Authors: Zeju Li, Yizhou Zhou, Qiang Xu
Abstract: Efficient long-context LLM deployment is stalled by a dichotomy between amortized compression, which struggles with out-of-distribution generalization, and Test-Time Training, which incurs prohibitive synthetic data costs and requires modifying model weights, creating stateful parameters that complicate concurrent serving. We propose Latent Context Compilation, a framework that fundamentally shifts context processing from adaptation to compilation. By utilizing a disposable LoRA module as a compiler, we distill long contexts into compact buffer tokens -- stateless, portable memory artifacts that are plug-and-play compatible with frozen base models. Crucially, we introduce a self-aligned optimization strategy that eliminates the need for synthetic context-relevant QA pairs. By regularizing context reconstruction task with context-agnostic random queries, we force compressed tokens to reside within the model's existing instruction-following manifold. Experiments with Llama-3.1-8B demonstrate that Latent Context Compilation preserves fine-grained details and reasoning capabilities where prior methods falter, effectively decoupling memory density from model parameters even at a 16x compression ratio.
Authors: Ramchand Kumaresan
Abstract: We present ACAR (Adaptive Complexity and Attribution Routing), a measurement framework for studying multi-model orchestration under auditable conditions. ACAR uses self-consistency variance (sigma) computed from N=3 probe samples to route tasks across single-model, two-model, and three-model execution modes. The system is implemented on top of TEAMLLM, a deterministic execution substrate with immutable artifacts and complete decision traces. We evaluate ACAR on 1,510 tasks spanning four benchmarks: MathArena, Reasoning Gym, LiveCodeBench, and SuperGPQA, using Claude Sonnet 4, GPT-4o, and Gemini 2.0 Flash, producing more than 7,550 auditable runs. Results show that sigma-based routing achieves 55.6 percent accuracy, exceeding the two-model baseline of 54.4 percent while avoiding full ensembling on 54.2 percent of tasks. The routing mechanism is model-agnostic and requires no learned components. We also document negative results. First, retrieval augmentation reduced accuracy by 3.4 percentage points, as median retrieval similarity was only 0.167, demonstrating that experience injection without semantic alignment introduces noise rather than grounding. Second, when models agree on incorrect answers (sigma equals zero), no downstream ensemble can recover; this agreement-but-wrong failure mode is intrinsic to self-consistency and bounds achievable accuracy at approximately eight percentage points below full ensembling. Third, attribution estimates based on proxy signals such as response similarity and entropy showed weak correlation with ground-truth leave-one-out values, indicating that practical attribution requires explicit counterfactual computation. This work documents which assumptions fail in practice and provides falsifiable baselines for future research on routing, retrieval, and multi-model attribution.
Authors: Sumin Han, Jisun An, Dongman Lee
Abstract: Urban vibrancy reflects the dynamic human activity within urban spaces and is often measured using mobile data that captures floating population trends. This study proposes a novel approach to derive Urban Vibrancy embeddings from real-time floating population data to enhance traffic prediction models. Specifically, we utilize variational autoencoders (VAE) to compress this data into actionable embeddings, which are then integrated with long short-term memory (LSTM) networks to predict future embeddings. These are subsequently applied in a sequence-to-sequence framework for traffic forecasting. Our contributions are threefold: (1) We use principal component analysis (PCA) to interpret the embeddings, revealing temporal patterns such as weekday versus weekend distinctions and seasonal patterns; (2) We propose a method that combines VAE and LSTM, enabling forecasting dynamic urban knowledge embedding; and (3) Our approach improves accuracy and responsiveness in traffic prediction models, including RNN, DCRNN, GTS, and GMAN. This study demonstrates the potential of Urban Vibrancy embeddings to advance traffic prediction and offer a more nuanced analysis of urban mobility.
Authors: Rui Cen, QiangQiang Hu, Hong Huang, Hong Liu, Song Liu, Xin Luo, Lin Niu, Yifan Tan, Decheng Wu, Linchuan Xie, Rubing Yang, Guanghua Yu, Jianchen Zhu
Abstract: This technical report introduces AngelSlim, a comprehensive and versatile toolkit for large model compression developed by the Tencent Hunyuan team. By consolidating cutting-edge algorithms, including quantization, speculative decoding, token pruning, and distillation. AngelSlim provides a unified pipeline that streamlines the transition from model compression to industrial-scale deployment. To facilitate efficient acceleration, we integrate state-of-the-art FP8 and INT8 Post-Training Quantization (PTQ) algorithms alongside pioneering research in ultra-low-bit regimes, featuring HY-1.8B-int2 as the first industrially viable 2-bit large model. Beyond quantization, we propose a training-aligned speculative decoding framework compatible with multimodal architectures and modern inference engines, achieving 1.8x to 2.0x throughput gains without compromising output correctness. Furthermore, we develop a training-free sparse attention framework that reduces Time-to-First-Token (TTFT) in long-context scenarios by decoupling sparse kernels from model architectures through a hybrid of static patterns and dynamic token selection. For multimodal models, AngelSlim incorporates specialized pruning strategies, namely IDPruner for optimizing vision tokens via Maximal Marginal Relevance and Samp for adaptive audio token merging and pruning. By integrating these compression strategies from low-level implementations, AngelSlim enables algorithm-focused research and tool-assisted deployment.
Authors: Wang Zixian
Abstract: We present Group Orthogonalized Policy Optimization (GOPO), a new alignment algorithm for large language models derived from the geometry of Hilbert function spaces. Instead of optimizing on the probability simplex and inheriting the exponential curvature of Kullback-Leibler divergence, GOPO lifts alignment into the Hilbert space L2(pi_k) of square-integrable functions with respect to the reference policy. Within this space, the simplex constraint reduces to a linear orthogonality condition
Authors: Jianneng Yu, Alexandre V. Morozov
Abstract: Neural networks are trained by optimizing multi-dimensional sets of fitting parameters on non-convex loss landscapes. Low-loss regions of the landscapes correspond to the parameter sets that perform well on the training data. A key issue in machine learning is the performance of trained neural networks on previously unseen test data. Here, we investigate neural network training by stochastic gradient descent (SGD) - a non-convex global optimization algorithm which relies only on the gradient of the objective function. We contrast SGD solutions with those obtained via a non-stochastic quasi-Newton method, which utilizes curvature information to determine step direction and Golden Section Search to choose step size. We use several computational tools to investigate neural network parameters obtained by these two optimization methods, including kernel Principal Component Analysis and a novel, general-purpose algorithm for finding low-height paths between pairs of points on loss or energy landscapes, FourierPathFinder. We find that the choice of the optimizer profoundly affects the nature of the resulting solutions. SGD solutions tend to be separated by lower barriers than quasi-Newton solutions, even if both sets of solutions are regularized by early stopping to ensure adequate performance on test data. When allowed to fit extensively on the training data, quasi-Newton solutions occupy deeper minima on the loss landscapes that are not reached by SGD. These solutions are less generalizable to the test data however. Overall, SGD explores smooth basins of attraction, while quasi-Newton optimization is capable of finding deeper, more isolated minima that are more spread out in the parameter space. Our findings help understand both the topography of the loss landscapes and the fundamental role of landscape exploration strategies in creating robust, transferrable neural network models.
Authors: Hadi Khalaf, Serena L. Wang, Daniel Halpern, Itai Shapira, Flavio du Pin Calmon, Ariel D. Procaccia
Abstract: The standard way to evaluate language models on subjective tasks is through pairwise comparisons: an annotator chooses the "better" of two responses to a prompt. Leaderboards aggregate these comparisons into a single Bradley-Terry (BT) ranking, forcing heterogeneous preferences into a total order and violating basic social-choice desiderata. In contrast, social choice theory provides an alternative approach called maximal lotteries, which aggregates pairwise preferences without imposing any assumptions on their structure. However, we show that maximal lotteries are highly sensitive to preference heterogeneity and can favor models that severely underperform on specific tasks or user subpopulations. We introduce robust lotteries that optimize worst-case performance under plausible shifts in the preference data. On large-scale preference datasets, robust lotteries provide more reliable win rate guarantees across the annotator distribution and recover a stable set of top-performing models. By moving from rankings to pluralistic sets of winners, robust lotteries offer a principled step toward an ecosystem of complementary AI systems that serve the full spectrum of human preferences.
Authors: Elizabeth S. Z. Tan, Adil Soubki, Miles Cranmer
Abstract: Symbolic distillation replaces neural networks, or components thereof, with interpretable, closed-form mathematical expressions. This approach has shown promise in discovering physical laws and mathematical relationships directly from trained deep learning models, yet adoption remains limited due to the engineering barrier of integrating symbolic regression into deep learning workflows. We introduce SymTorch, a library that automates this distillation by wrapping neural network components, collecting their input-output behavior, and approximating them with human-readable equations via PySR. SymTorch handles the engineering challenges that have hindered adoption: GPU-CPU data transfer, input-output caching, model serialization, and seamless switching between neural and symbolic forward passes. We demonstrate SymTorch across diverse architectures including GNNs, PINNs and transformer models. Finally, we present a proof-of-concept for accelerating LLM inference by replacing MLP layers with symbolic surrogates, achieving an 8.3\% throughput improvement with moderate performance degradation.
Authors: Guancheng Tu, Shiyang Zhang, Tianyu Zhang, Yi Zhang, Diji Yang
Abstract: Large Language Models (LLMs) are converging towards a singular Artificial Hivemind, where shared Nature (pre-training priors) result in a profound collapse of distributional diversity, limiting the distinct perspectives necessary for creative exploration and scientific discovery. To address this, we propose to equip models with inference-time Nurture (individualized epistemic trajectories) using Epistemic Evolution paradigm, progressing through explore, internalize, and express. We instantiate this via PRISM (Pluralistic Reasoning via In-context Structure Modeling), a model-agnostic system that augments LLM with dynamic On-the-fly Epistemic Graphs. On three creativity benchmarks, PRISM achieves state-of-the-art novelty and significantly expands distributional diversity. Moreover, we evaluate the real-world utility via a challenging rare-disease diagnosis benchmark. Results demonstrate that PRISM successfully uncovers correct long-tail diagnoses that standard LLM miss, confirming that its divergence stems from meaningful exploration rather than incoherent noise. Overall, this work establishes a new paradigm for Pluralistic AI, moving beyond monolithic consensus toward a diverse ecosystem of unique cognitive individuals capable of collective, multi-perspective discovery.
Authors: Marion Neumeier, Niklas Ro{\ss}berg, Michael Botsch, Wolfgang Utschick
Abstract: Accurate and uncertainty-aware trajectory prediction remains a core challenge for autonomous driving, driven by complex multi-agent interactions, diverse scene contexts and the inherently stochastic nature of future motion. Diffusion-based generative models have recently shown strong potential for capturing multimodal futures, yet existing approaches such as cVMD suffer from slow sampling, limited exploitation of generative diversity and brittle scenario encodings. This work introduces cVMDx, an enhanced diffusion-based trajectory prediction framework that improves efficiency, robustness and multimodal predictive capability. Through DDIM sampling, cVMDx achieves up to a 100x reduction in inference time, enabling practical multi-sample generation for uncertainty estimation. A fitted Gaussian Mixture Model further provides tractable multimodal predictions from the generated trajectories. In addition, a CVQ-VAE variant is evaluated for scenario encoding. Experiments on the publicly available highD dataset show that cVMDx achieves higher accuracy and significantly improved efficiency over cVMD, enabling fully stochastic, multimodal trajectory prediction.
Authors: Emre Can Acikgoz, Cheng Qian, Jonas H\"ubotter, Heng Ji, Dilek Hakkani-T\"ur, Gokhan Tur
Abstract: Large language models (LLMs) are becoming the foundation for autonomous agents that can use tools to solve complex tasks. Reinforcement learning (RL) has emerged as a common approach for injecting such agentic capabilities, but typically under tightly controlled training setups. It often depends on carefully constructed task-solution pairs and substantial human supervision, which creates a fundamental obstacle to open-ended self-evolution toward superintelligent systems. In this paper, we propose Tool-R0 framework for training general purpose tool-calling agents from scratch with self-play RL, under a zero-data assumption. Initialized from the same base LLM, Tool-R0 co-evolves a Generator and a Solver with complementary rewards: one proposes targeted challenging tasks at the other's competence frontier and the other learns to solve them with real-world tool calls. This creates a self-evolving cycle that requires no pre-existing tasks or datasets. Evaluation on different tool-use benchmarks show that Tool-R0 yields 92.5 relative improvement over the base model and surpasses fully supervised tool-calling baselines under the same setting. Our work further provides empirical insights into self-play LLM agents by analyzing co-evolution, curriculum dynamics, and scaling behavior.
Authors: Quan Xiao, Jindan Li, Zhaoxian Wu, Tayfun Gokmen, Tianyi Chen
Abstract: Analog in-memory computing (AIMC) performs computation directly within resistive crossbar arrays, offering an energy-efficient platform to scale large vision and language models. However, non-ideal analog device properties make the training on AIMC devices challenging. In particular, its update asymmetry can induce a systematic drift of weight updates towards a device-specific symmetric point (SP), which typically does not align with the optimum of the training objective. To mitigate this bias, most existing works assume the SP is known and pre-calibrate it to zero before training by setting the reference point as the SP. Nevertheless, calibrating AIMC devices requires costly pulse updates, and residual calibration error can directly degrade training accuracy. In this work, we present the first theoretical characterization of the pulse complexity of SP calibration and the resulting estimation error. We further propose a dynamic SP estimation method that tracks the SP during model training, and establishes its convergence guarantees. In addition, we develop an enhanced variant based on chopping and filtering techniques from digital signal processing. Numerical experiments demonstrate both the efficiency and effectiveness of the proposed method.
Authors: Elbert Du, Cynthia Dwork, Lunjia Hu, Reid McIlroy-Young, Han Shao, Linjun Zhang
Abstract: Individuals with similar qualifications and skills may vary in their demeanor, or outward manner: some tend toward self-promotion while others are modest to the point of omitting crucial information. Comparing the self-descriptions of equally qualified job-seekers with different self-presentation styles is therefore problematic. We build an interactive AI for skill elicitation that provides accurate determination of skills while simultaneously allowing individuals to speak in their own voice. Such a system can be deployed, for example, when a new user joins a professional networking platform, or when matching employees to needs during a company reorganization. To obtain sufficient training data, we train an LLM to act as synthetic humans. Elicitation mitigates endogenous bias arising from individuals' own self-reports. To address systematic model bias we enforce a mathematically rigorous notion of equitability ensuring that the covariance between self-presentation manner and skill evaluation error is small.
Authors: Teodor Vanislavov Marinov, Mehryar Mohri, Princewill Okoroafor, Jon Schneider, Julian Zimmert
Abstract: We study the problem of opportunistic approachability: a generalization of Blackwell approachability where the learner would like to obtain stronger guarantees (i.e., approach a smaller set) when their adversary limits themselves to a subset of their possible action space. Bernstein et al. (2014) introduced this problem in 2014 and presented an algorithm that guarantees sublinear approachability rates for opportunistic approachability. However, this algorithm requires the ability to produce calibrated online predictions of the adversary's actions, a problem whose standard implementations require time exponential in the ambient dimension and result in approachability rates that scale as $T^{-O(1/d)}$. In this paper, we present an efficient algorithm for opportunistic approachability that achieves a rate of $O(T^{-1/4})$ (and an inefficient one that achieves a rate of $O(T^{-1/3})$), bypassing the need for an online calibration subroutine. Moreover, in the case where the dimension of the adversary's action set is at most two, we show it is possible to obtain the optimal rate of $O(T^{-1/2})$.
Authors: Jack Goffinet, Casey Hanks, David E. Carlson
Abstract: Representing the past in a compressed, efficient, and informative manner is a central problem for systems trained on sequential data. The HiPPO framework, originally proposed by Gu & Dao et al., provides a principled approach to sequential compression by projecting signals onto orthogonal polynomial (OP) bases via structured linear ordinary differential equations. Subsequent works have embedded these dynamics in state space models (SSMs), where HiPPO structure serves as an initialization. Nonlinear successors of these SSM methods such as Mamba are state-of-the-art for many tasks with long-range dependencies, but the mechanisms by which they represent and prioritize history remain largely implicit. In this work, we revisit the HiPPO framework with the goal of making these mechanisms explicit. We show how polynomial representations of history can be extended to support capabilities of modern SSMs such as adaptive allocation of memory and associative memory while retaining direct interpretability in the OP basis. We introduce a unified framework comprising five such extensions, which we collectively refer to as a "HiPPO zoo." Each extension exposes a specific modeling capability through an explicit, interpretable modification of the HiPPO framework. The resulting models adapt their memory online and train in streaming settings with efficient updates. We illustrate the behaviors and modeling advantages of these extensions through a range of synthetic sequence modeling tasks, demonstrating that capabilities typically associated with modern SSMs can be realized through explicit, interpretable polynomial memory structures.
Authors: Nikolaos Nakis, Chrysoula Kosma, Panagiotis Promponas, Michail Chatzianastasis, Giannis Nikolentzos
Abstract: Representation learning has been essential for graph machine learning tasks such as link prediction, community detection, and network visualization. Despite recent advances in achieving high performance on these downstream tasks, little progress has been made toward self-explainable models. Understanding the patterns behind predictions is equally important, motivating recent interest in explainable machine learning. In this paper, we present GraphHull, an explainable generative model that represents networks using two levels of convex hulls. At the global level, the vertices of a convex hull are treated as archetypes, each corresponding to a pure community in the network. At the local level, each community is refined by a prototypical hull whose vertices act as representative profiles, capturing community-specific variation. This two-level construction yields clear multi-scale explanations: a node's position relative to global archetypes and its local prototypes directly accounts for its edges. The geometry is well-behaved by design, while local hulls are kept disjoint by construction. To further encourage diversity and stability, we place principled priors, including determinantal point processes, and fit the model under MAP estimation with scalable subsampling. Experiments on real networks demonstrate the ability of GraphHull to recover multi-level community structure and to achieve competitive or superior performance in link prediction and community detection, while naturally providing interpretable predictions.
Authors: Charafeddine Mouzouni
Abstract: Given a black-box AI system and a task, at what confidence level can a practitioner trust the system's output? We answer with a reliability level -- a single number per system-task pair, derived from self-consistency sampling and conformal calibration, that serves as a black-box deployment gate with exact, finite-sample, distribution-free guarantees. Self-consistency sampling reduces uncertainty exponentially; conformal calibration guarantees correctness within 1/(n+1) of the target level, regardless of the system's errors -- made transparently visible through larger answer sets for harder questions. Weaker models earn lower reliability levels (not accuracy -- see Definition 2.4): GPT-4.1 earns 94.6% on GSM8K and 96.8% on TruthfulQA, while GPT-4.1-nano earns 89.8% on GSM8K and 66.5% on MMLU. We validate across five benchmarks, five models from three families, and both synthetic and real data. Conditional coverage on solvable items exceeds 0.93 across all configurations; sequential stopping reduces API costs by around 50%.
Authors: Sai Surya Duvvuri, Chanakya Ekbote, Rachit Bansal, Rishabh Tiwari, Devvrit Khatri, David Brandfonbrener, Paul Liang, Inderjit Dhillon, Manzil Zaheer
Abstract: Multi-Head Attention (MHA) is the core computational primitive underlying modern Large Language Models (LLMs). However, MHA suffers from a fundamental linear scaling limitation: $H$ attention heads produce exactly $H$ independent attention matrices, with no communication between heads during attention computation. This becomes problematic for multi-step reasoning, where correct answers depend on aggregating evidence from multiple parts of the context and composing latent token-to-token relations over a chain of intermediate inferences. To address this, we propose Interleaved Head Attention (IHA), which enables cross-head mixing by constructing $P$ pseudo-heads per head (typically $P=H$), where each pseudo query/key/value is a learned linear combination of all $H$ original queries, keys and values respectively. Interactions between pseudo-query and pseudo-key heads induce up to $P^2$ attention patterns per head with modest parameter overhead $\mathcal{O}(H^2P)$. We provide theory showing improved efficiency in terms of number of parameters on the synthetic Polynomial task (IHA uses $\Theta(\sqrt{k}n^2)$ parameters vs. $\Theta(kn^2)$ for MHA) and on the synthetic order-sensitive CPM-3 task (IHA uses $\lceil\sqrt{N_{\max}}\rceil$ heads vs. $N_{\max}$ for MHA). On real-world benchmarks, IHA improves Multi-Key retrieval on RULER by 10-20% (4k-16k) and, after fine-tuning for reasoning on OpenThoughts, improves GSM8K by 5.8% and MATH-500 by 2.8% (Majority Vote) over full attention.
Authors: Sameer Ambekar, Reza Nasirigerdeh, Peter J. Schuffler, Lina Felsner, Daniel M. Lang, Julia A. Schnabel
Abstract: Model merging under unseen test-time distribution shifts often renders naive strategies, such as mean averaging unreliable. This challenge is especially acute in medical imaging, where models are fine-tuned locally at clinics on private data, producing domain-specific models that differ by scanner, protocol, and population. When deployed at an unseen clinical site, test cases arrive in unlabeled, non-i.i.d. batches, and the model must adapt immediately without labels. In this work, we introduce an entropy-adaptive, fully online model-merging method that yields a batch-specific merged model via only forward passes, effectively leveraging target information. We further demonstrate why mean merging is prone to failure and misaligned under heterogeneous domain shifts. Next, we mitigate encoder classifier mismatch by decoupling the encoder and classification head, merging with separate merging coefficients. We extensively evaluate our method with state-of-the-art baselines using two backbones across nine medical and natural-domain generalization image classification datasets, showing consistent gains across standard evaluation and challenging scenarios. These performance gains are achieved while retaining single-model inference at test-time, thereby demonstrating the effectiveness of our method.
Authors: Gene Yu, Ce Guo, Wayne Luk
Abstract: Time series causal discovery is essential for understanding dynamic systems, yet many existing methods remain sensitive to noise, non-stationarity, and sampling variability. We propose the Validated Consensus-Driven Framework (VCDF), a simple and method-agnostic layer that improves robustness by evaluating the stability of causal relations across blocked temporal subsets. VCDF requires no modification to base algorithms and can be applied to methods such as VAR-LiNGAM and PCMCI. Experiments on synthetic datasets show that VCDF improves VAR-LiNGAM by approximately 0.08-0.12 in both window and summary F1 scores across diverse data characteristics, with gains most pronounced for moderate-to-long sequences. The framework also benefits from longer sequences, yielding up to 0.18 absolute improvement on time series of length 1000 and above. Evaluations on simulated fMRI data and IT-monitoring scenarios further demonstrate enhanced stability and structural accuracy under realistic noise conditions. VCDF provides an effective reliability layer for time series causal discovery without altering underlying modeling assumptions.
Authors: Gabriele Farina, Juan Carlos Perdomo
Abstract: We study the problem of efficiently producing, in an online fashion, generative models of scalar, multiclass, and vector-valued outcomes that cannot be falsified on the basis of the observed data and a pre-specified collection of computational tests. Our contributions are twofold. First, we expand on connections between online high-dimensional multicalibration with respect to an RKHS and recent advances in expected variational inequality problems, enabling efficient algorithms for the former. We then apply this algorithmic machinery to the problem of outcome indistinguishability. Our procedure, Defensive Generation, is the first to efficiently produce online outcome indistinguishable generative models of non-Bernoulli outcomes that are unfalsifiable with respect to infinite classes of tests, including those that examine higher-order moments of the generated distributions. Furthermore, our method runs in near-linear time in the number of samples and achieves the optimal, vanishing T^{-1/2} rate for generation error.
Authors: Alina Devkota, Jacob Thrasher, Donald Adjeroh, Binod Bhattarai, Prashnna K. Gyawali
Abstract: Federated Learning (FL) enables collaborative model training across multiple clients without sharing their private data. However, data heterogeneity across clients leads to client drift, which degrades the overall generalization performance of the model. This effect is further compounded by overemphasis on poorly performing clients. To address this problem, we propose FedVG, a novel gradient-based federated aggregation framework that leverages a global validation set to guide the optimization process. Such a global validation set can be established using readily available public datasets, ensuring accessibility and consistency across clients without compromising privacy. In contrast to conventional approaches that prioritize client dataset volume, FedVG assesses the generalization ability of client models by measuring the magnitude of validation gradients across layers. Specifically, we compute layerwise gradient norms to derive a client-specific score that reflects how much each client needs to adjust for improved generalization on the global validation set, thereby enabling more informed and adaptive federated aggregation. Extensive experiments on both natural and medical image benchmarking datasets, across diverse model architectures, demonstrate that FedVG consistently improves performance, particularly in highly heterogeneous settings. Moreover, FedVG is modular and can be seamlessly integrated with various state-of-the-art FL algorithms, often further improving their results. Our code is available at https://github.com/alinadevkota/FedVG.
Authors: Nick Polson, Vadim Sokolov
Abstract: Gaussian process (GP) surrogates are the default tool for emulating expensive computer experiments, but cubic cost, stationarity assumptions, and Gaussian predictive distributions limit their reach. We propose Generative Bayesian Computation (GBC) via Implicit Quantile Networks (IQNs) as a surrogate framework that targets all three limitations. GBC learns the full conditional quantile function from input--output pairs; at test time, a single forward pass per quantile level produces draws from the predictive distribution. Across fourteen benchmarks we compare GBC to four GP-based methods. GBC improves CRPS by 11--26\% on piecewise jump-process benchmarks, by 14\% on a ten-dimensional Friedman function, and scales linearly to 90,000 training points where dense-covariance GPs are infeasible. A boundary-augmented variant matches or outperforms Modular Jump GPs on two-dimensional jump datasets (up to 46\% CRPS improvement). In active learning, a randomized-prior IQN ensemble achieves nearly three times lower RMSE than deep GP active learning on Rocket LGBB. Overall, GBC records a favorable point estimate in 12 of 14 comparisons. GPs retain an edge on smooth surfaces where their smoothness prior provides effective regularization.
Authors: Sunki Hong, Jisoo Lee, Yuanyuan Shi
Abstract: Selecting the right deep learning model for power grid forecasting is challenging, as performance heavily depends on the data available to the operator. This paper presents a comprehensive benchmark of five modern neural architectures: two state space models (PowerMamba, S-Mamba), two Transformers (iTransformer, PatchTST), and a traditional LSTM. We evaluate these models on hourly electricity demand across six diverse US power grids for forecast windows between 24 and 168 hours. To ensure a fair comparison, we adapt each model with specialized temporal processing and a modular layer that cleanly integrates weather covariates. Our results reveal that there is no single best model for all situations. When forecasting using only historical load, PatchTST and the state space models provide the highest accuracy. However, when explicit weather data is added to the inputs, the rankings reverse: iTransformer improves its accuracy three times more efficiently than PatchTST. By controlling for model size, we confirm that this advantage stems from the architecture's inherent ability to mix information across different variables. Extending our evaluation to solar generation, wind power, and wholesale prices further demonstrates that model rankings depend on the forecast task: PatchTST excels on highly rhythmic signals like solar, while state space models are better suited for the chaotic fluctuations of wind and price. Ultimately, this benchmark provides grid operators with actionable guidelines for selecting the optimal forecasting architecture based on their specific data environments.
Authors: Yuanda Xu, Hejian Sang, Zhengze Zhou, Ran He, Zhipeng Wang
Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become the leading paradigm for enhancing reasoning in Large Language Models (LLMs). However, standard RLVR algorithms suffer from a well-documented pathology: while they improve Pass@1 accuracy through sharpened sampling, they simultaneously narrow the model's reasoning boundary and reduce generation diversity. We identify a root cause that existing methods overlook: the uniform penalization of errors. Current approaches -- whether data-filtering methods that select prompts by difficulty, or advantage normalization schemes -- treat all incorrect rollouts within a group identically. We show that this uniformity allows overconfident errors (incorrect reasoning paths that the RL process has spuriously reinforced) to persist and monopolize probability mass, ultimately suppressing valid exploratory trajectories. To address this, we propose the Asymmetric Confidence-aware Error Penalty (ACE). ACE introduces a per-rollout confidence shift metric, c_i = log(pi_theta(y_i|x) / pi_ref(y_i|x)), to dynamically modulate negative advantages. Theoretically, we demonstrate that ACE's gradient can be decomposed into the gradient of a selective regularizer restricted to overconfident errors, plus a well-characterized residual that partially moderates the regularizer's strength. We conduct extensive experiments fine-tuning Qwen2.5-Math-7B, Qwen3-8B-Base, and Llama-3.1-8B-Instruct on the DAPO-Math-17K dataset using GRPO and DAPO within the VERL framework. Evaluated on MATH-500 and AIME 2025, ACE composes seamlessly with existing methods and consistently improves the full Pass@k spectrum across all three model families and benchmarks.
Authors: Alexander Galozy
Abstract: Reinforcement learning (RL) agents under partial observability often condition actions on internally accumulated information such as memory or inferred latent context. We formalise such information-conditioned interaction patterns as behavioural dependency: variation in action selection with respect to internal information under fixed observations. This induces a probe-relative notion of $\epsilon$-behavioural equivalence and a within-policy behavioural distance that quantifies probe sensitivity. We establish three structural results. First, the set of policies exhibiting non-trivial behavioural dependency is not closed under convex aggregation. Second, behavioural distance contracts under convex combination. Third, we prove a sufficient local condition under which gradient ascent on a skewed mixture objective decreases behavioural distance when a dominant-mode gradient aligns with the direction of steepest contraction. Minimal bandit and partially observable gridworld experiments provide controlled witnesses of these mechanisms. In the examined settings, behavioural distance decreases under convex aggregation and under continued optimisation with skewed latent priors, and in these experiments it precedes degradation under latent prior shift. These results identify structural conditions under which probe-conditioned behavioural separation is not preserved under common policy transformations.
Authors: Youguang Chen, George Biros
Abstract: We consider the problem of sampling from a posterior distribution arising in Bayesian inverse problems in science, engineering, and imaging. Our method belongs to the family of independence Metropolis-Hastings (IMH) sampling algorithms, which are common in Bayesian inference. Relying on the existence of an approximate posterior distribution that is cheaper to sample from but may have significant bias, we introduce Proximal-IMH, a scheme that removes this bias by correcting samples from the approximate posterior through an auxiliary optimization problem. This yields a local adjustment that trades off adherence to the exact model against stability around the approximate reference point. For idealized settings, we prove that the proximal correction tightens the match between approximate and exact posteriors, thereby improving acceptance rates and mixing. The method applies to both linear and nonlinear input-output operators and is particularly suitable for inverse problems where exact posterior sampling is too expensive. We present numerical experiments including multimodal and data-driven priors with nonlinear input-output operators. The results show that Proximal-IMH reliably outperforms existing IMH variants.
