana Cai, Cheng Zhang, David M. Blei
Abstract: Empirical Bayes (EB) performs simultaneous inference across many related latent variables. Classical EB assumes that the likelihood p(x | z) is tractable. In many scientific applications, however, the likelihood is available only through a simulator. This paper develops EB for such implicit likelihoods. We introduce simulation-based empirical Bayes (SBEB), which connects nonparametric EB to simulation-based inference (SBI). SBEB computes EB estimates without an explicit density by using the observed data, simulator samples, and an amortized inference network. SBEB iteratively refines the fitted EB prior toward the population prior. With several scientific simulators and real-world data, we demonstrate that SBEB improves accuracy over SBI with a fixed prior.
Authors: Khai Nguyen, Yang Ni, Elizabeth Juarez-Colunga, Peter Mueller
Abstract: We introduce the distributional determinantal point process (dDPP) as a novel repulsive point process whose atoms are probability distributions rather than points in a real space. The dDPP is constructed via an L-ensemble with a sliced Wasserstein (SW) kernel between distributions. We show its validity as a well-defined point process. In the discrete setting, we derive concentration results for plug-in estimators of the L-ensemble, the correlation kernel, and their determinants given i.i.d. samples from the distributional atoms. Leveraging this framework, we propose a distribution-valued random partition model by way of a repulsive generalized Bayesian mixture model. The model places a dDPP prior over the atoms of the mixing measure and defines a generalized likelihood based on SW distance. To summarize posterior inference, we develop a decision-theoretic approach to report a point estimate of the mixing measure as a Bayes rule under a hierarchical optimal transport utility function. The latter is a natural choice given that the mixing measure is itself a distribution over distributions. We use the proposed framework for inference with single-cell gene expression data and human epilepsy data, producing interpretable and well-separated clusters that reflect meaningful structure in the data.
Authors: Mohammadreza Narimani, Vikram Anand, Parastoo Farajpoor
Abstract: Agricultural field maps are often proprietary, incomplete, or outdated, yet they provide the spatial framework for crop monitoring, production accounting, and land-conversion analysis. This study presents a reproducible workflow for mapping farmland extent and visible boundaries from 1 m NAIP RGB imagery. Thirty-seven scenes spanning open cropland, peri-urban interfaces, semi-arid irrigation geometries, and fragmented mosaics were annotated in CVAT and converted to binary masks. Non-overlapping 256 x 256 patches yielded 5,698 samples, split by source scene into 3,850 training, 770 validation, and 1,078 test patches. A residual U-Net (ResUNet) trained with a Dice-dominant loss, L = 2.5(1 - Dice) + BCE, achieved test accuracy 0.8808, IoU 0.8605, Dice 0.9234, precision 0.8766, and recall 0.9794. A frozen SAM 3 branch prompted with "agricultural farmland field" was fused with ResUNet by logical OR. On selected difficult patches, Dice improved from 0.858 to 0.955 (orchard rows) and from 0.804 to 0.903 (fragmented parcels). Sliding-window stitching produced coherent regional masks (example tile Dice 0.898 and 0.919). The product is a semantic farmland-extent layer, not a cadastral parcel map, and supports agricultural monitoring where current field layers are unavailable.
Authors: Lu Luo, Dandan Mo, Chengdong Xu, Ting Li, Jinhan Xie, Huiqiong Li, Niansheng Tang
Abstract: As large language models (LLMs) are increasingly deployed, reliable and efficient mechanisms for distinguishing AI-generated text from human-written content have become essential. Statistical watermarking has emerged as a promising solution, yet most existing methods are typically fixed-horizon procedures, precluding valid early stopping in streaming generation. In this paper, we develop an efficient online watermark detection framework with anytime-valid inference based on Rao-Blackwellized e-processes, enabling recursive token-level evidence updates without storing the full history. In particular, we instantiate the framework for the Gumbel-max watermark and reduce the original token-level dependence testing problem to a pivot-induced sequential testing problem with an explicit null distribution. Theoretically, we prove anytime-valid Type I error control under arbitrary optional stopping and establish positive asymptotic log-growth under watermarking, implying consistency of the proposed stopping rules. Simulations and experiments on real LLM-generated text demonstrate efficient online detection with rigorous anytime-valid guarantees.
Authors: Jinhyeok Kim, Yejoon Lee, Jaeyoung Do
Abstract: The increasing deployment of large language models (LLMs) has magnified the computational and memory bottlenecks of autoregressive decoding, where low compute intensity and bandwidth-bound kernels dominate inference cost. Weight pruning offers a promising remedy, but existing methods remain confined to either static pruning (SP), which permanently removes redundant weights but lacks adaptivity, or dynamic pruning (DP), which adapts to input sparsity but introduces runtime irregularity. This paper presents SPDP, a unified sparse-inference framework that integrates unstructured SP with input-adaptive DP for efficient LLM inference on GPUs. SPDP co-designs a new Tiled-Column-wise Bitmap Compressed (Tiled-CBC) format and two complementary GPU kernels: (1) a CUDA-core spMspV kernel featuring Hybrid Activation-aware Dynamic Shared-Memory Bitmap Decoding (HAD-SMBD) for fine-grained, runtime activation skipping, and (2) a Tensor-Core SpMM kernel optimized for prefill computation. This joint format-kernel design harmonizes static and dynamic sparsity, maintaining bandwidth-efficient memory access and high compute intensity under both phases of LLM inference. Comprehensive evaluations on inference-optimized GPUs demonstrate that SPDP achieves 1.24x-1.37x average speedup (up to 2.51x) over state-of-the- art sparse frameworks such as SpInfer, while matching. perplexity with up to 25% higher sparsity. SPDP advances the inference efficiency-quality Pareto frontier, showing that unified static-dynamic pruning can deliver substantial throughput and performance-per-watt improvements in large-scale LLM serving
Authors: Harsh Milind Tirhekar, Chandrajit Bajaj
Abstract: Rare-regime discovery in parameterized dynamical systems is an active-search problem: find one verified parameter at which a scientifically defined qualitative threshold is crossed, even when acceptable candidates are rare, nonconvex, or fragmented. We introduce Quantum-Classical Phase-space and Stability-Threshold Search (QC-PHAST), an evidence-gated decision protocol and query-accounting framework for finite candidate libraries. A candidate induces a dynamical object, simulator-derived criticality score, and verified first-hit predicate. Scientific metadata and charged pilot evidence are used to assess whether equation-aware search, scalar-score active search, predicate-only search, or only a query-model comparison is admissible. The quantum row is the inherited Grover/Boyer--Brassard--Hoyer--Tapp (BBHT) unknown-$M$ marked-set query reference; it is not a new quantum-search theorem, materialized circuit, or hardware-speedup claim. The result is a regime map. Direct boundary constructions, geometry controls, online simulator loops, and learned-label accounting further identify when classical structure, false positives, calibration cost, or state preparation erases the query-model margin. QC-PHAST is therefore an auditable protocol for deciding when a finite-pool marked-set reference is informative and when classical or resource-aware search should dominate.
Authors: M M Asif Ferdous
Abstract: Vision-language models (VLMs) are increasingly deployed on consumer hardware where input images are degraded by compression, camera shake, and poor lighting. In such settings, a reliable uncertainty signal matters more than raw accuracy, because it determines when a system should defer rather than answer. We evaluate two small open-weight VLMs -- Qwen2-VL-2B-Instruct and SmolVLM-Instruct -- across six realistic photographic degradations at three severity levels, comparing two confidence signals: the confidence the model states in natural language, and the model's own mean token probability over its generated answer. Across 3,800 predictions, we find a large and consistent gap. Verbalized confidence in Qwen2-VL is almost constant (mean 0.87-0.90 across all conditions) and detects its own errors at chance level (AUROC 0.39-0.75, typically ~0.50), while internal token probability from the same model separates correct from incorrect answers with AUROC 0.92-0.99. In SmolVLM, verbalized confidence proved largely unobtainable: across three prompt templates, only one of five pilot attempts produced a parseable confidence value, while internal probability again yielded above-chance error detection (AUROC 0.54-0.92). Both models fail in the same place: under severe underexposure, accuracy collapses (0.99->0.22 for Qwen2-VL, 0.97->0.42 for SmolVLM) while both confidence signals barely move, and internal error-detection falls to chance. We conclude that small VLMs encode usable self-knowledge that their verbalized output does not express, that internal probability is therefore the better deferral signal in constrained deployment, and that neither signal should be trusted under severe low-light conditions.
Authors: Yu Wang, Hongyu Yang
Abstract: Multi-branch architectures and CNN-Transformer fusion have long been regarded as effective ways to improve vehicle re-identification (Re-ID) by combining complementary representations. In this work, we revisit this assumption in the foundation-model era through a comprehensive empirical study. A single DINOv3-pretrained ConvNeXt trained with a tuned recipe achieves 88.19 mAP on VeRi-Wild Small and 77.47 mAP on VeRi-Wild Large using visual cues alone, matching the strongest protocol-verified metadata-dependent multi-branch baseline. Applying training-free re-ranking further improves performance to 92.38 and 83.68 mAP, respectively. Using this strong baseline together with retrieval-level branch diagnostics, we evaluate whether increasing representational diversity still provides measurable gains. Across both benchmarks, concatenating multiple branches built on a shared backbone changes the best single-branch performance by less than one mAP point while increasing the embedding dimension by 4x, and the resulting representation has an effective rank close to the original feature dimension. We further study cross-backbone fusion using an asymmetric frozen-anchor strategy to combine ConvNeXt and Vision Transformer representations. Despite these favorable conditions, Transformer branches consistently remain 13-15 mAP below the ConvNeXt backbone, and paired per-query bootstrap analysis estimates the largest observed fusion gain to be only +0.11 mAP (95% confidence interval). Our results suggest that, under the evaluated setting, improving a single strong foundation-model backbone together with retrieval-stage re-ranking is more effective than increasing architectural complexity through additional branches or heterogeneous backbones. We restrict our conclusions to single-seed training and one family of foundation models and discuss conditions under which these observations may not hold.
Authors: Phurich Saengthong, Takahiro Shinozaki
Abstract: Autoencoder-based anomalous sound detection is attractive for machine condition monitoring because it can be trained using only normal recordings and yields an interpretable anomaly score from reconstruction error. Most prior work uses spectrogram autoencoders, but reconstructing detailed time--frequency patterns is sensitive to noise and transients, and models can reconstruct some anomalous inputs well, weakening normal--anomaly separation. We propose MemNMF, a constrained reconstruction method that operates on the Linear Predictive Coding spectrum, a compact estimate of the spectral envelope. MemNMF initializes a memory module from an NMF dictionary learned on normal LPC spectra and reconstructs each input as an attention-weighted combination of prototypical normal spectral patterns. Experiments on MIMII and DCASE 2020 Task 2 across multiple machine types and operating conditions show that LPC-spectrum inputs improve a standard autoencoder baseline and that MemNMF yields further gains, with especially strong robustness under noisy, non-stationary settings.
Authors: Junlin Fang, Do Nguyen-Thanh, Xiaogang Xu, Zhen Fang, Sean Du
Abstract: Large reasoning models (LRMs) generate long reasoning traces before producing final answers. While these traces may contain useful signals for hallucination detection, harnessing them is non-trivial because long trajectories often include noisy steps that obscure the cues relevant to truthfulness assessment. In this paper, we identify two prevalent forms of reasoning noises, i.e., irrelevant steps and repetitive steps, and show that both substantially degrade hallucination detection performance. Existing confidence-based scores and naive embedding-based filtering fail to reliably separate noisy from informative steps. To address this challenge, we propose REDE, a novel learning framework for denoising reasoning traces for hallucination detection. Specifically, REDE leverages final-answer attention as an automatic supervision signal to shape the step-level representation space, yielding refined embeddings in which noisy steps can be reliably identified and filtered. REDE can be readily plugged into diverse hallucination detectors by operating on the filtered reasoning trajectory after removing noisy steps. Extensive experiments on multiple reasoning benchmarks show that REDE consistently improves detection performance over competitive baselines.
Authors: Jan Ole von Hartz, Abhinav Valada, Joschka Boedecker
Abstract: Multi-stream robot manipulation policies achieve unparalleled sample efficiency and generalization by modeling actions relative to environmental reference frames. However, existing approaches typically assume these frames to be strictly exogenous. This causal assumption collapses in dynamic settings, such as when a single robot arm manipulates a moving object or when two arms coordinate, where each arm effectively becomes part of the dynamic environment of the other. We propose DynaMAC, a lightweight, policy-agnostic framework that resolves this causal limitation while preserving the sample efficiency, computational speed, and flexibility of multi-stream policies, DynaMAC treats the opposite arm as a dynamic task parameter, thereby providing a unified formulation for dynamic manipulation and bimanual coordination without requiring an explicit leader-follower relationship. To rigorously evaluate these capabilities, we introduce DynaBench, a novel benchmark for robot manipulation in dynamic environments. Across both dynamic environments and bimanual manipulation tasks, DynaMAC outperforms leading probabilistic and generative baselines by over 35 percentage points while requiring 20 times fewer samples. Crucially, DynaMAC generalizes zero-shot from static demonstrations to dynamic environments, substantially simplifying data collection and establishing an elegant bridge toward human-robot collaboration.
Authors: Dominik Bernard Lau, Hubert Malinowski, Jerzy Szyjut, Adam Brzeski, Tomasz Dziubich, Rados{\l}aw Targo\'nski, Tomasz Figatowski, Natalia Zieli\'nska
Abstract: Accurate pixel-level classification of coronary angiograms is critical for cardiovascular disease assessment, yet the field lacks standardized evaluation protocols. In this work we demonstrate a new benchmark for the assessment of deep learning models which densely classify pixels of coronary angiograms to one of SYNTAX classes (or background). The evaluation covers 24 distinct architectures starting with classic convnets to recent state-space-based vision algorithms. We release CARDIAG - a multi-center, multi-label dataset which we carefully split to reliably compute metrics, accounting for diameter error, overlap, centerline quality and calibration. The data contains SYNTAX labels, binary, uncertainty and segmentation masks as well as intermediate frames together with the selected non-sensitive DICOM metadata. From the multitude of algorithms, we nominate ConvNeXt V2 encoder with DeepLab V3 Plus decoder as the best performing, achieving macro $F_1=0.456$, which we then ensemble with Mamba U-Net and Feature Pyramid Network, for an increased $F_1=0.479$. We demonstrate all the architectures to be well calibrated and determine the generalization of the top 5 methods, together with the data efficiency of these architectures. We highlight the importance of both high-resolution and low-resolution features in encoding. We also demonstrate the model correctness in the context of patient demographic, vessel sides and projection angle configurations. Overall the released benchmark allows for future studies to robustly and rigorously assess the proposals, not only for SYNTAX segmentation, but lesion detection and many more.
Authors: Deshui Li, Xiao-Ming Yuan, Zishun Wang
Abstract: Industrial health management increasingly relies on heterogeneous information sources, including condition monitoring systems, supervisory control and data acquisition systems, maintenance records, inspection results, and prognostic models. Although large language models provide new opportunities for cross-source reasoning, industrial data and analytical outputs differ substantially in structure, temporal resolution, physical meaning, and reliability. Directly integrating such heterogeneous information into a monolithic model may reduce interpretability, traceability, and adaptability to equipment and data changes. This paper introduces Industrial Tokenization, a conceptual interface for transforming source-specific analytical outputs into structured and machine-interpretable units of industrial evidence, termed Industrial Tokens. Unlike numerical tokens used to encode raw time-series data, Industrial Tokens represent domain-grounded evidence together with source, temporal scope, operating context, analytical meaning, quality or confidence information, and provenance. Based on this concept, a federated industrial architecture is proposed, where heterogeneous analytical subsystems retain autonomy while exposing standardized Industrial Tokens to a central reasoning layer. As an initial implementation, this study presents an end-to-end DiagnosisToken pathway based on vibration-diagnostic outputs, rule-based event aggregation, structured textual token generation, and LLM-based interpretation. Other Industrial Tokens, including SCADA-based condition-monitoring tokens, maintenance tokens, and prognostic tokens, are reserved as future extensions. The proposed framework positions Industrial Tokenization as a semantic interface between domain-specific industrial intelligence and LLM- or agent-based reasoning, rather than another method for encoding raw industrial data.
Authors: Junming Chen, Junyang Jiang, Xu Chen, Zibo Liang, Kai Zheng
Abstract: LLM-based database agents show promise, but differing task scopes, testbeds, and metrics hinder comparison. We identify four gaps between evaluation and production operations: live-environment fidelity (multi-turn read-write interaction with a running database); observation-space scale and complexity (causal diagnosis across thousands of time series, business logs, and concurrent activity); solution-space openness (multiple remediations with different operational trade-offs); and scenario complexity and coverage (faults cascading across internal mechanisms and operational domains). We present DBA-Bench, a benchmark addressing these gaps through production fidelity, outcome-first evaluation, and controlled scenario reproducibility. It uses instrumented PostgreSQL environments with active workloads, persistent state, and multi-source observations; defines success by measurable recovery or fault elimination under safety constraints; and restores snapshots with scenario-specific checks before each run. The benchmark contains 106 scenarios across seven task domains, with two public difficulty labels based on reference-path diagnostic depth and environmental complexity. We evaluate nine baseline groups, including six foundation-model systems, two GPT-5.5-backed database agents, and a Human DBA reference. Across 848 automated runs, Diagnosis, Outcome, and Safe Pass rates are 32.7%, 19.6%, and 12.4%; the best automated baseline reaches 17.9% Safe Pass versus 93.4% for the Human DBA reference. Automated Safe Pass falls from 19.6% on Easy scenarios to 7.6% on Hard scenarios, underscoring the difficulty of safe end-to-end remediation.
Authors: Moritz Vandenhirtz, Andrea Agostini, Dana Belde, M\'elanie Roschewitz, Ismaiel Chikh Bakri, Tilo Niemann, Andr\'e Euler, Julia E Vogt
Abstract: Bowel obstruction is a common and potentially life-threatening gastrointestinal condition. In the face of rising diagnostic workloads, the automated diagnosis of bowel obstruction on CT scans supports radiologists by accelerating detection and improving patient outcomes. In this work, we propose a deep learning framework with a multi-task objective that jointly detects bowel obstruction and localizes its transition zone. Additionally, we extend the method with an inherently interpretable classification method that locates the suspected transition point within a slice. It does so by learning a probabilistic selection mask that faithfully bases the classifier's prediction solely on a small image region. The proposed method is evaluated on an internal dataset comprising 1,427 abdominal CTs. Here, the model achieves an obstruction detection test accuracy of 93% and a Hit@10 transition zone localization of 95%. As the first method to reliably localize the transition zone, this marks a significant step towards the automated identification of this critical clinical landmark.