Authors: Darshan Gadginmath, Ahmed Allibhoy, Fabio Pasqualetti
Abstract: Flow-based generative models, such as diffusion models and flow matching models, have achieved remarkable success in learning complex data distributions. However, a critical gap remains for their deployment in safety-critical domains: the lack of formal guarantees that generated samples will satisfy hard constraints. We address this by proposing a safety filtering framework that acts as an online shield for any pre-trained generative model. Our key insight is to cooperate with the generative process rather than override it. We define a constricting safety tube that is relaxed at the initial noise distribution and progressively tightens to the target safe set at the final data distribution, mirroring the coarse-to-fine structure of the generative process itself. By characterizing this tube via Control Barrier Functions (CBFs), we synthesize a feedback control input through a convex Quadratic Program (QP) at each sampling step. As the tube is loosest when noise is high and intervention is cheapest in terms of control energy, most constraint enforcement occurs when it least disrupts the model's learned structure. We prove that this mechanism guarantees safe sampling while minimizing the distributional shift from the original model at each sampling step, as quantified by the KL divergence. Our framework applies to any pre-trained flow-based generative scheme requiring no retraining or architectural modifications. We validate the approach across constrained image generation, physically-consistent trajectory sampling, and safe robotic manipulation policies, achieving 100% constraint satisfaction while preserving semantic fidelity.
Authors: Shiwei Tan, Hengyi Wang, Weiyi Qin, Qi Xu, Zhigang Hua, Hao Wang
Abstract: Multimodal Large Language Models (MLLMs) deliver detailed responses on vision-language tasks, yet remain susceptible to object hallucination (introducing objects not present in the image), undermining reliability in practice. Prior efforts often rely on heuristic penalties, post-hoc correction, or generic decoding tweaks, which do not directly intervene in the mechanisms that trigger object hallucination and thus yield limited gains. To address this challenge, we propose a causal decoding framework that applies targeted causal interventions during generation to curb spurious object mentions. By reshaping the decoding dynamics to attenuate spurious dependencies, our approach reduces false object tokens while maintaining descriptive quality. Across captioning and QA benchmarks, our framework substantially lowers object-hallucination rates and achieves state-of-the-art faithfulness without degrading overall output quality.
Authors: Jesse He, Helen Jenne, Max Vargas, Davis Brown, Gal Mishne, Yusu Wang, Henry Kvinge
Abstract: The recent field of neural algorithmic reasoning (NAR) studies the ability of graph neural networks (GNNs) to emulate classical algorithms like Bellman-Ford, a phenomenon known as algorithmic alignment. At the same time, recent advances in large language models (LLMs) have spawned the study of mechanistic interpretability, which aims to identify granular model components like circuits that perform specific computations. In this work, we introduce Mechanistic Interpretability for Neural Algorithmic Reasoning (MINAR), an efficient circuit discovery toolbox that adapts attribution patching methods from mechanistic interpretability to the GNN setting. We show through two case studies that MINAR recovers faithful neuron-level circuits from GNNs trained on algorithmic tasks. Our study sheds new light on the process of circuit formation and pruning during training, as well as giving new insight into how GNNs trained to perform multiple tasks in parallel reuse circuit components for related tasks. Our code is available at https://github.com/pnnl/MINAR.
Authors: Alexander Morgan, Ummay Sumaya Khan, Lingjia Liu, Lizhong Zheng
Abstract: Recurrent neural networks (RNNs) can be interpreted as discrete-time state-space models, where the state evolution corresponds to an infinite-impulse-response (IIR) filtering operation governed by both feedforward weights and recurrent poles. While, in principle, all parameters including pole locations can be optimized via backpropagation through time (BPTT), such joint learning incurs substantial computational overhead and is often impractical for applications with limited training data. Echo state networks (ESNs) mitigate this limitation by fixing the recurrent dynamics and training only a linear readout, enabling efficient and stable online adaptation. In this work, we analytically and empirically examine why learning recurrent poles does not provide tangible benefits in data-constrained, real-time learning scenarios. Our analysis shows that pole learning renders the weight optimization problem highly non-convex, requiring significantly more training samples and iterations for gradient-based methods to converge to meaningful solutions. Empirically, we observe that for complex-valued data, gradient descent frequently exhibits prolonged plateaus, and advanced optimizers offer limited improvement. In contrast, fixed-pole architectures induce stable and well-conditioned state representations even with limited training data. Numerical results demonstrate that fixed-pole networks achieve superior performance with lower training complexity, making them more suitable for online real-time tasks.
Authors: Alan F. Karr, Regina Ruane
Abstract: We describe extensive numerical experiments assessing and quantifying how classifier performance depends on the quality of the training data, a frequently neglected component of the analysis of classifiers. More specifically, in the scientific context of metagenomic assembly of short DNA reads into "contigs," we examine the effects of degrading the quality of the training data by multiple mechanisms, and for four classifiers -- Bayes classifiers, neural nets, partition models and random forests. We investigate both individual behavior and congruence among the classifiers. We find breakdown-like behavior that holds for all four classifiers, as degradation increases and they move from being mostly correct to only coincidentally correct, because they are wrong in the same way. In the process, a picture of spatial heterogeneity emerges: as the training data move farther from analysis data, classifier decisions degenerate, the boundary becomes less dense, and congruence increases.
Authors: YuQing Xie, Ameya Daigavane, Mit Kotak, Tess Smidt
Abstract: $E(3)$-equivariant neural networks have proven to be effective in a wide range of 3D modeling tasks. A fundamental operation of such networks is the tensor product, which allows interaction between different feature types. Because this operation scales poorly, there has been considerable work towards accelerating this interaction. However, recently \citet{xieprice} have pointed out that most speedups come from a reduction in expressivity rather than true algorithmic improvements on computing Clebsch-Gordan tensor products. A modification of Gaunt tensor product \citep{gaunt} can give a true asymptotic speedup but is incomplete and misses many interactions. In this work, we provide the first complete algorithm which truly provides asymptotic benefits Clebsch-Gordan tensor products. For full CGTP, our algorithm brings runtime complexity from the naive $O(L^6)$ to $O(L^4\log^2 L)$, close to the lower bound of $O(L^4)$. We first show how generalizing fast Fourier based convolution naturally leads to the previously proposed Gaunt tensor product \citep{gaunt}. To remedy antisymmetry issues, we generalize from scalar signals to irrep valued signals, giving us tensor spherical harmonics. We prove a generalized Gaunt formula for the tensor harmonics. Finally, we show that we only need up to vector valued signals to recover the missing interactions of Gaunt tensor product.
Authors: William Youngwoo Chung, Calvin Yeung, Hansen Jin Lillemark, Zhuowen Zou, Xiangjian Liu, Mohsen Imani
Abstract: A key challenge in artificial intelligence and neuroscience is understanding how neural systems learn representations that capture the underlying dynamics of the world. Most world models represent the transition function with unstructured neural networks, limiting interpretability, sample efficiency, and generalization to unseen states or action compositions. We address these issues with a generalizable world model grounded in Vector Symbolic Architecture (VSA) principles as geometric priors. Our approach utilizes learnable Fourier Holographic Reduced Representation (FHRR) encoders to map states and actions into a high dimensional complex vector space with learned group structure and models transitions with element-wise complex multiplication. We formalize the framework's group theoretic foundation and show how training such structured representations to be approximately invariant enables strong multi-step composition directly in latent space and generalization performances over various experiments. On a discrete grid world environment, our model achieves 87.5% zero shot accuracy to unseen state-action pairs, obtains 53.6% higher accuracy on 20-timestep horizon rollouts, and demonstrates 4x higher robustness to noise relative to an MLP baseline. These results highlight how training to have latent group structure yields generalizable, data-efficient, and interpretable world models, providing a principled pathway toward structured models for real-world planning and reasoning.
Authors: Meet Hemant Parikh, Yaqin Chen, Jian-Xun Wang
Abstract: Data assimilation and scientific inverse problems require reconstructing high-dimensional physical states from sparse and noisy observations, ideally with uncertainty-aware posterior samples that remain faithful to learned priors and governing physics. While training-free conditional generation is well developed for diffusion models, corresponding conditioning and posterior sampling strategies for Flow Matching (FM) priors remain comparatively under-explored, especially on scientific benchmarks where fidelity must be assessed beyond measurement misfit. In this work, we study training-free conditional generation for scientific inverse problems under FM priors and organize existing inference-time strategies by where measurement information is injected: (i) guided transport dynamics that perturb sampling trajectories using likelihood information, and (ii) source-distribution inference that performs posterior inference over the source variable while keeping the learned transport fixed. Building on the latter, we propose D-Flow SGLD, a source-space posterior sampling method that augments differentiable source inference with preconditioned stochastic gradient Langevin dynamics, enabling scalable exploration of the source posterior induced by new measurement operators without retraining the prior or modifying the learned FM dynamics. We benchmark representative methods from both families on a hierarchy of problems: 2D toy posteriors, chaotic Kuramoto-Sivashinsky trajectories, and wall-bounded turbulence reconstruction. Across these settings, we quantify trade-offs among measurement assimilation, posterior diversity, and physics/statistics fidelity, and establish D-Flow SGLD as a practical FM-compatible posterior sampler for scientific inverse problems.
Authors: Louis Bethune, Victor Turrisi, Bruno Kacper Mlodozeniec, Pau Rodriguez Lopez, Lokesh Boominathan, Nikhil Bhendawade, Amitis Shidani, Joris Pelemans, Theo X. Olausson, Devon Hjelm, Paul Dixon, Joao Monteiro, Pierre Ablin, Vishnu Banna, Arno Blaas, Nick Henderson, Kari Noriy, Dan Busbridge, Josh Susskind, Marco Cuturi, Irina Belousova, Luca Zappella, Russ Webb, Jason Ramapuram
Abstract: Discrete diffusion models have emerged as strong alternatives to autoregressive language models, with recent work initializing and fine-tuning a base unimodal model for bimodal generation. Diverging from previous approaches, we introduce the first tri-modal masked diffusion model pretrained from scratch on text, image-text, and audio-text data. We systematically analyze multimodal scaling laws, modality mixing ratios, noise schedules, and batch-size effects, and we provide optimized inference sampling defaults. Our batch-size analysis yields a novel stochastic differential equation (SDE)-based reparameterization that eliminates the need for tuning the optimal batch size as reported in recent work. This reparameterization decouples the physical batch size, often chosen based on compute constraints (GPU saturation, FLOP efficiency, wall-clock time), from the logical batch size, chosen to balance gradient variance during stochastic optimization. Finally, we pretrain a preliminary 3B-parameter tri-modal model on 6.4T tokens, demonstrating the capabilities of a unified design and achieving strong results in text generation, text-to-image tasks, and text-to-speech tasks. Our work represents the largest-scale systematic open study of multimodal discrete diffusion models conducted to date, providing insights into scaling behaviors across multiple modalities.
Authors: Ningyuan Yang, Weihua Du, Weiwei Sun, Sean Welleck, Yiming Yang
Abstract: Reinforcement learning (RL) has become a central post-training paradigm for large language models (LLMs), but its performance is highly sensitive to the quality of training problems. This sensitivity stems from the non-stationarity of RL: rollouts are generated by an evolving policy, and learning is shaped by exploration and reward feedback, unlike supervised fine-tuning (SFT) with fixed trajectories. As a result, prior work often relies on manual curation or simple heuristic filters (e.g., accuracy), which can admit incorrect or low-utility problems. We propose GradAlign, a gradient-aligned data selection method for LLM reinforcement learning that uses a small, trusted validation set to prioritize training problems whose policy gradients align with validation gradients, yielding an adaptive curriculum. We evaluate GradAlign across three challenging data regimes: unreliable reward signals, distribution imbalance, and low-utility training corpus, showing that GradAlign consistently outperforms existing baselines, underscoring the importance of directional gradient signals in navigating non-stationary policy optimization and yielding more stable training and improved final performance. We release our implementation at https://github.com/StigLidu/GradAlign
Authors: Boyuan Li, Zhen Liu, Yicheng Luo, Qianli Ma
Abstract: Irregular Multivariate Time Series (IMTS) are characterized by uneven intervals between consecutive timestamps, which carry sampling pattern information valuable and informative for learning temporal and variable dependencies. In addition, IMTS often exhibit diverse dependencies across multiple time scales. However, many existing multi-scale IMTS methods use resampling to obtain the coarse series, which can alter the original timestamps and disrupt the sampling pattern information. To address the challenge, we propose ReIMTS, a Recursive multi-scale modeling approach for Irregular Multivariate Time Series forecasting. Instead of resampling, ReIMTS keeps timestamps unchanged and recursively splits each sample into subsamples with progressively shorter time periods. Based on the original sampling timestamps in these long-to-short subsamples, an irregularity-aware representation fusion mechanism is proposed to capture global-to-local dependencies for accurate forecasting. Extensive experiments demonstrate an average performance improvement of 27.1\% in the forecasting task across different models and real-world datasets. Our code is available at https://github.com/Ladbaby/PyOmniTS.
Authors: Haoyuan He, Yu Zheng, Jie Zhou, Jiwen Lu
Abstract: Robust watermarking is critical for intellectual property protection, whereas existing methods face a severe vulnerability against regeneration-based AIGC attacks. We identify that existing methods fail because they entangle the watermark with high-frequency cover texture, which is susceptible to being rewritten during generative purification. To address this, we propose WaterVIB, a theoretically grounded framework that reformulates the encoder as an information sieve via the Variational Information Bottleneck. Instead of overfitting to fragile cover details, our approach forces the model to learn a Minimal Sufficient Statistic of the message. This effectively filters out redundant cover nuances prone to generative shifts, retaining only the essential signal invariant to regeneration. We theoretically prove that optimizing this bottleneck is a necessary condition for robustness against distribution-shifting attacks. Extensive experiments demonstrate that WaterVIB significantly outperforms state-of-the-art methods, achieving superior zero-shot resilience against unknown diffusion-based editing.
Authors: Chengrui Qu, Yizhou Zhang, Nicholas Lanzetti, Eric Mazumdar
Abstract: Many emerging agentic paradigms require agents to collaborate with one another (or people) to achieve shared goals. Unfortunately, existing approaches to learning policies for such collaborative problems produce brittle solutions that fail when paired with new partners. We attribute these failures to a combination of free-riding during training and a lack of strategic robustness. To address these problems, we study the concept of strategic risk aversion and interpret it as a principled inductive bias for generalizable cooperation with unseen partners. While strategically risk-averse players are robust to deviations in their partner's behavior by design, we show that, in collaborative games, they also (1) can have better equilibrium outcomes than those at classical game-theoretic concepts like Nash, and (2) exhibit less or no free-riding. Inspired by these insights, we develop a multi-agent reinforcement learning (MARL) algorithm that integrates strategic risk aversion into standard policy optimization methods. Our empirical results across collaborative benchmarks (including an LLM collaboration task) validate our theory and demonstrate that our approach consistently achieves reliable collaboration with heterogeneous and previously unseen partners across collaborative tasks.
Authors: Ruijie Zhang, Yequan Zhao, Ziyue Liu, Zhengyang Wang, Zheng Zhang
Abstract: The Muon optimizer has demonstrated promising performance in pre-training large language models through gradient (or momentum) orthogonalization. In this work, we propose a simple yet effective enhancement to Muon, namely Muon+, which introduces an additional normalization step after orthogonalization. We demonstrate the effectiveness of Muon+ through extensive pre-training experiments across a wide range of model scales and architectures. Our evaluation includes GPT-style models ranging from 130M to 774M parameters and LLaMA-style models ranging from 60M to 1B parameters. We comprehensively evaluate the effectiveness of Muon+ in the compute-optimal training regime and further extend the token-to-parameter (T2P) ratio to an industrial level of $\approx 200$. Experimental results show that Muon+ provides a consistent boost on training and validation perplexity over Muon. We provide our code here: https://github.com/K1seki221/MuonPlus.
Authors: Zhi Cao, Cong Zhang, Yaoxin Wu, Yaqing Hou, Hongwei Ge
Abstract: The Flexible Job Shop Problem (FJSP) is a well-studied combinatorial optimization problem with extensive applications for manufacturing and production scheduling. It involves assigning jobs to various machines to optimize criteria, such as minimizing total completion time. Current learning-based methods in this domain often rely on localized feature extraction models, limiting their capacity to capture overarching dependencies spanning operations and machines. This paper introduces an innovative architecture that harnesses Mamba, a state-space model with linear computational complexity, to facilitate comprehensive sequence modeling tailored for FJSP. In contrast to prevalent graph-attention-based frameworks that are computationally intensive for FJSP, we show our model is more efficient. Specifically, the proposed model possesses an encoder and a decoder. The encoder incorporates a dual Mamba block to extract operation and machine features separately. Additionally, we introduce an efficient cross-attention decoder to learn interactive embeddings of operations and machines. Our experimental results demonstrate that our method achieves faster solving speed and surpasses the performance of state-of-the-art learning-based methods for FJSP across various benchmarks.
Authors: Zhao Yang, Yi Duan, Jiwei Zhu, Ying Ba, Chuan Cao, Bing Su
Abstract: Gene expression prediction, which predicts mRNA expression levels from DNA sequences, presents significant challenges. Previous works often focus on extending input sequence length to locate distal enhancers, which may influence target genes from hundreds of kilobases away. Our work first reveals that for current models, long sequence modeling can decrease performance. Even carefully designed algorithms only mitigate the performance degradation caused by long sequences. Instead, we find that proximal multimodal epigenomic signals near target genes prove more essential. Hence we focus on how to better integrate these signals, which has been overlooked. We find that different signal types serve distinct biological roles, with some directly marking active regulatory elements while others reflect background chromatin patterns that may introduce confounding effects. Simple concatenation may lead models to develop spurious associations with these background patterns. To address this challenge, we propose Prism, a framework that learns multiple combinations of high-dimensional epigenomic features to represent distinct background chromatin states and uses backdoor adjustment to mitigate confounding effects. Our experimental results demonstrate that proper modeling of multimodal epigenomic signals achieves state-of-the-art performance using only short sequences for gene expression prediction.
Authors: Zhihao Li, Yu Feng, Zhilu Lai, Wei Wang
Abstract: Learning PDE dynamics for fluids increasingly relies on neural operators and Transformer-based models, yet these approaches often lack interpretability and struggle with localized, high-frequency structures while incurring quadratic cost in spatial samples. We propose representing fields with a Gaussian basis, where learned atoms carry explicit geometry (centers, anisotropic scales, weights) and form a compact, mesh-agnostic, directly visualizable state. Building on this representation, we introduce a Gaussian Particle Operator that acts in modal space: learned Gaussian modal windows perform a Petrov-Galerkin measurement, and PG Gaussian Attention enables global cross-scale coupling. This basis-to-basis design is resolution-agnostic and achieves near-linear complexity in N for a fixed modal budget, supporting irregular geometries and seamless 2D-to-3D extension. On standard PDE benchmarks and real datasets, our method attains state-of-the-art competitive accuracy while providing intrinsic interpretability.
Authors: Seokwon Yoon, Youngbin Choi, Seunghyuk Cho, Seungbeom Lee, MoonJeong Park, Dongwoo Kim
Abstract: Generative Flow Networks (GFlowNets) learn to sample diverse candidates in proportion to a reward function, making them well-suited for scientific discovery, where exploring multiple promising solutions is crucial. Further extending GFlowNets to multi-objective settings has attracted growing interest since real-world applications often involve multiple, conflicting objectives. However, existing approaches require additional training for each set of objectives, limiting their applicability and incurring substantial computational overhead. We propose a training-free mixing policy that composes pre-trained GFlowNets at inference time, enabling rapid adaptation without finetuning or retraining. Importantly, our framework is flexible, capable of handling diverse reward combinations ranging from linear scalarization to complex non-linear logical operators, which are often handled separately in previous literature. We prove that our method exactly recovers the target distribution for linear scalarization and quantify the approximation quality for nonlinear operators through a distortion factor. Experiments on a synthetic 2D grid and real-world molecule-generation tasks demonstrate that our approach achieves performance comparable to baselines that require additional training.
Authors: Sweta Karlekar, Carolina Zheng, Magnus Saebo, Nicolas Beltran-Velez, Shuyang Yu, John Bowlan, Michal Kucer, David Blei
Abstract: Many applications seek to optimize LLM outputs at test time by iteratively proposing, scoring, and refining candidates over a discrete output space. Existing methods use a calibrated scalar evaluator for the target objective to guide search, but for many tasks such scores are unavailable, too sparse, or unreliable. Pairwise comparisons, by contrast, are often easier to elicit, still provide useful signal on improvement directions, and can be obtained from the LLM itself without external supervision. Building on this observation, we introduce Duel-Evolve, an evolutionary optimization algorithm that replaces external scalar rewards with pairwise preferences elicited from the same LLM used to generate candidates. Duel-Evolve aggregates these noisy candidate comparisons via a Bayesian Bradley-Terry model, yielding uncertainty-aware estimates of candidate quality. These quality estimates guide allocation of the comparison budget toward plausible optima using Double Thompson Sampling, as well as selection of high-quality parents to generate improved candidates. We evaluate Duel-Evolve on MathBench, where it achieves 20 percentage points higher accuracy over existing methods and baselines, and on LiveCodeBench, where it improves over comparable iterative methods by over 12 percentage points. Notably, the method requires no reward model, no ground-truth labels during search, and no hand-crafted scoring function. Results show that pairwise self-preferences provide strong optimization signal for test-time improvement over large, discrete output spaces.
Authors: Sharv Murgai, Utkarsh Utkarsh, Kyle C. Nguyen, Alan Edelman, Erin C. S. Acquesta, Christopher Vincent Rackauckas
Abstract: Agent-based epidemic models (ABMs) encode behavioral and policy heterogeneity but are too slow for nightly hospital planning. We develop county-ready surrogates that learn directly from exascale ABM trajectories using Universal Differential Equations (UDEs): mechanistic SEIR-family ODEs with a neural-parameterized contact rate $\kappa_\phi(u,t)$ (no additive residual). Our contributions are threefold: we adapt multiple shooting and an observer-based prediction-error method (PEM) to stabilize identification of neural-augmented epidemiological dynamics across intervention-driven regime shifts; we enforce positivity and mass conservation and show the learned contact-rate parameterization yields a well-posed vector field; and we quantify accuracy, calibration, and compute against ABM ensembles and UDE baselines. On a representative ExaEpi scenario, PEM-UDE reduces mean MSE by 77% relative to single-shooting UDE (3.00 vs. 13.14) and by 20% relative to MS-UDE (3.75). Reliability improves in parallel: empirical coverage of ABM $10$-$90$% and $25$-$75$% bands rises from 0.68/0.43 (UDE) and 0.79/0.55 (MS-UDE) to 0.86/0.61 with PEM-UDE and 0.94/0.69 with MS+PEM-UDE, indicating calibrated uncertainty rather than overconfident fits. Inference runs in seconds on commodity CPUs (20-35 s per $\sim$90-day forecast), enabling nightly ''what-if'' sweeps on a laptop. Relative to a $\sim$100 CPU-hour ABM reference run, this yields $\sim10^{4}\times$ lower wall-clock per scenario. This closes the realism-cadence gap, supports threshold-aware decision-making (e.g., maintaining ICU occupancy $<75$%), preserves mechanistic interpretability, and enables calibrated, risk-aware scenario planning on standard institutional hardware. Beyond epidemics, the ABM$\to$UDE recipe provides a portable path to distill agent-based simulators into fast, trustworthy surrogates for other scientific domains.
Authors: Zheng Gao, Xiaoyu Li, Zhicheng Bao, Xiaoyan Feng, Jiaojiao Jiang
Abstract: Generative images have proliferated on Web platforms in social media and online copyright distribution scenarios, and semantic watermarking has increasingly been integrated into diffusion models to support reliable provenance tracking and forgery prevention for web content. Traditional noise-layer-based watermarking, however, remains vulnerable to inversion attacks that can recover embedded signals. To mitigate this, recent content-aware semantic watermarking schemes bind watermark signals to high-level image semantics, constraining local edits that would otherwise disrupt global coherence. Yet, large language models (LLMs) possess structured reasoning capabilities that enable targeted exploration of semantic spaces, allowing locally fine-grained but globally coherent semantic alterations that invalidate such bindings. To expose this overlooked vulnerability, we introduce a Coherence-Preserving Semantic Injection (CSI) attack that leverages LLM-guided semantic manipulation under embedding-space similarity constraints. This alignment enforces visual-semantic consistency while selectively perturbing watermark-relevant semantics, ultimately inducing detector misclassification. Extensive empirical results show that CSI consistently outperforms prevailing attack baselines against content-aware semantic watermarking, revealing a fundamental security weakness of current semantic watermark designs when confronted with LLM-driven semantic perturbations.
Authors: Zhongwei Xie, Jiaxin Bai, Shujie Liu, Haoyu Huang, Yufei Li, Yisen Gao, Hong Ting Tsang, Yangqiu Song
Abstract: Neural Graph Databases (NGDBs) facilitate complex logical reasoning over incomplete knowledge structures, yet their training efficiency and expressivity are constrained by rigid query-level batching and structure-exclusive embeddings. We present NGDB-Zoo, a unified framework that resolves these bottlenecks by synergizing operator-level training with semantic augmentation. By decoupling logical operators from query topologies, NGDB-Zoo transforms the training loop into a dynamically scheduled data-flow execution, enabling multi-stream parallelism and achieving a $1.8\times$ - $6.8\times$ throughput compared to baselines. Furthermore, we formalize a decoupled architecture to integrate high-dimensional semantic priors from Pre-trained Text Encoders (PTEs) without triggering I/O stalls or memory overflows. Extensive evaluations on six benchmarks, including massive graphs like ogbl-wikikg2 and ATLAS-Wiki, demonstrate that NGDB-Zoo maintains high GPU utilization across diverse logical patterns and significantly mitigates representation friction in hybrid neuro-symbolic reasoning.
Authors: Kart Leong Lim, Ji Lin
Abstract: High stress occurs when 3D heterogeneous IC packages are subjected to thermal cycling at extreme temperatures. Stress mainly occurs at the interface between different materials. We investigate stress image using latent space representation which is based on using deep generative model (DGM). However, most DGM approaches are unsupervised, meaning they resort to image pairing (input and output) to train DGM. Instead, we rely on a recent boundary-decoder (BD) net, which uses boundary condition and image pairing for stress modeling. The boundary net maps material parameters to the latent space co-shared by its image counterpart. Because such a setup is dimensionally wise ill-posed, we further couple BD net with deep clustering. To access the performance of our proposed method, we simulate an IC chip dataset comprising of 1825 stress images. We compare our new approach using variants of BD net as well as a baseline approach. We show that our approach is able to outperform all the comparison in terms of train and test error reduction.
Authors: Chaowei Wu, Huazhu Chen, Congde Yuan, Qirui Yang, Guoqing Song, Yue Gao, Li Luo, Frank Youhua Chen, Mengzhuo Guo
Abstract: Lifetime Value (LTV) prediction is critical in advertising, recommender systems, and e-commerce. In practice, LTV data patterns vary across decision scenarios. As a result, practitioners often build complex, scenario-specific pipelines and iterate over feature processing, objective design, and tuning. This process is expensive and hard to transfer. We propose AgentLTV, an agent-based unified search-and-evolution framework for automated LTV modeling. AgentLTV treats each candidate solution as an {executable pipeline program}. LLM-driven agents generate code, run and repair pipelines, and analyze execution feedback. Two decision agents coordinate a two-stage search. The Monte Carlo Tree Search (MCTS) stage explores a broad space of modeling choices under a fixed budget, guided by the Polynomial Upper Confidence bounds for Trees criterion and a Pareto-aware multi-metric value function. The Evolutionary Algorithm (EA) stage refines the best MCTS program via island-based evolution with crossover, mutation, and migration. Experiments on a large-scale proprietary dataset and a public benchmark show that AgentLTV consistently discovers strong models across ranking and error metrics. Online bucket-level analysis further indicates improved ranking consistency and value calibration, especially for high-value and negative-LTV segments. We summarize practitioner-oriented takeaways: use MCTS for rapid adaptation to new data patterns, use EA for stable refinement, and validate deployment readiness with bucket-level ranking and calibration diagnostics. The proposed AgentLTV has been successfully deployed online.
Authors: Toktam Khatibi
Abstract: Clinical risk prediction models often underperform in real-world settings due to poor calibration, limited transportability, and subgroup disparities. These challenges are amplified in high-dimensional multimodal cancer datasets characterized by complex feature interactions and a p >> n structure. We present a fully reproducible multimodal machine learning framework for 5-year overall survival prediction in breast cancer, integrating clinical variables with high-dimensional transcriptomic and copy-number alteration (CNA) features from the METABRIC cohort. After variance- and sparsity-based filtering and dimensionality reduction, models were trained using stratified train/validation/test splits with validation-based hyperparameter tuning. Two survival approaches were compared: an elastic-net regularized Cox model (CoxNet) and a gradient-boosted survival tree model implemented using XGBoost. CoxNet provides embedded feature selection and stable estimation, whereas XGBoost captures nonlinear effects and higher-order interactions. Performance was assessed using time-dependent area under the ROC curve (AUC), average precision (AP), calibration curves, Brier score, and bootstrapped 95 percent confidence intervals. CoxNet achieved validation and test AUCs of 98.3 and 96.6, with AP values of 90.1 and 80.4. XGBoost achieved validation and test AUCs of 98.6 and 92.5, with AP values of 92.5 and 79.9. Fairness diagnostics showed stable discrimination across age groups, estrogen receptor status, molecular subtypes, and menopausal state. This work introduces a governance-oriented multimodal survival framework emphasizing calibration, fairness auditing, robustness, and reproducibility for high-dimensional clinical machine learning.
Authors: Loes Kruger, Sebastian Junges, Jurriaan Rot
Abstract: Active automata learning (AAL) algorithms can learn a behavioral model of a system from interacting with it. The primary challenge remains scaling to larger models, in particular in the presence of many possible inputs to the system. Modern AAL algorithms fail to scale even if, in every state, most inputs lead to errors. In various challenging problems from the literature, these errors are observable, i.e., they emit a known error output. Motivated by these problems, we study learning these systems more efficiently. Further, we consider various degrees of knowledge about which inputs are non-error producing at which state. For each level of knowledge, we provide a matching adaptation of the state-of-the-art AAL algorithm L# to make the most of this domain knowledge. Our empirical evaluation demonstrates that the methods accelerate learning by orders of magnitude with strong but realistic domain knowledge to a single order of magnitude with limited domain knowledge.
Authors: David Eckel, Henri Mee{\ss}
Abstract: Cooperative Multi-Agent Reinforcement Learning (MARL) solves complex tasks that require coordination from multiple agents, but is often limited to either local (independent learning) or global (centralized learning) perspectives. In this paper, we introduce a novel sequential training scheme and MARL architecture, which learns from multiple perspectives on different hierarchy levels. We propose the Hierarchical Lead Critic (HLC) - inspired by natural emerging distributions in team structures, where following high-level objectives combines with low-level execution. HLC demonstrates that introducing multiple hierarchies, leveraging local and global perspectives, can lead to improved performance with high sample efficiency and robust policies. Experimental results conducted on cooperative, non-communicative, and partially observable MARL benchmarks demonstrate that HLC outperforms single hierarchy baselines and scales robustly with increasing amounts of agents and difficulty.
Authors: Jiafeng Lin, Yuxuan Wang, Huakun Luo, Zhongyi Pei, Jianmin Wang
Abstract: Multimodal time series forecasting has garnered significant attention for its potential to provide more accurate predictions than traditional single-modality models by leveraging rich information inherent in other modalities. However, due to fundamental challenges in modality alignment, existing methods often struggle to effectively incorporate multimodal data into predictions, particularly textual information that has a causal influence on time series fluctuations, such as emergency reports and policy announcements. In this paper, we reflect on the role of textual information in numerical forecasting and propose Time series transformers with Multimodal Mixture-of-Experts, TiMi, to unleash the causal reasoning capabilities of LLMs. Concretely, TiMi utilizes LLMs to generate inferences on future developments, which serve as guidance for time series forecasting. To seamlessly integrate both exogenous factors and time series into predictions, we introduce a Multimodal Mixture-of-Experts (MMoE) module as a lightweight plug-in to empower Transformer-based time series models for multimodal forecasting, eliminating the need for explicit representation-level alignment. Experimentally, our proposed TiMi demonstrates consistent state-of-the-art performance on sixteen real-world multimodal forecasting benchmarks, outperforming advanced baselines while offering both strong adaptability and interpretability.
Authors: Michele Cazzola, Alberto Ghione, Lucia Sargentini, Julien Nespoulous, Riccardo Finotello
Abstract: A central challenge in scientific machine learning (ML) is the correct representation of physical systems governed by multi-regime behaviours. In these scenarios, standard data analysis techniques often fail to capture the nature of the data, as the system's response varies significantly across the state space due to its stochasticity and the different physical regimes. Uncertainty quantification (UQ) should thus not be viewed merely as a safety assessment, but as a support to the learning task itself, guiding the model to internalise the behaviour of the data. We address this by focusing on the Critical Heat Flux (CHF) benchmark and dataset presented by the OECD/NEA Expert Group on Reactor Systems Multi-Physics. This case study represents a test for scientific ML due to the non-linear dependence of CHF on the inputs and the existence of distinct microscopic physical regimes. These regimes exhibit diverse statistical profiles, a complexity that requires UQ techniques to internalise the data behaviour and ensure reliable predictions. In this work, we conduct a comparative analysis of UQ methodologies to determine their impact on physical representation. We contrast post-hoc methods, specifically conformal prediction, against end-to-end coverage-oriented pipelines, including (Bayesian) heteroscedastic regression and quality-driven losses. These approaches treat uncertainty not as a final metric, but as an active component of the optimisation process, modelling the prediction and its behaviour simultaneously. We show that while post-hoc methods ensure statistical calibration, coverage-oriented learning effectively reshapes the model's representation to match the complex physical regimes. The result is a model that delivers not only high predictive accuracy but also a physically consistent uncertainty estimation that adapts dynamically to the intrinsic variability of the CHF.
Authors: Sijia Xu, Fan Li, Xiaoyang Wang, Zhengyi Yang, Xuemin Lin
Abstract: Tabular data is the primary data format in industrial relational databases, underpinning modern data analytics and decision-making. However, the increasing scale of tabular data poses significant computational and storage challenges to learning-based analytical systems. This highlights the need for data-efficient learning, which enables effective model training and generalization using substantially fewer samples. Dataset condensation (DC) has emerged as a promising data-centric paradigm that synthesizes small yet informative datasets to preserve data utility while reducing storage and training costs. However, existing DC methods are computationally intensive due to reliance on complex gradient-based optimization. Moreover, they often overlook key characteristics of tabular data, such as heterogeneous features and class imbalance. To address these limitations, we introduce C$^{2}$TC (Class-Adaptive Clustering for Tabular Condensation), the first training-free tabular dataset condensation framework that jointly optimizes class allocation and feature representation, enabling efficient and scalable condensation. Specifically, we reformulate the dataset condensation objective into a novel class-adaptive cluster allocation problem (CCAP), which eliminates costly training and integrates adaptive label allocation to handle class imbalance. To solve the NP-hard CCAP, we develop HFILS, a heuristic local search that alternates between soft allocation and class-wise clustering to efficiently obtain high-quality solutions. Moreover, a hybrid categorical feature encoding (HCFE) is proposed for semantics-preserving clustering of heterogeneous discrete attributes. Extensive experiments on 10 real-world datasets demonstrate that C$^{2}$TC improves efficiency by at least 2 orders of magnitude over state-of-the-art baselines, while achieving superior downstream performance.
Authors: Aleena Siji, Amir Mohammad Karimi Mamaghan, Ferdinand Kapl, Tobias H\"oppe, Emmanouil Angelis, Andrea Dittadi, Maurice Brenner, Michael Heinzinger, Karl Henrik Johansson, Kaitlin Maile, Johannes von Oswald, Stefan Bauer
Abstract: Protein language models (PLMs) have become widely adopted as general-purpose models, demonstrating strong performance in protein engineering and de novo design. Like large language models (LLMs), they are typically trained as deep transformers with next-token or masked-token prediction objectives on massive sequence corpora and are scaled by increasing model depth. Recent work on autoregressive LLMs has identified the Curse of Depth: later layers contribute little to the final output predictions. These findings naturally raise the question of whether a similar depth inefficiency also appears in PLMs, where many widely used models are not autoregressive, and some are multimodal, accepting both protein sequence and structure as input. In this work, we present a depth analysis of six popular PLMs across model families and scales, spanning three training objectives, namely autoregressive, masked, and diffusion, and quantify how layer contributions evolve with depth using a unified set of probing- and perturbation-based measurements. Across all models, we observe consistent depth-dependent patterns that extend prior findings on LLMs: later layers depend less on earlier computations and mainly refine the final output distribution, and these effects are increasingly pronounced in deeper models. Taken together, our results suggest that PLMs exhibit a form of depth inefficiency, motivating future work on more depth-efficient architectures and training methods.
Authors: Xiannan Huang, Quan Yuan, Chao Yang
Abstract: Accurately predicting short-term traffic demand is critical for intelligent transportation systems. While deep learning models achieve strong performance under stationary conditions, their accuracy often degrades significantly when faced with distribution shifts caused by external events or evolving urban dynamics. Frequent model retraining to adapt to such changes incurs prohibitive computational costs, especially for large-scale or foundation models. To address this challenge, we propose FORESEE (Forecasting Online with Residual Smoothing and Ensemble Experts), a lightweight online adaptation framework that is accurate, robust, and computationally efficient. FORESEE operates without any parameter updates to the base model. Instead, it corrects today's forecast in each region using yesterday's prediction error, stabilized through exponential smoothing guided by a mixture-of-experts mechanism that adapts to recent error dynamics. Moreover, an adaptive spatiotemporal smoothing component propagates error signals across neighboring regions and time slots, capturing coherent shifts in demand patterns. Extensive experiments on seven real-world datasets with three backbone models demonstrate that FORESEE consistently improves prediction accuracy, maintains robustness even when distribution shifts are minimal (avoiding performance degradation), and achieves the lowest computational overhead among existing online methods. By enabling real-time adaptation of traffic forecasting models with negligible computational cost, FORESEE paves the way for deploying reliable, up-to-date prediction systems in dynamic urban environments. Code and data are available at https://github.com/xiannanhuang/FORESEE
Authors: Kenton Tang, Yuzhu Chen, Fengxiang He
Abstract: Alignment and adaptation in large language models heavily rely on reinforcement learning from human feedback (RLHF); yet, theoretical understanding of its generalisability remains premature, especially when the learned reward could shift, and the KL control is estimated and clipped. To address this issue, we develop generalisation theory for RLHF that explicitly accounts for (1) \emph{reward shift}: reward models are trained on preference data from earlier or mixed behaviour policies while RLHF optimises the current policy on its own rollouts; and (2) \emph{clipped KL regularisation}: the KL regulariser is estimated from sampled log-probability ratios and then clipped for stabilisation, resulting in an error to RLHF. We present generalisation bounds for RLHF, suggesting that the generalisation error stems from a sampling error from prompts and rollouts, a reward shift error, and a KL clipping error. We also discuss special cases of (1) initialising RLHF parameters with a uniform prior over a finite space, and (2) training RLHF by stochastic gradient descent, as an Ornstein-Uhlenbeck process. The theory yields practical implications in (1) optimal KL clipping threshold, and (2) budget allocation in prompts, rollouts, and preference data.
Authors: JuneHyoung Kwon, MiHyeon Kim, Eunju Lee, Yoonji Lee, Seunghoon Lee, YoungBin Kim
Abstract: Machine unlearning, which enables a model to forget specific data, is crucial for ensuring data privacy and model reliability. However, its effectiveness can be severely undermined in real-world scenarios where models learn unintended biases from spurious correlations within the data. This paper investigates the unique challenges of unlearning from such biased models. We identify a novel phenomenon we term ``shortcut unlearning," where models exhibit an ``easy to learn, yet hard to forget" tendency. Specifically, models struggle to forget easily-learned, bias-aligned samples; instead of forgetting the class attribute, they unlearn the bias attribute, which can paradoxically improve accuracy on the class intended to be forgotten. To address this, we propose CUPID, a new unlearning framework inspired by the observation that samples with different biases exhibit distinct loss landscape sharpness. Our method first partitions the forget set into causal- and bias-approximated subsets based on sample sharpness, then disentangles model parameters into causal and bias pathways, and finally performs a targeted update by routing refined causal and bias gradients to their respective pathways. Extensive experiments on biased datasets including Waterbirds, BAR, and Biased NICO++ demonstrate that our method achieves state-of-the-art forgetting performance and effectively mitigates the shortcut unlearning problem.
Authors: Sagi Shaier
Abstract: We propose Excitation, a novel optimization framework designed to accelerate learning in sparse architectures such as Mixture-of-Experts (MoEs). Unlike traditional optimizers that treat all parameters uniformly, Excitation dynamically modulates updates using batch-level expert utilization. It introduces a competitive update dynamic that amplifies updates to highly-utilized experts and can selectively suppress low-utilization ones, effectively sharpening routing specialization. Notably, we identify a phenomenon of "structural confusion" in deep MoEs, where standard optimizers fail to establish functional signal paths; Excitation acts as a specialization catalyst, "rescuing" these models and enabling stable training where baselines remain trapped. Excitation is optimizer-, domain-, and model-agnostic, requires minimal integration effort, and introduces neither additional per-parameter optimizer state nor learnable parameters, making it highly viable for memory-constrained settings. Across language and vision tasks, Excitation consistently improves convergence speed and final performance in MoE models, indicating that active update modulation is a key mechanism for effective conditional computation.
Authors: Marcel Lamott, Saifullah Saifullah, Nauman Riaz, Yves-Noel Weweler, Tobias Alt-Veit, Ahmad Sarmad Ali, Muhammad Armaghan Shakir, Adrian Kalwa, Momina Moetesum, Andreas Dengel, Sheraz Ahmed, Faisal Shafait, Ulrich Schwanecke, Adrian Ulges
Abstract: Effective document intelligence models rely on large amounts of annotated training data. However, procuring sufficient and high-quality data poses significant challenges due to the labor-intensive and costly nature of data acquisition. Additionally, leveraging language models to annotate real documents raises concerns about data privacy. Synthetic document generation has emerged as a promising, privacy-preserving alternative. We propose DocDjinn, a novel framework for controllable synthetic document generation using Vision-Language Models (VLMs) that produces annotated documents from unlabeled seed samples. Our approach generates visually plausible and semantically consistent synthetic documents that follow the distribution of an existing source dataset through clustering-based seed selection with parametrized sampling. By enriching documents with realistic diffusion-based handwriting and contextual visual elements via semantic-visual decoupling, we generate diverse, high-quality annotated synthetic documents. We evaluate across eleven benchmarks spanning key information extraction, question answering, document classification, and document layout analysis. To our knowledge, this is the first work demonstrating that VLMs can generate faithful annotated document datasets at scale from unlabeled seeds that can effectively enrich or approximate real, manually annotated data for diverse document understanding tasks. We show that with only 100 real training samples, our framework achieves on average $87\%$ of the performance of the full real-world dataset. We publicly release our code and 140k+ synthetic document samples.
Authors: Ruichen Xu, Ying-Jun Angela Zhang, Jianwei Huang
Abstract: Differentially private federated learning faces a fundamental tension: privacy protection mechanisms that safeguard client data simultaneously create quantifiable privacy costs that discourage participation, undermining the collaborative training process. Existing incentive mechanisms rely on unbiased client selection, forcing servers to compensate even the most privacy-sensitive clients ("privacy stragglers"), leading to systemic inefficiency and suboptimal resource allocation. We introduce JSAM (Joint client Selection and privacy compensAtion Mechanism), a Bayesian-optimal framework that simultaneously optimizes client selection probabilities and privacy compensation to maximize training effectiveness under budget constraints. Our approach transforms a complex 2N-dimensional optimization problem into an efficient three-dimensional formulation through novel theoretical characterization of optimal selection strategies. We prove that servers should preferentially select privacy-tolerant clients while excluding high-sensitivity participants, and uncover the counter-intuitive insight that clients with minimal privacy sensitivity may incur the highest cumulative costs due to frequent participation. Extensive evaluations on MNIST and CIFAR-10 demonstrate that JSAM achieves up to 15% improvement in test accuracy compared to existing unbiased selection mechanisms while maintaining cost efficiency across varying data heterogeneity levels.
Authors: Lin Zhu, Lei You
Abstract: Counterfactual explanation (CE) is an important domain within post-hoc explainability. However, the explanations generated by most CE generators are often highly redundant. This work introduces an open-source Python library xai-cola, which provides an end-to-end pipeline for sparsifying CEs produced by arbitrary generators, reducing superfluous feature changes while preserving their validity. It offers a documented API that takes as input raw tabular data in pandas DataFrame form, a preprocessing object (for standardization and encoding), and a trained scikit-learn or PyTorch model. On this basis, users can either employ the built-in or externally imported CE generators. The library also implements several sparsification policies and includes visualization routines for analysing and comparing sparsified counterfactuals. xai-cola is released under the MIT license and can be installed from PyPI. Empirical experiments indicate that xai-cola produces sparser counterfactuals across several CE generators, reducing the number of modified features by up to 50% in our setting. The source code is available at https://github.com/understanding-ml/COLA.
Authors: Alexander Heinlein, Johannes Taraz
Abstract: Operator learning has the potential to strongly impact scientific computing by learning solution operators for differential equations, potentially accelerating multi-query tasks such as design optimization and uncertainty quantification by orders of magnitude. Despite proven universal approximation properties, deep operator networks (DeepONets) often exhibit limited accuracy and generalization in practice, which hinders their adoption. Understanding these limitations is therefore crucial for further advancing the approach. This work analyzes performance limitations of the classical DeepONet architecture. It is shown that the approximation error is dominated by the branch network when the internal dimension is sufficiently large, and that the learned trunk basis can often be replaced by classical basis functions without a significant impact on performance. To investigate this further, a modified DeepONet is constructed in which the trunk network is replaced by the left singular vectors of the training solution matrix. This modification yields several key insights. First, a spectral bias in the branch network is observed, with coefficients of dominant, low-frequency modes learned more effectively. Second, due to singular-value scaling of the branch coefficients, the overall branch error is dominated by modes with intermediate singular values rather than the smallest ones. Third, using a shared branch network for all mode coefficients, as in the standard architecture, improves generalization of small modes compared to a stacked architecture in which coefficients are computed separately. Finally, strong and detrimental coupling between modes in parameter space is identified.
Authors: Cuong Anh Pham, Praneeth Vepakomma, Samuel Horv\'ath
Abstract: Alleviating catastrophic forgetting while enabling further learning is a primary challenge in continual learning (CL). Orthogonal-based training methods have gained attention for their efficiency and strong theoretical properties, and many existing approaches enforce orthogonality through gradient projection. In this paper, we revisit orthogonality and exploit the fact that small singular values correspond to directions that are nearly orthogonal to the input space of previous tasks. Building on this principle, we introduce NESS (Null-space Estimated from Small Singular values), a CL method that applies orthogonality directly in the weight space rather than through gradient manipulation. Specifically, NESS constructs an approximate null space using the smallest singular values of each layer's input representation and parameterizes task-specific updates via a compact low-rank adaptation (LoRA-style) formulation constrained to this subspace. The subspace basis is fixed to preserve the null-space constraint, and only a single trainable matrix is learned for each task. This design ensures that the resulting updates remain approximately in the null space of previous inputs while enabling adaptation to new tasks. Our theoretical analysis and experiments on three benchmark datasets demonstrate competitive performance, low forgetting, and stable accuracy across tasks, highlighting the role of small singular values in continual learning. The code is available at https://github.com/pacman-ctm/NESS.
Authors: Ayush Mohanty, Paritosh Ramanan, Nagi Gebraeel
Abstract: Root cause analysis (RCA) in networked industrial systems, such as supply chains and power networks, is notoriously difficult due to unknown and dynamically evolving interdependencies among geographically distributed clients. These clients represent heterogeneous physical processes and industrial assets equipped with sensors that generate large volumes of nonlinear, high-dimensional, and heterogeneous IoT data. Classical RCA methods require partial or full knowledge of the system's dependency graph, which is rarely available in these complex networks. While federated learning (FL) offers a natural framework for decentralized settings, most existing FL methods assume homogeneous feature spaces and retrainable client models. These assumptions are not compatible with our problem setting. Different clients have different data features and often run fixed, proprietary models that cannot be modified. This paper presents a federated cross-client interdependency learning methodology for feature-partitioned, nonlinear time-series data, without requiring access to raw sensor streams or modifying proprietary client models. Each proprietary local client model is augmented with a Machine Learning (ML) model that encodes cross-client interdependencies. These ML models are coordinated via a global server that enforces representation consistency while preserving privacy through calibrated differential privacy noise. RCA is performed using model residuals and anomaly flags. We establish theoretical convergence guarantees and validate our approach on extensive simulations and a real-world industrial cybersecurity dataset.
Authors: Bahrul Ilmi Nasution, Mark Elliot, Richard Allmendinger
Abstract: Generative Adversarial Networks (GAN) have been used in many studies to synthesise mixed tabular data. Conditional tabular GAN (CTGAN) have been the most popular variant but struggle to effectively navigate the risk-utility trade-off. Bayesian GAN have received less attention for tabular data, but have been explored with unstructured data such as images and text. The most used technique employed in Bayesian GAN is Markov Chain Monte Carlo (MCMC), but it is computationally intensive, particularly in terms of weight storage. In this paper, we introduce Gaussian Approximation of CTGAN (GACTGAN), an integration of the Bayesian posterior approximation technique using Stochastic Weight Averaging-Gaussian (SWAG) within the CTGAN generator to synthesise tabular data, reducing computational overhead after the training phase. We demonstrate that GACTGAN yields better synthetic data compared to CTGAN, achieving better preservation of tabular structure and inferential statistics with less privacy risk. These results highlight GACTGAN as a simpler, effective implementation of Bayesian tabular synthesis.
Authors: Dusica Marijan, Hamza Haruna Mohammed, Bakht Zaman
Abstract: To reduce carbon emissions and minimize shipping costs, improving the fuel efficiency of ships is crucial. Various measures are taken to reduce the total fuel consumption of ships, including optimizing vessel parameters and selecting routes with the lowest fuel consumption. Different estimation methods are proposed for predicting fuel consumption, while various optimization methods are proposed to minimize fuel oil consumption. This paper provides a comprehensive review of methods for estimating and optimizing fuel oil consumption in maritime transport. Our novel contributions include categorizing fuel oil consumption \& estimation methods into physics-based, machine-learning, and hybrid models, exploring their strengths and limitations. Furthermore, we highlight the importance of data fusion techniques, which combine AIS, onboard sensors, and meteorological data to enhance accuracy. We make the first attempt to discuss the emerging role of Explainable AI in enhancing model transparency for decision-making. Uniquely, key challenges, including data quality, availability, and the need for real-time optimization, are identified, and future research directions are proposed to address these gaps, with a focus on hybrid models, real-time optimization, and the standardization of datasets.
Authors: Bendeg\'uz Sulyok, Gergely Palla, Filippo Radicchi, Santo Fortunato
Abstract: We investigate the robustness of sparse artificial neural networks trained with adaptive topology. We focus on a simple yet effective architecture consisting of three sparse layers with 99% sparsity followed by a dense layer, applied to image classification tasks such as MNIST and Fashion MNIST. By updating the topology of the sparse layers between each epoch, we achieve competitive accuracy despite the significantly reduced number of weights. Our primary contribution is a detailed analysis of the robustness of these networks, exploring their performance under various perturbations including random link removal, adversarial attack, and link weight shuffling. Through extensive experiments, we demonstrate that adaptive topology not only enhances efficiency but also maintains robustness. This work highlights the potential of adaptive sparse networks as a promising direction for developing efficient and reliable deep learning models.
Authors: Joseph Margaryan, Thomas Hamelryck
Abstract: Critical applications in areas such as medicine, robotics and autonomous systems require compact (i.e., memory efficient), uncertainty-aware neural networks suitable for edge and other resource-constrained deployments. We study compact spectral circulant and block-circulant-with-circulant-blocks (BCCB) layers: FFT-diagonalizable circular convolutions whose weights live directly in the real FFT (RFFT) half (1D) or half-plane (2D). Parameterizing filters in the frequency domain lets us impose simple spectral structure, perform structured variational inference in a low-dimensional weight space, and calculate exact layer spectral norms, enabling inexpensive global Lipschitz bounds and margin-based robustness diagnostics. By placing independent complex Gaussians on the Hermitian support we obtain a discrete instance of the spectral representation of stationary kernels, inducing an exact stationary Gaussian-process prior over filters on the discrete circle/torus. We exploit this to define a practical spectral prior and a Hermitian-aware low-rank-plus-diagonal variational posterior in real coordinates. Empirically, spectral circulant/BCCB layers are effective compact building blocks in both (variational) Bayesian and point estimate regimes: compact Bayesian neural networks on MNIST->Fashion-MNIST, variational heads on frozen CIFAR-10 features, and deterministic ViT projections on CIFAR-10/Tiny ImageNet; spectral layers match strong baselines while using substantially fewer parameters and with tighter Lipschitz certificates.
Authors: Hailiang Liu, Yan-Han Chen
Abstract: In recent years, the machine learning community has increasingly embraced the optimal transport (OT) framework for modeling distributional relationships. In this work, we introduce a sample-based neural solver for computing the Wasserstein geodesic between a source and target distribution, along with the associated velocity field. Building on the dynamical formulation of the optimal transport (OT) problem, we recast the constrained optimization as a minimax problem, using deep neural networks to approximate the relevant functions. This approach not only provides the Wasserstein geodesic but also recovers the OT map, enabling direct sampling from the target distribution. By estimating the OT map, we obtain velocity estimates along particle trajectories, which in turn allow us to learn the full velocity field. The framework is flexible and readily extends to general cost functions, including the commonly used quadratic cost. We demonstrate the effectiveness of our method through experiments on both synthetic and real datasets.
Authors: Pengcheng Hao, Ercan Engin Kuruoglu
Abstract: Bayesian deep learning (BDL) has emerged as a principled approach to produce reliable uncertainty estimates by integrating deep neural networks with Bayesian inference, and the selection of informative prior distributions remains a significant challenge. Various function-space variational inference (FSVI) regularisation methods have been presented, assigning meaningful priors over model predictions. However, these methods typically rely on a Gaussian prior, which fails to capture the heavy-tailed statistical characteristics inherent in neural network outputs. By contrast, this work proposes a novel function-space empirical Bayes regularisation framework -- termed ST-FS-EB -- which employs heavy-tailed Student's $t$ priors in both parameter and function spaces. Also, we approximate the posterior distribution through variational inference (VI), inducing an evidence lower bound (ELBO) objective based on Monte Carlo (MC) dropout. Furthermore, the proposed method is evaluated against various VI-based BDL baselines, and the results demonstrate its robust performance in in-distribution prediction, out-of-distribution (OOD) detection and handling distribution shifts.
Authors: Sterre de Jonge (Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, The Netherlands), Elisabeth J. Vinke (Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, The Netherlands, Department of Epidemiology, Erasmus MC, Rotterdam, The Netherlands), Meike W. Vernooij (Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, The Netherlands, Department of Epidemiology, Erasmus MC, Rotterdam, The Netherlands), Daniel C. Alexander (Hawkes Institute, Department of Computer Science, University College London, London, United Kingdom), Alexandra L. Young (Hawkes Institute, Department of Computer Science, University College London, London, United Kingdom), Esther E. Bron (Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, The Netherlands)
Abstract: Disease progression modeling provides a robust framework to identify long-term disease trajectories from short-term biomarker data. It is a valuable tool to gain a deeper understanding of diseases with a long disease trajectory, such as Alzheimer's disease. A key limitation of most disease progression models is that they are specific to a single data type (e.g., continuous data), thereby limiting their applicability to heterogeneous, real-world datasets. To address this limitation, we propose the Mixed Events model, a novel disease progression model that handles both discrete and continuous data types. This model is implemented within the Subtype and Stage Inference (SuStaIn) framework, resulting in Mixed-SuStaIn, enabling subtype and progression modeling. We demonstrate the effectiveness of Mixed-SuStaIn through simulation experiments and real-world data from the Alzheimer's Disease Neuroimaging Initiative, showing that it performs well on mixed datasets. The code is available at: https://github.com/ucl-pond/pySuStaIn.
Authors: Hamza Haruna Mohammed, Dusica Marijan, Arnbj{\o}rn Maressa
Abstract: Accurate prediction of shaft rotational speed, shaft power, and fuel consumption is crucial for enhancing operational efficiency and sustainability in maritime transportation. Conventional physics-based models provide interpretability but struggle with real-world variability, while purely data-driven approaches achieve accuracy at the expense of physical plausibility. This paper introduces a Physics-Informed Kolmogorov-Arnold Network (PI-KAN), a hybrid method that integrates interpretable univariate feature transformations with a physics-informed loss function and a leakage-free chained prediction pipeline. Using operational and environmental data from five cargo vessels, PI-KAN consistently outperforms the traditional polynomial method and neural network baselines. The model achieves the lowest mean absolute error (MAE) and root mean squared error (RMSE), and the highest coefficient of determination (R^2) for shaft power and fuel consumption across all vessels, while maintaining physically consistent behavior. Interpretability analysis reveals rediscovery of domain-consistent dependencies, such as cubic-like speed-power relationships and cosine-like wave and wind effects. These results demonstrate that PI-KAN achieves both predictive accuracy and interpretability, offering a robust tool for vessel performance monitoring and decision support in operational settings.
Authors: Jinpeng Li, Zhongyi Pei, Huaze Xue, Bojian Zheng, Chen Wang, Jianmin Wang
Abstract: Time-series foundation models (TSFMs) have achieved strong univariate forecasting through large-scale pre-training, yet effectively extending this success to multivariate forecasting remains challenging. To address this, we propose DualWeaver, a novel framework that adapts univariate TSFMs (Uni-TSFMs) for multivariate forecasting by using a pair of learnable, structurally symmetric surrogate series. Generated by a shared auxiliary feature-fusion module that captures cross-variable dependencies, these surrogates are mapped to TSFM-compatible series via the forecasting objective. The symmetric structure enables parameter-free reconstruction of final predictions directly from the surrogates, without additional parametric decoding. A theoretically grounded regularization term is further introduced to enhance robustness against adaptation collapse. Extensive experiments on diverse real-world datasets show that DualWeaver outperforms state-of-the-art multivariate forecasters in both accuracy and stability. We release the code at https://github.com/li-jinpeng/DualWeaver.
Authors: Pantia-Marina Alchirch, Dimitrios I. Diochnos
Abstract: Many real-world applications provide a continuous stream of data that is subsequently used by machine learning models to solve regression tasks of interest. Hoeffding trees and their variants have a long-standing tradition due to their effectiveness, either alone or as base models in broader ensembles. At the same time a recent line of work in batch learning has shown that kernel density estimation (KDE) is an effective approach for smoothed predictions in imbalanced regression tasks [Yang et al., 2021]. Moreover, another recent line of work for batch learning, called hierarchical shrinkage (HS) [Agarwal et al., 2022], has introduced a post-hoc regularization method for decision trees that does not alter the structure of the learned tree. Using a telescoping argument we cast KDE to streaming environments and extend the implementation of HS to incremental decision tree models. Armed with these extensions we investigate the performance of decision trees that may enjoy such options in datasets commonly used for regression in online settings. We conclude that KDE is beneficial in the early parts of the stream, while HS hardly, if ever, offers performance benefits. Our code is publicly available at: https://github.com/marinaAlchirch/DSFA_2026.
Authors: Andrea Apicella, Francesco Isgr\`o, Andrea Pollastro, Roberto Prevete
Abstract: Despite the extensive literature on training loss functions, the evaluation of generalization on the validation set remains underexplored. In this work, we conduct a systematic empirical and statistical study of how the validation criterion used for model selection affects test performance in neural classifiers, with attention to early stopping. Using fully connected networks on standard benchmarks under $k$-fold evaluation, we compare: (i) early stopping with patience and (ii) post-hoc selection over all epochs (i.e. no early stopping). Models are trained with cross-entropy, C-Loss, or PolyLoss; the model parameter selection on the validation set is made using accuracy or one of the three loss functions, each considered independently. Three main findings emerge. (1) Early stopping based on validation accuracy performs worst, consistently selecting checkpoints with lower test accuracy than both loss-based early stopping and post-hoc selection. (2) Loss-based validation criteria yield comparable and more stable test accuracy. (3) Across datasets and folds, any single validation rule often underperforms the test-optimal checkpoint. Overall, the selected model typically achieves test-set performance statistically lower than the best performance across all epochs, regardless of the validation criterion. Our results suggest avoiding validation accuracy (in particular with early stopping) for parameter selection, favoring loss-based validation criteria.