Authors: Mintae Kim, Koushil Sreenath
Abstract: We introduce trajectory-regularized stochastic optimal control (TRSOC), which augments standard stochastic optimal control (SOC) with a Kullback--Leibler (KL) divergence between controlled and reference trajectory distributions. Using Girsanov's theorem, the trajectory KL reduces to a quadratic drift mismatch penalty, yielding a modified running cost that preserves the dynamic programming (DP) structure. We derive the corresponding Hamilton--Jacobi--Bellman (HJB) equation and characterize the optimal policy. In the linear-quadratic (LQ) setting, the formulation admits a closed-form solution with an augmented control cost. Experiments show that the regularization parameter induces a trade-off between performance-driven and reference-preserving behavior, including cases with reference dynamics learned from offline data.
Authors: Alireza Dastmalchi Saei, Shervin Rahimzadeh Arashloo
Abstract: Visual anomaly detection requires adaptive representations and reliable decision boundaries, particularly when anomalous training samples are scarce and class distributions are highly imbalanced. Classical kernel-based methods yield principled geometric decision regions but typically operate on fixed features, while deep detectors learn task-specific representations but often fail to provide an explicit margin-aware kernel boundary. In this study, we propose DLM-SVDD, a deep large-margin novelty-detection framework that jointly learns convolutional features and an explicit kernel-based decision boundary. By drawing on the large-margin $\ell_p$-Support Vector Data Description ($\ell_p$-SVDD) approach, the proposed method performs explicit margin maximization and nonlinear slack penalization while adapting the representation to the target task. To train the proposed model, we present an optimization scheme that alternates between a Frank--Wolfe--based update of the convex dual boundary and a CNN update step operating on a smooth margin-violation loss induced by the recovered boundary. To improve scalability, we analyze the efficiency--accuracy trade-offs for different kernel approximation strategies, deriving practical propositions for large-scale anomaly detection. Extensive experiments on multiple standard benchmarks show consistent performance improvements over the baseline and strong overall performance compared with state-of-the-art methods while illustrating that the proposed joint representation--boundary learning scheme remains effective under severe imbalanced class distributions.
Authors: Ruijian Han, Ding Lu, Yiming Xu
Abstract: Zermelo's algorithm is a classical method for computing the maximum likelihood estimator in the Bradley--Terry (BT) model, but its convergence can be slow in practice. To accelerate computation, Newman introduced a family of Zermelo-type fixed-point iterations parameterized by $\alpha$, with Zermelo's algorithm recovered at $\alpha=1$. Empirical evidence suggests that the choice $\alpha=0$ often converges substantially faster, making it a promising alternative, yet the mechanism underlying this acceleration remains elusive. This paper provides theoretical insight into this phenomenon through a systematic local convergence analysis. We derive closed-form expressions for local convergence factors under synchronous and asynchronous updates and analyze their dependence on $\alpha$ via spectral analysis of the associated Jacobian matrices. For synchronous updates, we show that the algorithm may fail to converge when $\alpha<1$, and its local convergence factor is quasi-convex in $\alpha$ under the population BT model. In contrast, asynchronous updates are always locally convergent, and their local convergence factor is provably monotonically increasing in $\alpha$ under the population BT model of consistently ordered bipartite comparison graphs, establishing the optimality of $\alpha=0$ in this setting. We further establish asymptotic approximation results for the population convergence factors under the BT model, justifying their practical relevance. Numerical experiments on synthetic and real-world datasets confirm the theory. Our analysis complements existing convergence results and shows that the acceleration of $\alpha=0$ arises not only from the parameter choice but, more importantly, from the use of asynchronous updates.
Authors: Laura M. Montaldo, Ricardo A. Borsoi, Sebastian Miron, Tulay Adali
Abstract: Modeling shared and subject-specific structure in multisubject spatiotemporal data remains challenging, particularly in neuroimaging, where both spatial and temporal patterns exhibit rich variability across subjects. Existing matrix and tensor decompositions provide interpretable factorizations, but rely on fixed multilinear structures or coupling schemes that may limit their flexibility in capturing complex variability. In this work, we introduce a spatiotemporal variational tensor decomposition (ST-VTD) framework that combines a tensor factorization generative model with structured priors to jointly represent spatial maps and temporal dynamics. Spatial factors are regularized to promote a low-rank structure inspired by the LL1 decomposition, while temporal factors are modeled using a learned Long short-term memory (LSTM)-based prior, enabling flexible and adaptive dynamics. Posterior inference is performed using an amortized variational formulation by unrolling iterations of an optimization algorithm, leading to an interpretable and parameter-efficient architecture. The proposed inference framework employs a warm-start strategy based on group independent component analysis, which we found to improve optimization performance. Experiments on a realistic synthetic functional MRI (fMRI) dataset demonstrate that the proposed approach significantly improves latent factor recovery compared with representative classical and probabilistic decomposition benchmarks.
Authors: Akira Kitaoka
Abstract: A data-driven inverse optimization problem (DDIOP) is the problem of estimating the objective-function parameters (weights) that explain observed optimal-solution data, and it arises in many applications, including integer linear programming (ILP). It is known that, by applying gradient-based optimization methods to the suboptimality loss, the inverse optimization of ILPs can be solved exactly within finitely many oracle iterations, and that the required number of iterations is bounded as $T=O(1/\gamma(\ell_{\mathrm{sub}})^2)$ in terms of a problem-dependent geometric constant $\gamma(\ell_{\mathrm{sub}})$. However, no means of bounding $\gamma(\ell_{\mathrm{sub}})$ from below as a function of the problem size has been available, and hence the number of iterations could not be given as an explicit function of the problem size. We therefore give, when the forward problem is an integer linear program (ILP), the number of iterations sufficient for projected subgradient descent applied to the suboptimality loss to achieve exact consistency with the observed data, as a fully explicit function of the number of samples, the dimension of the features, the ranges of the features, and the structure of the constraint coefficient matrix, up to polynomial factors in the basic constants (the diameter of the weight set, the step-size parameter, and the Lipschitz constant of the suboptimality loss).
Authors: Hao Yan, Ali Sarabi, Qing Zou, Boyang Xu
Abstract: Remaining useful life (RUL) prediction and failure-mode classification are central tasks in predictive maintenance. Many data-driven pipelines use fixed-window supervised learning with complete terminal labels; such routes do not naturally encode the temporal recursion linking successive degradation-state predictions when observations are partial or unit identities are unavailable. We formulate prognostics as vector General Value Function (GVF) prediction on an absorbing degradation process, treating RUL and failure-mode probabilities as temporally consistent targets rather than independent window-level labels, and estimate them with a multi-step temporal-difference estimator, TD($n,\lambda$). Supporting theory identifies the Bellman fixed point of the vector GVFs, characterizes the linear projected-TD limit and its relation to complete-return Monte Carlo regression under realizability, and explains when bootstrapped TD targets are less variable than Monte Carlo returns. On an event-triggered multimode simulation and NASA C-MAPSS label-scarce stitch data, TD improves RUL and failure-mode prediction relative to a supervised same-backbone Monte Carlo control, especially under scarce complete labels. Practically, fragmented, identity-free degradation records can contribute local Bellman transitions instead of being discarded until complete run-to-failure labels are available.
Authors: Wan Zhang, Qinjie Lin, Chan Lee, Weijian Li, Han Liu, Kai Zhang
Abstract: Forecasting multiple time-series with high-dimensional covariates presents a core challenge: unifying common temporal patterns while retaining meaningful series-specific information. We introduce Hopformer (Homogeneity-Pursuit Transformer), a two-stage framework that addresses this challenge. In the first stage, we perform a Sparsity Pattern Aggregation (SPA) scheme extracting a common low-variance trend that incorporates the covariates. This acts as a homogenization layer. In the second stage, a LoRA-fine-tuned Transformer models the remaining complex dependencies in the residual. Our method is theoretically grounded. We prove that SPA achieves a near-optimal bias-variance trade-off via an oracle inequality. We also provide generalization bounds for the second stage under dependent time series data. Hopformer sets a new state of the art, improving MASE by an average of 6.56% across synthetic and real-world forecasting benchmarks.
Authors: Masahiro Tanaka
Abstract: Estimating contemporaneous bidirectional interactions from observational data is difficult because each outcome is endogenous to the other, while flexible regressions may capture only reduced-form dependence. This paper proposes SEM-DNN, a heteroscedastic neural simultaneous-equation estimator that learns reciprocal structural interactions without external instruments. Identification exploits conditional covariance diagonalization: when structural shocks have zero conditional means, are conditionally uncorrelated given predetermined covariates, and exhibit nonproportional conditional variances, only the true interaction coefficients diagonalize the conditional residual covariance across the feature space. The method jointly approximates nonlinear structural mean functions and feature-dependent variances using a diagonal Gaussian quasi-likelihood that incorporates the simultaneous-system Jacobian. We establish unique identification and positive-definite local curvature of the profiled population criterion and show that, under neural-profile compatibility conditions, the implemented neural criterion inherits this curvature despite nonunique network parameterizations. The coefficients admit a causal interpretation when the structural equations represent autonomous mechanisms that remain invariant under the relevant interventions. Monte Carlo experiments with nonlinear, high-dimensional nuisance functions and non-Gaussian shocks show that SEM-DNN recovers structural effects more reliably than parametric, kernel-based, and separate-equation neural alternatives as information increases, although at greater computational cost. An application to ready-to-eat cereal scanner data illustrates how the method can study contemporaneous price-sales feedback and assess identification strength, residual diagonalization, variance calibration, and optimization sensitivity.
Authors: Amaury Wei, Olga Fink
Abstract: Diagnosing the root cause of anomalies is essential for safe industrial operation. Despite extensive sensor instrumentation, formulating hypotheses and gathering evidence remains a manual process, creating a major operational bottleneck. While existing data-driven approaches aim to automate this, two critical limitations restrict their deployment: their operate as black boxes unable to justify their diagnosis, and they require scarce labeled examples of faulty operation. To address this gap, we introduce AgentRCA, a zero-shot agentic framework for evidence-grounded root cause analysis. Rather than learning fault-specific mappings, AgentRCA performs inference-time reasoning by combining a data-driven digital twin (modeling normal system dynamics) with a tool-augmented large language model. The agent iteratively gathers statistical evidence, evaluates competing hypotheses, and identifies the physical fault that best explains the observed behavior. Evaluated on a real-world multiphase-flow facility and a large-scale chemical plant, AgentRCA achieves diagnostic performance competitive with fully supervised baselines without relying on fault-specific training. Crucially, it produces transparent reasoning traces that explicitly link observed symptoms to their underlying physical causes. These results establish autonomous hypothesis-driven reasoning as a practical foundation for scalable industrial root cause analysis.
Authors: Chao Fang, Jun Yin, Man Shi, Marian Verhelst
Abstract: With the rapid adoption of long-context large language models (LLMs), the continuously growing KV cache during decoding has become the critical memory bottleneck. To tackle this challenge, we propose HiKV, a novel algorithm-hardware co-design that exploits KV cache redundancy through hierarchical importance awareness. Algorithmically, HiKV compresses the KV cache at two granularities: Stage I evicts unimportant tokens within a fixed budget, and Stage II further loads only the significant elements of each retained token, reaching compression ratios unattainable at a single granularity. Architecturally, we develop a dedicated accelerator centered on a reconfigurable importance sorter that switches between the distinct sorting datapaths each stage requires, unifying the two-stage acceleration in one circuit with minimal overhead. Evaluated on representative LLMs, HiKV achieves up to 7.95x speedup and 90% energy reduction in the attention computation over the vanilla KV cache baseline within negligible 1% accuracy loss. Under iso-accuracy constraints, HiKV outperforms state-of-the-art importance-based methods by achieving an additional 1.82~4.87x reduction in external memory accesses. These benefits are enabled by specialized hardware components that add only 8% to the system area.
Authors: Sergey Musienko
Abstract: Frozen EEG encoders proliferate; per-model fine-tune defaults do not scale. We present Nimbus Personalizer: one contract encode to Bayesian head to BrainState (optional affine mid-tier) that sits on heterogeneous frozen trunks without a new personalization stack per architecture. Thesis (systems): the contribution is the trunk-agnostic API - not LDA-on-embeddings as an ML novelty - so OEMs integrate once and swap trunks. Evidence: the same surface runs on five classical trunks EEGNet, Shallow, Deep, Conformer, ATCNet x four MI datasets (18 cells) and on a foundation encoder (REVE) under the same Personalizer. Where embedding capacity exists, the head is a cheap default mid-point versus warm-start fine-tune or PEFT, costing orders of magnitude less adaptation wall time while recovering much of the fine-tune accuracy gain; calibration-only-when-clean holds in 12/18 cells. Head gains are supporting evidence that the API is useful where capacity exists. Subject-level confidence intervals identify the clearest dataset and span zero elsewhere. All results are exploratory (subject-level bootstrap, no confirmatory tests); the decision logic for when to escalate adaptation is addressed in our companion work on the control layer.
Authors: Oleksii Kachaiev, Silvia Villa, Lorenzo Rosasco
Abstract: We consider the problem of learning from a single finite trajectory of an ergodic stochastic dynamical system. More precisely, we study discrete-time autonomous stochastic systems defining time-homogeneous Markov processes. We first focus on estimating the optimal one-step prediction function by nonlinear least squares, and derive high-probability guarantees measured with respect to the invariant measure of the process. These results make explicit how the non-independent and non-identically distributed nature of trajectory data modifies the classical statistical learning analysis. We then extend the framework to higher-order systems and finite-state spaces. Finally, we show that the same least squares and concentration arguments naturally extend to learning Koopman operators. Our approach combines tools from statistical learning theory and quantitative ergodic theory for Markov chains. It relies, in particular, on a concentration inequality for Hilbert-space-valued additive functionals of uniformly geometrically ergodic Markov chains.
Authors: Austin Rockman
Abstract: Sample retrieval tools can help composers find harmonically compatible material, but querying from a fixed reference sample becomes less informative as arrangements evolve and the harmonic context shifts with each musical decision. We present Reflector, an interactive audio workstation that tracks harmonic combinations as they accumulate on the composer's timeline and adapts retrieval as the arrangement develops. The system is organized around a fixed interval-class oracle: a hand-designed table of weights that scores how pitch-class content combines between sources. An encoder trained entirely on synthetic audio learns to approximate the oracle in a 128-dimensional embedding space, where dot products stand in for compatibility scores at interactive speed. As the composer arranges material on a multi-track timeline, a sweep-line analysis discovers co-sounding regions, computes oracle-weighted centroids, and retrieves against the composite harmonic identity of the session as it evolves. Session centroids projected into a navigable 3-D space reveal structural harmonic relations across the composer's body of work. This paper is a systems account: we give the design rationale for each architectural decision, characterize Reflector's behavior through intrinsic measurements on a working sample library, and describe the implementation. The characterization yields a central finding: the learned embedding preserves the kernel's pairwise judgments while covering the whole library, something the kernel cannot do when used directly as a retrieval rule, because the embedding's normalized geometry cannot express the degenerate solutions that direct scoring favors. The entire pipeline runs locally with no copyrighted training data. Reflector is free, and the training pipeline is open source.
Authors: Ahmed M. Abuzuraiq, Philippe Pasquier
Abstract: Explainable AI (XAI) in creative practice can be less about technocentric explanation and more about enabling artists to inspect modify and debug models as part of making Yet largescale texttoimage diffusion systems are typically presented as opaque endtoend tools limiting this kind of material engagement We argue that even large models can function as creative materials when their internal structure is made visible and manipulable To support this we propose a handson approach to explainability centred on experimentation and intervention We instantiate this approach with a model bending and an interactive (inspection) interface integrated into ComfyUIs nodebased workflow including interactive layer selection and intervention controls Through qualitative and quantitative analysis of bending interventions in Stable Diffusion 15 we show how manipulating specific components of a diffusion pipeline produces relatively consistent families of visual effects allowing artists to build practical layerlevel intuition about how different parts of the model shape generated images
Authors: Ali Fakhar (UGA), K{\'e}vin Polisano (UGA), Ir{\`e}ne Gannaz (G-SCOP\_GROG, G-SCOP, Grenoble INP, UGA), Sophie Achard (STATIFY, LJK, UGA)
Abstract: This work addresses the generation of theoretical correlation matrices with prescribed sparsity patterns associated to graph structures. We propose a novel convex optimization framework in which an initial matrix is projected onto an elliptope under a positive semidefiniteness constraint. Several numerical schemes are implemented and compared. The problem falls within the broader class of matrix completion, where off-diagonal entries corresponding to absent edges are fixed to zero and diagonal entries are fixed to one. Beyond this structural constraint, the approach offers greater flexibility than existing methods by allowing control over the mean of the off-diagonal entry distribution, enabling the generation of correlation matrices that better reflect realistic data. This procedure is not designed to yield a uniform distribution over the feasible set; rather, it provides a principled and tunable way to construct correlation matrices suitable for benchmarking statistical methods for graphical model inference. Theoretical guarantees on the existence of solutions are established, both in the general setting and under the additional mean constraint. Simulation studies illustrate the properties of the generated matrices with respect to graph structure. The methodology is applied to two real-world datasets from neuroscience and finance, and a comparison with GAN-based correlation matrix generation is provided.
Authors: Ritik Raj, Souvik Kundu, Sarbartha Banerjee, Dheemanth Joshi, Ishita Vohra, Tushar Krishna
Abstract: Routing to select large language models (LLMs) with different cost-quality trade-offs has become a fundamental deployment feature of enterprise AI. Existing routers, primarily make independent routing decisions for each LLM call. However, agentic applications execute as long-horizon workflows whose quality is determined only by a delayed, task-level outcome. This mismatch prevents per-call routers from correctly attributing feedback to individual routing decisions. Towards mitigating this, we present TRACE-Router, a task-level routing framework that aligns routing with the unit of supervision. TRACE-Router assigns each task to a model once at admission using a contextual bandit, pins all subsequent LLM calls to the selected backend, and updates its policy using the task's terminal reward, jointly accounting for accuracy and latency. By leveraging delayed task feedback, TRACE-Router learns routing policies that adapt to the workload while avoiding explicit task-complexity estimation. Across three agentic benchmarks, TRACE-Router consistently improves the accuracy-latency trade-off, achieving non-dominated Pareto frontier points. On tau2-Bench, it outperforms latency-matched interpolation between individual models by 7-8 accuracy points, while on Terminal-Bench it achieves 7.1 higher accuracy points than the strongest single model baseline with 36% lower latency.
Authors: Stephen Becker
Abstract: Singular value soft-thresholding can be computed via a reduction to the matrix polar decomposition, which allows one to exploit GPU-friendly algorithms for computing the polar decomposition. Empirically, there is a significant speed-up on GPUs compared to the standard approach using the SVD. We leave the investigation of robustness to future work, but note that due to the discontinuous nature of the sign function, the reduction to the polar decomposition is likely only suitable for low-accuracy applications.