Authors: Ilias Diakonikolas, Giannis Iakovidis, Daniel M. Kane, Sihan Liu
Abstract: We study the basic task of mean estimation in the presence of mean-shift contamination. In the mean-shift contamination model, an adversary is allowed to replace a small constant fraction of the clean samples by samples drawn from arbitrarily shifted versions of the base distribution. Prior work characterized the sample complexity of this task for the special cases of the Gaussian and Laplace distributions. Specifically, it was shown that consistent estimation is possible in these cases, a property that is provably impossible in Huber's contamination model. An open question posed in earlier work was to determine the sample complexity of mean estimation in the mean-shift contamination model for general base distributions. In this work, we study and essentially resolve this open question. Specifically, we show that, under mild spectral conditions on the characteristic function of the (potentially multivariate) base distribution, there exists a sample-efficient algorithm that estimates the target mean to any desired accuracy. We complement our upper bound with a qualitatively matching sample complexity lower bound. Our techniques make critical use of Fourier analysis, and in particular introduce the notion of a Fourier witness as an essential ingredient of our upper and lower bounds.
Authors: Qunyou Liu, Pengbo Yu, Marina Zapater, David Atienza
Abstract: Deep neural networks (DNNs) are essential for performing advanced tasks on edge or mobile devices, yet their deployment is often hindered by severe resource constraints, including limited memory, energy, and computational power. While uniform quantization provides a straightforward approach to compress model and reduce hardware requirement, it fails to fully leverage the varying robustness across layers, and often lead to accuracy degradation or suboptimal resource usage, particularly at low bitwidths. In contrast, heterogeneous quantization, which allocates different bitwidths to individual layers, can mitigate these drawbacks. Nonetheless, current heterogeneous quantization methods either needs huge brute-force design space search or lacks the adaptability to meet different hardware conditions, such as memory size, energy budget, and latency requirement. Filling these gaps, this work introduces \textbf{\textit{SigmaQuant}}, an adaptive layer-wise heterogeneous quantization framework designed to efficiently balance accuracy and resource usage for varied edge environments without exhaustive search.
Authors: Yining Li, Peizhong Ju, Ness Shroff
Abstract: Reinforcement Learning from Human Feedback (RLHF) plays a significant role in aligning Large Language Models (LLMs) with human preferences. While RLHF with expected reward constraints can be formulated as a primal-dual optimization problem, standard primal-dual methods only guarantee convergence with a distributional policy where the saddle-point problem is in convex-concave form. Moreover, standard primal-dual methods may exhibit instability or divergence in the last iterate under policy parameterization in practical applications. In this work, we propose a universal primal-dual framework for safe RLHF that unifies a broad class of existing alignment algorithms, including safe-RLHF, one-shot, and multi-shot based methods. Building on this framework, we introduce an optimistic primal-dual (OPD) algorithm that incorporates predictive updates for both primal and dual variables to stabilize saddle-point dynamics. We establish last-iterate convergence guarantees for the proposed method, covering both exact policy optimization in the distributional space and convergence to a neighborhood of the optimal solution whose gap is related to approximation error and bias under parameterized policies. Our analysis reveals that optimism plays a crucial role in mitigating oscillations inherent to constrained alignment objectives, thereby closing a key theoretical gap between constrained RL and practical RLHF.
Authors: Mhd Jawad Al Rahwanji, Sascha Xu, Nils Philipp Walter, Jilles Vreeken
Abstract: In many applications, it is important to identify subpopulations that survive longer or shorter than the rest of the population. In medicine, for example, it allows determining which patients benefit from treatment, and in predictive maintenance, which components are more likely to fail. Existing methods for discovering subgroups with exceptional survival characteristics require restrictive assumptions about the survival model (e.g. proportional hazards), pre-discretized features, and, as they compare average statistics, tend to overlook individual deviations. In this paper, we propose Sysurv, a fully differentiable, non-parametric method that leverages random survival forests to learn individual survival curves, automatically learns conditions and how to combine these into inherently interpretable rules, so as to select subgroups with exceptional survival characteristics. Empirical evaluation on a wide range of datasets and settings, including a case study on cancer data, shows that Sysurv reveals insightful and actionable survival subgroups.
Authors: Nathalie C. Pinheiro, Donghu Guo, Hannah P. Menke, Aniket C. Joshi, Claire E. Heaney, Ahmed H. ElSheikh, Christopher C. Pain
Abstract: Modelling rock-fluid interaction requires solving a set of partial differential equations (PDEs) to predict the flow behaviour and the reactions of the fluid with the rock on the interfaces. Conventional high-fidelity numerical models require a high resolution to obtain reliable results, resulting in huge computational expense. This restricts the applicability of these models for multi-query problems, such as uncertainty quantification and optimisation, which require running numerous scenarios. As a cheaper alternative to high-fidelity models, this work develops eight surrogate models for predicting the fluid flow in porous media. Four of these are reduced-order models (ROM) based on one neural network for compression and another for prediction. The other four are single neural networks with the property of grid-size invariance; a term which we use to refer to image-to-image models that are capable of inferring on computational domains that are larger than those used during training. In addition to the novel grid-size-invariant framework for surrogate models, we compare the predictive performance of UNet and UNet++ architectures, and demonstrate that UNet++ outperforms UNet for surrogate models. Furthermore, we show that the grid-size-invariant approach is a reliable way to reduce memory consumption during training, resulting in good correlation between predicted and ground-truth values and outperforming the ROMs analysed. The application analysed is particularly challenging because fluid-induced rock dissolution results in a non-static solid field and, consequently, it cannot be used to help in adjustments of the future prediction.
Authors: Rui Yang, Qianhui Wu, Zhaoyang Wang, Hanyang Chen, Ke Yang, Hao Cheng, Huaxiu Yao, Baoling Peng, Huan Zhang, Jianfeng Gao, Tong Zhang
Abstract: Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation tasks. This gap stems from two limitations: a shortage of high-quality, action-aligned reasoning data, and the direct adoption of generic post-training pipelines that overlook the unique challenges of GUI agents. We identify two fundamental issues in these pipelines: (i) standard SFT with CoT reasoning often hurts grounding, and (ii) step-wise RLVR-tyle training faces partial verifiability, where multiple actions can be correct but only a single demonstrated action is used for verification. This makes offline step-wise metrics weak predictors of online task success. In this work, we present GUI-Libra, a tailored training recipe that addresses these challenges. First, to mitigate the scarcity of action-aligned reasoning data, we introduce a data construction and filtering pipeline and release a curated 81K GUI reasoning dataset. Second, to reconcile reasoning with grounding, we propose action-aware SFT that mixes reasoning-then-action and direct-action data and reweights tokens to emphasize action and grounding. Third, to stabilize RL under partial verifiability, we identify the overlooked importance of KL regularization in RLVR and show that a KL trust region is critical for improving offline-to-online predictability; we further introduce success-adaptive scaling to downweight unreliable negative gradients. Across diverse web and mobile benchmarks, GUI-Libra consistently improves both step-wise accuracy and end-to-end task completion. Our results suggest that carefully designed post-training and data curation can unlock significantly stronger task-solving capabilities without costly online data collection. We release our dataset, code, and models to facilitate further research on data-efficient post-training for reasoning-capable GUI agents.
Authors: Ria Stevens, Fangshuo Liao, Barbara Su, Jianqiang Li, Anastasios Kyrillidis
Abstract: We approach the Max-3-Cut problem through the lens of maximizing complex-valued quadratic forms and demonstrate that low-rank structure in the objective matrix can be exploited, leading to alternative algorithms to classical semidefinite programming (SDP) relaxations and heuristic techniques. We propose an algorithm for maximizing these quadratic forms over a domain of size $K$ that enumerates and evaluates a set of $O\left(n^{2r-1}\right)$ candidate solutions, where $n$ is the dimension of the matrix and $r$ represents the rank of an approximation of the objective. We prove that this candidate set is guaranteed to include the exact maximizer when $K=3$ (corresponding to Max-3-Cut) and the objective is low-rank, and provide approximation guarantees when the objective is a perturbation of a low-rank matrix. This construction results in a family of novel, inherently parallelizable and theoretically-motivated algorithms for Max-3-Cut. Extensive experimental results demonstrate that our approach achieves performance comparable to existing algorithms across a wide range of graphs, while being highly scalable.
Authors: Takato Yasuno
Abstract: Natural disasters such as earthquakes, torrential rainfall, floods, and volcanic eruptions occur with extremely low frequency and affect limited geographic areas. When individuals face disaster situations, they often experience confusion and lack the domain-specific knowledge and experience necessary to determine appropriate responses and actions. While disaster information is continuously updated, even when utilizing RAG search and large language models for inquiries, obtaining relevant domain knowledge about natural disasters and experiences similar to one's specific situation is not guaranteed. When hallucinations are included in disaster question answering, artificial misinformation may spread and exacerbate confusion. This work introduces a disaster-focused question answering system based on Japanese disaster situations and response experiences. Utilizing the cl-tohoku/bert-base-japanese-v3 + Bi-LSTM + Enhanced Position Heads architecture with LoRA efficiency optimization, we achieved 70.4\% End Position accuracy with only 5.7\% of the total parameters (6.7M/117M). Experimental results demonstrate that the combination of Japanese BERT-base optimization and Bi-LSTM contextual understanding achieves accuracy levels suitable for real disaster response scenarios, attaining a 0.885 Span F1 score. Future challenges include: establishing natural disaster Q\&A benchmark datasets, fine-tuning foundation models with disaster knowledge, developing lightweight and power-efficient edge AI Disaster Q\&A applications for situations with insufficient power and communication during disasters, and addressing disaster knowledge base updates and continual learning capabilities.
Authors: Amin Banayeeanzade, Qingchuan Yang, Deqing Fu, Spencer Hong, Erin Babinsky, Alfy Samuel, Anoop Kumar, Robin Jia, Sai Praneeth Karimireddy
Abstract: High-quality data is essential for modern machine learning, yet many valuable corpora are sensitive and cannot be freely shared. Synthetic data offers a practical substitute for downstream development, and large language models (LLMs) have emerged as powerful engines for generating it. However, existing private text generation methods are severely inefficient: they are data-intensive, computationally slow, and often require large private corpora or batch sizes to achieve usable quality. We introduce EPSVec, a differentially-private lightweight alternative that steers LLM generation using *dataset vectors*--directions in activation space that capture the distributional gap between private data and public priors. EPSVec extracts and sanitizes steering vectors just once and then performs standard decoding. This decouples the privacy budget from generation, enabling arbitrarily many synthetic samples without additional privacy cost and yielding strong fidelity even in low-data regimes. Furthermore, we enhance our method by utilizing pretrained (base) models and introducing fixed-shot prompting to boost generation diversity and fidelity. Our experiments demonstrate that EPSVec outperforms existing baselines in distributional alignment and downstream utility, particularly in low-data regimes, while significantly reducing computational overhead.
Authors: Subhadip Mitra
Abstract: We present a memory system for AI agents that treats stored information as continuous fields governed by partial differential equations rather than discrete entries in a database. The approach draws from classical field theory: memories diffuse through semantic space, decay thermodynamically based on importance, and interact through field coupling in multi-agent scenarios. We evaluate the system on two established long-context benchmarks: LoCoMo (ACL 2024) with 300-turn conversations across 35 sessions, and LongMemEval (ICLR 2025) testing multi-session reasoning over 500+ turns. On LongMemEval, the field-theoretic approach achieves significant improvements: +116% F1 on multi-session reasoning (p<0.01, d= 3.06), +43.8% on temporal reasoning (p<0.001, d= 9.21), and +27.8% retrieval recall on knowledge updates (p<0.001, d= 5.00). Multi-agent experiments show near-perfect collective intelligence (>99.8%) through field coupling. Code is available at github.com/rotalabs/rotalabs-fieldmem.
Authors: Riya Adsul, Balachandra Devarangadi Sunil, Isha Nalawade, Sudharshan Govindan
Abstract: Parameter efficient fine tuning methods like LoRA have enabled task specific adaptation of large language models, but efficiently composing multiple specialized adapters for unseen tasks remains challenging. We present a novel framework for dynamic LoRA adapter composition that leverages similarity retrieval in vector databases to enable zero-shot generalization across diverse NLP tasks. Our approach constructs a task-aware vector database by embedding training examples from 22 datasets spanning commonsense reasoning, question answering, natural language inference, and sentiment analysis. At inference time, we retrieve the most similar training examples, compute task similarity distributions via nucleus sampling, and dynamically merge relevant LoRA adapters using retrieval weighted fusion strategies. We evaluated four merging methods Linear, Concatenation, TIES, and Magnitude Prune demonstrating that our dataset centric retrieval approach often matches or exceeds the performance of individually fine-tuned task-specific adapters. Notably, Linear merging achieves 70.95% on PIQA and 77.62% on RTE, substantially outperforming single-task baselines (46% and 52%, respectively). Our framework requires no additional retriever training, operates with frozen embeddings, and enables efficient, interpretable adapter composition. These results suggest that retrieval based dynamic merging offers a promising direction for scalable, parameter-efficient multitask learning without requiring full model retraining for each new task.
Authors: Yuetao Chen, Xuliang Wang, Xinzhou Zheng, Ming Li, Peng Wang, Hong Xu
Abstract: Speculative decoding has emerged as a pivotal technique to accelerate LLM inference by employing a lightweight draft model to generate candidate tokens that are subsequently verified by the target model in parallel. However, while this paradigm successfully increases the arithmetic intensity of memory-bound inference, it causes significant compute inefficiency: the majority of draft tokens fail verification and are discarded, resulting in waste of computation. Motivated by the goal of recollecting this wasted computation, we propose a novel system that transforms discarded drafts into reusable tokens. Our key insight is to perform auto-regressive prediction at the hidden states level and postpone the integrating token information after the hidden states generation, so the draft hidden states are not contaminated by incorrect tokens, enabling hidden state reuse. To implement such a system, first we introduce a draft model architecture based on auto-regressive hidden states, which preserves richer semantics than token-based drafters to facilitate draft repurposing. Second, we design an efficient token information injection mechanism that leverages our specialized draft model to construct high-quality draft token trees and enables resampling tokens from verification failures. Third, we eliminate the overhead hidden in our design to further maximize hardware utilization. We conducted extensive evaluations against various baselines, demonstrating up to a 3.3x speedup against standard speculative decoding.
Authors: Mohammed Hamdan, Vincenzo Dentamaro, Giuseppe Pirlo, Mohamed Cheriet
Abstract: We investigate whether progressive data scheduling -- a curriculum learning strategy that incrementally increases training data exposure (33\%$\rightarrow$67\%$\rightarrow$100\%) -- yields consistent efficiency gains across architecturally distinct document understanding models. By evaluating BERT (text-only, 110M parameters) and LayoutLMv3 (multimodal, 126M parameters) on the FUNSD and CORD benchmarks, we establish that this schedule reduces wall-clock training time by approximately 33\%, commensurate with the reduction from 6.67 to 10.0 effective epoch-equivalents of data. To isolate curriculum effects from compute reduction, we introduce matched-compute baselines (Standard-7) that control for total gradient updates. On the FUNSD dataset, the curriculum significantly outperforms the matched-compute baseline for BERT ($\Delta$F1 = +0.023, $p=0.022$, $d_z=3.83$), constituting evidence for a genuine scheduling benefit in capacity-constrained models. In contrast, no analogous benefit is observed for LayoutLMv3 ($p=0.621$), whose multimodal representations provide sufficient inductive bias. On the CORD dataset, all conditions converge to equivalent F1 scores ($\geq$0.947) irrespective of scheduling, indicating a performance ceiling. Schedule ablations comparing progressive, two-phase, reverse, and random pacing confirm that the efficiency gain derives from reduced data volume rather than ordering. Taken together, these findings demonstrate that progressive scheduling is a reliable compute-reduction strategy across model families, with curriculum-specific benefits contingent on the interaction between model capacity and task complexity.
Authors: Sumin Kim, Jihoon Kwon, Yoon Kim, Nicole Kagan, Raffi Khatchadourian, Wonbin Ahn, Alejandro Lopez-Lira, Jaewon Lee, Yoontae Hwang, Oscar Levy, Yongjae Lee, Chanyeol Choi
Abstract: Mention markets, a type of prediction market in which contracts resolve based on whether a specified keyword is mentioned during a future public event, require accurate probabilistic forecasts of keyword-mention outcomes. While recent work shows that large language models (LLMs) can generate forecasts competitive with human forecasters, it remains unclear how input context should be designed to support accurate prediction. In this paper, we study this question through experiments on earnings-call mention markets, which require forecasting whether a company will mention a specified keyword during its upcoming call. We run controlled comparisons varying (i) which contextual information is provided (news and/or prior earnings-call transcripts) and (ii) how \textit{market probability}, (i.e., prediction market contract price) is used. We introduce Market-Conditioned Prompting (MCP), which explicitly treats the market-implied probability as a prior and instructs the LLM to update this prior using textual evidence, rather than re-predicting the base rate from scratch. In our experiments, we find three insights: (1) richer context consistently improves forecasting performance; (2) market-conditioned prompting (MCP), which treats the market probability as a prior and updates it using textual evidence, yields better-calibrated forecasts; and (3) a mixture of the market probability and MCP (MixMCP) outperforms the market baseline. By dampening the LLM's posterior update with the market prior, MixMCP yields more robust predictions than either the market or the LLM alone.
Authors: Rahul D Ray
Abstract: Security monitoring systems typically treat anomaly detection as identifying statistical deviations from observed data distributions. In cryptographic traffic analysis, however, violations are defined not by rarity but by explicit policy constraints, including key reuse prohibition, downgrade prevention, and bounded key lifetimes. This fundamental mismatch limits the interpretability and adaptability of conventional anomaly detection methods. We introduce INTACT (INTent-Aware Cryptographic Traffic), a policy-conditioned framework that reformulates violation detection as conditional constraint learning. Instead of learning a static decision boundary over behavioral features, INTACT models the probability of violation conditioned on both observed behavior and declared security intent. The architecture factorizes representation learning into behavioral and intent encoders whose fused embeddings produce a violation score, yielding a policy-parameterized family of decision boundaries. We evaluate the framework on a real-world network flow dataset and a 210,000-trace synthetic multi-intent cryptographic dataset. INTACT matches or exceeds strong unsupervised and supervised baselines, achieving near-perfect discrimination (AUROC up to 1.0000) in the real dataset and consistent superiority in detecting relational and composite violations in the synthetic setting. These results demonstrate that explicit intent conditioning improves discrimination, interpretability, and robustness in cryptographic monitoring.
Authors: Sasha Robinson, Kerem Oktar, Katherine M. Collins, Ilia Sucholutsky, Kelsey R. Allen
Abstract: With increasing integration of Large Language Models (LLMs) into areas of high-stakes human decision-making, it is important to understand the risks they introduce as advisors. To be useful advisors, LLMs must sift through large amounts of content, written with both benevolent and malicious intent, and then use this information to convince a user to take a specific action. This involves two social capacities: vigilance (the ability to determine which information to use, and which to discard) and persuasion (synthesizing the available evidence to make a convincing argument). While existing work has investigated these capacities in isolation, there has been little prior investigation of how these capacities may be linked. Here, we use a simple multi-turn puzzle-solving game, Sokoban, to study LLMs' abilities to persuade and be rationally vigilant towards other LLM agents. We find that puzzle-solving performance, persuasive capability, and vigilance are dissociable capacities in LLMs. Performing well on the game does not automatically mean a model can detect when it is being misled, even if the possibility of deception is explicitly mentioned. % as part of the prompt. However, LLMs do consistently modulate their token use, using fewer tokens to reason when advice is benevolent and more when it is malicious, even if they are still persuaded to take actions leading them to failure. To our knowledge, our work presents the first investigation of the relationship between persuasion, vigilance, and task performance in LLMs, and suggests that monitoring all three independently will be critical for future work in AI safety.
Authors: Hyeonje Choi, Jeongsoo Lee, Hyojun Lee, Jay-Yoon Lee
Abstract: We introduce \ToolMATH, a math-grounded benchmark that evaluates tool-augmented language models in realistic multi-tool environments where the output depends on calling schema-specified tools and sustaining multi-step execution. It turns math problems into a controlled, correctness-checkable benchmark with tool sets, enabling systematic evaluation of model reliability under (1) large, overlapping tool catalogs and (2) the absence of the intended capability. \ToolMATH provides actionable diagnostic evidence of failure modes in tool-augmented agents, helping identify the control mechanisms required for robustness. \ToolMATH roughly contains 8k questions and 12k tools; we provide an additional hard-set \ToolMATHHard with questions and tools. Our evaluation reveals that the key failure factor is due to the inability to reason, leading to the accumulation of intermediate results' errors and constrain later decisions. Tool-list redundancy do not simply add noise, but amplify small early deviations into irreversible execution drift. The benchmark highlights that when the intended capability is missing, distractor tools can sometimes serve as partial substitutes in solution paths, yet they can also mislead models into ungrounded tool trajectories. Finally, comparisons between tool-use protocols emphasize that improvements come less from local action selection and more from long-range plan coherence and disciplined use of observations.
Authors: Reuben Cohn-Gordon, Uro\v{s} Seljak, Dries Sels
Abstract: Hamiltonian Monte Carlo (HMC) is a state of the art method for sampling from distributions with differentiable densities, but can converge slowly when applied to challenging multimodal problems. Running HMC with a time varying Hamiltonian, in order to interpolate from an initial tractable distribution to the target of interest, can address this problem. In conjunction with a weighting scheme to eliminate bias, this can be viewed as a special case of Sequential Monte Carlo (SMC) sampling \cite{doucet2001introduction}. However, this approach can be inefficient, since it requires slow change between the initial and final distribution. Inspired by \cite{sels2017minimizing}, where a learned \emph{counterdiabatic} term added to the Hamiltonian allows for efficient quantum state preparation, we propose \emph{Counterdiabatic Hamiltonian Monte Carlo} (CHMC), which can be viewed as an SMC sampler with a more efficient kernel. We establish its relationship to recent proposals for accelerating gradient-based sampling with learned drift terms, and demonstrate on simple benchmark problems.
Authors: Micha{\l} Szyfelbein, Dariusz Dereniowski
Abstract: This work considers a number of optimization problems and reductive relations between them. The two main problems we are interested in are the \emph{Optimal Decision Tree} and \emph{Set Cover}. We study these two fundamental tasks under precedence constraints, that is, if a test (or set) $X$ is a predecessor of $Y$, then in any feasible decision tree $X$ needs to be an ancestor of $Y$ (or respectively, if $Y$ is added to set cover, then so must be $X$). For the Optimal Decision Tree we consider two optimization criteria: worst case identification time (height of the tree) or the average identification time. Similarly, for the Set Cover we study two cost measures: the size of the cover or the average cover time. Our approach is to develop a number of algorithmic reductions, where an approximation algorithm for one problem provides an approximation for another via a black-box usage of a procedure for the former. En route we introduce other optimization problems either to complete the `reduction landscape' or because they hold the essence of combinatorial structure of our problems. The latter is brought by a problem of finding a maximum density precedence closed subfamily, where the density is defined as the ratio of the number of items the family covers to its size. By doing so we provide $\cO^*(\sqrt{m})$-approximation algorithms for all of the aforementioned problems. The picture is complemented by a number of hardness reductions that provide $o(m^{1/12-\epsilon})$-inapproximability results for the decision tree and covering problems. Besides giving a complete set of results for general precedence constraints, we also provide polylogarithmic approximation guarantees for two most typically studied and applicable precedence types, outforests and inforests. By providing corresponding hardness results, we show these results to be tight.
Authors: Ali Siahkoohi, Hyunwoo Oh
Abstract: Bayesian inference for inverse problems involves computing expectations under posterior distributions -- e.g., posterior means, variances, or predictive quantities -- typically via Monte Carlo (MC) estimation. When the quantity of interest varies significantly under the posterior, accurate estimates demand many samples -- a cost often prohibitive for partial differential equation-constrained problems. To address this challenge, we introduce conditional neural control variates, a modular method that learns amortized control variates from joint model-data samples to reduce the variance of MC estimators. To scale to high-dimensional problems, we leverage Stein's identity to design an architecture based on an ensemble of hierarchical coupling layers with tractable Jacobian trace computation. Training requires: (i) samples from the joint distribution of unknown parameters and observed data; and (ii) the posterior score function, which can be computed from physics-based likelihood evaluations, neural operator surrogates, or learned generative models such as conditional normalizing flows. Once trained, the control variates generalize across observations without retraining. We validate our approach on stylized and partial differential equation-constrained Darcy flow inverse problems, demonstrating substantial variance reduction, even when the analytical score is replaced by a learned surrogate.
Authors: Oliver Hoidn, Aashwin Mishra, Steven Henke, Albert Vong, Matthew Seaberg
Abstract: Ptychographic imaging at synchrotron and XFEL sources requires dense overlapping scans, limiting throughput and increasing dose. Extending coherent diffractive imaging to overlap-free operation on extended samples remains an open problem. Here, we extend PtychoPINN (O. Hoidn \emph{et al.}, \emph{Scientific Reports} \textbf{13}, 22789, 2023) to deliver \emph{overlap-free, single-shot} reconstructions in a Fresnel coherent diffraction imaging (CDI) geometry while also accelerating conventional multi-shot ptychography. The framework couples a differentiable forward model of coherent scattering with a Poisson photon-counting likelihood; real-space overlap enters as a tunable parameter via coordinate-based grouping rather than a hard requirement. On synthetic benchmarks, reconstructions remain accurate at low counts ($\sim\!10^4$ photons/frame), and overlap-free single-shot reconstruction with an experimental probe reaches amplitude structural similarity (SSIM) 0.904, compared with 0.968 for overlap-constrained reconstruction. Against a data-saturated supervised model with the same backbone (16,384 training images), PtychoPINN achieves higher SSIM with only 1,024 images and generalizes to unseen illumination profiles. Per-graphics processing unit (GPU) throughput is approximately $40\times$ that of least-squares maximum-likelihood (LSQ-ML) reconstruction at matched $128\times128$ resolution. These results, validated on experimental data from the Advanced Photon Source and the Linac Coherent Light Source, unify single-exposure Fresnel CDI and overlapped ptychography within one framework, supporting dose-efficient, high-throughput imaging at modern light sources.
Authors: Dominik Schneider, Lalithkumar Seenivasan, Sampath Rapuri, Vishalroshan Anil, Aiza Maksutova, Yiqing Shen, Jan Emily Mangulabnan, Hao Ding, Jose L. Porras, Masaru Ishii, Mathias Unberath
Abstract: Purpose: Curating large-scale datasets of operating room (OR) workflow, encompassing rare, safety-critical, or atypical events, remains operationally and ethically challenging. This data bottleneck complicates the development of ambient intelligence for detecting, understanding, and mitigating rare or safety-critical events in the OR. Methods: This work presents an OR video diffusion framework that enables controlled synthesis of rare and safety-critical events. The framework integrates a geometric abstraction module, a conditioning module, and a fine-tuned diffusion model to first transform OR scenes into abstract geometric representations, then condition the synthesis process, and finally generate realistic OR event videos. Using this framework, we also curate a synthetic dataset to train and validate AI models for detecting near-misses of sterile-field violations. Results: In synthesizing routine OR events, our method outperforms off-the-shelf video diffusion baselines, achieving lower FVD/LPIPS and higher SSIM/PSNR in both in- and out-of-domain datasets. Through qualitative results, we illustrate its ability for controlled video synthesis of counterfactual events. An AI model trained and validated on the generated synthetic data achieved a RECALL of 70.13% in detecting near safety-critical events. Finally, we conduct an ablation study to quantify performance gains from key design choices. Conclusion: Our solution enables controlled synthesis of routine and rare OR events from abstract geometric representations. Beyond demonstrating its capability to generate rare and safety-critical scenarios, we show its potential to support the development of ambient intelligence models.
Authors: Mohammadreza Ghaffarzadeh-Esfahani, Nahid Yousefian, Ebrahim Heidari-Farsani, Ali Akbar Omidvarian, Sepehr Ghahraei, Atena Farangi, AmirBahador Boroumand
Abstract: Extracting clinical information from medical transcripts in low-resource languages remains a significant challenge in healthcare natural language processing (NLP). This study evaluates a two-step pipeline combining Aya-expanse-8B as a Persian-to-English translation model with five open-source small language models (SLMs) -- Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, Llama-3.2-3B-Instruct, Qwen2.5-1.5B-Instruct, and Gemma-3-1B-it -- for binary extraction of 13 clinical features from 1,221 anonymized Persian transcripts collected at a cancer palliative care call center. Using a few-shot prompting strategy without fine-tuning, models were assessed on macro-averaged F1-score, Matthews Correlation Coefficient (MCC), sensitivity, and specificity to account for class imbalance. Qwen2.5-7B-Instruct achieved the highest overall performance (median macro-F1: 0.899; MCC: 0.797), while Gemma-3-1B-it showed the weakest results. Larger models (7B--8B parameters) consistently outperformed smaller counterparts in sensitivity and MCC. A bilingual analysis of Aya-expanse-8B revealed that translating Persian transcripts to English improved sensitivity, reduced missing outputs, and boosted metrics robust to class imbalance, though at the cost of slightly lower specificity and precision. Feature-level results showed reliable extraction of physiological symptoms across most models, whereas psychological complaints, administrative requests, and complex somatic features remained challenging. These findings establish a practical, privacy-preserving blueprint for deploying open-source SLMs in multilingual clinical NLP settings with limited infrastructure and annotation resources, and highlight the importance of jointly optimizing model scale and input language strategy for sensitive healthcare applications.
Authors: Daniel Tamayo, I\~naki Lacunza, Paula Rivera-Hidalgo, Severino Da Dalt, Javier Aula-Blasco, Aitor Gonzalez-Agirre, Marta Villegas
Abstract: We introduce MrBERT, a family of 150M-300M parameter encoders built on the ModernBERT architecture and pre-trained on 35 languages and code. Through targeted adaptation, this model family achieves state-of-the-art results on Catalan- and Spanish-specific tasks, while establishing robust performance across specialized biomedical and legal domains. To bridge the gap between research and production, we incorporate Matryoshka Representation Learning (MRL), enabling flexible vector sizing that significantly reduces inference and storage costs. Ultimately, the MrBERT family demonstrates that modern encoder architectures can be optimized for both localized linguistic excellence and efficient, high-stakes domain specialization. We open source the complete model family on Huggingface.