Authors: Jiyuan Tan, Vasilis Syrgkanis
Abstract: Automating theoretical research is constrained not only by the generation of candidate results, but also by their reliable evaluation. A common approach is to close the research loop with a large language model (LLM) reviewer. However, such reviewers remain empirically unreliable: they may accept fabricated papers and detect them at rates close to chance (Bad Scientist, 2025). We present CausalForge, a framework for automated theoretical research in causal inference grounded in the Lean proof assistant. CausalForge combines Causalean, a foundational Lean library for causal inference containing 7,035 machine-checked declarations developed with language-model assistance under human design and review, with CausalSmith, a self-improving agentic pipeline that selects research topics, proposes results, formalizes statements, constructs proofs, and presents the resulting artifacts for human inspection. Because a machine-checked proof establishes only that a formal statement follows from its assumptions, not that the statement faithfully captures the intended scientific claim, the pipeline augments kernel verification with a statement audit that compares each formal theorem against the informal claim it is intended to express. We evaluate the system using artifacts produced by completed autonomous research runs. The source code, formal library, and run records are available at https://github.com/Jiyuan-Tan/CausalForge.
Authors: Peiyong Wang, Udaya Parampalli, Casey R. Myers
Abstract: A central design principle in modern machine learning and artificial intelligence is to align a model's inductive bias with the structure of its input data. For matrix-valued inputs, relevant matrix-level relationships can be characterised through spectral values and spectral subspaces; however, common coordinate-wise rotation-gate data-encoding unitaries used in most quantum machine learning models do not explicitly construct such a matrix-level representation. We introduce Quantum Spectral Models (QSMs), in which we construct the generator of the data-encoding unitary directly from each input matrix. We study three QSM variants based on symmetric, global block, and non-overlapping patch-local block Hamiltonians. Their outputs admit truncated Fourier representations in which input-dependent spectral gaps supply candidate phase carriers, while spectral subspaces help determine their coefficients. We evaluate the QSMs and comparison quantum models on two matrix representations of Pendigits and two controlled synthetic tasks defined by spectral statistics. At the largest evaluated circuit depth, QSM variants lead the tested quantum models in mean test accuracy across all four benchmarks. The patch-local QSM leads on Pendigits, whereas the global block-Hamiltonian QSM leads on the controlled spectral tasks. Ablations show a task-dependent reversal: subspace-preserving controls perform better on Pendigits, whereas spectral-value-only controls lead among the tested ablations on the synthetic tasks. Together, these results shed new light on quantum machine-learning model design by showing how input-conditioned spectral representations can provide an analysable inductive bias, while offering a broader perspective on structure-aware model design in machine learning and artificial intelligence.
Authors: Olafur Gudmundsson, Bo Zhao, Huayi Liao, Anna Kiyantseva, Sai Xiao, Heath Vinicombe, Mostafa Keikha, Luke DeLuccia, Zihao Chen, Junpeng Hou, Weijie Jiang, Bhawna Juneja, Andreanne Lemay, Wei-Ting Lin, Keyvan Moghadam, Jiaxing Qu, Zhiqing Rao, Zhihua Zhang
Abstract: In this paper, we propose a new solution for addressing the content cold-start problem in industry-scale search and recommender systems. Compared to prior approaches, we have made the following new contributions: 1) our solution spans the entire multi-stage funnel and generalizes well for both search and recommendation surfaces, 2) our solution reduces bias favoring existing content, allowing more accurate model prediction across content types and reducing short-term tradeoffs associated with high volumes of explicit content exploration, 3) our solution is evaluated with a scalable measurement framework that enables fast short-term experimentation while validating long-term impact. We have iteratively built and successfully deployed this new system at Pinterest in the past two years and observed significant improvements in fresh content exploration, overall user engagement, and content ecosystem health.
Authors: Seyeon Kim, Joonhun Lee, Namhoon Cho, Sungjun Han, Wooseop Hwang
Abstract: Conventional uncertainty-aware temporal difference (TD) learning often models TD errors as zero-mean Gaussian. This assumption can miss the heavy-tailed and heteroscedastic residuals induced by bootstrapping and exploration. We introduce a state-conditioned shape head based on the Generalized Gaussian Distribution (GGD) and use a numerically modified GGD loss as an online surrogate for nonstationary TD residuals. We distinguish two mathematical facts that are sometimes conflated: the exact GGD likelihood is normalized for every $\beta>0$, whereas its exponential density kernel is positive definite for $\beta\in(0,2]$. We use the learned shape to construct a simple monotone weighting heuristic and propose Batch Inverse Error Variance (BIEV) regularization from the variance and sample excess kurtosis of ensemble TD errors. Across continuous and discrete control benchmarks, the shape-aware variants improve over Gaussian-based variants in several settings, although the gains are task- and regime-dependent.
Authors: Jianyu Xu, Xuan Wang, Yu-Xiang Wang, Jiashuo Jiang
Abstract: We study online learning for a seller that jointly chooses per-period inventory positions and a uniform price, then fulfills realized demand through a downstream allocation. The main difficulty is not only demand learning: the price shifts demand and reshapes the transportation LP, making the population objective globally non-convex and non-smooth. To solve this problem, we propose OCSAA, an algorithm that exploits demand observations through counterfactual translation and proposes joint (price, inventory) decisions through lower-confidence optimism. OCSAA admits a polynomial-time additive-accuracy implementation for rational-polytope inventory sets. We prove a high-probability $\widetilde O(\sqrt T)$ regret guarantee and establish a matching-in-$T$ information-theoretic lower bound. Our results illustrate an effective integration of statistical learning methodologies with complex operations research problems.
Authors: Thanh Linh Nguyen, Dinh Thai Hoang, Diep N. Nguyen, Quoc-Viet Pham
Abstract: Critical learning periods (CLPs) in federated learning (FL) refer to early stages during which low-quality contributions (e.g., sparse training data availability) can permanently impair the performance of the global model. However, existing incentive mechanisms typically assume temporal homogeneity, treating all training rounds as equally important, thereby failing to prioritize and attract high-quality contributions during CLPs. This inefficiency is compounded by information asymmetry due to privacy regulations, where the cloud lacks knowledge of client training capabilities, leading to adverse selection and moral hazard. Thus, in this article, we propose a time-aware contract-theoretic incentive framework, named Right Reward Right Time (R3T), to encourage client involvement, especially during CLPs, to maximize the utility of the cloud. We formulate a cloud utility function that captures the trade-off between the achieved model performance and rewards allocated for clients' contributions, explicitly accounting for client heterogeneity in system capabilities, effort, and joining time. Then, we devise a CLP-aware incentive mechanism deriving an optimal contract design that satisfies individual rationality, incentive compatibility, and budget feasibility constraints, motivating rational clients to participate early and contribute efforts. By providing the right reward at the right time, our approach can attract the highest-quality contributions during CLPs. Simulation studies show that R3T mitigates information asymmetry, increases cloud utility, and yields superior economic efficiency compared to conventional incentive mechanisms. Our proof-of-concept yields a 2-3x training speedup, reduces the required client pool by 5.2-47.6% to reach target performance, and improves final accuracy by up to 9%. The source code can be found at https://github.com/linhnt31/R3T.
Authors: Shuwen Sun, Lihong Feng, Peter Benner
Abstract: We explore the promising performance of a transformer model in predicting outputs of parametric dynamical systems with external time-varying input signals. The outputs of such systems vary not only with physical parameters but also with external time-varying input signals. Accurately catching the dynamics of such systems is challenging. We have adapted and extended an existing transformer model, called temporal fusion transformer (TFT), for single-output prediction to a multiple-output transformer, named as Spatially-Enhanced Temporal Fusion Transformer (SE-TFT), which is able to predict multiple output responses of these systems. The SE-TFT generalizes the interpretability of the original TFT model. The generalized interpretable attention weight matrix explores not only the temporal correlations in the sequence, but also the interactions between the multiple outputs, providing explanation for the spatial correlation in the output domain. This proposed SE-TFT accurately predicts the sequence of multiple outputs, regardless of the nonlinearity of the system and the dimensionality of the parameter space.
Authors: Roseline Polle, Agnes Norbury, Alexandra Livia Georgescu, Nicholas Cummins, Stefano Goria
Abstract: Speaker-dependent modelling can substantially improve performance in speech-based health monitoring applications. While mixed-effect models are commonly used for such speaker adaptation, they require computationally expensive retraining for each new observation, making them impractical in a production environment. We reformulate this task as a meta-learning problem and explore three approaches of increasing complexity: ensemble-based distance models, prototypical networks, and transformer-based sequence models. Using pre-trained speech embeddings, we evaluate these methods on a large longitudinal dataset of shift workers (N=1,185, 10,286 recordings), predicting time since sleep from speech as a function of fatigue, a symptom commonly associated with ill-health. Our results demonstrate that all meta-learning approaches tested outperformed both cross-sectional and conventional mixed-effects models, with a transformer-based method achieving the strongest performance.
Authors: Wu Fei, Shuxian Liang, Yibo Yang, Yang Lin, Jing Tang, Lei Chen, Xiansheng Hua, Hao Kong
Abstract: Process Reinforcement Learning~(PRL) has demonstrated considerable potential in enhancing the reasoning capabilities of Large Language Models~(LLMs). However, introducing additional process reward models incurs substantial computational overhead, and there is no unified theoretical framework for process-level advantage estimation. To bridge this gap, we propose \textbf{S}elf-Guided \textbf{P}rocess \textbf{R}eward \textbf{O}ptimization~(\textbf{SPRO}), a novel framework that enables process-aware RL through two key innovations: (1) we show that process rewards can be derived intrinsically from the policy model itself, and (2) we redefine step-wise advantage by introducing well-defined Cumulative Process Rewards~(\textbf{CPR}) and \textbf{M}asked \textbf{S}tep \textbf{A}dvantage~(\textbf{MSA}), which facilitates rigorous step-wise action advantage estimation within shared-prompt sampling groups. Our experimental results show that SPRO outperforms vanilla GRPO with 3.4x higher training efficiency and a 12.9\% test accuracy improvement. Furthermore, SPRO maintains a stable and elevated policy entropy throughout training while achieving a considerable reduction in response length, evidencing sufficient exploration and prevention of reward hacking. Notably, SPRO incurs no additional computational overhead compared to outcome-supervised RL methods such as GRPO, which benefit industrial implementation.
Authors: Rodrigo Tertulino
Abstract: Machine learning can predict in-hospital mortality, but data privacy and the statistical heterogeneity of clinical data hamper its use. Federated Learning (FL) is privacy-preserving, yet its behavior under non-IID and imbalanced conditions needs scrutiny. We benchmark five FL strategies - FedAvg, FedProx, FedAdagrad, FedAdam, and FedCluster - for mortality prediction on the MIMIC-IV dataset, partitioning 466,351 admissions across five care units to induce a realistic non-IID setting and enriching the features with an 11-item first-24-hour laboratory panel. At a prevalence of 1.98%, we adopt AUC-ROC and AUC-PR as primary, threshold-independent metrics rather than F1. Over 50 rounds and five random seeds, FedProx attains the best AUC-ROC (0.897) and mean AUC-PR (0.230), with paired t-tests confirming its AUC-ROC lead is significant against every other strategy; on F1, however, FedCluster (0.280) narrowly surpasses FedProx (0.273), so no single strategy dominates every metric. The best centralized baseline achieves AUC-ROC and AUC-PR of 0.929 and 0.312, respectively, significantly outperforming FedProx on both. A per-client breakdown shows the global model does not serve all care units equally (AUC-ROC 0.809-0.902), with the smallest, most clinically distinct clients faring worst. We conclude that regularization-based methods such as FedProx are the more robust federated choice, while centralization retains a slight predictive edge, and that per-client heterogeneity and evaluation-set construction deserve attention independent of aggregate numbers.
Authors: Feihu Huang, Yuning Luo, Songcan Chen
Abstract: Large models recently are widely applied in machine learning, so efficient training of large models has received widespread attention. More recently, the useful Muon optimizer is specifically designed for matrix-structured parameters of large models. Although some works have begun to study the Muon optimizer, the existing Muon and its variants still suffer from high sample complexity or high memory for large models. To fill this gap, we propose a light and fast Muon (LiMuon) optimizer for training large models, which builds on the momentum-based variance reduced technique and randomized Singular Value Decomposition (SVD). In particular, our LiMuon simultaneously has a lower memory and lower sample complexity than the Muon and its variants. Moreover, we prove that our LiMuon with lower memory has a lower sample complexity of $O(\epsilon^{-3})$ for finding an $\epsilon$-stationary solution of non-convex stochastic optimization under the generalized smoothness condition. To further narrow practice and theory gap, we also prove that our LiMuon with Newton-Schulz steps has a lower sample complexity than the Muon with Newton-Schulz steps. Numerical experimental results on pre-training Mamba-130M, Qwen2.5-0.5B and ViT models demonstrate effectiveness of our LiMuon.
Authors: Jianglan Wei, Zhenyu Zhang, Pengcheng Wang, Mingjie Zeng, Zhigang Zeng
Abstract: Efficient medical data classification is essential for modern disease screening, particularly in resource-constrained environments where power budgets and computing capabilities are limited. We present HD3C, a lightweight classification framework designed for low-power edge devices. HD3C encodes data into high-dimensional hypervectors, aggregates them into multiple cluster prototypes, and performs classification through similarity search in hyperspace. We evaluate HD3C across three medical classification tasks; on heart sound classification, HD3C is 350x more energy-efficient than Bayesian ResNet with less than 1% difference in accuracy. Moreover, HD3C 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.
Authors: Marie Brockschmidt, Maresa Schr\"oder, Stefan Feuerriegel
Abstract: Survival analysis is a cornerstone of clinical research by modeling time-to-event outcomes such as metastasis, disease relapse, or patient death. Unlike standard tabular data, survival data often come with incomplete event information due to dropout, or loss to follow-up. This poses unique challenges for synthetic data generation, where it is crucial for clinical research to faithfully reproduce both the event-time distribution and the censoring mechanism. In this paper, we propose SurvDiff an end-to-end diffusion model specifically designed for generating synthetic data in survival analysis. SurvDiff is tailored to capture the data-generating mechanism by jointly generating mixed-type covariates, event times, and right-censoring, guided by a survival-tailored loss function. The loss encodes the time-to-event structure and directly optimizes for downstream survival tasks, which ensures that SurvDiff (i) reproduces realistic event-time distributions and (ii) preserves the censoring mechanism. Across multiple datasets, we show that SurvDiff consistently outperforms state-of-the-art generative baselines in both distributional fidelity and survival model evaluation metrics across multiple medical datasets. To the best of our knowledge, SurvDiff is the first end-to-end diffusion model explicitly designed for generating synthetic survival data.
Authors: Amir Moeini, Minjae Kwon, Alper Kamil Bozkurt, Yuichi Motai, Rohan Chandra, Lu Feng, Shangtong Zhang
Abstract: In-context reinforcement learning (ICRL) is an emerging RL paradigm where an agent, after pretraining, can adapt to out-of-distribution test tasks without any parameter updates, instead relying on an expanding context of interaction history. While ICRL has shown impressive generalization, safety during this adaptation process remains unexplored, limiting its applicability in real-world deployments where test-time behavior is expected to be safe. In this work, we propose SCARED: Safe Contextual Adaptive Reinforcement via Exact-penalty Dual, the first method that promotes safe adaptation of ICRL under the constrained Markov decision process framework. During the parameter-update-free adaptation process, our agent not only maximizes the reward but also keeps the accumulated cost within a user-specified safety budget. We also demonstrate that the agent actively reacts to the safety budget; with a higher safety budget, the agent behaves more aggressively, and with a lower safety budget the agent behaves more conservatively. Across challenging benchmarks, SCARED consistently enables safe and robust in-context adaptation, outperforming existing ICRL and safe meta-RL baselines.
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: Jinwoo Baek
Abstract: Low-precision execution can induce substantial forward discrepancies in Transformers even for fixed weights and input, yet these discrepancies are usually monitored only at the output and lack a layer-wise theoretical account. We develop a first-order decomposition of output mismatch into layer-local attention, LayerNorm, and residual-transport terms, and derive from it a practical causal risk estimator and a budgeted controller, Bound-Guided Selective Stabilization (BGSS). Controlled sweeps verify the predicted local sign, monotonicity, and transport structure. On GPT-2, the transport-aware combined predictor is positively correlated with FP32-reference mismatch in all $18$ runs and improves over a no-transport ablation in $17/18$ runs. Reference-patch attribution shows that the same score preserves useful layer ordering information (mean Spearman $0.362$). In budget-matched mitigation, BGSS outperforms random same-budget control in onset events ($10.67$ vs. $11.67$), final mismatch ($1.243\times 10^{-3}$ vs. $1.284\times 10^{-3}$), and worst-case mismatch ($3.14\times 10^{-3}$ vs. $8.49\times 10^{-3}$), while matching a risk-only same-budget controller on onset suppression and sharply reducing worst-case mismatch ($3.14\times 10^{-3}$ vs. $5.71\times 10^{-3}$). These results support a theory-to-algorithm account of Transformer numerical fragility in which finite-precision risk can be analyzed, estimated, localized, and selectively stabilized.
Authors: Kazuma Kano, Yuki Mori, Shin Katayama, Kenta Urano, Takuro Yonezawa, Nobuo Kawaguchi
Abstract: Logistics warehouses have struggled with labor shortages, but the inbound processes remain particularly human-powered. Worker location data is a key to higher productivity in such cases. Fixed cameras are a promising tool for localization, as they also offer valuable environmental information such as package status. However, identifying individuals from visual data alone is often impractical. To enable identity-aware localization, prior studies have attempted to identify people in videos by associating their trajectories with wearable sensor measurements. Although this appearance-independent approach has several advantages, existing methods may fail under real-world conditions. Therefore, we propose CorVS+, a novel data-driven person identification framework based on the correspondence between visual tracking trajectories and sensor measurements. Firstly, our deep learning model predicts the correspondence probabilities and reliabilities for every pair of a trajectory and sensor measurements. Secondly, our algorithm matches the pairs over time based on the model predictions. We developed a dataset comprising 27 hours of sensor measurements and 38 km of trajectories in a warehouse. This dataset covers actual activities and challenging situations, such as multiple stationary workers inspecting items. The evaluation indicated the superiority of CorVS+ over existing methods and the effectiveness of its unique designs for industrial-scale settings. The model and dataset will be available at https://doi.org/10.5281/zenodo.17745683.
Authors: Meng Zhu, Quan Xiao, Weidong Min
Abstract: This paper studies the exponential decay mechanism of the second-moment estimate in Adam. We propose AdamNX and a time-varying second-moment decay rate that gradually weakens the correction applied to the update scale. Under the assumptions used in our analysis, this mechanism makes the updates approach momentum-SGD-like behavior during the training plateau phase. We report results on the image-classification, object-detection, and semantic-segmentation tasks, configurations, and comparators included in this paper. These results do not establish multi-seed statistical effects, flatness, or generalization beyond the reported tasks. Our code is open-sourced at https://github.com/mengzhu0308/AdamNX.
Authors: Marcus M. Noack, Mark D. Risser, Hengrui Luo, Vardaan Tekriwal, Ronald J. Pandolfi
Abstract: Despite a large corpus of recent work on scaling up Gaussian processes, a stubborn trade-off between computational speed, prediction and uncertainty quantification accuracy, and customizability persists. This is because the vast majority of existing methodologies exploit various levels of approximations that lower accuracy and limit the flexibility of kernel and noise-model designs -- an unacceptable drawback at a time when expressive non-stationary kernels are on the rise in many fields. Here, we propose a methodology we term \emph{gp2Scale} that scales exact Gaussian processes to more than 10 million data points without relying on inducing points, kernel interpolation, or neighborhood-based approximations, and instead leveraging the existing capabilities of a GP: its kernel design. Highly flexible, compactly supported, and non-stationary kernels lead to the identification of naturally occurring sparse structure in the covariance matrix, which is then exploited for the calculations of the linear system solution and the log-determinant for training. We demonstrate our method's functionality on several real-world datasets and compare it with state-of-the-art approximation algorithms. Although we show superior approximation performance in many cases, the method's real power lies in its agnosticism toward arbitrary GP customizations -- core kernel design, noise, and mean functions -- and the type of input space, making it optimally suited for modern Gaussian process applications.
Authors: Pritthijit Nath, Sebastian Schemm, Henry Moss, Peter Haynes, Emily Shuckburgh, Mark J. Webb
Abstract: Weather and climate models rely on parametrisations to represent unresolved sub-grid processes. Traditional schemes rely on fixed coefficients that are weakly constrained and tuned offline, contributing to persistent biases that limit their ability to adapt to underlying physics. This study presents a framework that learns components of parametrisation schemes online as a function of the evolving model state using reinforcement learning (RL) and evaluates policy-driven parameter updates across idealised testbeds spanning a simple climate bias correction (SCBC), a radiative-convective equilibrium (RCE), and a zonal mean energy balance model (EBM) with single-agent and federated multi-agent settings. Across nine RL algorithms, Truncated Quantile Critics (TQC), Deep Deterministic Policy Gradient (DDPG), and Twin Delayed DDPG (TD3) achieved the highest skill and stable convergence, with performance assessed against a static baseline using area-weighted RMSE, temperature and pressure-level diagnostics. For the EBM, single-agent RL outperformed static parameter tuning with the strongest gains in tropical and mid-latitude bands, while federated RL on multi-agent setups enabled specialised control and faster convergence, with a six-agent DDPG configuration using frequent aggregation yielding the lowest area-weighted RMSE across the tropics and mid-latitudes. The learnt corrections were also physically meaningful as agents modulated EBM radiative parameters to reduce meridional biases, adjusted RCE lapse rates to match vertical temperature errors, and stabilised heating increments to limit drift. Overall, results show that RL can learn skilful state-dependent parametrisation components in idealised settings, offering a scalable pathway for online learning within numerical models and a starting point for evaluation in weather and climate models.
Authors: Alireza Bakhtiari, Alex Ayoub, Samuel Robertson, David Janz, Csaba Szepesv\'ari
Abstract: We establish a lower bound on the eluder dimension of generalised linear model classes, showing that standard eluder dimension-based analysis cannot lead to first-order regret bounds. To address this, we introduce a localisation method for the eluder dimension; our analysis immediately recovers and improves on classic results for Bernoulli bandits, and allows for the first genuine first-order bounds for finite-horizon reinforcement learning tasks with bounded cumulative returns.
Authors: Samaresh Kumar Singh, Joyjit Roy, Chirag Agrawal
Abstract: As Industrial Internet of Things (IIoT) environments scale to tens of thousands of connected devices, centralized security architectures introduce latency bottlenecks that sophisticated attackers can exploit to compromise an entire manufacturing ecosystem. We present a Decentralized Multi-Agent Swarm (DMAS) architecture that deploys autonomous agents at each edge gateway, forming a distributed defense layer for IIoT networks. Rather than relying on static firewalls or cloud-forwarded telemetry, DMAS agents coordinate through a lightweight peer-to-peer protocol, detecting threats locally without cloud dependency. We describe a Consensus-based Threat Validation (CVT) protocol in which agents collectively vote on detected threats, enabling near-instant quarantine of compromised nodes. Experiments on a 2000-device hardware testbed show that DMAS achieves sub-millisecond response times (0.85 ms average), 97.3% detection accuracy under high load, and 87% accuracy on zeroday attacks, each exceeding both centralized and edge-computing baselines. Bandwidth consumption drops by 89% relative to cloud-based solutions.
Authors: Barak Or
Abstract: Training modern neural networks is increasingly fragile, with rare but severe destabilizing updates often causing irreversible divergence or silent performance degradation. Existing optimization methods primarily rely on preventive mechanisms embedded within the optimizer, offering limited ability to detect and recover from instability once it occurs. We introduce a supervisory runtime stability framework that treats optimization as a controlled stochastic process. By isolating an innovation signal derived from secondary measurements, such as validation probes, the framework enables automatic detection and recovery from destabilizing updates without modifying the underlying optimizer. We provide theoretical runtime safety guarantees that formalize bounded degradation and recovery. Our implementation incurs minimal overhead and is compatible with memory-constrained training settings.
Authors: Samaresh Kumar Singh, Joyjit Roy
Abstract: Though Explainable AI (XAI) has made significant advancements, its inclusion in edge and IoT systems is typically ad-hoc and inefficient. Most current methods are "coupled" in such a way that they generate explanations simultaneously with model inferences. As a result, these approaches incur redundant computation, high latency and poor scalability when deployed across heterogeneous sets of edge devices. In this work we propose Explainability-as-a-Service (XaaS), a distributed architecture for treating explainability as a first-class system service (as opposed to a model-specific feature). The key innovation in our proposed XaaS architecture is that it decouples inference from explanation generation allowing edge devices to request, cache and verify explanations subject to resource and latency constraints. To achieve this, we introduce three main innovations: (1) A distributed explanation cache with a semantic similarity based explanation retrieval method which significantly reduces redundant computation; (2) A lightweight verification protocol that ensures the fidelity of both cached and newly generated explanations; and (3) An adaptive explanation engine that chooses explanation methods based upon device capability and user requirement. We evaluated the performance of XaaS on three real-world edgeAI use cases: (i) manufacturing quality control; (ii) autonomous vehicle perception; and (iii) healthcare diagnostics. Experimental results show that XaaS reduces latency by 38% while maintaining high explanation quality across three real-world deployments. Overall, this work enables the deployment of transparent and accountable AI across large scale, heterogeneous IoT systems, and bridges the gap between XAI research and edge-practicality.
Authors: Keith Ando Ogawa, Bruno Lopes Yamamoto, Lucas Lauton de Alcantara, Lucas Pellicer, Rosimeire Pereira Costa, Edson Bollis, Anna Helena Reali Costa, Artur Jordao
Abstract: Pre-training Large Language Models (LLMs) on web-scale datasets becomes fundamental for advancing general-purpose AI. In contrast, enhancing their predictive performance on downstream tasks typically involves adapting their knowledge through fine-tuning. Parameter-efficient fine-tuning techniques, such as Low-Rank Adaptation (LoRA), aim to reduce the computational cost of this process by freezing the pre-trained model and updating a smaller number of parameters. In comparison to full fine-tuning, these methods achieve over 99\% reduction in trainable parameter count, depending on the configuration. Unfortunately, such a reduction may prove insufficient as LLMs continue to grow in scale. In this work, we address the previous problem by systematically selecting only a few layers to fine-tune using LoRA or its variants. We argue that not all layers contribute equally to the model adaptation. Leveraging this, we identify the most relevant layers to fine-tune by measuring their contribution to changes in internal representations. Our method is orthogonal to and readily compatible with existing low-rank adaptation techniques. We reduce the trainable parameters in LoRA-based techniques by up to 50\%, while maintaining the predictive performance across different models and tasks. Specifically, on encoder-only architectures, this reduction in trainable parameters leads to a negligible predictive performance drop on the GLUE benchmark. On decoder-only architectures, we achieve a small drop or even improvements in the predictive performance on mathematical problem-solving capabilities and coding tasks. Finally, this effectiveness extends to multimodal models, for which we also observe competitive results relative to fine-tuning with LoRA modules in all layers. Code is available at: https://github.com/c2d-usp/Layer-wise-LoRA-with-CKA
Authors: Mario Sayde, Christopher Khater, Jihad Fahs, Ibrahim Abou-Faycal
Abstract: Principal Component Analysis (PCA) is a cornerstone of dimensionality reduction, yet its classical formulation relies critically on second-order moments and is therefore fragile in the presence of heavy-tailed data and impulsive noise. While numerous robust PCA variants have been proposed, most either assume finite variance, rely on sparsity-driven decompositions, or address robustness through surrogate loss functions without a unified treatment of infinite-variance models. In this paper, we study PCA for high-dimensional data generated according to a superstatistical dependent model of the form $\mathbf{X} = A^{1/2}\mathbf{G}$, where $A$ is a positive random scalar and $\mathbf{G}$ is a Gaussian vector. This framework captures a wide class of heavy-tailed distributions, including multivariate $t$ and sub-Gaussian $\alpha$-stable laws. We formulate PCA under a logarithmic loss, which remains well defined even when moments do not exist. Our main theoretical result shows that, under this loss, the principal components of the heavy-tailed observations coincide with those obtained by applying standard PCA to the covariance matrix of the underlying Gaussian generator. Building on this insight, we propose robust estimators for this covariance matrix directly from heavy-tailed data and compare them with the empirical covariance and Tyler's scatter estimator. Extensive experiments, including background denoising tasks, demonstrate that the proposed approach reliably recovers principal directions and significantly outperforms classical PCA in the presence of heavy-tailed and impulsive noise, while remaining competitive under Gaussian noise.
Authors: Ines Aitsahalia, Kiyohito Iigaya
Abstract: Learning systems must balance generalization across experiences with discrimination of task-relevant details. Effective learning therefore requires representations that support both. Online latent-cause models support incremental inference but assume flat partitions, whereas hierarchical Bayesian models capture multilevel structure but typically require offline inference. We introduce the \textbf{Hierarchical Online Learning of Multiscale Experience Structure (HOLMES) model}, a computational framework for hierarchical latent structure learning through online inference. HOLMES combines a variation on the nested Chinese Restaurant Process prior with sequential Monte Carlo inference to perform tractable trial-by-trial inference over hierarchical latent representations without explicit supervision over the latent structure. In simulations, HOLMES matched the predictive performance of flat models while learning more compact representations that supported one-shot backward transfer to higher-level latent categories. In a forward transfer task, HOLMES additionally achieved above-chance outcome prediction for stimuli with never-before-seen feature combinations, by exploiting abstract shape-level representations learned across diverse training instances. These results provide a tractable computational framework for discovering hierarchical structure in sequential data.
Authors: Lei Liu, Jialin Chen, Kathy Macropol
Abstract: Causal inference from electronic health records (EHR) is fundamentally limited by unmeasured confounding: critical clinical states such as frailty, goals of care, and mental status are documented in free-text notes but absent from structured data. Large language models can extract these latent confounders as interpretable, structured covariates, yet how to effectively integrate them into causal estimation pipelines has not been systematically studied. Using the MIMIC-IV database with 21,859 sepsis patients, we compare seven covariate-integration strategies for estimating the effect of early vasopressor initiation on 28-day mortality, spanning tabular-only baselines, traditional NLP representations, and three LLM-augmented approaches. A central finding is that not all integration strategies are equally effective: directly augmenting the propensity score model with LLM covariates achieves the best performance, while dual-caliper matching on text-derived categorical distances restricts the donor pool and degrades estimation. In semi-synthetic experiments with known ground-truth effects, LLM-augmented propensity scores reduce estimation bias from 0.0143 to 0.0003 relative to tabular-only methods, and this advantage persists under substantial simulated extraction error. On real data, incorporating LLM-extracted covariates reduces the estimated treatment effect from 0.055 to 0.027, directionally consistent with the CLOVERS randomized trial, and a doubly robust estimator yielding 0.031 confirms the robustness of this finding. Our results offer practical guidance on when and how text-derived covariates improve causal estimation in critical care. Our code is available at https://github.com/fpxlei/LLM-Covariates-Causal.
Authors: Yuelin Hu, Zhenbo Yu, Zhengxue Cheng, Wei Liu, Li Song
Abstract: Many continual-learning methods modify gradients upstream (e.g., projection, penalty rescaling, replay mixing) while treating Adam as a neutral backend. We show this composition has a hidden failure mode. In a high-overlap, non-adaptive 8-domain continual LM, all shared-routing projection baselines collapse close to vanilla forgetting (12.5--12.8 vs. 13.2). A 0.5% replay buffer is the strongest shared alternative but still reaches 11.6, while fixed-strength decoupling falls below vanilla at 14.1. Only adaptive decoupled routing remains stable at 9.4, improving over vanilla by 3.8 units. On a 16-domain stream, its gain over the strongest shared-routing projection baseline grows to 4.5--4.8 units. The failure is largely invisible on clean benchmarks. We explain this effect through Adam's second-moment pathway: in the tested regime, projection induces a 1/(1-alpha) inflation of the old-direction effective learning rate, matching measurements within 8% across eight alpha values. The same conflict appears with penalty methods, replay mixing, and at 7B scale under LoRA. Our fix routes the modified gradient only to the first moment while preserving magnitude-faithful second-moment statistics, with overlap-aware adaptive strength. This simple change is the only tested configuration that consistently avoids collapse across methods, optimizers, and scale.
Authors: Chao Zhou
Abstract: Behavioral curve modeling -- fitting parametric functions to engagement-versus-exposure data -- is standard practice in recommendation, advertising, and clinical dosing. We show that aggregation introduces a systematic distortion: Simpson's paradox in behavioral curves. On Goodreads (3.3M users, 9 genres), individual users peak at n* approximately 11 exposures while the aggregate peaks at n* approximately 34 -- a 3x gap driven by survival bias. Amazon Electronics (18M reviews) shows a 5.3x distortion. MovieLens-25M (D approximately 1) serves as a negative control, confirming that survival bias -- not aggregation per se -- is the operative mechanism. The distortion is robust to category granularity, engagement operationalization, and classifier calibration. We develop Synthetic Null Calibration to address a 32% false positive rate in per-user classification. Our findings apply wherever individual behavioral parameters are estimated from aggregate curves under differential attrition.
Authors: Ali Falahati, Elliot Creager, Gautam Kamath, Shubhankar Mohapatra
Abstract: Drifting Models have emerged as a new paradigm for one-step generative modeling, achieving strong image quality without iterative inference. The premise is to replace the iterative denoising process in diffusion models with a single evaluation of a generator. However, this creates a different trade-off: drifting reduces inference cost by moving much of the computation into training. We introduce DriftXpress, an accelerated formulation of drifting models based on projected RKHS fields. DriftXpress approximates the drifting kernel in a low-rank feature space. This preserves the attraction-repulsion structure of the original drifting field while reducing the cost of field evaluation. Across image-generation benchmarks, DriftXpress achieves comparable FID to standard drifting while reducing wall-clock training cost. These results show that the training-inference trade-off of drifting models can be pushed further without giving up their one-step inference advantage.
Authors: Taewoon Kim, Vincent Fran\c{c}ois-Lavet, Michael Cochez
Abstract: Reinforcement learning under partial observability requires deciding what information to retain, yet most memory-based approaches do not explicitly model short-term-to-long-term transfer of symbolic observations. We study this transfer process in a temporal knowledge-graph memory setting and cast it as a neuro-symbolic value-based decision problem: for each observed triple, the agent chooses whether to keep or drop it before long-term insertion. To handle variable-sized short-term buffers, we use a per-item Q-learning design with shared parameters and a practical temporal-difference update over matched items across consecutive steps. On the RoomKG benchmark at long-term memory capacity 128, learned transfer decisions outperform symbolic and neural baselines, including symbolic baselines with temporal annotations and history-based LSTM/Transformer baselines. Across transfer-policy ablations, a lightweight local short-term-only variant performs best, and step-level behavior shows that the policy keeps navigation- and query-relevant facts while discarding lower-value candidate facts, supporting explicit and interpretable memory decisions under memory constraints.
Authors: Yiran Xu, Yiming Ren, Zicheng Lin, Chufan Shi, Yukang Chen, Dingdong Wang, Tianhe Wu, Junjie Wang, Yujiu Yang, Yu Qiao, Ruihang Chu
Abstract: We identify a new dimension for enhancing rollout diversity in Group Relative Policy Optimization (GRPO) for LLMs. While GRPO relies on diverse rollouts, prevailing strategies primarily increase diversity by injecting more token-level randomness, which may introduce step-wise noise and lead to incoherent trajectories. We uncover that smaller models within the same model family inherently exhibit higher policy-level diversity, indicated by their superior pass@k relative to larger counterparts as sample counts increase. Unlike token-level noise, this diversity is temporally correlated, preserves logical consistency, and provides structured exploration signals for gradient estimation. We thus propose S2L-PO (Small-to-Large Policy Optimization), a framework that leverages fixed small models as natural explorers to train larger models. To balance exploration and exploitation, we design a progressive annealing strategy that transitions from offline small-model rollouts to the large learner's own sampling. This shift elegantly avoids mid-training performance drops caused by the small model's capacity limits, achieving faster convergence and unlocking a higher performance ceiling. S2L-PO improves accuracy on diverse mathematical reasoning benchmarks (e.g., +8.8% on AIME 24 using a 1.7B explorer to guide the 8B model) while reducing rollout compute.
Authors: Akarsh Kumar, Phillip Isola
Abstract: Training recurrent neural networks (RNNs) requires assigning credit across long sequences of computations. Standard backpropagation through time (BPTT) addresses this problem poorly: it is sequential in time, limiting parallelism, and suffers from vanishing or exploding gradients, making long-range associations difficult to learn. We propose Supervised Memory Training (SMT), a method for training nonlinear RNNs that sidesteps recurrent credit propagation entirely by reducing RNN training to supervised learning on one-step memory transition labels $(m_t, x_{t+1}) \rightarrow m_{t+1}$. SMT acquires these memory labels by training a Transformer-based encoder on a predictive state objective--retaining only information from the past necessary to predict the future. By decoupling what to remember from how to update memory, SMT enables time-parallel RNN training with a stable $O(1)$ length gradient path between any two tokens--without ever unrolling the RNN. We find that SMT outperforms BPTT when pretraining various RNN architectures on tasks like language modeling and pixel sequence modeling. SMT enables nonlinear RNNs to better capture long-range dependencies and train in parallel, potentially unlocking the scaling of models that build temporal abstractions of past experience.
Authors: Yash Tomar, Aryav Das
Abstract: LayerNorm-based GNNs routinely erase the topology signals (degree, centrality, $k$-core) that node-selection policies should depend on, but the literature has not located where in the residual block the erasure happens. We answer that question: a positive per-node scalar inserted before LayerNorm is divided out up to a stabilizer term, while the same scalar inserted after LayerNorm reaches the score head as representation magnitude. The surviving slot is the post-LayerNorm position. We instantiate it with PostDeg, a parameter-free post-LayerNorm inverse-degree scale, and pre-register four falsifiers (graphwise scalars, extra LayerNorm, expressive same-slot capacity, backbone-agnostic source) that would reject the rule. PostDeg gains $+3.5\%/+2.5\%/+5.6\%$ over the LN backbone on influence maximization, network dismantling, and maximum independent set, with $10/10$ paired-seed wins per task; none of the four falsifiers fires. The takeaway is that placement, not parameterization, carries the gain -- a small invariance check that generalizes to any positive topology scalar in any normalized residual stack.