Authors: Sajjad Ghiasvand, Haniyeh Ehsani Oskouie, Mahnoosh Alizadeh, Ramtin Pedarsani
Abstract: Prompt learning has become a dominant paradigm for adapting vision-language models (VLMs) such as CLIP to downstream tasks without modifying pretrained weights. While extending prompts to both vision and text encoders across multiple transformer layers significantly boosts performance, it dramatically increases the number of trainable parameters, with state-of-the-art methods requiring millions of parameters and abandoning the parameter efficiency that makes prompt tuning attractive. In this work, we propose \textbf{MMLoP} (\textbf{M}ulti-\textbf{M}odal \textbf{Lo}w-Rank \textbf{P}rompting), a framework that achieves deep multi-modal prompting with only \textbf{11.5K trainable parameters}, comparable to early text-only methods like CoOp. MMLoP parameterizes vision and text prompts at each transformer layer through a low-rank factorization, which serves as an implicit regularizer against overfitting on few-shot training data. To further close the accuracy gap with state-of-the-art methods, we introduce three complementary components: a self-regulating consistency loss that anchors prompted representations to frozen zero-shot CLIP features at both the feature and logit levels, a uniform drift correction that removes the global embedding shift induced by prompt tuning to preserve class-discriminative structure, and a shared up-projection that couples vision and text prompts through a common low-rank factor to enforce cross-modal alignment. Extensive experiments across three benchmarks and 11 diverse datasets demonstrate that MMLoP achieves a highly favorable accuracy-efficiency tradeoff, outperforming the majority of existing methods including those with orders of magnitude more parameters, while achieving a harmonic mean of 79.70\% on base-to-novel generalization.
Authors: Jan Pauls, Karsten Schr\"odter, Sven Ligensa, Martin Schwartz, Berkant Turan, Max Zimmer, Sassan Saatchi, Sebastian Pokutta, Philippe Ciais, Fabian Gieseke
Abstract: Forest monitoring is critical for climate change mitigation. However, existing global tree height maps provide only static snapshots and do not capture temporal forest dynamics, which are essential for accurate carbon accounting. We introduce ECHOSAT, a global and temporally consistent tree height map at 10 m resolution spanning multiple years. To this end, we resort to multi-sensor satellite data to train a specialized vision transformer model, which performs pixel-level temporal regression. A self-supervised growth loss regularizes the predictions to follow growth curves that are in line with natural tree development, including gradual height increases over time, but also abrupt declines due to forest loss events such as fires. Our experimental evaluation shows that our model improves state-of-the-art accuracies in the context of single-year predictions. We also provide the first global-scale height map that accurately quantifies tree growth and disturbances over time. We expect ECHOSAT to advance global efforts in carbon monitoring and disturbance assessment. The maps can be accessed at https://github.com/ai4forest/echosat.
Authors: Binesh Sadanandan, Vahid Behzadan
Abstract: Medical Vision Language Models (VLMs) can change their answers when clinicians rephrase the same question, which raises deployment risks. We introduce Paraphrase Sensitivity Failure (PSF)-Med, a benchmark of 19,748 chest Xray questions paired with about 92,000 meaningpreserving paraphrases across MIMIC-CXR and PadChest. Across six medical VLMs, we measure yes/no flips for the same image and find flip rates from 8% to 58%. However, low flip rate does not imply visual grounding: text-only baselines show that some models stay consistent even when the image is removed, suggesting they rely on language priors. To study mechanisms in one model, we apply GemmaScope 2 Sparse Autoencoders (SAEs) to MedGemma 4B and analyze FlipBank, a curated set of 158 flip cases. We identify a sparse feature at layer 17 that correlates with prompt framing and predicts decision margin shifts. In causal patching, removing this feature's contribution recovers 45% of the yesminus-no logit margin on average and fully reverses 15% of flips. Acting on this finding, we show that clamping the identified feature at inference reduces flip rates by 31% relative with only a 1.3 percentage-point accuracy cost, while also decreasing text-prior reliance. These results suggest that flip rate alone is not enough; robustness evaluations should test both paraphrase stability and image reliance.
Authors: Arnab Maiti, Claire Jie Zhang, Kevin Jamieson, Jamie Heather Morgenstern, Ioannis Panageas, Lillian J. Ratliff
Abstract: In this paper, we study last-iterate convergence of learning algorithms in bilinear saddle-point problems, a preferable notion of convergence that captures the day-to-day behavior of learning dynamics. We focus on the challenging setting where players select actions from compact convex sets and receive only bandit feedback. Our main contribution is the design of an uncoupled learning algorithm that guarantees last-iterate convergence to the Nash equilibrium with high probability. We establish a convergence rate of $\tilde{O}(T^{-1/4})$ up to polynomial factors in problem parameters. Crucially, our proposed algorithm is computationally efficient, requiring only an efficient linear optimization oracle over the players' compact action sets. The algorithm is obtained by combining techniques from experimental design and the classic Follow-The-Regularized-Leader (FTRL) framework, with a carefully chosen regularizer function tailored to the geometry of the action set of each learner.
Authors: Ziyi Liang, Hamed Poursiami, Zhishun Yang, Keiland Cooper, Akhilesh Jaiswal, Maryam Parsa, Norbert Fortin, Babak Shahbaba
Abstract: Hyperdimensional Computing (HDC) offers a computationally efficient paradigm for neuromorphic learning. Yet, it lacks rigorous uncertainty quantification, leading to open decision boundaries and, consequently, vulnerability to outliers, adversarial perturbations, and out-of-distribution inputs. To address these limitations, we introduce ConformalHDC, a unified framework that combines the statistical guarantees of conformal prediction with the computational efficiency of HDC. For this framework, we propose two complementary variations. First, the set-valued formulation provides finite-sample, distribution-free coverage guarantees. Using carefully designed conformity scores, it forms enclosed decision boundaries that improve robustness to non-conforming inputs. Second, the point-valued formulation leverages the same conformity scores to produce a single prediction when desired, potentially improving accuracy over traditional HDC by accounting for class interactions. We demonstrate the broad applicability of the proposed framework through evaluations on multiple real-world datasets. In particular, we apply our method to the challenging problem of decoding non-spatial stimulus information from the spiking activity of hippocampal neurons recorded as subjects performed a sequence memory task. Our results show that ConformalHDC not only accurately decodes the stimulus information represented in the neural activity data, but also provides rigorous uncertainty estimates and correctly abstains when presented with data from other behavioral states. Overall, these capabilities position the framework as a reliable, uncertainty-aware foundation for neuromorphic computing.
Authors: Inderjeet Singh, Vikas Pahuja, Aishvariya Priya Rathina Sabapathy, Chiara Picardi, Amit Giloni, Roman Vainshtein, Andr\'es Murillo, Hisashi Kojima, Motoyoshi Sekiya, Yuki Unno, Junichi Suga
Abstract: Current stateless defences for multimodal agentic RAG fail to detect adversarial strategies that distribute malicious semantics across retrieval, planning, and generation components. We formulate this security challenge as a Partially Observable Markov Decision Process (POMDP), where adversarial intent is a latent variable inferred from noisy multi-stage observations. We introduce MMA-RAG^T, an inference-time control framework governed by a Modular Trust Agent (MTA) that maintains an approximate belief state via structured LLM reasoning. Operating as a model-agnostic overlay, MMA-RAGT mediates a configurable set of internal checkpoints to enforce stateful defence-in-depth. Extensive evaluation on 43,774 instances demonstrates a 6.50x average reduction factor in Attack Success Rate relative to undefended baselines, with negligible utility cost. Crucially, a factorial ablation validates our theoretical bounds: while statefulness and spatial coverage are individually necessary (26.4 pp and 13.6 pp gains respectively), stateless multi-point intervention can yield zero marginal benefit under homogeneous stateless filtering when checkpoint detections are perfectly correlated.
Authors: Brandon Yee, Wilson Collins, Maximilian Rutkowski
Abstract: The spin-$1/2$ $J_1$-$J_2$ Heisenberg model on the square lattice exhibits a debated intermediate phase between N\'eel antiferromagnetic and stripe ordered regimes, with competing theories proposing plaquette valence bond, nematic, and quantum spin liquid ground states. We apply the Prometheus variational autoencoder framework -- previously validated on classical (2D, 3D Ising) and quantum (disordered transverse field Ising) phase transitions -- to systematically explore the $J_1$-$J_2$ phase diagram via unsupervised analysis of exact diagonalization ground states for a $4 \times 4$ lattice. Through dense parameter scans of $J_2/J_1 \in [0.3, 0.7]$ with step size 0.01 and comprehensive latent space analysis, we investigate the nature of the intermediate regime using unsupervised order parameter discovery and critical point detection via multiple independent methods. This work demonstrates the application of rigorously validated machine learning methods to open questions in frustrated quantum magnetism, where traditional order parameter identification is challenged by competing interactions and limited accessible system sizes.
Authors: Chun-wei Ho, Sabato Marco Siniscalchi, Kai Li, Chin-Hui Lee
Abstract: We propose a knowledge-driven, model-based approach to segmenting audio into single-category and mixed-category chunks with applications to source separation. "Knowledge" here denotes information associated with the data, such as music scores. "Model" here refers to tool that can be used for audio segmentation and recognition, such as hidden Markov models. In contrast to conventional learning that often relies on annotated data with given segment categories and their corresponding boundaries to guide the learning process, the proposed framework does not depend on any pre-segmented training data and learns directly from the input audio and its related knowledge sources to build all necessary models autonomously. Evaluation on simulation data shows that score-guided learning achieves very good music segmentation and separation results. Tested on movie track data for cinematic audio source separation also shows that utilizing sound category knowledge achieves better separation results than those obtained with data-driven techniques without using such information.
Authors: Zikai Shen, Houssam Zenati, Nathan Kallus, Arthur Gretton, Koulik Khamaru, Aur\'elien Bibaut
Abstract: We study inference on scalar-valued pathwise differentiable targets after adaptive data collection, such as a bandit algorithm. We introduce a novel target-specific condition, directional stability, which is strictly weaker than previously imposed target-agnostic stability conditions. Under directional stability, we show that estimators that would have been efficient under i.i.d. data remain asymptotically normal and semiparametrically efficient when computed from adaptively collected trajectories. The canonical gradient has a martingale form, and directional stability guarantees stabilization of its predictable quadratic variation, enabling high-dimensional asymptotic normality. We characterize efficiency using a convolution theorem for the adaptive-data setting, and give a condition under which the one-step estimator attains the efficiency bound. We verify directional stability for LinUCB, yielding the first semiparametric efficiency guarantee for a regular scalar target under LinUCB sampling.
Authors: Beepul Bharti, Ambar Pal, Jeremias Sulam
Abstract: Across many risk-sensitive areas, it is critical to continuously audit the performance of machine learning systems and detect any unusual behavior quickly. This can be modeled as a sequential hypothesis testing problem with $k$ incoming streams of data and a global null hypothesis that asserts that the system is working as expected across all $k$ streams. The standard global test employs a Bonferroni correction and has an expected stopping time bound of $O\left(\ln\frac{k}{\alpha}\right)$ when $k$ is large and the significance level of the test, $\alpha$, is small. In this work, we construct new sequential tests by using ideas of merging test martingales with different trade-offs in expected stopping times under different, sparse or dense alternative hypotheses. We further derive a new, balanced test that achieves an improved expected stopping time bound that matches Bonferroni's in the sparse setting but that naturally results in $O\left(\frac{1}{k}\ln\frac{1}{\alpha}\right)$ under a dense alternative. We empirically demonstrate the effectiveness of our proposed tests on synthetic and real-world data.
Authors: Lars van der Laan
Abstract: This guide develops high-probability regret bounds for empirical risk minimization (ERM). The presentation is modular: we state broadly applicable guarantees under high-level conditions and give tools for verifying them for specific losses and function classes. We emphasize that many ERM rate derivations can be organized around a three-step recipe -- a basic inequality, a uniform local concentration bound, and a fixed-point argument -- which yields regret bounds in terms of a critical radius, defined via localized Rademacher complexity, under a mild Bernstein-type variance--risk condition. To make these bounds concrete, we upper bound the critical radius using local maximal inequalities and metric-entropy integrals, recovering familiar rates for VC-subgraph, Sobolev/H\"older, and bounded-variation classes. We also review ERM with nuisance components -- including weighted ERM and Neyman-orthogonal losses -- as they arise in causal inference, missing data, and domain adaptation. Following the orthogonal learning framework, we highlight that these problems often admit regret-transfer bounds linking regret under an estimated loss to population regret under the target loss. These bounds typically decompose regret into (i) statistical error under the estimated (optimized) loss and (ii) approximation error due to nuisance estimation. Under sample splitting or cross-fitting, the first term can be controlled using standard fixed-loss ERM regret bounds, while the second term depends only on nuisance-estimation accuracy. We also treat the in-sample regime, where nuisances and the ERM are fit on the same data, deriving regret bounds and giving sufficient conditions for fast rates.
Authors: Jinwon Park, Kunwoong Kim, Jihu Lee, Yongdai Kim
Abstract: The goal of fair clustering is to find clusters such that the proportion of sensitive attributes (e.g., gender, race, etc.) in each cluster is similar to that of the entire dataset. Various fair clustering algorithms have been proposed that modify standard K-means clustering to satisfy a given fairness constraint. A critical limitation of several existing fair clustering algorithms is that the number of parameters to be learned is proportional to the sample size because the cluster assignment of each datum should be optimized simultaneously with the cluster center, and thus scaling up the algorithms is difficult. In this paper, we propose a new fair clustering algorithm based on a finite mixture model, called Fair Model-based Clustering (FMC). A main advantage of FMC is that the number of learnable parameters is independent of the sample size and thus can be scaled up easily. In particular, mini-batch learning is possible to obtain clusters that are approximately fair. Moreover, FMC can be applied to non-metric data (e.g., categorical data) as long as the likelihood is well-defined. Theoretical and empirical justifications for the superiority of the proposed algorithm are provided.
Authors: Yue Yang, Shuo Cheng, Yu Fang, Homanga Bharadhwaj, Mingyu Ding, Gedas Bertasius, Daniel Szafir
Abstract: General-purpose robots must master long-horizon manipulation, defined as tasks involving multiple kinematic structure changes (e.g., attaching or detaching objects) in unstructured environments. While Vision-Language-Action (VLA) models offer the potential to master diverse atomic skills, they struggle with the combinatorial complexity of sequencing them and are prone to cascading failures due to environmental sensitivity. To address these challenges, we propose LiLo-VLA (Linked Local VLA), a modular framework capable of zero-shot generalization to novel long-horizon tasks without ever being trained on them. Our approach decouples transport from interaction: a Reaching Module handles global motion, while an Interaction Module employs an object-centric VLA to process isolated objects of interest, ensuring robustness against irrelevant visual features and invariance to spatial configurations. Crucially, this modularity facilitates robust failure recovery through dynamic replanning and skill reuse, effectively mitigating the cascading errors common in end-to-end approaches. We introduce a 21-task simulation benchmark consisting of two challenging suites: LIBERO-Long++ and Ultra-Long. In these simulations, LiLo-VLA achieves a 69% average success rate, outperforming Pi0.5 by 41% and OpenVLA-OFT by 67%. Furthermore, real-world evaluations across 8 long-horizon tasks demonstrate an average success rate of 85%. Project page: https://yy-gx.github.io/LiLo-VLA/.
Authors: Dong Hyeon Mok, Seoin Back, Victor Fung, Guoxiang Hu
Abstract: Large language models (LLMs) are becoming increasingly applied beyond natural language processing, demonstrating strong capabilities in complex scientific tasks that traditionally require human expertise. This progress has extended into materials discovery, where LLMs introduce a new paradigm by leveraging reasoning and in-context learning, capabilities absent from conventional machine learning approaches. Here, we present a Multi-Agent-based Electrocatalyst Search Through Reasoning and Optimization (MAESTRO) framework in which multiple LLMs with specialized roles collaboratively discover high-performance single atom catalysts for the oxygen reduction reaction. Within an autonomous design loop, agents iteratively reason, propose modifications, reflect on results and accumulate design history. Through in-context learning enabled by this iterative process, MAESTRO identified design principles not explicitly encoded in the LLMs' background knowledge and successfully discovered catalysts that break conventional scaling relations between reaction intermediates. These results highlight the potential of multi-agent LLM frameworks as a powerful strategy to generate chemical insight and discover promising catalysts.
Authors: Wenqing Zheng, Dmitri Kalaev, Noah Fatsi, Daniel Barcklow, Owen Reinert, Igor Melnyk, Senthil Kumar, C. Bayan Bruss
Abstract: Retrieval-Augmented Generation (RAG) systems rely critically on the retriever module to surface relevant context for large language models. Although numerous retrievers have recently been proposed, each built on different ranking principles such as lexical matching, dense embeddings, or graph citations, there remains a lack of systematic understanding of how these mechanisms differ and overlap. Existing benchmarks primarily compare entire RAG pipelines or introduce new datasets, providing little guidance on selecting or combining retrievers themselves. Those that do compare retrievers directly use a limited set of evaluation tools which fail to capture complementary and overlapping strengths. This work presents MIGRASCOPE, a Mutual Information based RAG Retriever Analysis Scope. We revisit state-of-the-art retrievers and introduce principled metrics grounded in information and statistical estimation theory to quantify retrieval quality, redundancy, synergy, and marginal contribution. We further show that if chosen carefully, an ensemble of retrievers outperforms any single retriever. We leverage the developed tools over major RAG corpora to provide unique insights on contribution levels of the state-of-the-art retrievers. Our findings provide a fresh perspective on the structure of modern retrieval techniques and actionable guidance for designing robust and efficient RAG systems.
Authors: Huan Qing
Abstract: Estimating the asymmetric numbers of communities in multi-layer directed networks is a challenging problem due to the multi-layer structures and inherent directional asymmetry, leading to possibly different numbers of sender and receiver communities. This work addresses this issue under the multi-layer stochastic co-block model, a model for multi-layer directed networks with distinct community structures in sending and receiving sides, by proposing a novel goodness-of-fit test. The test statistic relies on the deviation of the largest singular value of an aggregated normalized residual matrix from the constant 2. The test statistic exhibits a sharp dichotomy: Under the null hypothesis of correct model specification, its upper bound converges to zero with high probability; under underfitting, the test statistic itself diverges to infinity. With this property, we develop a sequential testing procedure that searches through candidate pairs of sender and receiver community numbers in a lexicographic order. The process stops at the smallest such pair where the test statistic drops below a decaying threshold. For robustness, we also propose a ratio-based variant algorithm, which detects sharp changes in the sequence of test statistics by comparing consecutive candidates. Both methods are proven to consistently determine the true numbers of sender and receiver communities under the multi-layer stochastic co-block model.
Authors: Huan Qing
Abstract: Ordinal categorical data are widely collected in psychology, education, and other social sciences, appearing commonly in questionnaires, assessments, and surveys. Latent class models provide a flexible framework for uncovering unobserved heterogeneity by grouping individuals into homogeneous classes based on their response patterns. A fundamental challenge in applying these models is determining the number of latent classes, which is unknown and must be inferred from data. In this paper, we propose one test statistic for this problem. The test statistic centers the largest singular value of a normalized residual matrix by a simple sample-size adjustment. Under the null hypothesis that the candidate number of latent classes is correct, its upper bound converges to zero in probability. Under an under-fitted alternative, the statistic itself exceeds a fixed positive constant with probability approaching one. This sharp dichotomous behavior of the test statistic yields two sequential testing algorithms that consistently estimate the true number of latent classes. Extensive experimental studies confirm the theoretical findings and demonstrate their accuracy and reliability in determining the number of latent classes.
Authors: Arnab Maiti, Junyan Liu, Kevin Jamieson, Lillian J. Ratliff
Abstract: We study the discrete Bertrand pricing game with a non-increasing demand function. The game has $n \ge 2$ players who simultaneously choose prices from the set $\{1/k, 2/k, \ldots, 1\}$, where $k\in\mathbb{N}$. The player who sets the lowest price captures the entire demand; if multiple players tie for the lowest price, they split the demand equally. We study the Bertrand paradox, where classical theory predicts low prices, yet real markets often sustain high prices. To understand this gap, we analyze a repeated-game model in which firms set prices using no-regret learners. Our goal is to characterize the equilibrium outcomes that can arise under different no-regret learning guarantees. We are particularly interested in questions such as whether no-external-regret learners can converge to undesirable high-price outcomes, and how stronger guarantees such as no-swap regret shape the emergence of competitive low-price behavior. We address these and related questions through a theoretical analysis, complemented by experiments that support the theory and reveal surprising phenomena for no-swap regret learners.
Authors: Tangsang Chongbang, Pranesh Pyara Shrestha, Amrit Sarki, Anku Jaiswal
Abstract: This paper presents and evaluates an optimized cascaded Nepali speech-to-English text translation (S2TT) system, focusing on mitigating structural noise introduced by Automatic Speech Recognition (ASR). We first establish highly proficient ASR and NMT components: a Wav2Vec2-XLS-R-300m model achieved a state-of-the-art 2.72% CER on OpenSLR-54, and a multi-stage fine-tuned MarianMT model reached a 28.32 BLEU score on the FLORES-200 benchmark. We empirically investigate the influence of punctuation loss, demonstrating that unpunctuated ASR output significantly degrades translation quality, causing a massive 20.7% relative BLEU drop on the FLORES benchmark. To overcome this, we propose and evaluate an intermediate Punctuation Restoration Module (PRM). The final S2TT pipeline was tested across three configurations on a custom dataset. The optimal configuration, which applied the PRM directly to ASR output, achieved a 4.90 BLEU point gain over the direct ASR-to-NMT baseline (BLEU 36.38 vs. 31.48). This improvement was validated by human assessment, which confirmed the optimized pipeline's superior Adequacy (3.673) and Fluency (3.804). This work validates that targeted punctuation restoration is the most effective intervention for mitigating structural noise in the Nepali S2TT pipeline. It establishes an optimized baseline and demonstrates a critical architectural insight for developing cascaded speech translation systems for similar low-resource languages.
Authors: Zhenxiang Xu, Jiawei Chen, Sirui Chen, Yong He, Jieyu Yang, Chuan Yuan, Ke Ding, Can Wang
Abstract: Generative recommendation (GR) aligns with advances in generative AI by casting next-item prediction as token-level generation rather than score-based ranking. Most GR methods adopt a two-stage pipeline: (i) \textit{item tokenization}, which maps each item to a sequence of discrete, hierarchically organized tokens; and (ii) \textit{autoregressive generation}, which predicts the next item's tokens conditioned on the tokens of user's interaction history. Although hierarchical tokenization induces a prefix tree (trie) over items, standard autoregressive modeling with conventional Transformers often flattens item tokens into a linear stream and overlooks the underlying topology. To address this, we propose TrieRec, a trie-aware generative recommendation method that augments Transformers with structural inductive biases via two positional encodings. First, a \textit{trie-aware absolute positional encoding} aggregates a token's (node's) local structural context (\eg depth, ancestors, and descendants) into the token representation. Second, a \textit{topology-aware relative positional encoding} injects pairwise structural relations into self-attention to capture topology-induced semantic relatedness. TrieRec is also model-agnostic, efficient, and hyperparameter-free. In our experiments, we implement TrieRec within three representative GR backbones, achieving notably improvements of 8.83\% on average across four real-world datasets.
Authors: Xiaohan Lei, Min Wang, Wengang Zhou, Xingyu Lu, Houqiang Li
Abstract: Multi-modal distribution in robotic manipulation action sequences poses critical challenges for imitation learning. To this end, existing approaches often model the action space as either a discrete set of tokens or a continuous, latent-variable distribution. However, both approaches present trade-offs: some methods discretize actions into tokens and therefore lose fine-grained action variations, while others generate continuous actions in a single stage tend to produce unstable mode transitions. To address these limitations, we propose Primary-Fine Decoupling for Action Generation (PF-DAG), a two-stage framework that decouples coarse action consistency from fine-grained variations. First, we compress action chunks into a small set of discrete modes, enabling a lightweight policy to select consistent coarse modes and avoid mode bouncing. Second, a mode conditioned MeanFlow policy is learned to generate high-fidelity continuous actions. Theoretically, we prove PF-DAG's two-stage design achieves a strictly lower MSE bound than single-stage generative policies. Empirically, PF-DAG outperforms state-of-the-art baselines across 56 tasks from Adroit, DexArt, and MetaWorld benchmarks. It further generalizes to real-world tactile dexterous manipulation tasks. Our work demonstrates that explicit mode-level decoupling enables both robust multi-modal modeling and reactive closed-loop control for robotic manipulation.
Authors: T. Schaffer, A. Brawanski, S. Wein, A. M. Tom\'e, E. W. Lang
Abstract: A U-Net based deep learning architecture is designed to segment brain tumors as they appear on various MRI modalities. Special emphasis is lent to the non-enhancing tumor compartment. The latter has not been considered anymore in recent brain tumor segmentation challenges like the MICCAI challenges. However, it is considered to be indicative of the survival time of the patient as well as of areas of further tumor growth. Hence it deems essential to have means to automatically delineate its extension within the tumor.
Authors: Joshua Schulz, David Schote, Christoph Kolbitsch, Kostas Papafitsoros, Andreas Kofler
Abstract: State-of-the-art learned reconstruction methods often rely on black-box modules that, despite their strong performance, raise questions about their interpretability and robustness. Here, we build on a recently proposed image reconstruction method, which is based on embedding data-driven information into a model-based convolutional dictionary regularization via neural network-inferred spatially adaptive sparsity level maps. By means of improved network design and dedicated training strategies, we extend the method to achieve filter-permutation invariance as well as the possibility to change the convolutional dictionary at inference time. We apply our method to low-field MRI and compare it to several other recent deep learning-based methods, also on in vivo data, in which the benefit for the use of a different dictionary is showcased. We further assess the method's robustness when tested on in- and out-of-distribution data. When tested on the latter, the proposed method suffers less from the data distribution shift compared to the other learned methods, which we attribute to its reduced reliance on training data due to its underlying model-based reconstruction component.
Authors: Delio Jaramillo Velez, Gergely Biczok, Alexandre Graell i Amat, Johan Ostman, Balazs Pejo
Abstract: Cross-silo federated learning allows multiple organizations to collaboratively train machine learning models without sharing raw data, but client updates can still leak sensitive information through inference attacks. Secure aggregation protects privacy by hiding individual updates, yet it complicates contribution evaluation, which is critical for fair rewards and detecting low-quality or malicious participants. Existing marginal-contribution methods, such as the Shapley value, are incompatible with secure aggregation, and practical alternatives, such as Leave-One-Out, are crude and rely on self-evaluation. We introduce two marginal-difference contribution scores compatible with secure aggregation. Fair-Private satisfies standard fairness axioms, while Everybody-Else eliminates self-evaluation and provides resistance to manipulation, addressing a largely overlooked vulnerability. We provide theoretical guarantees for fairness, privacy, robustness, and computational efficiency, and evaluate our methods on multiple medical image datasets and CIFAR10 in cross-silo settings. Our scores consistently outperform existing baselines, better approximate Shapley-induced client rankings, and improve downstream model performance as well as misbehavior detection. These results demonstrate that fairness, privacy, robustness, and practical utility can be achieved jointly in federated contribution evaluation, offering a principled solution for real-world cross-silo deployments.
Authors: MD. Sagor Chowdhury, Adiba Fairooz Chowdhury
Abstract: We describe our end-to-end system for Bengali long-form speech recognition (ASR) and speaker diarization submitted to the DL Sprint 4.0 competition on Kaggle. Bengali presents substantial challenges for both tasks: a large phoneme inventory, significant dialectal variation, frequent code-mixing with English, and a relative scarcity of large-scale labelled corpora. For ASR we achieve a best private Word Error Rate (WER) of 0.37738 and public WER of 0.36137, combining a BengaliAI fine-tuned Whisper medium model with Demucs source separation for vocal isolation, silence-boundary chunking, and carefully tuned generation hyperparameters. For speaker diarization we reach a best private Diarization Error Rate (DER) of 0.27671 and public DER of 0.20936 by replacing the default segmentation model inside the pyannote.audio pipeline with a Bengali-fine-tuned variant, pairing it with wespeaker-voxceleb-resnet34-LM embeddings and centroid-based agglomerative clustering. Our experiments demonstrate that domain-specific fine-tuning of the segmentation component, vocal source separation, and natural silence-aware chunking are the three most impactful design choices for low-resource Bengali speech processing.
Authors: Longlong Zhang, Xi Wang, Haotong Du, Yangyi Xu, Zhuo Liu, Yang Liu
Abstract: Social bot detection is pivotal for safeguarding the integrity of online information ecosystems. Although recent graph neural network (GNN) solutions achieve strong results, they remain hindered by two practical challenges: (i) severe class imbalance arising from the high cost of generating bots, and (ii) topological noise introduced by bots that skillfully mimic human behavior and forge deceptive links. We propose the Reinforcement-guided graph Augmentation social Bot detector (RABot), a multi-granularity graph-augmentation framework that addresses both issues in a unified manner. RABot employs a neighborhood-aware oversampling strategy that linearly interpolates minority-class embeddings within local subgraphs, thereby stabilizing the decision boundary under low-resource regimes. Concurrently, a reinforcement-learning-driven edge-filtering module combines similarity-based edge features with adaptive threshold optimization to excise spurious interactions during message passing, yielding a cleaner topology. Extensive experiments on three real-world benchmarks and four GNN backbones demonstrate that RABot consistently surpasses state-of-the-art baselines. In addition, since its augmentation and filtering modules are orthogonal to the underlying architecture, RABot can be seamlessly integrated into existing GNN pipelines to boost performance with minimal overhead.
Authors: Deogyong Kim, Junseong Lee, Jeongeun Lee, Changhoe Kim, Junguel Lee, Jungseok Lee, Dongha Lee
Abstract: Recent advances in large language models (LLMs) offer new opportunities for recommender systems by capturing the nuanced semantics of user interests and item characteristics through rich semantic understanding and contextual reasoning. In particular, LLMs have been employed as rerankers that reorder candidate items based on inferred user-item relevance. However, these approaches often require expensive online inference-time reasoning, leading to high latency that hampers real-world deployment. In this work, we introduce Persona4Rec, a recommendation framework that performs offline reasoning to construct interpretable persona representations of items, enabling lightweight and scalable real-time inference. In the offline stage, Persona4Rec leverages LLMs to reason over item reviews, inferring diverse user motivations that explain why different types of users may engage with an item; these inferred motivations are materialized as persona representations, providing multiple, human-interpretable views of each item. Unlike conventional approaches that rely on a single item representation, Persona4Rec learns to align user profiles with the most plausible item-side persona through a dedicated encoder, effectively transforming user-item relevance into user-persona relevance. At the online stage, this persona-profiled item index allows fast relevance computation without invoking expensive LLM reasoning. Extensive experiments show that Persona4Rec achieves performance comparable to recent LLM-based rerankers while substantially reducing inference time. Moreover, qualitative analysis confirms that persona representations not only drive efficient scoring but also provide intuitive, review-grounded explanations. These results demonstrate that Persona4Rec offers a practical and interpretable solution for next-generation recommender systems.