Authors: Tong Shi, Jiacheng Wang, Hui Xie, Ying Li, Aishan Liu, Jinyang Guo, Xianglong Liu
Abstract: OpenPangu models are attractive targets for private and domestic large-language-model deployment, yet their robustness under aggressive post-training quantization on Ascend NPUs has not been systematically characterized. This paper conducts a controlled empirical study of OpenPangu 1B and 7B models on Huawei Ascend 910B1 NPUs. We evaluate representative weight-only and weight-activation post-training quantization methods, including RTN, GPTQ, AWQ, SmoothQuant, GPTAQ, BiLLM, and SliM-LLM, under a unified calibration and evaluation protocol. Across 18 evaluation tasks, we find that 8-bit weight-only quantization is effectively lossless for both models, while 4-bit quantization remains practical for the 7B model but is visibly more harmful for the 1B model on reasoning, math, and code tasks. Ultra-low precision remains challenging: most 2-bit and binary settings collapse to near-random behavior, and W4A4 SmoothQuant produces non-finite perplexity in our evaluation. These results provide an NPU-oriented accuracy map for selecting OpenPangu quantization settings and highlight the persistent difficulty of extreme low-bit compression.
Authors: Tal Weissblat
Abstract: In this work, we present a general Graph Neural Network (GNN) framework for learning algebraic properties of finite groups from their Cayley graph representations. The framework provides a unified computational pipeline consisting of a common graph construction procedure, feature representation, training methodology, and GNN architecture, with only the target labeling function varying across classification tasks. To demonstrate the generality of the proposed approach, we consider three representative algebraic properties: abelianity, nilpotency, and solvability. Experiments were conducted on a benchmark of 176 finite groups drawn from several classical families, with all groups included in each classification task. To address class imbalance, class-weighted cross-entropy loss was employed where appropriate during training. Furthermore, the family PSL(2,q) was reserved exclusively for testing, enabling evaluation of the framework's ability to generalize to previously unseen group families. The best-performing models achieved test balanced accuracies of 1.000, 0.856, and 0.875 for abelianity, nilpotency, and solvability, respectively. Although the same computational framework was employed across all tasks, different GNN architectures proved optimal for different algebraic properties, suggesting that the representational complexity required to learn a property depends on its underlying algebraic structure. These results demonstrate that GNNs can effectively learn multiple algebraic properties directly from Cayley graph representations while exhibiting strong generalization to unseen group families. More broadly, the proposed framework establishes a computational methodology for studying algebraic properties of finite groups using graph-based machine learning.
Authors: Emmanuel E. Oguadimma, Victory C. Obieke, Xueying Yu
Abstract: We consider the cubic nonlinear Schr\"odinger (NLS) equation on two-dimensional flat tori with varying aspect ratios. In this formulation, the choice of aspect ratio governs the Fourier resonance structure, so rational and irrational geometries can exhibit different high-frequency cascade behaviors. We present a geometry-conditioned Fourier neural operator (FNO) for the cubic defocusing NLS equation, where the input consists of the real and imaginary parts of the solution together with the aspect-ratio parameter \(\omega^2\). The model is trained to approximate the one-step solution operator and is evaluated on unseen trajectories generated from random-phase initial data using Fourier pseudospectral method. Our numerical experiments show that the learned operator captures the main solution dynamics on both tori and reproduces the distinct Sobolev norm behavior of the two geometries, with stronger \(H^2\)-growth on the rational torus and more constrained behavior on the irrational torus, consistent with the findings of \cite{hrabski2021energy}. We perform ablation studies to examine the roles of retained Fourier modes, activation functions, Fourier-layer depth, and explicit geometry conditioning. The results indicate that including $\omega^2$ improves long-time predictive accuracy, especially for the rational geometry, and supports the use of geometry-aware neural operators for learning spectral-transfer phenomena in nonlinear dispersive partial differential equations.
Authors: Yaohui Guo, X. Jessie Yang, Cong Shi
Abstract: We address the problem of online multi-human multi-robot matching through the lens of a linear matching bandit framework, where a learner assigns robots with unknown features from a fixed pool to distinct sets of human agents over multiple rounds. To solve this problem, we propose LinMatch, an online learning algorithm that updates the confidence intervals of the unknown features and makes the optimistic matching under uncertainty. The contributions and novelty of this work are twofold. First, we recast the optimistic matching problem in each round as a linear program of maximum weighted matching, efficiently solvable by the celebrated Hungarian algorithm. Second, we provide novel bounds for matching with linear feature problems, showing that $\Theta(\sqrt{T})$ is the optimal achievable regret with respect to the total number of rounds $T$. The proposed algorithm and bounds apply to a wide range of matching problems with applications beyond human-robot matching, such as housing allocation, recommendation systems, and more.
Authors: Roberto Rossi
Abstract: The Gaussian Error Linear Unit is usually motivated as the expected output of an input-dependent Bernoulli gate. This work gives an alternative interpretation: GELU is the expected output of a hard linear gate with a Gaussian random threshold. This view provides a generative interpretation for the Bernoulli gate: the gate opens once the input clears a latent Gaussian threshold. This interpretation stems from a decomposition based on well-known results in stochastic inventory theory and leads to a threshold-transmission family that includes ReLU, GELU, SiLU/Swish, and hard swish as special cases. By considering a latent uniform threshold, we recover a hard-swish-like piecewise-polynomial gate whose nonlinear transition is confined to a finite interval, yielding fixed- and learned-width variants. Controlled experiments on compact vision and language models show that calibrated or learned uniform-threshold gates are consistently competitive with GELU, ReLU, and SiLU/Swish, display architecture-dependent learned widths, and use the finite transition region nontrivially.
Authors: Anthony Baez, Sheer Karny, Pat Pataranutaporn
Abstract: Large Language Models (LLMs) frequently exhibit sycophancy, agreeing with a user's statement even when it is incorrect. While often studied as a single, uniform behavior, sycophancy can manifest in substantially distinct ways across contexts, raising the question of whether this heterogeneity is reflected in its internal mechanisms. To address this gap, we dissociate the representations of sycophancy into factual and opinion subtypes, motivated by prior evidence of heterogeneous truth representations in LLMs. We train linear probes and construct steering vectors on one subtype's activations and evaluate their transfer to the other, measuring the extent to which representations are shared and visualizing them via Linear Discriminant Analysis. We find that different LLMs represent these subtypes differently, with either more aligned or more distinct representations, and apply this insight to improve representational interventions for reducing sycophancy. Our dissociation method offers a general framework for studying the representational structure of complex model behaviors.
Authors: Dharshan Kumaran, Viorica Patraucean, Maks Ovsjanikov, Petar Veli\v{c}kovi\'c, Nathaniel Daw
Abstract: Reliable confidence -- the probability that a model's own answer is correct -- is essential for the trustworthy deployment of language models. Existing work has largely evaluated confidence by how well it predicts correctness and whether it is calibrated, leaving open a more fundamental question: what does the confidence signal itself represent? Answer logits may reflect a latent decision variable sufficient to compute normative confidence, or instead a heuristic preference signal that combines the available evidence in a non-Bayesian manner. We address this using statistical decision confidence (SDC), a normative framework from computational neuroscience. Treating the answer-logit difference (LD) as a candidate readout of the latent decision variable, we test the qualitative signatures predicted by SDC. Across three perceptual discrimination tasks and a memory-based decision task, spanning three multimodal non-reasoning models and one reasoning model, LD satisfied these signatures -- including the diagnostic correct/error folded-X pattern -- showing that, in these settings, answer logits behave as monotonic readouts of a latent decision variable rather than heuristic preference scores. In complex visual reasoning, LD continued to predict correctness beyond objective task difficulty, but the full geometric signatures of SDC were absent, illustrating the current boundary of the framework when explicit normative process models are unavailable. These results provide a computational account of confidence in multimodal language models, delineate when answer logits behave as readouts of a latent decision variable, and establish SDC as a unifying framework for studying confidence across biological and artificial intelligence.
Authors: Abdallah Aaraba, Alexis Vieloszynski, Remon Polus, Soumaya Cherkaoui, Ola Ahmad
Abstract: The broadcast nature of wireless channels exposes radio-frequency (RF) networks to anomalous and malicious transmissions, making anomaly detection a fundamental requirement for secure spectrum management. Quantum Kitchen Sinks (QKS) offer a lightweight hybrid quantum feature map suitable for near-term quantum devices, yet their behavior on structured signal data remains poorly understood. In this paper, we extend the standard QKS template with multi-depth data re-uploading and ring entanglement, and evaluate the resulting pipeline on controlled RF spectrogram anomaly detection. We introduce a validation-locked five-stage ablation protocol that systematically separates the effects of shallow architecture, re-uploading depth, episode budget, input representation, and classical readout. Across the completed benchmark, Discrete Cosine Transform (DCT) representations consistently dominate raw and Principal Component Analysis (PCA) inputs, moderate-depth entangled QKS configurations form the strongest operating regime, and QKS improves over matched classical direct-readout baselines across all evaluated representation-readout pairs on the held-out test set, with the best configuration reaching a test Area Under the Receiver Operating Characteristic curve (AUROC) of 0.8778 and a test F1 of 0.7995. The study bridges two levels of realism: real measured sub-6\,GHz cellular signals on the data side and real-device validation on the ibm_quebec Quantum Processing Unit (QPU) on the computing side, with AUROC deviations below 0.013 relative to simulation. These results provide a practical, reproducible framework for deploying QKS-based anomaly detection in wireless networks.
Authors: James O' Neill, Fergal Reid
Abstract: Looped, weight-tied Transformers reduce parameters by reusing a single block, but decoding still stores a separate K/V cache for every recurrence step. We show that this loop-indexed cache is highly structured. For a fixed token, layer and head, K/V vectors trace a short low-rank trajectory across loops, while the head and layer axes remain much flatter. We introduce Looped Latent Attention (\lla{}), a post-training cache codec that stores compact K and V latents and reconstructs loop-specific K/V vectors only when attention reads them. The default per-head codec compresses recurrence, while \lla{}-2D also folds heads into one latent for the extreme-compression regime. The codec is initialized from the SVD of teacher activations and refined with logit and attention-output distillation. At matched cache budget, per-head \lla{} outperforms head-axis MLA, cross-layer sharing, KV quantization and final-loop reuse, showing that the recurrent cache is low-rank but not safely collapsible to a single state. The same axis advantage holds on Ouro-2.6B-Thinking and transfers to Huginn-3.5B, where an SVD codec remains near-lossless to $32\times$ compression in decoder-independent evaluation. The cache reduction is exact. On one H200, the latent-store path increases measured Ouro-1.4B batch capacity at 4k context from 32 to 768 sequences at $21.3\times$ compression. Lastly, for long reasoning rollouts such as in MATH-500, on-policy refinement on student-generated prefixes raises accuracy at $4\times$ compression from 0.43 to 0.66 and reduces no-answer generations when compared to token-level off-policy distillation.
Authors: Behnam Asadi
Abstract: We revisit Gaussian Mixture Models (GMMs) as a lightweight, interpretable tool for anomaly detection and, in particular, for detecting distributional drift in data streams. We make three practical choices explicit and evaluate them on seven public benchmarks. First, the number of mixture components is selected automatically by the Bayesian Information Criterion, initialised by k-means, removing the need to fix it in advance. Second, individual observations are scored by their negative log-likelihood under a GMM fitted to normal data, with thresholds set at a target false-alarm rate using Extreme Value Theory. Third, the same interpretable model extends to distributional drift: each Gaussian component is a named "regime," and the fraction of a stream window that matches no regime -- its unexplained mass -- is a drift signal that is itself the explanation. We benchmark this against a model-free kernel two-sample test (Maximum Mean Discrepancy, MMD) and against two GMM-to-GMM divergences (a closed-form Cauchy-Schwarz divergence and a matching-based KL surrogate). Across seven benchmarks ranging from 3 to 64 dimensions and five random splits, the GMM point detector is competitive with -- though rarely more accurate than -- Isolation Forest, Local Outlier Factor, one-class SVM, ECOD, COPOD and an autoencoder, while uniquely yielding an interpretable model. For drift, MMD is the strongest pure detector, but the interpretable unexplained-mass statistic matches it when anomalies form novel regimes (and honestly fails, as MMD does not, when drift is a pure re-weighting of existing regimes). Every alarm is explainable: anomalies lie a median of 3-10 sigma outside their nearest regime vs. about 1 sigma for normal points, and a drift alarm reports the fraction of the window matching no known regime. All code and experiments are released.
Authors: Peiyu Zang, Bosen Xie, Ruoxiang Xu, Yongqiang Cai
Abstract: Physics-Informed Neural Networks (PINNs) solve PDEs by incorporating physical constraints into neural-network training, but large-scale problems are limited by automatic-differentiation memory overhead and inefficient execution of grid-based PDE operators. We present FlashPDE, a drop-in fused operator library for grid-based scientific machine learning. FlashPDE replaces fragmented PyTorch finite-difference execution with differentiable Triton kernels. Each operator integrates fused stencil evaluation, an analytic discrete-adjoint backward pass, and boundary-gradient correction within a unified PyTorch autograd Function interface. The library provides 14 differentiable PDE operators covering 17 configurations across 1D--3D elliptic, parabolic, and Navier--Stokes systems, while remaining independent of neural architectures and training strategies. Experiments on an NVIDIA A100 GPU show that FlashPDE reduces peak memory usage by up to 37.0x compared with coordinate-based automatic differentiation and reduces CUDA kernel launches by up to 3.5x compared with eager PyTorch finite-difference implementations. Across six representative PDE benchmarks, FlashPDE achieves up to 2.30x end-to-end time-to-solution speedup and up to 19.2x kernel-level acceleration while maintaining numerical agreement with PyTorch finite-difference references. FlashPDE provides a hardware-efficient execution layer that bridges differentiable PDE solvers and GPU-optimized numerical computation within the PyTorch ecosystem.
Authors: Kushal Chakrabarti
Abstract: As language models scale, answers start truer but degrade faster: scaling buys capability but erodes reliability. The knowledge-gap account -- more data, retrieval, or scale -- misses an auto-regressive risk residual that increases with scale: the model commits to a low-probability token, conditions on it as established, and snowballs. We track this through per-position disagreement $\delta = \log p_M - \log p_O$ against a stronger same-family oracle, whose second moment splits exactly into bias$^2$ $\mathrm{KL}(p_M \,\|\, p_O)^2$ and risk $\mathrm{Var}[\delta]$. Across three model families, we present four findings: (i) under scaling, the knowledge gap falls up to $7\times$ while knowledge degradation grows up to $39\times$; (ii) at a fabrication, felt uncertainty $H(p_M)$ relaxes quickly while oracle-referenced risk persists up to $23\times$ longer, leaving a confident-but-precarious risk regime that bridges consecutive fabrications; (iii) this regime is causal -- a fixed-$\mathrm{KL}$ variance contraction cuts web-verified hallucination $35$-$74\%$; and, (iv) it evades self-monitoring, with $p_M$-only detectors (e.g. semantic entropy) firing $\approx$$30\%$ less ($p\!<\!10^{-16}$) on the risky branch despite it holding nearly $4\times$ more fabrications. Bigger models snowball mistakes faster, through a failure mode that is dominant, self-perpetuating, causal and invisible to the model itself.
Authors: Frederick Schindlegger, Kenzo Bounegta, Eva Gmelich Meijling, Johannes Jakubik, Arnt-B{\o}rre Salberg, Theodor Forgaard, Nicolas Longepe, Valerio Marsocci
Abstract: Benchmarks for Geospatial Foundation Models (GFMs) increasingly rank models by aggregate score, but such rankings obscure why models differ: how much of the gap is architecture, how much is decoder capacity, and how much is a use-case-specific artefact? This study addresses that gap through a controlled comparison of two GFMs developed under European Space Agency's $\Phi$-lab with contrasting design philosophies: THOR, which introduces a compute-adaptive architecture supporting variable patch sizes and unifies Sentinel-1, -2, and -3 data at their native resolutions; and TerraMind, a multimodal generative GFM pretrained with a dual-scale token/pixel objective that enables any-to-any cross-modal generation (Thinking-in-Modalities) to infer missing sensors at inference time. Rather than reporting a single leaderboard, we investigate the axes along which the two architectures actually differ - patch size, decoder complexity, finetuning regime, input modality, and model scale - across ten use cases spanning segmentation and regression in diverse domains, including climate disaster response, methane leak detection, snow monitoring, or sea ice mapping. We find that architectural design choices - patch size and decoder type in particular - explain more performance variance than model identity itself, that the two models embody complementary investment strategies (pretraining-time scale for TerraMind versus inference-time tokenisation for THOR), and that correctly interpreting results requires dataset-level characterisation. The resulting picture is not a single winner but a set of hypotheses and a diagnostic ablation methodology that we expect to generalise to future GFMs beyond THOR and TerraMind.
Authors: Junyao Yang, Yucheng Shi, Zongxia Li, Zhongzhi Li, Ruhan Wang, Xiangxin Zhou, Kishan Panaganti, Haitao Mi, Leowei Liang
Abstract: Asynchronous reinforcement learning improves throughput by decoupling rollout generation from optimization, but the resulting staleness is an inevitable byproduct, compounded jointly by policy lag, engine delays, and mixture-of-experts routing. From a trust-region perspective, this mismatch is critical: in the finite-horizon improvement bound, training-inference divergence governs the approximation error, whereas PPO clipping only gates sampled outward updates and therefore acts as a sampled surrogate rather than a full-policy constraint. As a result, the high-staleness update can remain weakly controlled in exactly the asynchronous regime where stale rollouts matter most. We introduce the Staleness-Adaptive Trust Region (SAT), which uses the detached sampled log-ratio as a practical staleness proxy, identifies the high-mismatch tail within each batch through Staleness-based kernel function scaling, and contracts only the sign-selected endpoint of the nominal PPO interval using Effective contraction factors. This design preserves the baseline behavior on ordinary tokens, while making the update more conservative exactly on newly intercepted outward bands. We evaluate SAT in a fully decoupled asynchronous reinforcement learning setup built on Qwen3-30B-A3B-Base, leveraging SGLang as the inference engine and Megatron as the training pipeline. In this setting, SAT-GSPO w/ R3 attains the best observed AIME24 avg@8, reaching 35.83 at lag 1 and 34.79 at lag 8, while SAT-GSPO reaches 34.17 at lag 1. More broadly, the results indicate that aligning the clip interval with observed staleness heterogeneity is an effective way to stabilize the reported asynchronous regime.
Authors: Qiye Cai, Yichuan Ma, Linyang Li, Peiji Li, Yongkang Chen, Qipeng Guo, Yicheng Zou, Xiaocheng Feng, Bing Qin
Abstract: Reinforcement learning with verifiable rewards (RLVR) provides reliable outcome supervision for language model reasoning, but a scalar trajectory reward offers limited token-level guidance. Existing self-distillation methods add a privileged teacher but typically assign it a fixed role: direct distribution matching may destabilize successful behavior, while magnitude-only modulation offers little corrective guidance after failure. We observe that successful and failed trajectories require different forms of hindsight supervision. A successful response already contains a valid student-generated reasoning path and can therefore serve as privileged context rather than being replaced by an external rationale. A failed response, however, requires corrective reference information. We introduce Hybrid Hindsight Self-Distillation ($\mathrm{H}^{2}\mathrm{SD}$), which jointly adapts teacher context and update strategy to trajectory correctness. For successful trajectories, we construct the teacher context from the verified response and a rephrasing instruction, and use the teacher only to re-evaluate the original response tokens. The resulting probabilities refine token credit assignment without changing the direction determined by the reward. For failed trajectories, a verified reference hint provides corrective guidance through reverse-KL distillation. Experiments on challenging reasoning benchmarks show that H$^2$SD achieves the strongest overall performance among representative RLVR and self-distillation baselines, with stable optimization and a favorable accuracy-efficiency trade-off.
Authors: Shifeng Xie, Ambroise Odonnat, Zehao Xiao, Lei Zan, Malik Tiomoko, Lujia Pan, Themis Palpanas, Boris N. Oreshkin, Chenghao Liu, Keli Zhang
Abstract: Time series foundation models (TSFMs) have emerged as general-purpose models for time series analysis, but pretraining alone is often insufficient for reliable downstream deployment. Bridging this gap requires further intervention to handle domain shift, task heterogeneity, limited supervision, and computational constraints, which motivates post-training as a broad class of methods to adapt, augment, compose, calibrate, or specialize pretrained TSFMs for downstream tasks. In this work, we analyze TSFM post-training methods based on their locus of intervention in the prediction pipeline, yielding five categories: parameter adaptation, context augmentation, model composition, output processing and uncertainty control, and compression and specialization. Within each category, we study main representative methods and discuss their current limitations. We further identify future directions toward controlled adaptation, reliable context construction, uncertainty-aware model composition, calibrated output processing, and deployment-aware specialization. Overall, by providing a unifying framework for the emerging TSFM post-training landscape, this work aims to support future research to navigate the design space between a pretrained TSFM and its reliable downstream deployment.
Authors: Mengda Xing (CRIL, UA), Jean-Marie Lagniez (CRIL, UA), Alejandro Franco (LRCS)
Abstract: Physics-based simulations are essential for understanding the electrode-scale discharge behavior of lithium-ion batteries (LIBs) but suffer from prohibitive computational costs. To address this, we introduce a novel deep learning surrogate pipeline based on the Swin3D Transformer to predict spatiotemporal discharge dynamics directly from volumetric data. Our approach integrates two key innovations: Gaussian Positional Encoding (GPE), which enhances spatial feature representation by adapting to the complex geometry of electrode microstructures, and a specialized Temporal Encoding module to capture non-linear timeseries evolution. Experimental validation on an Electrochemical Simulation (ES) dataset demonstrates that our pipeline significantly outperforms state-of-the-art point cloud baselines in prediction accuracy. Furthermore, the proposed method reduces the computational overhead by orders of magnitude, providing a scalable and efficient framework for high-throughput battery design and optimization.
Authors: Miguel P. Bento, Jo\~ao F. Seabra
Abstract: Transformers are known to have internal continuous symmetries that leave outputs invariant, while modifying quantization. GaugeQuant leverages this in-training by introducing a LogSumExp term to the loss that breaks the symmetries, thus selecting a basis that minimizes activation outliers. A stop-gradient operator ensures that only rotation matrices are updated, yielding the language modeling objective completely unaltered. Our requires no specific calibration data, no quantization simulation, and adds negligible training overhead. With the LLaMA-2 7B model under W4A4 quantization with group size 128, perplexity drops from 8.22 to 6.73, competing with post-training methods that require frozen models and calibration datasets. Under W4A16, perplexity drops from 11.16 to 5.45. Code is available at https://github.com/MPedraBento/gauge-quant.
Authors: Sreejeet Maity, Aritra Mitra
Abstract: Motivated by reinforcement learning in harsh environments, we consider the problem of learning an optimal policy subject to adversarially corrupted feedback. Specifically, at each time-step, an adversary can perturb both the reward and state observations of the learner following the Huber contamination model. To defend against such data corruption, we propose BR-Async-Q: a novel, epoch-based, robust Q-learning algorithm built upon two key ideas: (i) partitioning the online data stream into batches to reduce variance, and (ii) constructing robust estimates of the Bellman optimality operator using such batched data. We prove a high-probability $\ell_\infty$ error bound for BR-Async-Q that matches that for vanilla Q-learning, up to a small additive term that scales with the fraction of corrupted samples. To our knowledge, this provides the first robustness guarantee for asynchronous Q-learning subject to both reward and state corruption. Furthermore, when only rewards are corrupted, the dependence of our algorithm's bound on the corruption fraction is minimax optimal.
Authors: Rajiv Shailesh Chitale, Rahul Madhavan, Taneesh Gupta, Deepanway Ghosal, Aravindan Raghuveer
Abstract: Scaling inference-time computation has emerged as a reliable method to improve the performance of large language models on complex reasoning and programming tasks. However, standard approaches such as independent sampling and sequential multi-turn refinement operate without token-level credit assignment, resulting in computational inefficiency, since valid reasoning prefixes are frequently discarded. In this work, we introduce Test-Time Scaling via Error Localization (TTEL), an inference-time algorithm that utilizes fixed or environment feedback to perform token-level error localization. By comparing conditional probabilities under informed feedback against a null-context baseline, TTEL isolates the step at which an error occurred. The algorithm then truncates the trajectory and branches a new generation, maximally reusing the valid prefix. Extensive evaluations demonstrate that TTEL establishes strictly dominating Pareto frontiers across sequential reasoning domains, measured by pass-at-k vs. generated-token cost. With Qwen3-8B on LiveCodeBench, TTEL attains a pass@64 of 71.0% while generating approximately half as many tokens as independent sampling (360.4k vs. 735.0k). Generalizing to math benchmarks AIME-2025 and HMMT-2025, TTEL cleanly outperforms competing test-time baselines across both Qwen3-8B and Qwen3-4B-Thinking-2507.
Authors: Takashi Takahashi
Abstract: Self-training (ST) is a simple yet effective semi-supervised learning method. However, why and how ST improves generalization performance by using potentially erroneous pseudo-labels is still not well understood. To deepen the understanding of ST, we derive and analyze a sharp characterization of the behavior of iterative ST when training a linear classifier by minimizing the ridge-regularized convex loss on binary Gaussian mixtures, in the asymptotic limit where input dimension and data size diverge proportionally. The results show that ST improves generalization in different ways depending on the number of iterations. When the number of iterations is small, ST improves generalization performance by fitting the model to relatively reliable pseudo-labels and updating the model parameters by a large amount at each iteration. This suggests that ST works intuitively. On the other hand, with many iterations, ST can gradually improve the direction of the classification plane by updating the model parameters incrementally, using soft labels and small regularization. It is argued that this is because the small update of ST can extract information from the data in an almost noiseless way. However, in the presence of label imbalance, the generalization performance of ST underperforms supervised learning with true labels. To overcome this, two heuristics are proposed to enable ST to achieve nearly compatible performance with supervised learning even with significant label imbalance.
Authors: Xinjie Cui, Yuezun Li, Delong Zhu, Jiaran Zhou, Junyu Dong, Siwei Lyu
Abstract: We describe Forensics Adapter, an adapter network designed to transform CLIP into an effective and generalizable face forgery detector. Although CLIP is highly versatile, adapting it for face forgery detection is non-trivial as forgery-related knowledge is entangled with a wide range of unrelated knowledge. Existing methods treat CLIP merely as a feature extractor, lacking task-specific adaptation, which limits their effectiveness. To address this, we introduce an adapter to learn face forgery traces -- the blending boundaries unique to forged faces, guided by task-specific objectives. Then we enhance the CLIP visual tokens with a dedicated interaction strategy that communicates knowledge across CLIP and the adapter. Since the adapter is alongside CLIP, its versatility is highly retained, naturally ensuring strong generalizability in face forgery detection. {With only $\textbf{5.7M}$ trainable parameters, our method achieves superior performance across six standard datasets.} Additionally, we describe Forensics Adapter++, an extended method that incorporates textual modality via a newly proposed forgery-aware prompt learning strategy. This extension leads to a further $\textbf{1.3\%}$ performance boost over the original Forensics Adapter. We believe the proposed methods can serve as a baseline for future CLIP-based face forgery detection methods. The code has been released at https://github.com/OUC-VAS/ForensicsAdapter.
Authors: Mohamed Ndaoud, Peter Radchenko, Bradley Rava
Abstract: Selective classification is a powerful tool for automated decision-making in high-risk scenarios, allowing classifiers to act only when confident and abstain when uncertainty is high. Given a target accuracy, our goal is to minimize the number of indecisions, which are observations that we do not automate. For difficult problems, the target accuracy may be unattainable without abstaining from making a decision. By using indecisions, we can target a misclassification rate below the Bayes error rate, while minimizing overall indecision mass. We provide a characterization of the optimal risk in selective classification, establishing continuity and monotonicity properties that enable optimal indecision selection. We revisit selective inference via the Neyman-Pearson testing framework, where indecision enables control of Type~II error given a fixed Type~I error probability. For both classification and testing, we propose a calibration method, and analyze the excess risk of plug-in classifiers and the excess indecision mass produced by accuracy-based calibration. In the binary Gaussian mixture model, we identify an exponent-level phase transition, showing that minimal indecision can yield near-optimal accuracy even under poor class separation. Experiments on Gaussian mixtures and real datasets illustrate how indecision can improve selective accuracy.
Authors: Jean Barbier, Francesco Camilli, Minh-Toan Nguyen, Mauro Pastore, Rudy Skerk
Abstract: We consider a teacher-student model of supervised learning with a fully-trained two-layer neural network whose width $k$ and input dimension $d$ are large and proportional. We provide an effective theory for approximating the Bayes-optimal generalisation error of the network for any activation function in the regime of sample size $n$ scaling quadratically with the input dimension, i.e., around the interpolation threshold where the number of trainable parameters $kd+k$ and of data $n$ are comparable. Our analysis tackles generic weight distributions. We uncover a discontinuous phase transition separating a "universal" phase from a "specialisation" phase. In the first, the generalisation error is independent of the weight distribution and decays slowly with the sampling rate $n/d^2$, with the student learning only some non-linear combinations of the teacher weights. In the latter, the error is weight distribution-dependent and decays faster due to the alignment of the student towards the teacher network. We thus unveil the existence of a highly predictive solution near interpolation, which is however potentially hard to find by practical algorithms.
Authors: Abhineet Agarwal, Fange Xiao, Rebecca Barter, Omer Ronen, Boyu Fan, Bin Yu
Abstract: As machine learning (ML) enters high-stakes domains, trustworthy uncertainty quantification (UQ) is essential for safety. In this paper we introduce PCS-UQ, a framework based on the Predictability, Computability, and Stability (PCS) principles for veridical data science. Starting with a candidate set of models or algorithms, PCS-UQ integrates a rigorous prediction-check to screen out unsuitable models in the set and utilizes bootstrap samples in order to capture both inter-sample variability and algorithmic instability for the prediction-checked algorithms. We then introduce a novel multiplicative calibration scheme to enhance local adaptivity, which can be viewed as a new score in conformal prediction. Moreover, we produce a compilation of 17 real-world regression datasets with manually constructed subgroups. On this benchmark, PCS-UQ maintains the target coverage while outperforming or matching conformal methods equipped with oracle-selected algorithms in interval width. PCS-UQ achieves consistent subgroup coverage, outperforming these oracle-selected conformal methods. Notably, PCS-UQ stands out in achieving both competitive interval widths and consistent subgroup coverage. Across 6 classification datasets, PCS-UQ reduces prediction set sizes by 20\%. To scale the framework for deep learning, we propose computationally efficient variants that bypass expensive retraining. On three computer vision benchmarks, these variants reduce prediction set sizes by 20\% over conformal baselines. Finally, we provide a theoretical proof that a modified PCS-UQ algorithm preserves valid coverage under exchangeability as a form of split conformal inference.
Authors: Jean Barbier, Francesco Camilli, Minh-Toan Nguyen, Mauro Pastore, Rudy Skerk
Abstract: For three decades statistical mechanics has been providing a framework to analyse neural networks. However, the theoretically tractable models, e.g., perceptrons, random features models and kernel machines, or multi-index models and committee machines with few neurons, remained simple compared to those used in applications. In this paper we help reducing the gap between practical networks and their theoretical understanding through a statistical physics analysis of the supervised learning of a two-layer fully connected network with generic weight distribution and activation function, whose hidden layer is large but remains proportional to the inputs dimension. This makes it more realistic than infinitely wide networks where no feature learning occurs, but also more expressive than narrow ones or with fixed inner weights. We focus on the Bayes-optimal learning in the teacher-student scenario, i.e., with a dataset generated by another network with the same architecture. We operate around interpolation, where the number of trainable parameters and of data are comparable and feature learning emerges. Our analysis uncovers a rich phenomenology with various learning transitions as the number of data increases. In particular, the more strongly the features (i.e., hidden neurons of the target) contribute to the observed responses, the less data is needed to learn them. Moreover, when the data is scarce, the model only learns non-linear combinations of the teacher weights, rather than "specialising" by aligning its weights with the teacher's. Specialisation occurs only when enough data becomes available, but it can be hard to find for practical training algorithms, possibly due to statistical-to-computational~gaps.
Authors: Yigit Berkay Uslu, Navid NaderiAlizadeh, Mark Eisen, Alejandro Ribeiro
Abstract: We consider resource allocation problems in multi-user wireless networks, where the goal is to optimize a network-wide utility function subject to constraints on the ergodic average performance of users. We demonstrate how a state-augmented graph neural network (GNN) parametrization for the resource allocation policy circumvents the drawbacks of the ubiquitous dual subgradient methods by representing the network configurations (or states) as graphs and viewing dual variables as dynamic inputs to the model, treated as graph signals supported over the graphs. Lagrangian maximizing state-augmented policies are learned during the offline training phase, and the dual variables evolve through gradient updates while executing the learned state-augmented policies during the inference phase. Our main contributions are to illustrate how near-optimal initialization of dual multipliers for faster inference can be accomplished with dual variable regression, leveraging a secondary GNN parametrization, and how maximization of the Lagrangian over the multipliers sampled from the dual descent dynamics substantially improves the training of state-augmented models. We demonstrate the superior performance of the proposed algorithm with extensive numerical experiments in a case study of transmit power control. Finally, we prove a convergence result and an exponential probability bound on the excursions of the dual function (iterate) optimality gaps.
Authors: Rodrigo Tertulino
Abstract: Federated Learning (FL) presents a groundbreaking approach for collaborative health research, allowing model training on decentralized data while safeguarding patient privacy. FL offers formal security guarantees when combined with Differential Privacy (DP). The integration of these technologies, however, introduces a significant trade-off between privacy and clinical utility, a challenge further complicated by the severe class imbalance often present in medical datasets. The research presented herein addresses these interconnected issues through a systematic, multi-stage analysis. An FL framework was implemented for cardiovascular risk prediction, where initial experiments showed that standard methods struggled with imbalanced data, resulting in a recall of zero. To overcome such a limitation, we first integrated the hybrid Synthetic Minority Over-sampling Technique with Tomek Links (SMOTETomek) at the client level, successfully developing a clinically useful model. Subsequently, the framework was optimized for non-IID data using a tuned FedProx algorithm. Our final results reveal a clear, non-linear trade-off between the privacy budget (epsilon) and model recall, with the optimized FedProx consistently out-performing standard FedAvg. An optimal operational region was identified on the privacy-utility frontier, where strong privacy guarantees (with epsilon 9.0) can be achieved while maintaining high clinical utility (recall greater than 77%). Ultimately, our study provides a practical methodological blueprint for creating effective, secure, and accurate diagnostic tools that can be applied to real-world, heterogeneous healthcare data.
Authors: Sven Dummer, Tjeerd Jan Heeringa, Jos\'e A. Iglesias
Abstract: Recently, there has been growing interest in characterizing the function spaces underlying neural networks. While shallow and deep scalar-valued neural networks have been linked to scalar-valued reproducing kernel Banach spaces (RKBS), $\mathbb{R}^d$-valued neural networks and neural operator models remain less understood in the RKBS setting. To address this gap, we develop a notion of adjoint pairs of vector-valued RKBSs (vv-RKBS), which inherently involves an associated reproducing kernel, and prove that every vv-RKBS belongs to such a pair. Our construction extends existing kernel definitions by avoiding restrictive assumptions such as symmetric kernel domains, finite-dimensional output spaces, reflexivity, or separability, while still recovering familiar properties of vector-valued reproducing kernel Hilbert spaces (vv-RKHS). We then show that shallow $\mathbb{R}^d$-valued neural networks are elements of a specific vv-RKBS, namely an instance of an integral vv-RKBS. To also explore the functional structure of neural operators, we analyze the DeepONet and Hypernetwork architectures and demonstrate that they too belong to an integral vv-RKBS. In all cases, we establish a representer theorem, showing that optimization over these function spaces recovers the corresponding neural architectures.
Authors: Eduardo Fernandes Montesuma, Yassir Bendou, Mike Gartrell
Abstract: Wasserstein barycenters provide a principled approach for aggregating probability measures, while preserving the geometry of their ambient space. Existing discrete methods are not because as they assume access to the complete set of samples from the input measures. Meanwhile, neural network approaches do scale well, but rely on complex optimization problems and cannot easily incorporate label information. We address these limitations through gradient flows in the space of probability measures. Through time discretization, we achieve a scalable algorithm that i) relies on mini-batch optimal transport, ii) accepts modular regularization through task-aware functions, and iii) seamlessly integrates supervised information into the ground-cost. We empirically validate our approach on domain adaptation benchmarks that span computer vision, neuroscience, and chemical engineering. Our method establishes a new state-of-the-art Wasserstein barycenter solver, with labeled barycenters consistently outperforming unlabeled ones. Our code at https://github.com/SigmaNova/barycentric-gradient-flows
URLs: https://github.com/SigmaNova/barycentric-gradient-flows
Authors: Jean Barbier, Francesco Camilli, Minh-Toan Nguyen, Mauro Pastore, Rudy Skerk
Abstract: For four decades statistical physics has been providing a framework to analyse neural networks. A long-standing question remained on its capacity to tackle deep learning models capturing rich feature learning effects, thus going beyond the narrow networks or kernel methods analysed until now. We positively answer through the study of the supervised learning of a multi-layer perceptron. Importantly, (i) its width scales as the input dimension, making it more prone to feature learning than ultra wide networks, and more expressive than narrow ones or ones with fixed embedding layers; and (ii) we focus on the challenging interpolation regime where the number of trainable parameters and data are comparable, which forces the model to adapt to the task. We consider the matched teacher-student setting. Therefore, we provide the fundamental limits of learning random deep neural network targets and identify the sufficient statistics describing what is learnt by an optimally trained network as the data budget increases. A rich phenomenology emerges with various learning transitions. With enough data, optimal performance is attained through the model's "specialisation" towards the target, but it can be hard to reach for training algorithms which get attracted by sub-optimal solutions predicted by the theory. Specialisation occurs inhomogeneously across layers, propagating from shallow towards deep ones, but also across neurons in each layer. Furthermore, deeper targets are harder to learn. Despite its simplicity, the Bayes-optimal setting provides insights on how the depth, non-linearity and finite (proportional) width influence neural networks in the feature learning regime that are potentially relevant in much more general settings.