Authors: Mohamed Abdelmaksoud, Sheng Ding, Andrey Morozov, Ziawasch Abedjan
Abstract: Time-series data vary widely across domains, making a universal anomaly detector impractical. Methods that perform well on one dataset often fail to transfer because what counts as an anomaly is context dependent. The key challenge is to design a method that performs well in specific contexts while remaining adaptable across domains with varying data complexities. We present the Robust and Adaptive Model Selection for Time-Series Anomaly Detection RAMSeS framework. RAMSeS comprises two branches: (i) a stacking ensemble optimized with a genetic algorithm to leverage complementary detectors. (ii) An adaptive model-selection branch identifies the best single detector using techniques including Thompson sampling, robustness testing with generative adversarial networks, and Monte Carlo simulations. This dual strategy exploits the collective strength of multiple models and adapts to dataset-specific characteristics. We evaluate RAMSeS and show that it outperforms prior methods on F1.
Authors: Beatrice Luciani, Alex van den Berg, Matti Lang, Alexandre L. Ratschat, Laura Marchal-Crespo
Abstract: Robotic systems can enhance the amount and repeatability of physically guided motor training. Yet their real-world adoption is limited, partly due to non-intuitive trainer/therapist-trainee/patient interactions. To address this gap, we present a haptic teleoperation system for trainers to remotely guide and monitor the movements of a trainee wearing an arm exoskeleton. The trainer can physically interact with the exoskeleton through a commercial handheld haptic device via virtual contact points at the exoskeleton's elbow and wrist, allowing intuitive guidance. Thirty-two participants tested the system in a trainer-trainee paradigm, comparing our haptic demonstration system with conventional visual demonstration in guiding trainees in executing arm poses. Quantitative analyses showed that haptic demonstration significantly reduced movement completion time and improved smoothness, while speech analysis using large language models for automated transcription and categorization of verbal commands revealed fewer verbal instructions. The haptic demonstration did not result in higher reported mental and physical effort by trainers compared to the visual demonstration, while trainers reported greater competence and trainees lower physical demand. These findings support the feasibility of our proposed interface for effective remote human-robot physical interaction. Future work should assess its usability and efficacy for clinical populations in restoring clinicians' sense of agency during robot-assisted therapy.
Authors: Yifan Niu, Han Xiao, Dongyi Liu, Wei Zhou, Jia Li
Abstract: Scaling long-context capabilities is crucial for Multimodal Large Language Models (MLLMs). However, real-world multimodal datasets are extremely heterogeneous. Existing training frameworks predominantly rely on static parallelism strategies, which suffer from severe load imbalance, redundant communication, and suboptimal hardware utilization under data heterogeneity. In this work, we propose Dynamic Hybrid Parallelism (DHP), an efficient parallelism strategy that adaptively reconfigures communication groups and parallelism degrees during MLLM training. We generalize the non-power-of-two parallelism degrees and develop a polynomial-time algorithm to generate near-optimal parallelism strategies with only millisecond-level overhead per training batch. DHP is able to maintain high hardware efficiency even under extreme data variability. Experimental results demonstrate that DHP significantly outperforms Megatron-LM and DeepSpeed, achieving up to 1.36 $\times$ speedup in training throughput while maintaining near-linear scaling efficiency across large-scale NPU clusters.
Authors: Paolo Andreini, Alessandra Bernardi, Monica Bianchini, Barbara Toniella Corradini, Sara Marziali, Giacomo Nunziati, Franco Scarselli
Abstract: Fast matrix multiplication can be described as searching for low-rank decompositions of the matrix--multiplication tensor. We design a neural architecture, \textsc{StrassenNet}, which reproduces the Strassen algorithm for $2\times 2$ multiplication. Across many independent runs the network always converges to a rank-$7$ tensor, thus numerically recovering Strassen's optimal algorithm. We then train the same architecture on $3\times 3$ multiplication with rank $r\in\{19,\dots,23\}$. Our experiments reveal a clear numerical threshold: models with $r=23$ attain significantly lower validation error than those with $r\le 22$, suggesting that $r=23$ could actually be the smallest effective rank of the matrix multiplication tensor $3\times 3$. We also sketch an extension of the method to border-rank decompositions via an $\varepsilon$--parametrisation and report preliminary results consistent with the known bounds for the border rank of the $3\times 3$ matrix--multiplication tensor.
Authors: Masha Naslidnyk
Abstract: Representing, comparing, and measuring the distance between probability distributions is a key task in computational statistics and machine learning. The choice of representation and the associated distance determine properties of the methods in which they are used: for example, certain distances can allow one to encode robustness or smoothness of the problem. Kernel methods offer flexible and rich Hilbert space representations of distributions that allow the modeller to enforce properties through the choice of kernel, and estimate associated distances at efficient nonparametric rates. In particular, the maximum mean discrepancy (MMD), a kernel-based distance constructed by comparing Hilbert space mean functions, has received significant attention due to its computational tractability and is favoured by practitioners. In this thesis, we conduct a thorough study of kernel-based distances with a focus on efficient computation, with core contributions in Chapters 3 to 6. Part I of the thesis is focused on the MMD, specifically on improved MMD estimation. In Chapter 3 we propose a theoretically sound, improved estimator for MMD in simulation-based inference. Then, in Chapter 4, we propose an MMD-based estimator for conditional expectations, a ubiquitous task in statistical computation. Closing Part I, in Chapter 5 we study the problem of calibration when MMD is applied to the task of integration. In Part II, motivated by the recent developments in kernel embeddings beyond the mean, we introduce a family of novel kernel-based discrepancies: kernel quantile discrepancies. These address some of the pitfalls of MMD, and are shown through both theoretical results and an empirical study to offer a competitive alternative to MMD and its fast approximations. We conclude with a discussion on broader lessons and future work emerging from the thesis.
Authors: Jabez Magomere, Elena Kochkina, Samuel Mensah, Simerjot Kaur, Fernando Acero, Arturo Oncevay, Charese H. Smiley, Xiaomo Liu, Manuela Veloso
Abstract: Complex claim verification requires decomposing sentences into verifiable subclaims, yet existing methods struggle to align decomposition quality with verification performance. We propose a reinforcement learning (RL) approach that jointly optimizes decomposition quality and verifier alignment using Group Relative Policy Optimization (GRPO). Our method integrates: (i) structured sequential reasoning; (ii) supervised finetuning on teacher-distilled exemplars; and (iii) a multi-objective reward balancing format compliance, verifier alignment, and decomposition quality. Across six evaluation settings, our trained 8B decomposer improves downstream verification performance to (71.75%) macro-F1, outperforming prompt-based approaches ((+1.99), (+6.24)) and existing RL methods ((+5.84)). Human evaluation confirms the high quality of the generated subclaims. Our framework enables smaller language models to achieve state-of-the-art claim verification by jointly optimising for verification accuracy and decomposition quality.
Authors: Shiwei Lu, Yuhang He, Jiashuo Li, Qiang Wang, Yihong Gong
Abstract: Federated learning (FL) facilitates the secure utilization of decentralized images, advancing applications in medical image recognition and autonomous driving. However, conventional FL faces two critical challenges in real-world deployment: ineffective knowledge fusion caused by model updates biased toward majority-class features, and prohibitive communication overhead due to frequent transmissions of high-dimensional model parameters. Inspired by the human brain's efficiency in knowledge integration, we propose a novel Generative Federated Prototype Learning (GFPL) framework to address these issues. Within this framework, a prototype generation method based on Gaussian Mixture Model (GMM) captures the statistical information of class-wise features, while a prototype aggregation strategy using Bhattacharyya distance effectively fuses semantically similar knowledge across clients. In addition, these fused prototypes are leveraged to generate pseudo-features, thereby mitigating feature distribution imbalance across clients. To further enhance feature alignment during local training, we devise a dual-classifier architecture, optimized via a hybrid loss combining Dot Regression and Cross-Entropy. Extensive experiments on benchmarks show that GFPL improves model accuracy by 3.6% under imbalanced data settings while maintaining low communication cost.
Authors: Otto Nyberg, Fausto Carcassi, Giovanni Cin\`a
Abstract: Across a growing number of fields, human decision making is supported by predictions from AI models. However, we still lack a deep understanding of the effects of adoption of these technologies. In this paper, we introduce a general computational framework, the 2-Step Agent, which models the effects of AI-assisted decision making. Our framework uses Bayesian methods for causal inference to model 1) how a prediction on a new observation affects the beliefs of a rational Bayesian agent, and 2) how this change in beliefs affects the downstream decision and subsequent outcome. Using this framework, we show by simulations how a single misaligned prior belief can be sufficient for decision support to result in worse downstream outcomes compared to no decision support. Our results reveal several potential pitfalls of AI-driven decision support and highlight the need for thorough model documentation and proper user training.
Authors: Somyajit Chakraborty, Angshuman Jana, Avijit Gayen
Abstract: Understanding the role of researchers who return to academia after prolonged inactivity, termed "comeback researchers", is crucial for developing inclusive models of scientific careers. This study investigates the structural and semantic behaviors of comeback researchers, focusing on their role in cross-disciplinary knowledge transfer and network reintegration. Using the AMiner citation dataset, we analyze 113,637 early-career researchers and identify 1,425 comeback cases based on a three-year-or-longer publication gap followed by renewed activity. We find that comeback researchers cite 126% more distinct communities and exhibit 7.6% higher bridging scores compared to dropouts. They also demonstrate 74% higher gap entropy, reflecting more irregular yet strategically impactful publication trajectories. Predictive models trained on these bridging- and entropy-based features achieve a 97% ROC-AUC, far outperforming the 54% ROC-AUC of baseline models using traditional metrics like publication count and h-index. Finally, we substantiate these results via a multi-lens validation. These findings highlight the unique contributions of comeback researchers and offer data-driven tools for their early identification and institutional support.
Authors: Yuchun Tu, Zhiwei Li, Bingli Sun, Yixuan Li, Xiao Song
Abstract: Federated recommendation facilitates collaborative model training across distributed clients while keeping sensitive user interaction data local. Conventional approaches typically rely on synchronizing high-dimensional item representations between the server and clients. This paradigm implicitly assumes that precise geometric alignment of embedding coordinates is necessary for collaboration across clients. We posit that establishing relative semantic relationships among items is more effective than enforcing shared representations. Specifically, global semantic relations serve as structural constraints for items. Within these constraints, the framework allows item representations to vary locally on each client, which flexibility enables the model to capture fine-grained user personalization while maintaining global consistency. To this end, we propose Cluster-Guided FedRec framework (CGFedRec), a framework that transforms uploaded embeddings into compact cluster labels. In this framework, the server functions as a global structure discoverer to learn item clusters and distributes only the resulting labels. This mechanism explicitly cuts off the downstream transmission of item embeddings, relieving clients from maintaining global shared item embeddings. Consequently, CGFedRec achieves the effective injection of global collaborative signals into local item representations without transmitting full embeddings. Extensive experiments demonstrate that our approach significantly improves communication efficiency while maintaining superior recommendation accuracy across multiple datasets.
Authors: Ana Rodrigues, Rui Rego
Abstract: The optimization of complex medical appointment scheduling remains a significant operational challenge in multi-center healthcare environments, where clinical safety protocols and patient logistics must be reconciled. This study proposes and evaluates a Genetic Algorithm (GA) framework designed to automate the scheduling of multiple medical acts while adhering to rigorous inter-procedural incompatibility rules. Using a synthetic dataset encompassing 50 medical acts across four healthcare facilities, we compared two GA variants, Pre-Ordered and Unordered, against deterministic First-Come, First-Served (FCFS) and Random Choice baselines. Our results demonstrate that the GA framework achieved a 100% constraint fulfillment rate, effectively resolving temporal overlaps and clinical incompatibilities that the FCFS baseline failed to address in 60% and 40% of cases, respectively. Furthermore, the GA variants demonstrated statistically significant improvements (p < 0.001) in patient-centric metrics, achieving an Idle Time Ratio (ITR) frequently below 0.4 and reducing inter-healthcenter trips. While the GA (Ordered) variant provided a superior initial search locus, both evolutionary models converged to comparable global optima by the 100th generation. These findings suggest that transitioning from manual, human-mediated scheduling to an automated metaheuristic approach enhances clinical integrity, reduces administrative overhead, and significantly improves the patient experience by minimizing wait times and logistical burdens.
Authors: WeiZhe Xu, Mengyu Liu, Fanxin Kong
Abstract: Automated test generation is essential for software quality assurance, with coverage rate serving as a key metric to ensure thorough testing. Recent advancements in Large Language Models (LLMs) have shown promise in improving test generation, particularly in achieving higher coverage. However, while existing LLM-based test generation solutions perform well on small, isolated code snippets, they struggle when applied to complex methods under test. To address these issues, we propose a scalable LLM-based unit test generation method. Our approach consists of two key steps. The first step is context information retrieval, which uses both LLMs and static analysis to gather relevant contextual information associated with the complex methods under test. The second step, iterative test generation with code elimination, repeatedly generates unit tests for the code slice, tracks the achieved coverage, and selectively removes code segments that have already been covered. This process simplifies the testing task and mitigates issues arising from token limits or reduced reasoning effectiveness associated with excessively long contexts. Through comprehensive evaluations on open-source projects, our approach outperforms state-of-the-art LLM-based and search-based methods, demonstrating its effectiveness in achieving high coverage on complex methods.
Authors: Edgar Welte, Yitian Shi, Rosa Wolf, Maximillian Gilles, Rania Rayyes
Abstract: Generative manipulation policies can fail catastrophically under deployment-time distribution shift, yet many failures are near-misses: the robot reaches almost-correct poses and would succeed with a small corrective motion. We present FlowCorrect, a deployment-time correction framework that converts near-miss failures into successes using sparse human nudges, without full policy retraining. During execution, a human provides brief corrective pose nudges via a lightweight VR interface. FlowCorrect uses these sparse corrections to locally adapt the policy, improving actions without retraining the backbone while preserving the model performance on previously learned scenarios. We evaluate on a real-world robot across three tabletop tasks: pick-and-place, pouring, and cup uprighting. With a low correction budget, FlowCorrect improves success on hard cases by 85\% while preserving performance on previously solved scenarios. The results demonstrate clearly that FlowCorrect learns only with very few demonstrations and enables fast and sample-efficient incremental, human-in-the-loop corrections of generative visuomotor policies at deployment time in real-world robotics.
Authors: Quoc Hoan Tran, Koki Chinzei, Yasuhiro Endo, Hirotaka Oshima
Abstract: Generative models for quantum data pose significant challenges but hold immense potential in fields such as chemoinformatics and quantum physics. Quantum denoising diffusion probabilistic models (QuDDPMs) enable efficient learning of quantum data distributions by progressively scrambling and denoising quantum states; however, existing implementations typically rely on circuit-based random unitary dynamics that can be costly to realize and sensitive to control imperfections, particularly on analog quantum hardware. We propose the chaotic quantum diffusion model, a framework that generates projected ensembles via chaotic Hamiltonian time evolution, providing a flexible and hardware-compatible diffusion mechanism. Requiring only global, time-independent control, our approach substantially reduces implementation overhead across diverse analog quantum platforms while achieving accuracy comparable to QuDDPMs. This method improves trainability and robustness, broadening the applicability of quantum generative modeling.
Authors: Xiaxian Ou, Razieh Nabi
Abstract: A class of causal effect functionals requires integration over conditional densities of continuous variables, as in mediation effects and nonparametric identification in causal graphical models. Estimating such densities and evaluating the resulting integrals can be statistically and computationally demanding. A common workaround is to discretize the variable and replace integrals with finite sums. Although convenient, discretization alters the population-level functional and can induce non-negligible approximation bias, even under correct identification. Under smoothness conditions, we show that this coarsening bias is first order in the bin width and arises at the level of the target functional, distinct from statistical estimation error. We propose a simple bias-reduced functional that evaluates the outcome regression at within-bin conditional means, eliminating the leading term and yielding a second-order approximation error. We derive plug-in and one-step estimators for the bias-reduced functional. Simulations demonstrate substantial bias reduction and near-nominal confidence interval coverage, even under coarse binning. Our results provide a simple framework for controlling the impact of variable discretization on parameter approximation and estimation.
Authors: Evgeny Moerman, Adil Kabylda, Almaz Khabibrakhmanov, Alexandre Tkatchenko
Abstract: Van der Waals (vdW) interactions are essential for describing molecules and materials, from drug design and catalysis to battery applications. These omnipresent interactions must also be accurately included in machine-learned force fields. The many-body dispersion (MBD) method stands out as one of the most accurate and transferable approaches to capture vdW interactions, requiring only atomic $C_6$ coefficients and polarizabilities as input. We present MBD-ML, a pretrained message passing neural network that predicts these atomic properties directly from atomic structures. Through seamless integration with libMBD, our method enables the immediate calculation of MBD-inclusive total energies, forces, and stress tensors. By eliminating the need for intermediate electronic structure calculations, MBD-ML offers a practical and streamlined tool that simplifies the incorporation of state-of-the-art vdW interactions into any electronic structure code, as well as empirical and machine-learned force fields.
Authors: Luiz Fernando Paulino Queiroz, Carlos Henrique Leit\~ao Cavalcante, Thiago Alves Rocha
Abstract: Neural networks (NNs) are pervasive across various domains but often lack interpretability. To address the growing need for explanations, logic-based approaches have been proposed to explain predictions made by NNs, offering correctness guarantees. However, scalability remains a concern in these methods. This paper proposes an approach leveraging domain slicing to facilitate explanation generation for NNs. By reducing the complexity of logical constraints through slicing, we decrease explanation time by up to 40\% less time, as indicated through comparative experiments. Our findings highlight the efficacy of domain slicing in enhancing explanation efficiency for NNs.
Authors: Elio Moreau, Florentin Coeurdoux, Gr\'egoire Ferre, Eric Vanden-Eijnden
Abstract: Understanding the geometry of learned distributions is fundamental to improving and interpreting diffusion models, yet systematic tools for exploring their landscape remain limited. Standard latent-space interpolations fail to respect the structure of the learned distribution, often traversing low-density regions. We introduce a framework based on the string method that computes continuous paths between samples by evolving curves under the learned score function. Operating on pretrained models without retraining, our approach interpolates between three regimes: pure generative transport, which yields continuous sample paths; gradient-dominated dynamics, which recover minimum energy paths (MEPs); and finite-temperature string dynamics, which compute principal curves -- self-consistent paths that balance energy and entropy. We demonstrate that the choice of regime matters in practice. For image diffusion models, MEPs contain high-likelihood but unrealistic ''cartoon'' images, confirming prior observations that likelihood maxima appear unrealistic; principal curves instead yield realistic morphing sequences despite lower likelihood. For protein structure prediction, our method computes transition pathways between metastable conformers directly from models trained on static structures, yielding paths with physically plausible intermediates. Together, these results establish the string method as a principled tool for probing the modal structure of diffusion models -- identifying modes, characterizing barriers, and mapping connectivity in complex learned distributions.
Authors: Patrick Tser Jern Kon, Archana Pradeep, Ang Chen, Alexander P. Ellis, Warren Hunt, Zijian Wang, John Yang, Samuel Thompson
Abstract: Small language models (SLMs) offer compelling advantages in cost, latency, and adaptability, but have so far lagged behind larger models on long-horizon software engineering tasks such as SWE-bench, where they suffer from pervasive action looping and low resolution rates. We introduce SWE-Prot\'eg\'e, a post-training framework that reframes software repair as an expert-prot\'eg\'e collaboration problem. In SWE-Prot\'eg\'e, an SLM remains the sole decision-maker while learning to selectively seek guidance from a strong expert model, recognize stalled states, and follow through on expert feedback. Our approach combines supervised fine-tuning on expert-augmented trajectories with agentic reinforcement learning that explicitly discourages degenerative looping and unproductive expert collaboration. We lightly post-train Qwen2.5-Coder-7B-Instruct to achieve 42.4% Pass@1 on SWE-bench Verified, a +25.4% improvement over the prior SLM state of the art, while using expert assistance sparsely (~4 calls per task and 11% of total tokens).
Authors: Leon Pielage, Ole H\"atscher, Mitja Back, Bernhard Marschall, Benjamin Risse
Abstract: The inability of Large Language Models (LLMs) to modulate their personality expression in response to evolving dialogue dynamics hinders their performance in complex, interactive contexts. We propose a model-agnostic framework for dynamic personality simulation that employs state machines to represent latent personality states, where transition probabilities are dynamically adapted to the conversational context. Part of our architecture is a modular pipeline for continuous personality scoring that evaluates dialogues along latent axes while remaining agnostic to the specific personality models, their dimensions, transition mechanisms, or LLMs used. These scores function as dynamic state variables that systematically reconfigure the system prompt, steering behavioral alignment throughout the interaction.We evaluate this framework by operationalizing the Interpersonal Circumplex (IPC) in a medical education setting. Results demonstrate that the system successfully adapts its personality state to user inputs, but also influences user behavior, thereby facilitating de-escalation training. Notably, the scoring pipeline maintains comparable precision even when utilizing lightweight, fine-tuned classifiers instead of large-scale LLMs. This work demonstrates the feasibility of modular, personality-adaptive architectures for education, customer support, and broader human-computer interaction.
Authors: Hanna Yukhymenko, Anton Alexandrov, Martin Vechev
Abstract: The reliability of multilingual Large Language Model (LLM) evaluation is currently compromised by the inconsistent quality of translated benchmarks. Existing resources often suffer from semantic drift and context loss, which can lead to misleading performance metrics. In this work, we present a fully automated framework designed to address these challenges by enabling scalable, high-quality translation of datasets and benchmarks. We demonstrate that adapting test-time compute scaling strategies, specifically Universal Self-Improvement (USI) and our proposed multi-round ranking method, T-RANK, allows for significantly higher quality outputs compared to traditional pipelines. Our framework ensures that benchmarks preserve their original task structure and linguistic nuances during localization. We apply this approach to translate popular benchmarks and datasets into eight Eastern and Southern European languages (Ukrainian, Bulgarian, Slovak, Romanian, Lithuanian, Estonian, Turkish, Greek). Evaluations using both reference-based metrics and LLM-as-a-judge show that our translations surpass existing resources, resulting in more accurate downstream model assessment. We release both the framework and the improved benchmarks to facilitate robust and reproducible multilingual AI development.
Authors: Zhenkai Zhang, Krista A. Ehinger, Tom Drummond
Abstract: This paper introduces two key contributions aimed at improving the speed and quality of images generated through inverse diffusion processes. The first contribution involves reparameterizing the diffusion process in terms of the angle on a quarter-circular arc between the image and noise, specifically setting the conventional $\displaystyle \sqrt{\bar{\alpha}}=\cos(\eta)$. This reparameterization eliminates two singularities and allows for the expression of diffusion evolution as a well-behaved ordinary differential equation (ODE). In turn, this allows higher order ODE solvers such as Runge-Kutta methods to be used effectively. The second contribution is to directly estimate both the image ($\mathbf{x}_0$) and noise ($\mathbf{\epsilon}$) using our network, which enables more stable calculations of the update step in the inverse diffusion steps, as accurate estimation of both the image and noise are crucial at different stages of the process. Together with these changes, our model achieves faster generation, with the ability to converge on high-quality images more quickly, and higher quality of the generated images, as measured by metrics such as Frechet Inception Distance (FID), spatial Frechet Inception Distance (sFID), precision, and recall.
Authors: Mohammad Kohankhaki, Ahmad Ayad, Mahdi Barhoush, Anke Schmeink
Abstract: Distributed deep learning in resource-constrained environments faces scalability and generalization challenges due to large effective batch sizes and non-identically distributed client data. We introduce a server-driven sampling strategy that maintains a fixed global batch size by dynamically adjusting client-side batch sizes. This decouples the effective batch size from the number of participating devices and ensures that global batches better reflect the overall data distribution. Using standard concentration bounds, we establish tighter deviation guarantees compared to existing approaches. Empirical results on a benchmark dataset confirm that the proposed method improves model accuracy, training efficiency, and convergence stability, offering a scalable solution for learning at the network edge.
Authors: Shrenik Zinage, Ilias Bilionis, Peter Meckl
Abstract: The stringent regulatory requirements on nitrogen oxides (NOx) emissions from diesel compression ignition engines require accurate and reliable models for real time monitoring and diagnostics. Although traditional methods such as physical sensors and virtual engine control module (ECM) sensors provide essential data, they are only used for estimation. Ubiquitous literature primarily focuses on deterministic models with little emphasis on capturing the various uncertainties. The lack of probabilistic frameworks restricts the applicability of these models for robust diagnostics. The objective of this paper is to develop and validate a probabilistic model to predict engine-out NOx emissions using Gaussian process regression. Our approach is as follows. We employ three variants of Gaussian process models: the first with a standard radial basis function kernel with input window, the second incorporating a deep kernel using convolutional neural networks to capture temporal dependencies, and the third enriching the deep kernel with a causal graph derived via graph convolutional networks. The causal graph embeds physics knowledge into the learning process. All models are compared against a virtual ECM sensor using both quantitative and qualitative metrics. We conclude that our model provides an improvement in predictive performance when using an input window and a deep kernel structure. Even more compelling is the further enhancement achieved by the incorporation of a causal graph into the deep kernel. These findings are corroborated across different verification and validation datasets.
Authors: Joseph Arul Raj, Linglong Qian, Zina Ibrahim
Abstract: Missing values are pervasive in large-scale time-series data, posing challenges for reliable analysis and decision-making. Many neural architectures have been designed to model and impute the complex and heterogeneous missingness patterns of such data. Most existing methods are end-to-end, rendering imputation tightly coupled with downstream predictive tasks and leading to limited reusability of the trained model, reduced interpretability, and challenges in assessing model quality. In this paper, we call for a modular approach that decouples imputation and downstream tasks, enabling independent optimisation and greater adaptability. Using the largest open-source Python library for deep learning-based time-series analysis, PyPOTS, we evaluate a modular pipeline across six state-of-the-art models that perform imputation and prediction on seven datasets spanning multiple domains. Our results show that a modular approach maintains high performance while prioritising flexibility and reusability - qualities that are crucial for real-world applications. Through this work, we aim to demonstrate how modularity can benefit multivariate time-series analysis, achieving a balance between performance and adaptability.
Authors: Lara Kassab, Erin George, Deanna Needell, Haowen Geng, Nika Jafar Nia, Aoxi Li
Abstract: There has been a recent critical need to study fairness and bias in machine learning (ML) algorithms. Since there is clearly no one-size-fits-all solution to fairness, ML methods should be developed alongside bias mitigation strategies that are practical and approachable to the practitioner. Motivated by recent work on ``fair" PCA, here we consider the more challenging method of non-negative matrix factorization (NMF) as both a showcasing example and a method that is important in its own right for both topic modeling tasks and feature extraction for other ML tasks. We demonstrate that a modification of the objective function, by using a min-max formulation, may \textit{sometimes} be able to offer an improvement in fairness for groups in the population. We derive two methods for the objective minimization, a multiplicative update rule as well as an alternating minimization scheme, and discuss implementation practicalities. We include a suite of synthetic and real experiments that show how the method may improve fairness while also highlighting the important fact that this may sometime increase error for some individuals and fairness is not a rigid definition and method choice should strongly depend on the application at hand.
Authors: Weipu Zhang, Adam Jelley, Trevor McInroe, Amos Storkey, Gang Wang
Abstract: While deep reinforcement learning (RL) from pixels has achieved remarkable success, its sample inefficiency remains a critical limitation for real-world applications. Model-based RL (MBRL) addresses this by learning a world model to generate simulated experience, but standard approaches that rely on pixel-level reconstruction losses often fail to capture small, task-critical objects in complex, dynamic scenes. We posit that an object-centric (OC) representation can direct model capacity toward semantically meaningful entities, improving dynamics prediction and sample efficiency. In this work, we introduce OC-STORM, an object-centric MBRL framework that enhances a learned world model with object representations extracted by a pretrained segmentation network. By conditioning on a minimal number of annotated frames, OC-STORM learns to track decision-relevant object dynamics and inter-object interactions without extensive labeling or access to privileged information. Empirical results demonstrate that OC-STORM significantly outperforms the STORM baseline on the Atari 100k benchmark and achieves state-of-the-art sample efficiency on challenging boss fights in the visually complex game Hollow Knight. Our findings underscore the potential of integrating OC priors into MBRL for complex visual domains. Project page: https://oc-storm.weipuzhang.com
Authors: Daniel T. Speckhard, Tim Bechtel, Sebastian Kehl, Jonathan Godwin, Claudia Draxl
Abstract: Graph neural networks (GNN) have shown promising results for several domains such as materials science, chemistry, and the social sciences. GNN models often contain millions of parameters, and like other neural network (NN) models, are often fed only a fraction of the graphs that make up the training dataset in batches to update model parameters. The effect of batching algorithms on training time and model performance has been thoroughly explored for NNs but not yet for GNNs. We analyze two different batching algorithms for graph-based models, namely static and dynamic batching for two datasets, the QM9 dataset of small molecules and the AFLOW materials database. Our experiments show that changing the batching algorithm can provide up to a 2.7x speedup, but the fastest algorithm depends on the data, model, batch size, hardware, and number of training steps run. Experiments show that for a select number of combinations of batch size, dataset, and model, significant differences in model learning metrics are observed between static and dynamic batching algorithms.
Authors: Olga Zaghen, Floor Eijkelboom, Alison Pouplin, Cong Liu, Max Welling, Jan-Willem van de Meent, Erik J. Bekkers
Abstract: We present Riemannian Gaussian Variational Flow Matching (RG-VFM), a geometric extension of Variational Flow Matching (VFM) for generative modeling on manifolds. Motivated by the benefits of VFM, we derive a variational flow matching objective for manifolds with closed-form geodesics based on Riemannian Gaussian distributions. Crucially, in Euclidean space, predicting endpoints (VFM), velocities (FM), or noise (diffusion) is largely equivalent due to affine interpolations. However, on curved manifolds this equivalence breaks down. We formally analyze the relationship between our model and Riemannian Flow Matching (RFM), revealing that the RFM objective lacks a curvature-dependent penalty -- encoded via Jacobi fields -- that is naturally present in RG-VFM. Based on this relationship, we hypothesize that endpoint prediction provides a stronger learning signal by directly minimizing geodesic distances. Experiments on synthetic spherical and hyperbolic benchmarks, as well as real-world tasks in material and protein generation, demonstrate that RG-VFM more effectively captures manifold structure and improves downstream performance over Euclidean and velocity-based baselines. Code available at https://github.com/olgatticus/rg-vfm.