Authors: Renos Zabounidis, Aditya Golatkar, Michael Kleinman, Alessandro Achille, Wei Xia, Stefano Soatto
Abstract: We propose Re-FORC, an adaptive reward prediction method that, given a query, enables prediction of the expected future rewards as a function of the number of future thinking tokens. Re-FORC trains a lightweight adapter on reasoning models, demonstrating improved prediction with longer reasoning and larger models. Re-FORC enables: 1) early stopping of unpromising reasoning chains, reducing compute by up to 26\% compared to fixed-budget cutoffs, while maintaining accuracy, 2) optimized model and thinking length selection that outperforms the largest model alone--- reaching 1.7 percentage points higher peak accuracy while needing up to 12\% less compute to match the largest model's accuracy, 3) adaptive test-time scaling, which increases accuracy by 9.9 percentage points (on average at maximum compute) over confidence-based baselines. Re-FORC allows dynamic reasoning with length control via cost-per-token thresholds while estimating computation time upfront.
Authors: Samaresh Kumar Singh, Joyjit Roy, Sriharsha Anand Pushkala
Abstract: Sophisticated attackers can evade detection-based security by using encryption, stealth tactics, and low-rate attack patterns. This challenge is particularly acute in Internet of Things (IoT) and edge environments, where limited resources make ML-based intrusion detection systems impractical. Hereby, we present Economic Denial Security (EDS), a framework that renders attacks economically infeasible rather than trying to detect them. EDS exploits a fundamental asymmetry. Defenders control their own environment, whereas attackers do not. The four mechanisms in this framework amplify attack costs superlinearly. These mechanisms include adaptive computational puzzles, decoy-driven interaction entropy, temporal stretching, and bandwidth taxation. This paper uses game theory to mathematically prove the optimal configuration of EDS, and we found that combining multiple safety mechanisms usually costs 2.1 times as much as using them separately, a key trade-off to consider during design. The good news is that EDS is extremely efficient, using less than 12 KB of memory, making it practical to run on small embedded devices like microcontrollers rather than on expensive servers. EDS is tested on 20 different IoT devices under four attack scenarios. The results showed that attacks slow down significantly, costs become asymmetric, attack success rates drop, and the system adds only 20 ms of latency with no false positive results. When tested against real malware (Mirai, Torii, and Hajime), combining EDS with machine learning detection improved protection from 67 % to 88 %. Adding both techniques together reached 94 % protection, a 27 % improvement overall. Unlike traditional detection-based approaches, EDS operates independently, without requiring attack identification, making it practical for resource-limited IoT devices where other methods simply don't work.
Authors: Maximilian Alber, Timo Milbich, Alexandra Carpen-Amarie, Stephan Tietz, Jonas Dippel, Lukas Muttenthaler, Beatriz Perez Cancer, Alessandro Benetti, Panos Korfiatis, Elias Eulig, J\'er\^ome L\"uscher, Jiasen Wu, Sayed Abid Hashimi, Gabriel Dernbach, Simon Schallenberg, Neelay Shah, Moritz Kr\"ugener, Aniruddh Jammoria, Jake Matras, Patrick Duffy, Matt Redlon, Philipp Jurmeister, David Horst, Lukas Ruff, Klaus-Robert M\"uller, Frederick Klauschen, Andrew Norgan
Abstract: Pathology foundation models substantially advanced the possibilities in computational pathology --- yet tradeoffs in terms of performance, robustness, and computational requirements remained, which limited their clinical deployment. In this report, we present Atlas 2, Atlas 2-B, and Atlas 2-S, three pathology vision foundation models which bridge these shortcomings by showing state-of-the-art prediction performance, robustness, and resource efficiency in a comprehensive evaluation across eighty public benchmarks. Our models were trained on the largest pathology foundation model dataset to date comprising 5.5 million histopathology whole slide images, collected from three medical institutions Charit\'e - Universit\"atsmedizin Berlin, LMU Munich, and Mayo Clinic.
Authors: Sharan Sahu, Cameron J. Hogan, Martin T. Wells
Abstract: In this paper, we provide a comprehensive theoretical analysis of Stochastic Gradient Descent (SGD) and its momentum variants (Polyak Heavy-Ball and Nesterov) for tracking time-varying optima under strong convexity and smoothness. Our finite-time bounds reveal a sharp decomposition of tracking error into transient, noise-induced, and drift-induced components. This decomposition exposes a fundamental trade-off: while momentum is often used as a gradient-smoothing heuristic, under distribution shift it incurs an explicit drift-amplification penalty that diverges as the momentum parameter $\beta$ approaches 1, yielding systematic tracking lag. We complement these upper bounds with minimax lower bounds under gradient-variation constraints, proving this momentum-induced tracking penalty is not an analytical artifact but an information-theoretic barrier: in drift-dominated regimes, momentum is unavoidably worse because stale-gradient averaging forces systematic lag. Our results provide theoretical grounding for the empirical instability of momentum in dynamic settings and precisely delineate regime boundaries where vanilla SGD provably outperforms its accelerated counterparts.
Authors: Xiaofeng Luo, Jiayi He, Jiawen Kang, Ruichen Zhang, Zhaoshui He, Ekram Hossain, Dong In Kim
Abstract: The emergence of 6G-enabled vehicular metaverses enables Autonomous Vehicles (AVs) to operate across physical and virtual spaces through space-air-ground-sea integrated networks. The AVs can deploy AI agents powered by large AI models as personalized assistants, on edge servers to support intelligent driving decision making and enhanced on-board experiences. However, such cross-reality interactions may cause serious location privacy risks, as adversaries can infer AV trajectories by correlating the location reported when AVs request LBS in reality with the location of the edge servers on which their corresponding AI agents are deployed in virtuality. To address this challenge, we design a cross-reality location privacy protection framework based on hybrid actions, including continuous location perturbation in reality and discrete privacy-aware AI agent migration in virtuality. In this framework, a new privacy metric, termed cross-reality location entropy, is proposed to effectively quantify the privacy levels of AVs. Based on this metric, we formulate an optimization problem to optimize the hybrid action, focusing on achieving a balance between location protection, service latency reduction, and quality of service maintenance. To solve the complex mixed-integer problem, we develop a novel LLM-enhanced Hybrid Diffusion Proximal Policy Optimization (LHDPPO) algorithm, which integrates LLM-driven informative reward design to enhance environment understanding with double Generative Diffusion Models-based policy exploration to handle high-dimensional action spaces, thereby enabling reliable determination of optimal hybrid actions. Extensive experiments on real-world datasets demonstrate that the proposed framework effectively mitigates cross-reality location privacy leakage for AVs while maintaining strong user immersion within 6G-enabled vehicular metaverse scenarios.
Authors: Rui-Juan Jing, Yuegang Zhao, Changbo Chen
Abstract: Symbolic computation, powered by modern computer algebra systems, has important applications in mathematical reasoning through exact deep computations. The efficiency of symbolic computation is largely constrained by such deep computations in high dimension. This creates a fundamental barrier on labelled data acquisition if leveraging supervised deep learning to accelerate symbolic computation. Cylindrical algebraic decomposition (CAD) is a pillar symbolic computation method for reasoning with first-order logic formulas over reals with many applications in formal verification and automatic theorem proving. Variable orderings have a huge impact on its efficiency. Impeded by the difficulty to acquire abundant labelled data, existing learning-based approaches are only competitive with the best expert-based heuristics. In this work, we address this problem by designing a series of intimately connected tasks for which a large amount of annotated data can be easily obtained. We pre-train a Transformer model with these data and then fine-tune it on the datasets for CAD ordering. Experiments on publicly available CAD ordering datasets show that on average the orderings predicted by the new model are significantly better than those suggested by the best heuristic methods.
Authors: Muhammad Ahmed Atif, Nehal Naeem Haji, Mohammad Shahid Shaikh, Muhammad Ebad Atif
Abstract: Centralized value learning underlies a broad class of multi-agent reinforcement learning methods, but its claimed advantage is typically evaluated in settings that confound coordination structure with function approximation and partial observability. We isolate coordination structure in a fully tabular 8x8 predator-prey gridworld with explicit speed and stamina constraints, comparing all four pairings of Independent and Centralized Q-Learning across three kinematic regimes over 10 seeds. Fully independent learning (IQL-IQL) yields shorter episodes and higher predator returns than the fully centralized configuration (CQL-CQL) in every regime and every seed (Wilcoxon p = 0.00195, Cliff's delta = 1.0). Asymmetric IQL-CQL pairings produce coordination breakdowns that persist across the 40,000 episode training budget rather than resolving as transient instability. A best-response test against frozen IQL-IQL predators shows that even the strongest configuration has not converged to equilibrium at 40k episodes, so between-configuration differences reflect learning dynamics under a shared budget rather than end-state performance. We propose a mechanism we call temporal synchronization lock: a shared value function couples all agent decisions, so when one agent is stamina-limited the joint Q-value forces capable partners into suboptimal waits, while independent learners continue asynchronous pursuit. Because this pathology arises from credit assignment rather than function approximation, we conjecture analogous effects may arise in deep MARL methods that centralize credit during training. Centralized coordination is not uniformly beneficial; its advantage over independent learning shrinks or disappears under embodiment constraints, and mixed centralized-independent pairings can perform worse than either uniform choice.
Authors: Anselm Strohmaier, Samira B\"odefeld, Oliver Straser, Frank Reinhold
Abstract: The capabilities of generative AI in mathematics education are rapidly evolving, posing significant challenges for research to keep pace. Research syntheses remain scarce and risk being outdated by the time of publication. To address this issue, we present a Living Meta-Analysis (LIMA) on the effects of generative AI-based interventions for learning mathematics. Following PRISMA-LSR guidelines, we continuously update the literature base, apply a Bayesian multilevel meta-regression model to account for nested and cumulative data, and publish updated versions on a preprint server at regular intervals. This paper reports results from the fourth version, including 27 studies, 5 of which were newly included since the third version. Analyses indicate an overall positive effect (g = 0.49, CrI [0.24, 0.75]) and no publication bias. Moderator analyses indicate strong evidence that generative AI is substantially more beneficial when it is implemented together with teacher instruction rather than replacing teachers. For other moderators, evidence is still inconclusive.
Authors: Soroosh Tayebi Arasteh, Mina Farajiamiri, Mahshad Lotfinia, Behrus Hinrichs-Puladi, Jonas Bienzeisler, Mohamed Alhaskir, Mirabela Rusu, Christiane Kuhl, Sven Nebelung, Daniel Truhn
Abstract: Differential privacy protects the patients whose images train medical imaging models, but it lowers diagnostic accuracy, and the initialization is the strongest known remedy. Practice increasingly favors large generic self-supervised encoders. Yet the pretraining objective and the pretraining domain are confounded in existing comparisons, so which one preserves utility under privacy is unknown, and the pretraining corpus is treated as public even when it holds patient images. We trained ConvNeXt classifiers with differentially private stochastic gradient descent from five initializations that vary the objective and the domain independently, at four privacy budgets and without privacy, and evaluated them locally on more than 590,000 chest radiographs from five external datasets in four countries. Supervised pretraining on chest radiographs ranked first in 24 of 25 dataset and budget combinations. Its lead over ImageNet grew from 2.5 to 14.6 points of macro-averaged area under the receiver operating characteristic curve as the budget tightened, and the domain effect exceeded the objective effect by a factor of 2.2 to 3.4. Pretraining that corpus privately cost about 5 points and, under privacy, still beat every public initialization. Low-rank adaptation removed about half the residual gap, and in-domain pretraining raised the worst-performing demographic subgroup. Under privacy, what a model was pretrained on outweighs how it was pretrained.
Authors: Vid Kocijan, Jinu Sunil, Jan Eric Lenssen, Viman Deb, Xinwei Xe, Federico Reyes Gomez, Matthias Fey, Jure Leskovec
Abstract: The purpose of predictive modeling on relational data is to predict future or missing values in a relational database, for example, future purchases of a user, risk of readmission of the patient, or the likelihood that a financial transaction is fraudulent. Typically powered by machine learning methods, predictive models are used in recommendations, financial fraud detection, supply chain optimization, and other systems, providing billions of predictions every day. However, training a machine learning model requires manual work to extract the required training examples - prediction entities and target labels - from the database, which is slow, laborious, and prone to mistakes. Here, we present the Predictive Query Language (PQL), an SQL-inspired declarative language for defining predictive tasks on relational databases. PQL allows specifying a predictive task in a single declarative query, enabling the automatic computation of training labels for a large variety of machine learning tasks, such as regression, classification, time-series forecasting, and recommender systems. PQL is already successfully integrated and used in a collection of use cases as part of a predictive AI platform. The versatility of the language can be demonstrated through its many ongoing use cases, including financial fraud, item recommendations, and workload prediction. We demonstrate its versatile design through two implementations; one for small-scale, low-latency use and one that can handle large-scale databases.
Authors: Yangxinyu Xie, Tao Wang, Soham Mallick, Yan Sun, Georgy Noarov, Mengxin Yu, Tanwi Mallick, Edgar Dobriban
Abstract: While LLMs have seen substantial improvement in reasoning capabilities, they also sometimes overthink, generating unnecessary reasoning steps, particularly under uncertainty, given ill-posed or ambiguous queries. We introduce statistically principled early stopping methods that monitor uncertainty signals during generation to mitigate this issue. Our first approach is parametric: it models inter-arrival times of uncertainty keywords as a renewal process and applies sequential testing for stopping. Our second approach is nonparametric and provides finite-sample guarantees on the probability of halting too early on well-posed queries. We conduct empirical evaluations on reasoning tasks across several domains and models. Our results indicate that uncertainty-aware early stopping can improve both efficiency and reliability in LLM reasoning, and we observe especially significant gains for math reasoning.
Authors: Nikolaos Al. Papadopoulos, Ismael Tito Freire, Marti Sanchez-Fibla, Konstantinos E. Psannis
Abstract: Repeated multi-agent interactions require evaluation metrics that capture not only payoff distributions but also their temporal organization. Conventional outcome-based fairness measures can assign similar aggregate scores to temporally distinct coordination patterns, obscuring whether access to a shared resource is genuinely rotating or persistently monopolized. We study this problem in the Honey-Jar Game (HJG), a minimally dynamic repeated threshold-congestion Markov game in which n agents compete for exclusive access to a single high-reward resource. We introduce Perfect Alternation (PA), a reference turn-taking regime corresponding to the n-periodic round-robin picking sequence, together with six novel Alternation (ALT) metrics and a benchmarking methodology mapping ALT values to interpretable PA-equivalent performance. Using Q-learning agents as a minimal adaptive baseline against analytically derived random-policy baselines, we uncover a clear measurement failure: despite deceptively high traditional metrics (e.g., reward fairness often exceeding 0.9), learned policies perform worse than random on every ALT metric, by 34-74% on CALT and up to 92% on EALT, with PA-equivalent coordination falling to roughly one-fifth of the population at n=10. EALT further reveals two distinct failure patterns: without episodic memory (Type-A), the deficit grows from -20% at n=2 to -92% at n=10; with episodic memory (Type-B), it reaches a trough of -76% at n=5 before partially recovering to -10% at n=10. Conventional efficiency and fairness metrics do not reveal these differences. The ALT framework complements the temporal fair division and picking-sequence literature by diagnosing whether temporal fairness emerges spontaneously in decentralized adaptive systems rather than how to enforce it.
Authors: Hangyi Zhao
Abstract: We study contextual bilateral trade under full feedback when, conditionally on the context, trader valuations have bounded density but infinite variance. We first extend the self-bounding property of Bachoc et al. (ICML 2025) from bounded to real-valued valuations, showing that the expected regret of any price $\pi$ satisfies $E[g(m,V,W) - g(\pi,V,W)] \le L|m-\pi|^2$ under bounded density and finite first moments alone. Combining this with truncated-mean estimation, we prove that an epoch-based algorithm achieves regret $\widetilde{O}(T^{1-2\beta(p-1)/(\beta p + d(p-1))})$ when the noise has finite $p$-th moment for $p \in (1,2)$ and the market value function is $\beta$-H\"older, and we establish a matching $\Omega(\cdot)$ lower bound via Assouad's method with a fixed-support mixture construction. Our results characterize the minimax rate in $T$ for this problem up to logarithmic factors, interpolating between the classical nonparametric rate at $p=2$ and the trivial linear rate as $p \to 1^+$. Finally, we show these rates are achievable by fully parameter-free algorithms: median-of-means pricing attains the parametric oracle rate with no knowledge of $(p, \sigma_p)$ or the parameter norm, and a cell-width tournament extends this jointly to the tail and smoothness parameters when $\beta \le d$ -- under full feedback, tail-adaptivity is free.
Authors: Gil Kur, Pierre Bizeul
Abstract: The minimum-norm interpolator (MNI) framework has recently attracted considerable attention as a tool for understanding generalization in overparameterized models, such as neural networks. In this work, we study the MNI under a $2$-uniform convexity assumption, which is weaker than requiring the norm to be induced by an inner product; in this setting, the MNI typically does not admit a closed-form solution. At a high level, we show that this condition yields an upper bound on the MNI bias in both linear and nonlinear models. We further show that this bound is sharp for overparameterized linear regression when the norm's unit ball is in isotropic or John's position and the covariates are i.i.d.\ sub-Gaussian, for example, when each covariate vector has i.i.d. Rademacher entries. Finally, under the same assumption on the covariates, we prove sharp generalization bounds for the $\ell_p$-MNI when $p \in \bigl(1 + C/\log d, 2\bigr]$. To the best of our knowledge, this is the \emph{first} work to establish sharp bounds for non-Gaussian covariates in linear models when the norm is not induced by an inner product. This work is deeply inspired by classical work on $K$-convexity and recent work on the geometry of $2$-uniformly convex and isotropic convex bodies.
Authors: Ralntion Komini, Aikaterini Mandilara, Georgios Maragkopoulos, Dimitris Syvridis
Abstract: We investigate variational quantum classifiers (VQCs) for land-cover classification from multispectral satellite imagery, adopting a feature-map perspective in which the quantum circuit defines a nonlinear data embedding while the readout determines how this representation is exploited. Using the EuroSAT-MS dataset, we perform a systematic one-vs-one evaluation across all class pairs under a controlled experimental protocol, comparing classical baselines (logistic regression, SVMs, neural networks) with VQCs employing both linear readout and quantum-kernel SVM strategies. Our results show that, while VQCs with linear readout do not outperform strong classical baselines such as RBF-SVM, the same trained quantum feature map can significantly improve performance when reused within a kernel-based decision framework. A qubit-count sweep further reveals saturation effects consistent with the mismatch between exponential Hilbert space dimension and linear parameter scaling. Overall, our findings highlight that the effectiveness of quantum models depends critically on the interplay between representation and readout, and that meaningful gains may arise from combining learned quantum feature maps with classical decision mechanisms rather than seeking direct replacement of classical models.
Authors: Naomi Esposito, Anthony Tricarico, Luisa Porzio, Ali Aghazadeh Ardebili, Massimo Stella
Abstract: Understanding the impact of large language models (LLMs) on mathematics education requires data on LLMs' mathematical performance and biases. To this end, we introduce Math Education Digital Shadows (MEDS), a dataset mapping how LLMs reason about mathematics across human- and AI-like personifications. MEDS comprises 28,000 runs from 14 LLMs (i.e., Mistral, Qwen, DeepSeek, IBM Granite, Microsoft Phi, and xAI Grok) generated under human-shadow and AI-assistant conditions. Each record (digital shadow) includes a set of prompts; psychological and sociodemographic metadata; and four mathematics tasks: (i) interviews about relationships with mathematics, (ii) three psychometric questionnaires on mathematics self-efficacy and anxiety, (iii) one cognitive network capturing attitudes towards mathematics, and (iv) 18 high-school mathematics quiz items enriched with reasoning explanations and confidence scores. Analyses of the data show that LLMs exhibit differences in attitudes and performance across human-shadow and AI-assistant modes, including human-like negative attitudes towards mathematics, logical fallacies, and overconfidence in mathematics. As a data resource, MEDS can benefit learning scientists and developers of safer AI tutors in mathematics.
Authors: Jingxi Qiu, Zeyu Han, Cheng Huang
Abstract: Retrieval-augmented generation (RAG) grounds answers in retrieved passages, yet relevance does not guarantee sufficiency: a topical passage may still fail to justify the answer. We study evidence sufficiency verification for selective RAG answering, in which a verifier receives a question, a candidate answer, and retrieved evidence and decides whether the evidence supports, refutes, or is insufficient for the answer, answering only when support is established. We present SURE-RAG, an aggregation protocol that treats evidence sufficiency as a set-level property: missing hops and unresolved conflicts cannot be detected by scoring passages independently. A shared claim-evidence verifier produces a local relation distribution for each (claim, passage) pair, which SURE-RAG aggregates into four interpretable answer-level feature blocks (coverage, relation strength, uncertainty, and retrieval), producing a three-way decision and an auditable selective score. We evaluate on HotpotQA-RAG v3, a controlled multi-hop benchmark, under an artifact-aware protocol (shortcut baselines, counterfactual swaps, no-oracle checks, and GPT-4o audits). Calibrated SURE-RAG attains 0.9075 Macro-F1 (raw 0.8951 +/- 0.0069), well above DeBERTa mean-pooling (0.6516) and a GPT-4o judge (0.7284), and on par with a strong concat cross-encoder (0.8888 +/- 0.0109) while remaining fully auditable. At 30% coverage, risk falls from 0.2588 to 0.1642, a 37% relative reduction. As a boundary-mapping experiment, we contrast SURE-RAG with GPT-4o on HaluBench unsafe detection: the ranking reverses (0.3343 vs. 0.7389 unsafe-F1), indicating that controlled sufficiency verification and natural hallucination detection are distinct problems.
Authors: Anthony Stephenson
Abstract: We present a theoretically grounded Gaussian process framework that leverages neural feature maps to construct expressive kernels. We show that the learned feature map can be interpreted as an optimal low-rank approximation to a Gram matrix derived from an implied RKHS, from which we establish consistency of the GP posterior. We further analyse the spectral properties of the induced kernels and introduce product feature-map kernels to address oversmoothing. This simple yet powerful approach enables fast, scalable, and accurate exact GP inference with minimal upfront work. The flexibility of kernel design supports seamless application to both regression and classification tasks across diverse data modalities, including tabular inputs and structured domains such as images. On benchmark datasets, this approach surpasses pre-existing methods in terms of accuracy and training and prediction efficiency.
Authors: Oliver Hennh\"ofer, Maximilian Kirsch, Christine Preisach
Abstract: Most anomaly detection systems output scores rather than calibrated decisions, leaving practitioners to choose thresholds heuristically and without clear statistical interpretation. Conformal anomaly detection addresses this limitation by converting anomaly scores into calibrated p-values that are valid under the statistical assumption of data exchangeability, with a growing literature extending this idea beyond that setting. We present nonconform, a Python package for applying conformal anomaly detection within existing machine-learning workflows, and use it as the basis for an implementation-grounded introduction to the field. The package integrates with scikit-learn, pyod, and custom anomaly detectors, and provides a unified interface for calibration, p-value generation, and false discovery rate control. It supports several conformalization strategies, ranging from simple split-conformal calibration to more data-efficient and shift-aware extensions. Through a progression from foundational concepts to advanced conformalization strategies, complemented by code examples, the paper connects the statistical ideas behind conformal anomaly detection to their practical use in nonconform. Empirical results demonstrate that the implemented methods enable statistically principled anomaly detection. Together, the package and exposition aim to make core conformal anomaly detection workflows more accessible and reproducible in experimental and production-oriented settings.
Authors: Yunfei Yang, Jun Fan
Abstract: This paper studies how efficiently deep ReLU neural networks can approximate and learn smooth functions. When the error is measured in $L^p([0,1]^d)$ norm and the approximator is a network with width $W$ and depth $L$, recent works have proven the supper approximation rate $\mathcal{O}((WL)^{-2s/d})$ for Besov space $\mathcal{B}^s_{q,r}([0,1]^d)$ under the Sobolev embedding condition $s/d>1/q-1/p$. In order to overcome the curse of dimensionality in this rate, we extent this result to anisotropic and mixed smooth function classes. We establish the approximation rate $\mathcal{O}((WL)^{-2\tilde{s}})$ for anisotropic Besov space $\mathcal{B}^{\boldsymbol{s}}_{q,r}([0,1]^d)$ with anisotropic smoothness $\boldsymbol{s}=(s_1,\dots,s_d)$ under the embedding condition $\tilde{s} > 1/q-1/p$, where the mean smoothness $\tilde{s} = (\sum_{i=1}^d s_i^{-1})^{-1}$. For mixed smooth Besov space $\mathcal{MB}^s_{q,r}([0,1]^d)$ with mixed smoothness $s>1/q-1/p$, we show that the approximation rate $\mathcal{O}((WL)^{-2s})$ holds up to logarithmic factors. Using these results, we also derive approximation bounds for the composition of anisotropic Besov functions. As an application, it is shown that deep ReLU neural networks can achieve minimax optimal rates up to logarithmic factors for a wide range of smooth function classes.
Authors: Zach Moczkodan (Royal Military College of Canada, Kingston, Canada), Hany Ragab (Royal Military College of Canada, Kingston, Canada)
Abstract: Recent deep learning approaches for network intrusion detection increasingly incorporate temporal architectures such as recurrent networks and Transformers, often reporting near-perfect performance on CIC-IDS2017. However, many existing studies neither supply their temporal modules with genuine sequence inputs nor evaluate under realistic, leakage-free conditions, making it unclear whether reported gains arise from true sequence-modelling capability. In this work, we reformulate CIC-IDS2017 as a temporal intrusion-detection task by constructing ordered flow sequences from network conversations and benchmarking nine classical and deep learning architectures under a random split, two leakage-free splits, and a padding-scheme ablation. The central finding is that padding convention, not architecture, determines the Transformer's performance: on genuinely sequential (non-padded) windows the Transformer achieves the highest macro-F1 of any model in the experiment ($0.89$), yet under zero-pad+mask evaluation it drops markedly while LSTM, GRU, and 1D-CNN remain stable and a class-balanced Random Forest is the most robust model overall. The same repeat-last padding cue masks a $67\times$ increase in the Transformer's false-alarm rate that only leakage-free evaluation reveals. Evaluation methodology -- specifically padding convention and split protocol -- thus has a larger effect on reported performance than architectural choice. We advocate for leakage-free splits, explicit padding disclosure, and sequence-aware benchmarking as standard practice in future IDS research. Our code and implementation details are available here: https://github.com/zachmocz/temporal-ids-bench.
Authors: Greg Ongie, Rahul Parhi
Abstract: We develop a general framework for analyzing representation costs induced by parameter-space regularizers in data-fitting methods. For an arbitrary parametric method, we define its representation cost and native function space, prove existence, and identify conditions under which parameter-space and function-space problems have equal infimal values and minimizers transfer between them. This framework yields representer theorems and recovers classical formulations---including kernel methods and RKHSs, wavelets and Besov spaces, and shallow neural networks and variation spaces---as special cases. Our main new results concern depth-$L$ feedforward ReLU networks with weight-decay regularization. For these networks, we prove that the representation cost is a power of a quasi-seminorm and that, under suitable hypotheses, the native space is a quasi-Banach space with nonconvex unit ball when $L > 2$. These results identify a novel depth-dependent quasi-Banach function-space geometry induced by weight decay.
Authors: Irmak Bukey, Zachary Novack, Jongmin Jung, Dasaem Jeong, Chris Donahue
Abstract: Understanding music requires understanding localized relationships across data modalities, e.g., how time in performance audio maps onto position in a score image. Yet supervision for such local correspondences is difficult to obtain-in practice, we often only have access to coarser global supervision like paired segments of audio and images. To address this gap, we propose FuSiLi (Fused Sinkhorn-Localized Similarity), a similarity score for multimodal contrastive learning operating directly on local image patch and audio frame features via Sinkhorn-based soft alignment. We show that FuSiLi (i) effectively learns local relationships, (ii) requires only global supervision, and (iii) retains the global alignment capabilities of conventional contrastive approaches. We fine-tune pretrained CLIP and CLAP encoders on pairs of raw sheet music images and audio using a hybrid contrastive objective combining FuSiLi with conventional global similarity. We evaluate on cross-modal retrieval and frame-level alignment tasks against a range of global and local baselines, showing that our approach outperforms them on local alignment while remaining competitive on retrieval.
Authors: Jiarong Zhao, Zhikai Lei, Zhiheng Xi, Rui Zheng, Hang Yan, Jie Zhou, Qin Chen, Liang He
Abstract: Scaling executable agent training data for LLM post-training is bottlenecked by substrate-bound methods that tie task generation to predefined tools, repositories, or skill graphs: expanding coverage requires manual substrate engineering, each new domain demands a bespoke pipeline, and the resulting task distributions often reflect substrate biases rather than real-world demand. We introduce NexForge, a requirement-driven framework that takes high-level capability requirements as input and synthesizes diverse, executable agent tasks and expert trajectories for SFT. NexForge first investigates real-world demand to construct representative scenarios and task profiles, then performs distribution-aware compilation to generate task directives. For each directive, NexForge automatically retrieves or constructs the required files, dependencies, and runtime configurations, and finally synthesizes expert rollouts and produces training trajectories. Without domain-specific infrastructure, NexForge produces 3.6K terminal and 2K office tasks, improving Qwen3.5-35B-A3B Base from 22.5\% to 52.0\% on Terminal-Bench 2.0 and from 813 to 1338 Elo on GDPval; scaling further to 43.2K terminal tasks yields 58.4\%, on par with Claude Opus 4.6 equipped with Claude Code. Scaled further, NexForge-synthesized data contributes to the training of Nex-N2, a family of publicly available agent models that lift Qwen3.5-35B-A3B to 75.3\% on Terminal-Bench 2.1 and to 1585 Elo on GDPval---achieving state-of-the-art open-source performance and surpassing several frontier proprietary systems. Nex-N2 models are available at https://nex.sii.edu.cn/.
URLs: https://nex.sii.edu.cn/.
Authors: Boyuan Deng, Kshitiz Upadhyay, Michael Shields
Abstract: The Helmholtz equation governs time-harmonic wave propagation, and in dissipative media a complex modulus renders its squared wavenumber $\kappa^2$ complex. Inferring such fields from sparse, noisy data calls for solvers that also quantify their own uncertainty. Physics-informed Gaussian-process (GP) regression supplies this by returning a posterior over the solution, yet operator-conditioned formulations have been developed almost exclusively for real-valued fields. We extend operator-informed GP regression to complex-valued Helmholtz problems by realifying the complex operator into an equivalent coupled real block, which enables inference with standard real-valued GP conditioning. The construction admits a family of priors, from a proper diagonal prior to coregionalized and multiscale variants, and conditions on PDE residuals and boundary traces. On benchmark problems in one to three dimensions, the solver is competitive with finite-difference and neural-network baselines at a far smaller interior-constraint budget. Unlike those deterministic baselines, it returns a posterior over the complex wavefield rather than a point estimate. Applied to \textit{in vivo} brain magnetic resonance elastography, a proper multiscale prior reconstructs the shear curl field to a correlation of $0.77$ with measurement, above a $0.75$ target. The gain arises from the multiscale kernel rather than from real--imaginary coupling. We further identify a low-frequency accuracy ceiling set by model mismatch and a posterior uncertainty that is not yet calibrated. Calibrated uncertainty therefore emerges as the central next step for probabilistic wavefield inference in dissipative media.
Authors: Carson Rodrigues
Abstract: Brain-encoding foundation models predict fMRI responses to video, audio, and text well enough to win the Algonauts 2025 challenge. We ask whether their predicted responses, obtained with no scanner, are a useful feature lens for a downstream human-behavior task: forecasting the memorability of short videos. We project each clip into TRIBE v2's predicted cortical space and forecast short-term memorability with ridge regression, against a matched control: the model's own V-JEPA2 visual backbone taken before the brain projection. The answer is dataset-dependent, and cleanly so. Within Memento10k the backbone wins (Spearman 0.594 vs 0.544 for the brain projection); within VideoMem the brain projection wins (0.415 vs 0.368, delta +0.047, 95% CI [+0.009, +0.088]). Both within-dataset gaps have bootstrap intervals excluding zero, in opposite directions. Cross-dataset transfer inherits the split: trained on Memento10k and tested on VideoMem the brain projection beats the backbone (+0.076), while the reverse loses heavily (-0.311). Each representation transfers best onto the dataset it already fits better. The VideoMem advantage is not a sample-size artifact (it survives matched training size and a PCA-then-ridge pipeline) and not mere compression of the backbone (a compressed or heavily regularized backbone tops out below the brain projection, which also beats a transfer-tuned backbone, +0.053). So predicted-brain features carry a small but real memorability signal the backbone misses on one dataset and not the other: not a domain-general prior, but a dataset-specific representation. A vision-orthogonal component (partial Spearman 0.19, permutation p=2.5e-4) localizes to ventral occipito-temporal cortex. Code and predicted-response arrays are released; source videos and scores are not redistributed.
Authors: Maria Gragera Garces, Sabina Dr\u{a}goi, Lirand\"e Pira
Abstract: Circuit cutting promises to scale quantum computations beyond current hardware, but variational quantum advantage also requires low cutting overhead, classical hardness, and trainability. We show that these properties are strongly constrained by entanglement geometry. Matrix product state (MPS) and tree tensor network (TTN) circuits with constant seam bond dimension can be cut with \(O(1/\varepsilon^2)\) sampling overhead, but remain efficiently classically simulable, ruling out asymptotic quantum advantage within these families. By independently controlling seam and intra-block entanglement, we construct a two-block circuit family that remains cheaply cuttable while requiring a super-polynomial global MPS bond dimension, as supported numerically up to \(n=100\). However, MPS hardness and trainability require incompatible depth regimes, \(d=\omega(\log n)\) and \(d=O(\log n)\), respectively. Using magic rather than entanglement as the hardness resource avoids this conflict: shallow Clifford+\(T\) circuits remain cuttable and trainable while their stabiliser-simulation cost grows exponentially with the \(T\)-count.
Authors: Sijin Chen, Yinuo Ren, Heyang Zhao, Ziheng Cheng, Quanquan Gu, Lexing Ying
Abstract: Masked diffusion models (MDMs) are a promising family of language generators, but achieving high-quality few-step generation remains challenging. In MDMs, all forward trajectories collapse to a single fully masked state, leaving no terminal entropy for consistency-style few-step generation. While recent few-step alternatives based on uniform-state diffusion avoid this degeneracy, it becomes harder to distinguish clean tokens from noise than MDMs, which usually harms modeling quality and training efficiency. In this work, we propose a multi-mask diffusion model (MultiMDM) that preserves the masking structure towards few-step generation. In the forward process, each clean token is first pushed towards a designated mask and then gradually mixes over the mask set. As a result, the backward process has a drafting capability by predicting a designated mask before refining to a clean token. We derive a closed-form ELBO training objective for MultiMDM that supports continual training from pretrained MDMs. In addition, we formulate a purely discrete-state consistency distillation scheme, with a shared-Gumbel coupling to reduce pathwise entropy. Experiments on pretraining and distillation show that MultiMDM provides an effective foundation for principled few-step generation.
Authors: Raffi Khatchadourian
Abstract: A financial AI agent can repeat a decision while changing the tools, order, or recorded arguments and results used to reach it. Outcome-only evaluation misses this variation, even when it matters for replay and change control. DFAH-Bench operationalizes the Determinism-Faithfulness Assurance Harness (DFAH), where faithfulness means fidelity of observable execution under replay, not answer correctness. The protocol qualifies comparable, sufficiently observed replays and measures decision agreement (DAR) and tool-path agreement (TAR) over the same eligible groups. We analyze 4,157 retrospective episodes from configurations with observed tool use across 719 synthetic compliance and financial DataOps groups, together with an argument-aware prospective extension comprising 570 eligible episodes across 190 groups. In that extension, decisions agree 94.2-95.1% while exact tool-name paths agree 66.9-69.4%, producing 25.8-27.3 percentage-point gaps; argument-and-result trajectory agreement falls to 45.0-51.5%. Even among unanimous-decision groups, paths vary in 66.7-68.9% under task weighting. DFAH-Bench makes the execution behind a stable decision visible for replay, investigation, and change review.
Authors: Liu Zai (University of Glasgow), Yumeng Wang (Leiden University), Junchen Fu (University of Glasgow), Joemon M. Jose (University of Glasgow)
Abstract: Activation steering enables control and interpretation of LLMs, yet existing work primarily models personality through static trait frameworks such as the Big Five. We investigate whether personality can instead be represented and controlled as a set of cognitive processes using the eight Jungian Cognitive Functions. To this end, we introduce a framework comprising a Jungian evaluation protocol and a dataset of over 2,100 role-playing character narrations. Activation steering vector extraction and evaluation experiments on Llama-3.1-8B demonstrate effective monotonic control over all eight cognitive functions through activation steering. Beyond controllability, our analysis reveals that: 1. personality information is concentrated in middle transformer layers; 2. steering vectors exhibit structured geometric relationships consistent with distinctions between rational and irrational functions; 3. effective multi-dimensional steering directions cannot be recovered as linear combinations of single-function directions. These findings provide new insights into the representation of personality in LLM activation space and establish a framework for studying interpretable, effective, and multi-dimensional personality control.