Authors: Saman Khamesian, Asiful Arefeen, Maria Adela Grando, Bithika M. Thompson, Hassan Ghasemzadeh
Abstract: Managing Type 1 Diabetes (T1D) demands constant vigilance as individuals strive to regulate their blood glucose levels and avoid dysglycemia, including hyperglycemia and hypoglycemia. Despite advances in automated insulin delivery (AID) systems, achieving optimal glycemic control remains challenging. These systems integrate data from wearable devices such as insulin pumps and continuous glucose monitors (CGMs), helping reduce variability and improve time in range. However, they often fail to prevent dysglycemia due to limitations in prediction algorithms that cannot accurately anticipate glycemic excursions. This limitation highlights the need for more advanced glucose forecasting methods. To address this need, we introduce GLIMMER (Glucose Level Indicator Model with Modified Error Rate), a modular and architecture-agnostic training framework for glucose forecasting. GLIMMER combines structured preprocessing, a region-aware loss formulation, and genetic algorithm-based weight optimization to emphasize prediction accuracy in dysglycemic regions. We evaluate GLIMMER using two datasets: the publicly available OhioT1DM dataset and a newly collected AZT1D dataset consisting of data from 25 individuals with T1D. Our analyses demonstrate that GLIMMER consistently improves forecasting performance across baseline architectures, reducing RMSE and MAE by up to 24.6% and 29.6%, respectively. Additionally, GLIMMER achieves a recall of 98.4% and an F1-score of 86.8% for dysglycemia prediction, highlighting strong performance in clinically high-risk regions. Compared with state-of-the-art models containing millions of parameters-such as TimesNet (18.7M), BG-BERT (2.1M), and Gluformer (11.2M)-GLIMMER attains comparable accuracy while using only 10K parameters, demonstrating its efficiency as a lightweight and architecture-agnostic solution for glycemic forecasting.
Authors: Nick Winovich, Mitchell Daneker, Lu Lu, Guang Lin
Abstract: With the increased prevalence of neural operators being used to provide rapid solutions to partial differential equations (PDEs), understanding the accuracy of model predictions and the associated error levels is necessary for deploying reliable surrogate models in scientific applications. Existing uncertainty quantification (UQ) frameworks employ ensembles or Bayesian methods, which can incur substantial computational costs during both training and inference. We propose a lightweight predictive UQ method tailored for Deep operator networks (DeepONets) that also generalizes to other operator networks. Numerical experiments on linear and nonlinear PDEs demonstrate that the framework's uncertainty estimates are unbiased and provide accurate out-of-distribution uncertainty predictions with a sufficiently large training dataset. Our framework provides fast inference and uncertainty estimates that can efficiently drive outer-loop analyses that would be prohibitively expensive with conventional solvers. We demonstrate how predictive uncertainties can be used in the context of Bayesian optimization and active learning problems to yield improvements in accuracy and data-efficiency for outer-loop optimization procedures. In the active learning setup, we extend the framework to Fourier Neural Operators (FNO) and describe a generalized method for other operator networks. To enable real-time deployment, we introduce an inference strategy based on precomputed trunk outputs and a sparse placement matrix, reducing evaluation time by more than a factor of five. Our method provides a practical route to uncertainty-aware operator learning in time-sensitive settings.
Authors: Zhouyang Liu, Ning Liu, Yixin Chen, Jiezhong He, Shuai Ma, Dongsheng Li
Abstract: Graph Edit Distance (GED) is a widely used measure of graph similarity, valued for its flexibility in encoding domain knowledge through operation costs. However, existing learning-based approximation methods follow a modeling paradigm that decouples local candidate match selection from both operation costs and global dependencies between matches. This decoupling undermines their ability to capture the intrinsic flexibility of GED and often forces them to rely on costly iterative refinement to obtain accurate alignments. In this work, we revisit the formulation of GED and revise the prevailing paradigm, and propose Graph Edit Network (GEN), an implementation of the revised formulation that tightly integrates cost-aware expense estimation with globally guided one-step alignment. Specifically, GEN incorporates operation costs into node matching expenses estimation, ensuring match decisions respect the specified cost setting. Furthermore, GEN models match dependencies within and across graphs, capturing each match's impact on the overall alignment. These designs enable accurate GED approximation without iterative refinement. Extensive experiments on real-world and synthetic benchmarks demonstrate that GEN achieves up to a 37.8% reduction in GED predictive errors, while increasing inference throughput by up to 414x. These results highlight GEN's practical efficiency and the effectiveness of the revision. Beyond this implementation, our revision provides a principled framework for advancing learning-based GED approximation.
Authors: Erin Carson, Xinye Chen
Abstract: Motivated by the growing demand for low-precision arithmetic in computational science, we exploit lower-precision emulation in Python -- widely regarded as the dominant programming language for numerical analysis and machine learning. Low-precision training has revolutionized deep learning by enabling more efficient computation and reduced memory and energy consumption while maintaining model fidelity. To better enable numerical experimentation with and exploration of low precision computation, we developed the Pychop library, which supports customizable floating-point formats and a comprehensive set of rounding modes in Python, allowing users to benefit from fast, low-precision emulation in numerous applications. Pychop also introduces interfaces for both PyTorch and JAX, enabling efficient low-precision emulation on GPUs for neural network training and inference with unparalleled flexibility. In this paper, we offer a comprehensive exposition of the design, implementation, validation, and practical application of Pychop, establishing it as a foundational tool for advancing efficient mixed-precision algorithms. Furthermore, we present empirical results on low-precision emulation for image classification and object detection using published datasets, illustrating the sensitivity of the use of low precision and offering valuable insights into its impact. Pychop enables in-depth investigations into the effects of numerical precision, facilitates the development of novel hardware accelerators, and integrates seamlessly into existing deep learning workflows. Software and experimental code are publicly available at https://github.com/inEXASCALE/pychop.
Authors: Changhai Zhou, Qian Qiao, Yuhua Zhou, Yuxin Wu, Shichao Weng, Weizhong Zhang, Cheng Jin
Abstract: Low-rank and sparse composite approximation is a natural idea to compress Large Language Models (LLMs). However, such an idea faces two primary challenges that adversely affect the performance of existing methods. The first challenge relates to the interaction and cooperation between low-rank and sparse matrices, while the second involves determining weight allocation across different layers, as redundancy varies considerably among them. To address these challenges, we propose a novel two-stage LLM compression method with the capability of global resource allocation for rank and sparsity. It is noteworthy that the overall optimization space is vast, making comprehensive optimization computationally prohibitive. Therefore, to reduce the optimization space, our first stage utilizes robust principal component analysis to decompose the weight matrices of LLMs into low-rank and sparse components, which span the low dimensional and sparse spaces containing the resultant low-rank and sparse matrices, respectively. In the second stage, we propose a probabilistic global allocation strategy to jointly identify the low-rank and sparse structures within the above two spaces. The appealing feature of our approach is its ability to automatically detect the redundancy across different layers and to manage the interaction between the sparse and low-rank components. Extensive experimental results indicate that our method significantly surpasses state-of-the-art techniques for sparsification and composite approximation.
Authors: Benjamin Th\'erien, Xiaolong Huang, Aaron Defazio, Irina Rish, Eugene Belilovsky
Abstract: DiLoCo is a powerful framework for training large language models (LLMs), enabling larger optimal batch sizes and increased accelerator utilization under networking constraints. However, DiLoCo's performance has been shown to degrade as the number of workers (K) increases (Charles et al., 2025). In this work, we posit that a related but often overlooked factor in DiLoCo's behavior is the choice of inner optimizer, which shapes the pseudogradient used by the outer optimizer. Given the recent success of Muon relative to AdamW for data parallel (DP) training, we examine how Muon's normalized optimizer steps can affect the pseudogradient's quality. We find that, relative to AdamW, Muon yields more directionally correct pseudogradients as the number of workers (K) increases. In our experiments pre-training language models, we conduct extensive hyperparameter tuning across 150M, 416M, 914M, 1.76B, and 3.1B models for DiLoCo, MuLoCo, AdamW DP, and Muon DP. Consistently across all scales, we find that with K>=1 workers, MuLoCo (Muon inner optimizer DiLoCo) achieves superior performance to DiLoCo in absolute terms and for K>2 it outperforms DiLoCo relative to their data parallel baselines, while being compatible with quantization, streaming, and long synchronization intervals. At K=1, we find that MuLoCo can even outperform the data-parallel gold standard while having larger critical batch sizes. Finally, we extrapolate optimal hyperparameters to 15B scale and train a model with each method (six in total) using K=1 and K=16 workers. We find that K=16 MuLoCo nearly matches single-worker performance at this scale, while MuLoCo K=1 matches the best performing baseline while using a much larger 16M token batch size.
Authors: Yuxin Xiao, Sana Tonekaboni, Walter Gerych, Vinith Suriyakumar, Marzyeh Ghassemi
Abstract: Large language models (LLMs) can be prompted with specific styles (e.g., formatting responses as lists), including in malicious queries. Prior jailbreak research mainly augments these queries with additional string transformations to maximize attack success rate (ASR). However, the impact of style patterns in the original queries that are semantically irrelevant to the malicious intent remains unclear. In this work, we seek to understand whether style patterns compromise LLM safety, how superficial style alignment increases model vulnerability, and how best to mitigate these risks during alignment. We first define ASR inflation as the increase in ASR due to style patterns in existing jailbreak benchmark queries. By evaluating 36 LLMs across seven benchmarks, we find that nearly all models exhibit ASR inflation. Notably, the inflation correlates with an LLM's relative attention to style patterns, which also overlap more with its instruction-tuning data when inflation occurs. We then investigate superficial style alignment, and find that fine-tuning with specific styles makes LLMs more vulnerable to jailbreaks of those same styles. Finally, we propose SafeStyle, a defense strategy that incorporates a small amount of safety training data augmented to match the distribution of style patterns in the fine-tuning data. Across three LLMs, six fine-tuning style settings, and two real-world instruction-tuning datasets, SafeStyle consistently outperforms baselines in maintaining LLM safety.
Authors: Thomas Zhu, Joshua Clune, Jeremy Avigad, Albert Qiaochu Jiang, Sean Welleck
Abstract: Neural methods are transforming automated reasoning for proof assistants, yet integrating these advances into practical verification workflows remains challenging. A hammer is a tool that integrates premise selection, translation to external automatic theorem provers, and proof reconstruction into one overarching tool to automate tedious reasoning steps. We present LeanPremise, a novel neural premise selection system, and we combine it with existing translation and proof reconstruction components to create LeanHammer, the first end-to-end domain general hammer for the Lean proof assistant. Unlike existing Lean premise selectors, LeanPremise is specifically trained for use with a hammer in dependent type theory. It also dynamically adapts to user-specific contexts, enabling it to effectively recommend premises from libraries outside LeanPremise's training data as well as lemmas defined by the user locally. With comprehensive evaluations, we show that LeanPremise enables LeanHammer to solve 21% more goals than existing premise selectors and generalizes well to diverse domains. Our work helps bridge the gap between neural retrieval and symbolic reasoning, making formal verification more accessible to researchers and practitioners.
Authors: Tao Wang, Hewei Tang
Abstract: Underground hydrogen storage (UHS) is a promising energy storage option for the current energy transition to a low-carbon economy. Fast modeling of hydrogen plume migration and pressure field evolution is crucial for UHS field management. In this study, a new neural operator architecture, factorized Fourier improved neural operator or FFINO is proposed as a fast surrogate model for multiphase flow problems in UHS. Experimental relative permeability curves reported in the literature are also parameterized as key uncertainty parameters for the FFINO model. FFINO model performance with the state-of-the-art Fourier-enhanced multiple-input neural operators or FMIONet model are systematically studied through a comprehensive combination of metrics. Our new FFINO model has 38.1% fewer trainable parameters, 17.6% less training time, and 12% less GPU memory cost compared to FMIONet. The FFINO model also achieves a 9.8% accuracy improvement in predicting hydrogen plume in focused areas, and 16.3% higher accuracy in predicting pressure buildup. Sensitivity analysis identifies that the most influential input parameter to models' performance is the injection rate Q, while other parameters show moderate to minor impacts. The inference time of the trained FFINO model is 7,850 times faster than a numerical simulator, which guarantees its superior time efficiency. The novel FFINO model can serve as a fast, accurate, and stable alternative to estimate the temporal and spatial evolution of hydrogen plumes and pressure distributions for real-time UHS applications.
Authors: Prajwal Koirala, Cody Fleming
Abstract: Generative models such as diffusion and flow-matching offer expressive policies for offline reinforcement learning (RL) by capturing rich, multimodal action distributions, but their iterative sampling introduces high inference costs and training instability due to gradient propagation across sampling steps. We propose the Single-Step Completion Policy (SSCP), a generative policy trained with an augmented flow-matching objective to predict direct completion vectors from intermediate flow samples, enabling accurate, one-shot action generation. In an off-policy actor-critic framework, SSCP combines the expressiveness of generative models with the training and inference efficiency of unimodal policies, without requiring long backpropagation chains. Our method scales effectively to offline, offline-to-online, and online RL settings, offering substantial gains in speed and adaptability over diffusion-based baselines. We further extend SSCP to goal-conditioned RL, enabling flat policies to exploit subgoal structures without explicit hierarchical inference. SSCP achieves strong results across standard offline RL and behavior cloning benchmarks, positioning it as a versatile, expressive, and efficient framework for deep RL and sequential decision-making. The code is available at https://github.com/PrajwalKoirala/SSCP-Single-Step-Completion-Policy.
URLs: https://github.com/PrajwalKoirala/SSCP-Single-Step-Completion-Policy.
Authors: Anh Bui, Trang Vu, Trung Le, Junae Kim, Tamas Abraham, Rollin Omari, Amar Kaur, Dinh Phung
Abstract: In this paper, we investigate the semantic collapsing problem in generative personalization, an under-explored topic where the learned visual concept ($V$) gradually shifts from its original textual meaning and comes to dominate other concepts in multi-concept input prompts. This issue not only reduces the semantic richness of complex input prompts like "a photo of $V$ wearing glasses and playing guitar" into simpler, less contextually rich forms such as "a photo of $V$" but also leads to simplified output images that fail to capture the intended concept. We identify the root cause as unconstrained optimisation, which allows the learned embedding $V$ to drift arbitrarily in the embedding space, both in direction and magnitude. To address this, we propose a simple yet effective training-free method that adjusts the magnitude and direction of pre-trained embedding at inference time, effectively mitigating the semantic collapsing problem. Our method is broadly applicable across different personalization methods and demonstrates significant improvements in text-image alignment in diverse use cases. Our code is anonymously published at https://github.com/tuananhbui89/Embedding-Adjustment
Authors: Chuan Li, Jiang You, Hassine Moungla, Vincent Gauthier, Miguel Nunez-del-Prado, Hugo Alatrista-Salas
Abstract: Accurate modeling of human mobility is critical for understanding epidemic spread and deploying timely interventions. In this work, we leverage a large-scale spatio-temporal dataset collected from Peru's national Digital Contact Tracing (DCT) application during the COVID-19 pandemic to forecast mobility flows across urban regions. A key challenge lies in the spatial sparsity of hourly mobility counts across hexagonal grid cells, which limits the predictive power of conventional time series models. To address this, we propose a lightweight and model-agnostic Spatial Neighbourhood Fusion (SPN) technique that augments each cell's features with aggregated signals from its immediate H3 neighbors. We evaluate this strategy on three forecasting backbones: NLinear, PatchTST, and K-U-Net, under various historical input lengths. Experimental results show that SPN consistently improves forecasting performance, achieving up to 9.85 percent reduction in test MSE. Our findings demonstrate that spatial smoothing of sparse mobility signals provides a simple yet effective path toward robust spatio-temporal forecasting during public health crises.
Authors: Neha Verma, Kenton Murray, Kevin Duh
Abstract: Structured pruning methods designed for Large Language Models (LLMs) generally focus on identifying and removing the least important components to optimize model size. However, in this work, we question this prevalent approach by instead exploring how to recombine information from structures designated for pruning back into the reduced model. We specifically focus on neuron width reduction, and frame this problem as a Discrete Optimal Transport problem, and propose DOTResize, a novel Transformer compression method that uses optimal transport theory to transform and compress model width. To ensure applicability within the Transformer architecture, we motivate and incorporate necessary entropic regularization and matrix factorization techniques into the transportation maps produced by our method. Unlike pruning-based approaches which discard neurons based on importance measures, DOTResize re-projects the entire neuron width, allowing the retention and redistribution of useful signal across the reduced layer. Empirical results show that compared to simple or state-of-the-art neuron width-pruning techniques, DOTResize serves as a useful add-on to pruning, while achieving measurable reductions in real-world computational cost.
Authors: Kai Malcolm, C\'esar Uribe, Momona Yamagami
Abstract: Neural interfaces offer a pathway to intuitive, high-bandwidth interaction, but the sensitive nature of neural data creates significant privacy hurdles for large-scale model training. Federated learning (FL) has emerged as a promising privacy-preserving solution, yet its efficacy in real-time, online neural interfaces remains unexplored. In this study, we 1) propose a conceptual framework for applying FL to the distinct constraints of neural interface application and 2) provide a systematic evaluation of FL-based neural decoding using high-dimensional electromyography (EMG) across both offline simulations and a real-time, online user study. While offline results suggest that FL can simultaneously enhance performance and privacy, our online experiments reveal a more complex landscape. We found that standard FL assumptions struggle to translate to real-time, sequential interactions with human-decoder co-adaptation. Our results show that while FL retains privacy advantages, it introduces performance tensions not predicted by offline simulations. These findings identify a critical gap in current FL methodologies and highlight the need for specialized algorithms designed to navigate the unique co-adaptive dynamics of sequential-user neural decoding.
Authors: Hugo Negrel, Florentin Coeurdoux, Michael S. Albergo, Eric Vanden-Eijnden
Abstract: We propose a framework for learning maps between probability distributions that broadly generalizes the time dynamics of flow and diffusion models. To enable this, we generalize stochastic interpolants by replacing the scalar time variable with vectors, matrices, or linear operators, allowing us to bridge probability distributions across multiple dimensional spaces. This approach enables the construction of versatile generative models capable of fulfilling multiple tasks without task-specific training. Our operator-based interpolants not only provide a unifying theoretical perspective for existing generative models but also extend their capabilities. Through numerical experiments, we demonstrate the zero-shot efficacy of our method on conditional generation and inpainting, fine-tuning and posterior sampling, and multiscale modeling, suggesting its potential as a generic task-agnostic alternative to specialized models.
Authors: Viacheslav Barkov, Jonas Schmidinger, Robin Gebbers, Martin Atzmueller
Abstract: In the field of pedometrics, tabular machine learning is the predominant method for soil property prediction from remote and proximal soil sensing data, forming a central component of Digital Soil Mapping (DSM). At the field-scale, this predictive soil modeling (PSM) task is typically constrained by small training sample sizes and high feature-to-sample ratios in soil spectroscopy. Traditionally, these conditions have proven challenging for conventional deep learning methods. Classical machine learning algorithms, particularly tree-based models like Random Forest and linear models such as Partial Least Squares Regression, have long been the default choice for pedometric modeling within DSM. Recent advances in artificial neural networks (ANN) for tabular data challenge this view, yet their suitability for field-scale DSM has not been proven. We introduce a comprehensive benchmark that evaluates state-of-the-art ANN architectures, including the latest multilayer perceptron (MLP)-based models (TabM, RealMLP), attention-based transformer variants (FT-Transformer, ExcelFormer, T2G-Former, AMFormer), retrieval-augmented approaches (TabR, ModernNCA), and an in-context learning foundation model (TabPFN). Our evaluation encompasses 31 field- and farm-scale datasets containing 30-460 soil samples and three critical soil properties: soil organic matter or soil organic carbon, pH, and clay content. Our results reveal that modern ANNs consistently outperform classical methods on the majority of tasks, demonstrating that deep learning has matured sufficiently to overcome the long-standing dominance of classical machine learning in pedometrics. Notably, TabPFN delivers the strongest overall performance, showing robustness across varying conditions. We therefore recommend the adoption of modern ANNs for field-scale DSM and propose TabPFN as the new default choice in the toolkit of every pedometrician.
Authors: Pietro Buzzega, Riccardo Salami, Angelo Porrello, Simone Calderara
Abstract: Fine-tuning pretrained models has become a standard pathway to achieve state-of-the-art performance across a wide range of domains, leading to a proliferation of task-specific model variants. As the number of such specialized models increases, merging them into a unified model without retraining has become a critical challenge. Existing merging techniques operate at the level of individual layers, thereby overlooking the inter-layer dependencies inherent in deep networks. We show that this simplification leads to distributional mismatches, particularly in methods that rely on intermediate activations, as changes in early layers are not properly propagated to downstream layers during merging. We identify these mismatches as a form of internal covariate shift, comparable to the phenomenon encountered in the initial phases of neural networks training. To address this, we propose Chain of Merges (CoM), a layer-wise merging procedure that sequentially merges weights across layers while sequentially updating activation statistics. By explicitly accounting for inter-layer interactions, CoM mitigates covariate shift and produces a coherent merged model through a series of conditionally optimal updates. Experiments on standard benchmarks demonstrate that CoM achieves state-of-the-art performance.
Authors: Rajiv Kailasanathan, William R. Clements, Mohammad Reza Boskabadi, Shawn M. Gibford, Emmanouil Papadakis, Christopher J. Savoie, Seyed Soheil Mansouri
Abstract: The development of continuous biomanufacturing processes requires robust and early anomaly detection, since even minor deviations can compromise yield and stability, leading to disruptions in scheduling, reduced weekly production, and diminished economic performance. These processes are inherently complex and exhibit non-linear dynamics with intricate relationships between process variables, thus making advanced methods for anomaly detection essential for efficient operation. In this work, we present a novel framework for unsupervised anomaly detection in continuous biomanufacturing based on an ensemble of generative adversarial networks (GANs). We first establish a benchmark dataset simulating both normal and anomalous operation regimes in a continuous process for the production of a small molecule. We then demonstrate the effectiveness of our GAN-based framework in detecting anomalies caused by sudden feedstock variability. Finally, we evaluate the impact of using a hybrid quantum/classical GAN approach with both a simulated quantum circuit and a real photonic quantum processor on anomaly detection performance. We find that the hybrid approach yields improved anomaly detection rates. Our work shows the potential of hybrid quantum/classical approaches for solving real-world problems in complex continuous biomanufacturing processes.
Authors: Junkai Zhang, Zihao Wang, Lin Gui, Swarnashree Mysore Sathyendra, Jaehwan Jeong, Victor Veitch, Wei Wang, Yunzhong He, Bing Liu, Lifeng Jin
Abstract: Reinforcement fine-tuning (RFT) often suffers from reward over-optimization, where a policy model hacks the reward signals to achieve high scores while producing low-quality outputs. Our theoretical analysis shows that the key lies in reward misspecification at the high-reward tail: the inability to reliably distinguish Excellent responses from merely Great ones. This motivate us to focus on the high-reward region. However, such tail examples are scarce under the base LLM. While off-policy exemplars (e.g. from stronger models or rewrites) are easier to obtain, naively training on them yields a misspecified reward for the policy we aim to align. To address this, we study rubric-based rewards. By design, rubrics can leverage off-policy examples while remaining insensitive to their artifacts. To elicit rubrics that capture the high-reward tail, we highlight the importance of distinguishing among great and diverse responses, and introduce a workflow to implement this idea. We empirically demonstrate that rubric-based rewards substantially mitigate reward over-optimization and deliver effective LLM post-training improvements.
Authors: Seongwoong Shim, Myunsoo Kim, Jae Hyeon Cho, Byung-Jun Lee
Abstract: Retrieval-Augmented Generation (RAG) is a framework for grounding Large Language Models (LLMs) in external, up-to-date information. However, recent advancements in context window size allow LLMs to process inputs of up to 128K tokens or more, offering an alternative strategy: supplying the full document context directly to the model, rather than relying on RAG to retrieve a subset of contexts. Nevertheless, this emerging alternative strategy has notable limitations: (i) it is token-inefficient to handle large and potentially redundant contexts; (ii) it exacerbates the `lost in the middle' phenomenon; and (iii) under limited model capacity, it amplifies distraction, ultimately degrading LLM output quality. In this paper, we propose LDAR (Learning Distraction-Aware Retrieval), an adaptive retriever that learns to retrieve contexts in a way that mitigates interference from distracting passages, thereby achieving significantly higher performance with reduced token usage compared to long-context approaches. Extensive experiments across diverse LLM architectures and six knowledge-intensive benchmarks demonstrate the effectiveness and robustness of our approach, highlighting the importance of balancing the trade-off between information coverage and distraction.
Authors: Zheng Wang, Kaixuan Zhang, Wanfang Chen, Xiaonan Lu, Longyuan Li, Tobias Schlagenhauf
Abstract: Time series forecasting remains a critical challenge across numerous domains, yet the effectiveness of complex models often varies unpredictably across datasets. Recent studies highlight the surprising competitiveness of simple linear models, suggesting that their robustness and interpretability warrant deeper theoretical investigation. This paper presents a systematic study of linear models for time series forecasting, with a focus on the role of characteristic roots in temporal dynamics. We begin by analyzing the noise-free setting, where we show that characteristic roots govern long-term behavior and explain how design choices such as instance normalization and channel independence affect model capabilities. We then extend our analysis to the noisy regime, revealing that models tend to produce spurious roots. This leads to the identification of a key data-scaling property: mitigating the influence of noise requires disproportionately large training data, highlighting the need for structural regularization. To address these challenges, we propose two complementary strategies for robust root restructuring. The first uses rank reduction techniques, including \textbf{Reduced-Rank Regression (RRR)} and \textbf{Direct Weight Rank Reduction (DWRR)}, to recover the low-dimensional latent dynamics. The second, a novel adaptive method called \textbf{Root Purge}, encourages the model to learn a noise-suppressing null space during training. Extensive experiments on standard benchmarks demonstrate the effectiveness of both approaches, validating our theoretical insights and achieving state-of-the-art results in several settings. Our findings underscore the potential of integrating classical theories for linear systems with modern learning techniques to build robust, interpretable, and data-efficient forecasting models.
Authors: Gongxu Luo, Loka Li, Guangyi Chen, Haoyue Dai, Kun Zhang
Abstract: Interventional causal discovery seeks to identify causal relations by leveraging distributional changes introduced by interventions, even in the presence of latent confounders. Beyond the spurious dependencies induced by latent confounders, we highlight a common yet often overlooked challenge in the problem due to post-treatment selection, in which samples are selectively included in datasets after interventions. This fundamental challenge widely exists in biological studies; for example, in gene expression analysis, both observational and interventional samples are retained only if they meet quality control criteria (e.g., highly active cells). Neglecting post-treatment selection may introduce spurious dependencies and distributional changes under interventions, which can mimic causal responses, thereby distorting causal discovery results and challenging existing causal formulations. To address this, we introduce a novel causal formulation that explicitly models post-treatment selection and reveals how its differential reactions to interventions can distinguish causal relations from selection patterns, allowing us to go beyond traditional equivalence classes toward the underlying true causal structure. We then characterize its Markov properties and propose a Fine-grained Interventional equivalence class, named FI-Markov equivalence, represented by a new graphical diagram, F-PAG. Finally, we develop a provably sound and complete algorithm, F-FCI, to identify causal relations, latent confounders, and post-treatment selection up to $\mathcal{FI}$-Markov equivalence, using both observational and interventional data. Experimental results on synthetic and real-world datasets demonstrate that our method recovers causal relations despite the presence of both selection and latent confounders.
Authors: Marcin Mo\.zejko, Adam Bielecki, Jurand Pr\k{a}dzy\'nski, Marcin Traskowski, Antoni Janowski, Hyun-Su Lee, Marcelo Der Torossian Torres, Micha{\l} Kmicikiewicz, Paulina Szymczak, Karol Jurasz, Micha{\l} Kucharczyk, Cesar de la Fuente-Nunez, Ewa Szczurek
Abstract: Antimicrobial peptide discovery is challenged by the astronomical size of peptide space and the relative scarcity of active peptides. Generative models provide continuous latent "maps" of peptide space, but conventionally ignore decoder-induced geometry and rely on flat Euclidean metrics, rendering exploration and optimization distorted and inefficient. Prior manifold-based remedies assume fixed intrinsic dimensionality, which critically fails in practice for peptide data. Here, we introduce PepCompass, a geometry-aware framework for peptide exploration and optimization. At its core, we define a Union of $\kappa$-Stable Riemannian Manifolds $\mathbb{M}^{\kappa}$, a family of decoder-induced manifolds that captures local geometry while ensuring computational stability. We propose two local exploration methods: Second-Order Riemannian Brownian Efficient Sampling, which provides a convergent second-order approximation to Riemannian Brownian motion, and Mutation Enumeration in Tangent Space, which reinterprets tangent directions as discrete amino-acid substitutions. Combining these yields Local Enumeration Bayesian Optimization (LE-BO), an efficient algorithm for local activity optimization. Finally, we introduce Potential-minimizing Geodesic Search (PoGS), which interpolates between prototype embeddings along property-enriched geodesics, biasing discovery toward seeds, i.e. peptides with favorable activity. In-vitro validation confirms the effectiveness of PepCompass: PoGS yields four novel seeds, and subsequent optimization with LE-BO discovers 25 highly active peptides with broad-spectrum activity, including against resistant bacterial strains. These results demonstrate that geometry-informed exploration provides a powerful new paradigm for antimicrobial peptide design.
Authors: Makram Chahine, Philipp Nazari, Daniela Rus, T. Konstantin Rusch
Abstract: State Space Models (SSMs), developed to tackle long sequence modeling tasks efficiently, offer both parallelizable training and fast inference. At their core are recurrent dynamical systems that maintain a hidden state, with update costs scaling with the state dimension. A key design challenge is striking the right balance between maximizing expressivity and limiting this computational burden. Control theory, and more specifically Hankel singular value analysis, provides a potent framework for the measure of energy for each state, as well as the balanced truncation of the original system down to a smaller representation with performance guarantees. Leveraging the eigenvalue stability properties of Hankel matrices, we apply this lens to SSMs \emph{during training}, where only dimensions of high influence are identified and preserved. Our approach, \textsc{CompreSSM}, applies to Linear Time-Invariant SSMs such as Linear Recurrent Units, but is also extendable to selective models. Experiments show that in-training reduction significantly accelerates optimization while preserving expressivity, with compressed models retaining task-critical structure lost by models trained directly at smaller dimension. In other words, SSMs that begin large and shrink during training achieve computational efficiency while maintaining higher performance. Project code is available at github.com/camail-official/compressm.
Authors: Wen Wu, Ziyang Zhang, Liwei Liu, Xuenan Xu, Jimin Zhuang, Ke Fan, Qitan Lv, Junlin Liu, Chen Zhang, Zheqi Yuan, Siyuan Hou, Tianyi Lin, Kai Chen, Bowen Zhou, Chao Zhang
Abstract: The scientific reasoning ability of large language models (LLMs) has recently attracted significant attention. Time series, as a fundamental modality in scientific data, presents unique challenges that are often overlooked in current multimodal LLMs, which either encode numerical sequences as text or convert them into images. Such approaches may be insufficient for comprehensive scientific time series understanding and generation. Existing unified time series models typically specialise in either forecasting or analysis, and their effectiveness on non-periodic, heterogeneous scientific signals remains unclear. To address these gaps, we introduce SciTS, a benchmark spanning 12 scientific domains and 43 tasks, with over 50k+ instances, both univariate and multivariate signals ranging from $10^0$ to $10^7$ in length and up to 10~MHz in frequency. We benchmark 17 models, including text-only LLMs, multimodal LLMs, and unified time series models, and find that general-purpose LLMs exhibit stronger generalisability than specialised time series models, while representing time series as text or images limits their performance due to excessively long sequences and loss of numerical precision, respectively. We then introduce TimeOmni, a framework that equips LLMs with the ability to understand and generate time series while remaining compatible with general-purpose LLM training. This work fills a gap in both dedicated benchmarks and modelling frameworks for scientific time series, paving the way for LLMs to understand and generate complex temporal scientific data.
Authors: Wei Wang, Tianhao Ma, Ming-Kun Xie, Gang Niu, Masashi Sugiyama
Abstract: Partial multi-label learning and complementary multi-label learning are two popular weakly supervised multi-label classification paradigms that aim to alleviate the high annotation costs of collecting precisely annotated multi-label data. In partial multi-label learning, each instance is annotated with a candidate label set, among which only some labels are relevant; in complementary multi-label learning, each instance is annotated with complementary labels indicating the classes to which the instance does not belong. Existing consistent approaches for the two paradigms either require accurate estimation of the generation process of candidate or complementary labels or assume a uniform distribution to eliminate the estimation problem. However, both conditions are usually difficult to satisfy in real-world scenarios. In this paper, we propose consistent approaches that do not rely on the aforementioned conditions to handle both problems in a unified way. Specifically, we propose two risk estimators based on first- and second-order strategies. Theoretically, we prove consistency w.r.t. two widely used multi-label classification evaluation metrics and derive convergence rates for the estimation errors of the proposed risk estimators. Empirically, extensive experimental results on both real-world and synthetic datasets validate the effectiveness of our proposed approaches against state-of-the-art methods.
Authors: Yuval Golbari, Navve Wasserman, Gal Vardi, Michal Irani
Abstract: Determining which data samples were used to train a model, known as Membership Inference Attack (MIA), is a well-studied and important problem with implications on data privacy. SotA methods (which are black-box attacks) rely on training many auxiliary reference models to imitate the behavior of the attacked model. As such, they rely on assumptions which rarely hold in real-world settings: (i) the attacker knows the training hyperparameters; (ii) all available non-training samples come from the same distribution as the training data; and (iii) the fraction of training data in the evaluation set is known. We show that removing these assumptions significantly harms the performance of black-box attacks. We introduce ImpMIA, a Membership Inference Attack that exploits the Implicit Bias of neural networks. Building on the maximum-margin implicit bias theory, ImpMIA uses the Karush-Kuhn-Tucker (KKT) optimality conditions to identify training samples -- those whose gradients most strongly reconstruct the trained model's parameters. Our approach is optimization-based, and requires NO training of reference-models, thus removing the need for any knowledge/assumptions regarding the attacked model's training procedure. While ImpMIA is a white-box attack (a setting which assumes access to model weights), this is becoming increasingly realistic given that many models are publicly available (e.g., via Hugging Face). ImpMIA achieves SotA performance compared to both black and white box attacks in settings where only the model weights are known, and a superset of the training data is available.
Authors: Marcel Meyer, Sascha Kaltenpoth, Kevin Zalipski, Oliver M\"uller
Abstract: Time Series Foundation Models (TSFMs) represent a new paradigm for time-series forecasting, promising zero-shot predictions without the need for task-specific training or fine-tuning. However, similar to Large Language Models (LLMs), the evaluation of TSFMs is challenging: as training corpora grow increasingly large, it becomes difficult to ensure the integrity of the test sets used for benchmarking. An investigation of existing TSFM evaluation studies identifies two kinds of information leakage: (1) train-test sample overlaps arising from the multi-purpose reuse of datasets and (2) temporal overlap of correlated train and test series. Ignoring these forms of information leakage when benchmarking TSFMs risks producing overly optimistic performance estimates that fail to generalize to real-world settings. We therefore argue for the development of novel evaluation methodologies that avoid pitfalls already observed in both LLM and classical time-series benchmarking, and we call on the research community to adopt principled approaches to safeguard the integrity of TSFM evaluation.
Authors: Qinxuan Wang, Chuang Wang, Mingyu Zhang, Jingwei Sun, Peipei Yang, Shuo Tang, Shiming Xiang
Abstract: Neural operators have emerged as a powerful data-driven paradigm for solving partial differential equations (PDEs), while their accuracy and scalability are still limited, particularly on irregular domains where fluid flows exhibit rich multiscale structures. In this work, we introduce the Multiscale Neural Operator (MNO), a new architecture for computational fluid dynamics (CFD) on 3D unstructured point clouds. MNO explicitly decomposes information across three scales: a global dimension-shrinkage attention module for long-range dependencies, a local graph attention module for neighborhood-level interactions, and a micro point-wise attention module for fine-grained details. This design preserves multiscale inductive biases while remaining computationally efficient. We evaluate MNO on diverse benchmarks, covering steady-state and unsteady flow scenarios with up to 300k points. Across all tasks, MNO consistently outperforms state-of-the-art baselines, reducing prediction errors by 5% to 50%. The results highlight the importance of explicit multiscale design for neural operators and establish MNO as a scalable framework for learning complex fluid dynamics on irregular domains.
Authors: Wei-Jer Chang, Akshay Rangesh, Kevin Joseph, Matthew Strong, Masayoshi Tomizuka, Yihan Hu, Wei Zhan
Abstract: Developing autonomous vehicles (AVs) requires not only safety and efficiency, but also realistic, human-like behaviors that are socially aware and predictable. Achieving this requires sim agent policies that are human-like, fast, and scalable in multi-agent settings. Recent progress in imitation learning with large diffusion-based or tokenized models has shown that behaviors can be captured directly from human driving data, producing realistic policies. However, these models are computationally expensive, slow during inference, and struggle to adapt in reactive, closed-loop scenarios. In contrast, self-play reinforcement learning (RL) scales efficiently and naturally captures multi-agent interactions, but it often relies on heuristics and reward shaping, and the resulting policies can diverge from human norms. We propose SPACeR, a framework that leverages a pretrained tokenized autoregressive motion model as a centralized reference policy to guide decentralized self-play. The reference model provides likelihood rewards and KL divergence, anchoring policies to the human driving distribution while preserving RL scalability. Evaluated on the Waymo Sim Agents Challenge, our method achieves competitive performance with imitation-learned policies while being up to 10x faster at inference and 50x smaller in parameter size than large generative models. In addition, we demonstrate in closed-loop ego planning evaluation tasks that our sim agents can effectively measure planner quality with fast and scalable traffic simulation, establishing a new paradigm for testing autonomous driving policies.
Authors: Si-Yu Xiao, Xin-Di Zhao, Tian-Hao Mao, Yi-Wei Wang, Yu-Qiao Chen, Hong-Yun Zhang, Jian Wang, Jun-Jie Wang, Shuang Liu, Tu-Pei Chen, Yang Liu
Abstract: Accurate downhole depth measurement is essential for oil and gas well operations, directly influencing reservoir contact, production efficiency, and operational safety. Collar correlation using a casing collar locator (CCL) is fundamental for precise depth calibration. While neural network has achieved significant progress in collar recognition, preprocessing methods for such applications remain underdeveloped. Moreover, the limited availability of real well data poses substantial challenges for training neural network models that require extensive datasets. This paper presents a system integrated into a downhole toolstring for CCL log acquisition to facilitate dataset construction. Comprehensive preprocessing methods for data augmentation are proposed, and their effectiveness is evaluated using baseline neural network models. Through systematic experimentation across diverse configurations, the contribution of each augmentation method is analyzed. Results demonstrate that standardization, label distribution smoothing, and random cropping are fundamental prerequisites for model training, while label smoothing regularization, time scaling, and multiple sampling significantly enhance model generalization capabilities. Incorporating the proposed augmentation methods into the two baseline models results in maximum F1 score improvements of 0.027 and 0.024 for the TAN and MAN models, respectively. Furthermore, applying these techniques yields F1 score gains of up to 0.045 for the TAN model and 0.057 for the MAN model compared to prior studies. Performance evaluation on real CCL waveforms confirms the effectiveness and practical applicability of our approach. This work addresses the existing gaps in data augmentation methodologies for training casing collar recognition models under CCL data-limited conditions, and provides a technical foundation for the future automation of downhole operations.
Authors: Weixuan Ou, Yanzhao Zheng, Shuoshuo Sun, Wei Zhang, Baohua Dong, Hangcheng Zhu, Ruohui Huang, Gang Yu, Pengwei Yan, Yifan Qiao
Abstract: Reinforcement Learning (RL) has been shown to improve the capabilities of large language models (LLMs). However, applying RL to open-domain tasks faces two key challenges: (1) the inherent subjectivity of these tasks prevents the verifiable rewards as required by Reinforcement Learning with Verifiable Rewards (RLVR); (2) Reinforcement Learning from Human Feedback (RLHF) relies on external reward mechanisms. To overcome these limitations, we propose Self-Examining Reinforcement Learning (SERL), a novel self-improving framework where the LLM serves as both Actor and Judge. SERL introduces two synergistic reward mechanisms without any external signals. On the one hand, to improve the Actor's capability, we derive rewards from Copeland-style pairwise comparison judgments across a group of generated responses. On the other hand, a self-consistency reward that encourages coherent judgments is proposed to improve the Judge's reliability. This process refines the Judge's capability, which in turn provides a more robust reward for Actor. Experiments show that our method outperforms existing self-improvement training methods. SERL improves the LC win rate of Qwen3-8B on AlpacaEval 2 from 52.37% to 59.90%. To the best of our knowledge, our method achieves state-of-the-art performance among self-improving approaches. Furthermore, it achieves a performance comparable to significantly larger models like Qwen3-32B, demonstrating superior effectiveness and robustness on open-domain tasks.
Authors: Jiahe Shi, Zhengqi Gao, Ching-Yun Ko, Duane Boning
Abstract: Recent advances in large language models (LLMs) have demonstrated significant potential in hardware design automation, particularly in using natural language to synthesize Register-Transfer Level (RTL) code. Despite this progress, a gap remains between model capability and the demands of real-world RTL design, including syntax errors, functional hallucinations, and weak alignment to designer intent. Reinforcement Learning with Verifiable Rewards (RLVR) offers a promising approach to bridge this gap, as hardware provides executable and formally checkable signals that can be used to further align model outputs with design intent. However, in long, structured RTL code sequences, not all tokens contribute equally to functional correctness, and na\"ively spreading gradients across all tokens dilutes learning signals. A key insight from our entropy analysis in RTL generation is that only a small fraction of tokens (e.g., always, if, assign, posedge) exhibit high uncertainty and largely influence control flow and module structure. To address these challenges, we present EARL, an Entropy-Aware Reinforcement Learning framework for Verilog generation. EARL performs policy optimization using verifiable reward signals and introduces entropy-guided selective updates that gate policy gradients to high-entropy tokens. This approach preserves training stability and concentrates gradient updates on functionally important regions of code. Our experiments on VerilogEval and RTLLM show that EARL improves functional pass rates over prior LLM baselines by up to 14.7%, while reducing unnecessary updates and improving training stability. These results indicate that focusing RL on critical, high-uncertainty tokens enables more reliable and targeted policy improvement for structured RTL code generation.
Authors: Chen Zhang, Wei Zuo, Bingyang Cheng, Yikun Wang, Wei-Bin Kou, Yik Chung WU, Ngai Wong
Abstract: Implicit Neural Representations (INRs) parameterize continuous signals via multilayer perceptrons (MLPs), enabling compact, resolution-independent modeling for tasks like image, audio, and 3D reconstruction. However, fitting high-resolution signals demands optimizing over millions of coordinates, incurring prohibitive computational costs. To address it, we propose NTK-Guided Implicit Neural Teaching (NINT), which accelerates training by dynamically selecting coordinates that maximize global functional updates. Leveraging the Neural Tangent Kernel (NTK), NINT scores examples by the norm of their NTK-augmented loss gradients, capturing both fitting errors and heterogeneous leverage (self-influence and cross-coordinate coupling). This dual consideration enables faster convergence compared to existing methods. Through extensive experiments, we demonstrate that NINT significantly reduces training time by nearly half while maintaining or improving representation quality, establishing state-of-the-art acceleration among recent sampling-based strategies.
Authors: Chenliang Li, Adel Elmahdy, Alex Boyd, Zhongruo Wang, Siliang Zeng, Alfredo Garcia, Parminder Bhatia, Taha Kass-Hout, Cao Xiao, Mingyi Hong
Abstract: Reinforcement learning (RL) algorithms such as PPO and GRPO are widely used to train large language models (LLMs) for multi-turn agentic tasks. However, in off-policy training pipelines, these methods often exhibit unstable optimization dynamics and are prone to performance collapse. Through empirical analysis, we identify two fundamental sources of instability in this setting: (1)~a granularity mismatch between token-level policy optimization and turn-structured interactions, and (2) high-variance and unreliable gradient updates induced by off-policy importance sampling and inaccurate advantage estimation. To address these challenges, we propose SORL, \underline{S}tabilizing \underline{O}ff-Policy \underline{R}einforcement \underline{L}earning for Long-Horizon Agent Training. SORL introduces principled mechanisms that align policy optimization with the structure of multi-turn interactions and adaptively suppress unreliable off-policy updates, yielding more conservative and robust learning dynamics. Within this framework, we instantiate two stabilized algorithms: SO-PPO and SO-GRPO. Both algorithms are designed to mitigate gradient variance and prevent optimization collapse without requiring careful early stopping or heuristic tuning. We evaluate SO-PPO and SO-GRPO on a range of multi-turn search benchmarks, including general question answering, multi-hop question answering, and medical multiple-choice QA tasks. Experimental results show that both methods consistently prevent training instabilities and performance collapses observed in standard PPO and GRPO, maintain lower clipping ratios and more stable optimization trajectories, and achieve superior or comparable task performance. These results demonstrate that the proposed algorithm provides a practical, scalable, and general framework for stabilizing reinforcement learning in multi-turn LLM agent training.
Authors: Robert Joseph George, Carson Eisenach, Udaya Ghai, Dominique Perrault-Joncas, Anima Anandkumar, Dean Foster
Abstract: Large language models (LLMs) are good at generating code, but remain brittle for formal verification in systems like Lean4. A core scalability challenge is that verified synthesis requires consistent outputs across multiple artifacts: executable code, precise specifications, theorem statements, and ultimately proofs. Existing approaches rarely treat these as a unified pipeline. We present BRIDGE, a structured prompting framework that decomposes verification into three interconnected domains: Code (implementations), Specifications (formal intent), and Theorem Statements (constructive correctness claims), and elicits domain-specific intermediate reasoning to connect them. In Lean4, BRIDGE often adopts a code-first workflow, using the generated implementation as a semantic anchor for downstream specification and theorem statement generation. Across 178 algorithmic problems and five LLMs, BRIDGE improves Lean executable correctness by nearly 1.5x (pass at 5) over direct baselines and can be 2x more sample-efficient at inference time, requiring fewer samples per verified solution at comparable generation lengths. We further find that specification-driven prompting improves Python pass rates by up to 17.5 percent. Beyond inference-time prompting, supervised fine-tuning on BRIDGE-style reasoning traces yields nearly 1.5x higher Lean pass success than code-only SFT, indicating that these intermediate representations are learnable. BRIDGE provides a practical foundation for scaling verified synthesis and motivates future work on expert iteration and full proof generation.
Authors: Zhongjian Qiao, Rui Yang, Jiafei Lyu, Chenjia Bai, Xiu Li, Siyang Gao, Shuang Qiu
Abstract: Cross-domain offline reinforcement learning (RL) aims to train a well-performing agent in the target environment, leveraging both a limited target domain dataset and a source domain dataset with (possibly) sufficient data coverage. Due to the underlying dynamics misalignment between source and target domains, naively merging the two datasets may incur inferior performance. Recent advances address this issue by selectively leveraging source domain samples whose dynamics align well with the target domain. However, our work demonstrates that dynamics alignment alone is insufficient, by examining the limitations of prior frameworks and deriving a new target domain sub-optimality bound for the policy learned on the source domain. More importantly, our theory underscores an additional need for \textit{value alignment}, i.e., selecting high-quality, high-value samples from the source domain, a critical dimension overlooked by existing works. Motivated by such theoretical insight, we propose \textbf{\underline{D}}ynamics- and \textbf{\underline{V}}alue-aligned \textbf{\underline{D}}ata \textbf{\underline{F}}iltering (DVDF) method, a novel unified cross-domain RL framework that selectively incorporates source domain samples exhibiting strong alignment in \textit{both dynamics and values}. We empirically study a range of dynamics shift scenarios, including kinematic and morphology shifts, and evaluate DVDF on various tasks and datasets, even in the challenging setting where the target domain dataset contains an extremely limited amount of data. Extensive experiments demonstrate that DVDF consistently outperforms strong baselines with significant improvements.
Authors: Nima Dehmamy, Benjamin Hoover, Bishwajit Saha, Leo Kozachkov, Jean-Jacques Slotine, Dmitry Krotov
Abstract: Generative Pre-trained Transformer (GPT) architectures are the most popular design for language modeling. Energy-based modeling is a different paradigm that views inference as a dynamical process operating on an energy landscape. We propose a minimal modification of the GPT setting to unify it with the EBM framework. The inference step of our model, which we call eNeRgy-GPT (NRGPT), is conceptualized as an exploration of the tokens on the energy landscape. We prove, and verify empirically, that under certain circumstances this exploration becomes gradient descent, although they don't necessarily lead to the best performing models. We demonstrate that our model performs well for simple language (Shakespeare dataset), algebraic ListOPS tasks, and richer settings such as OpenWebText language modeling. We also observe that our models may be more resistant to overfitting, doing so only during very long training.
Authors: Ata Akbari Asanjan, Milad Memarzadeh, Bryan Matthews, Nikunj Oza
Abstract: In this study, we focus on the training process and inference improvements of deep neural networks (DNNs), specifically Autoencoders (AEs) and Variational Autoencoders (VAEs), using Random Fourier Transformation (RFT). We further explore the role of RFT in model training behavior using Frequency Principle (F-Principle) analysis and show that models with RFT turn to learn low frequency and high frequency at the same time, whereas conventional DNNs start from low frequency and gradually learn (if successful) high-frequency features. We focus on reconstruction-based anomaly detection using autoencoder and variational autoencoder and investigate the RFT's role. We also introduced a trainable variant of RFT that uses the existing computation graph to train the expansion of RFT instead of it being random. We showcase our findings with two low-dimensional synthetic datasets for data representation, and an aviation safety dataset, called Dashlink, for high-dimensional reconstruction-based anomaly detection. The results indicate the superiority of models with Fourier transformation compared to the conventional counterpart and remain inconclusive regarding the benefits of using trainable Fourier transformation in contrast to the Random variant.
Authors: Hao Bai, Alexey Taymanov, Tong Zhang, Aviral Kumar, Spencer Whitehead
Abstract: We present WebGym, the largest-to-date open-source environment for training realistic visual web agents. Real websites are non-stationary and diverse, making artificial or small-scale task sets insufficient for robust policy learning. WebGym contains nearly 300,000 tasks with rubric-based evaluations across diverse, real-world websites and difficulty levels. We train agents with a simple reinforcement learning (RL) recipe, which trains on the agent's own interaction traces (rollouts), using task rewards as feedback to guide learning. To enable scaling RL, we speed up sampling of trajectories in WebGym by developing a high-throughput asynchronous rollout system, designed specifically for web agents. Our system achieves a 4-5x rollout speedup compared to naive implementations. Second, we scale the task set breadth, depth, and size, which results in continued performance improvement. Fine-tuning a strong base vision-language model, Qwen-3-VL-8B-Instruct, on WebGym results in an improvement in success rate on an out-of-distribution test set from 26.2% to 42.9%, significantly outperforming agents based on proprietary models such as GPT-4o and GPT-5-Thinking that achieve 27.1% and 29.8%, respectively. This improvement is substantial because our test set consists only of tasks on websites never seen during training, unlike many other prior works on training visual web agents.
Authors: Chris Elliott, Einar Urdshals, David Quarel, Matthew Farrugia-Roberts, Daniel Murfet
Abstract: Singular learning theory characterizes Bayesian learning as an evolving tradeoff between accuracy and complexity, with transitions between qualitatively different solutions as sample size increases. We extend this theory to reinforcement learning, proving that the concentration of a generalized posterior over policies is governed by the local learning coefficient (LLC), an invariant of the geometry of the regret function. This theory predicts that deep reinforcement learning with SGD should proceed from simple policies with high regret to complex policies with low regret. We verify this prediction empirically in a gridworld environment exhibiting stagewise policy development: phase transitions over training manifest as "opposing staircases" where regret decreases sharply while the LLC increases.
Authors: Wang Zixian
Abstract: We propose Orthogonalized Policy Optimization (OPO), a principled framework for large language model alignment derived from optimization in the Hilbert function space L2(pi_k). Lifting policy updates from the probability simplex into L2(pi_k) transforms the nonlinear normalization constraint into a linear orthogonality condition
Authors: Antoine Siraudin, Christopher Morris
Abstract: Graph diffusion models achieve state-of-the-art performance in graph generation but suffer from quadratic complexity in the number of nodes -- and much of their capacity is wasted modeling the absence of edges in sparse graphs. Inspired by latent diffusion in other modalities, a natural idea is to compress graphs into a low-dimensional latent space and perform diffusion there. However, unlike images or text, graph generation requires nearly lossless reconstruction, as even a single error in decoding an adjacency matrix can render the entire sample invalid. This challenge has remained largely unaddressed. We propose LG-Flow, a latent graph diffusion framework that directly overcomes these obstacles. A permutation-equivariant autoencoder maps each node into a fixed-dimensional embedding from which the full adjacency is provably recoverable, enabling near-lossless reconstruction for both undirected graphs and DAGs. The dimensionality of this latent representation scales linearly with the number of nodes, eliminating the quadratic bottleneck and making it feasible to train larger and more expressive models. In this latent space, we train a Diffusion Transformer with flow matching, enabling efficient and expressive graph generation. Our approach achieves competitive results against state-of-the-art graph diffusion models, while achieving up to $1000\times$ speed-up. Our code is available at https://github.com/asiraudin/LG-Flow .
Authors: Filippo Portera
Abstract: We propose a new convex loss for Support Vector Machines, both for the binary classification and for the regression models. Therefore, we show the mathematical derivation of the dual problems and we experiment with them on several small datasets. The minimal dimension of those datasets is due to the difficult scalability of the SVM method to bigger instances. This preliminary study should prove that using pattern correlations inside the loss function could enhance the generalisation performances. Our method consistently achieved comparable or superior performance, with improvements of up to 2.0% in F1 scores for classification tasks and 1.0% reduction in Mean Squared Error (MSE) for regression tasks across various datasets, compared to standard losses. Coherently, results show that generalisation measures are never worse than the standard losses and several times they are better. In our opinion, it should be considered a careful study of this loss, coupled with shallow and deep neural networks. In fact, we present some novel results obtained with those architectures.
Authors: Michael Siebenmann, Javier Argota S\'anchez-Vaquerizo, Stefan Arisona, Krystian Samp, Luis Gisler, Dirk Helbing
Abstract: We present OGD4All, a transparent, auditable, and reproducible framework based on Large Language Models (LLMs) to enhance citizens' interaction with geospatial Open Government Data (OGD). The system combines semantic data retrieval, agentic reasoning for iterative code generation, and secure sandboxed execution that produces verifiable multimodal outputs. Evaluated on a 199-question benchmark covering both factual and unanswerable questions, across 430 City-of-Zurich datasets and 11 LLMs, OGD4All reaches 98% analytical correctness and 94% recall while reliably rejecting questions unsupported by available data, which minimizes hallucination risks. Statistical robustness tests, as well as expert feedback, show reliability and social relevance. The proposed approach shows how LLMs can provide explainable, multimodal access to public data, advancing trustworthy AI for open governance.
Authors: Minghao Li, Ruihang Wang, Rui Tan, Yonggang Wen
Abstract: Modern data centers (DCs) hosting artificial intelligence (AI)-dedicated devices operate at high power densities with rapidly varying workloads, making minute-level adaptation essential for safe and energy-efficient operation. However, manually designing piecewise deep reinforcement learning (DRL) agents cannot keep pace with frequent dynamics shifts and service-level agreement (SLA) changes of an evolving DC. This specification-to-policy lag causes a lack of timely, effective control policies, which may lead to service outages. To bridge the gap, we present DCoPilot, a hybrid framework for generative control policies in dynamic DC operation. DCoPilot synergizes two distinct generative paradigms, i.e., a large language model (LLM) that performs symbolic generation of structured reward forms, and a hypernetwork that conducts parametric generation of policy weights. DCoPilot operates through three coordinated phases: (i) simulation scale-up, which stress-tests reward candidates across diverse simulation-ready (SimReady) scenes; (ii) meta policy distillation, where a hypernetwork is trained to output policy weights conditioned on SLA and scene embeddings; and (iii) online adaptation, enabling zero-shot policy generation in response to updated specifications. Evaluated across five control task families spanning diverse DC components, DCoPilot achieves near-zero constraint violations and outperforms all baselines across specification variations. Ablation studies validate the effectiveness of LLM-based unified reward generation in enabling stable hypernetwork convergence.
Authors: Kanghyun Noh, Jinheon Choi, Yulhwa Kim
Abstract: Large language models (LLMs) demand substantial computational and memory resources, posing challenges for efficient deployment. Two complementary approaches have emerged to address these issues: token-adaptive layer execution, which reduces floating-point operations (FLOPs) by selectively bypassing layers, and quantization, which lowers memory footprint by reducing weight precision. However, naively integrating these techniques leads to additional accuracy degradation due to reduced redundancy in token-adaptive models. We propose QTALE (Quantization-Robust Token-Adaptive Layer Execution for LLMs), a novel framework that enables seamless integration of token-adaptive execution with quantization while preserving accuracy. Conventional token-adaptive methods reduce redundancy in two ways: (1) by limiting the diversity of training paths explored during fine-tuning, and (2) by lowering the number of parameters actively involved in inference. To overcome these limitations, QTALE introduces two key components: (1) a training strategy that ensures diverse execution paths are actively explored during fine-tuning, and (2) a post-training mechanism that allows flexible adjustment of the execution ratio at inference to reintroduce redundancy when needed. Experimental results show that QTALE enables seamless integration of token-adaptive layer execution with quantization, showing no noticeable accuracy difference, with the gap to quantization-only models kept below 0.5% on CommonsenseQA benchmarks. By combining token-adaptive execution for FLOPs reduction and quantization for memory savings, QTALE provides an effective solution for efficient LLM deployment.
Authors: Rui Ma
Abstract: We study same-source multi-view learning and adversarial robustness for next-day direction prediction using two deterministic, window-aligned image views derived from the same time series: an OHLCV-rendered chart (ohlcv) and a technical-indicator matrix (indic). To control label ambiguity from near-zero moves, we use an ex-post minimum-movement threshold min_move (tau) based on realized absolute next-day return, defining an offline benchmark on the subset where the absolute next-day return is at least tau. Under leakage-resistant time-block splits with embargo, we compare early fusion (channel stacking) and dual-encoder late fusion with optional cross-branch consistency. We then evaluate pixel-space L-infinity evasion attacks (FGSM/PGD) under view-constrained and joint threat models. We find that fusion is regime dependent: early fusion can suffer negative transfer under noisier settings, whereas late fusion is a more reliable default once labels stabilize. Robustness degrades sharply under tiny budgets with stable view-dependent vulnerabilities; late fusion often helps under view-constrained attacks, but joint perturbations remain challenging.
Authors: Dawon Ahn, Het Patel, Aemal Khattak, Jia Chen, Evangelos E. Papalexakis
Abstract: Railway crossings present complex safety challenges where driver behavior varies by location, time, and conditions. Traditional approaches analyze crossings individually, limiting the ability to identify shared behavioral patterns across locations. We propose a multi-view tensor decomposition framework that captures behavioral similarities across three temporal phases: Approach (warning activation to gate lowering), Waiting (gates down to train passage), and Clearance (train passage to gate raising). We analyze railway crossing videos from multiple locations using TimeSformer embeddings to represent each phase. By constructing phase-specific similarity matrices and applying non-negative symmetric CP decomposition, we discover latent behavioral components with distinct temporal signatures. Our tensor analysis reveals that crossing location appears to be a stronger determinant of behavior patterns than time of day, and that approach-phase behavior provides particularly discriminative signatures. Visualization of the learned component space confirms location-based clustering, with certain crossings forming distinct behavioral clusters. This automated framework enables scalable pattern discovery across multiple crossings, providing a foundation for grouping locations by behavioral similarity to inform targeted safety interventions.
Authors: Jim Zhao, Tin Sum Cheng, Wojciech Masarczyk, Aurelien Lucchi
Abstract: Neural Collapse (NC) refers to the emergence of highly symmetric geometric structures in the representations of deep neural networks during the terminal phase of training. Despite its prevalence, the theoretical understanding of NC remains limited. Existing analyses largely ignore the role of the optimizer, thereby suggesting that NC is universal across optimization methods. In this work, we challenge this assumption and demonstrate that the choice of optimizer plays a critical role in the emergence of NC. The phenomenon is typically quantified through NC metrics, which, however, are difficult to track and analyze theoretically. To overcome this limitation, we introduce a novel diagnostic metric, NC0, whose convergence to zero is a necessary condition for NC. Using NC0, we provide theoretical evidence that NC cannot emerge under decoupled weight decay in adaptive optimizers, as implemented in AdamW. Concretely, we prove that SGD, SignGD with coupled weight decay (a special case of Adam), and SignGD with decoupled weight decay (a special case of AdamW) exhibit qualitatively different NC0 dynamics. Also, we show the accelerating effect of momentum on NC (beyond convergence of train loss) when trained with SGD, being the first result concerning momentum in the context of NC. Finally, we conduct extensive empirical experiments consisting of 3,900 training runs across various datasets, architectures, optimizers, and hyperparameters, confirming our theoretical results. This work provides the first theoretical explanation for optimizer-dependent emergence of NC and highlights the overlooked role of weight-decay coupling in shaping the implicit biases of optimizers.
Authors: Aditya Agrawal, Albert Magyar, Hiteshwar Eswaraiah, Patrick Sheridan, Pradeep Janedula, Ravi Krishnan Venkatesan, Krishna Nair, Ravi Iyer
Abstract: Training and serving Large Language Models (LLMs) relies heavily on parallelization and collective operations, which are frequently bottlenecked by network bandwidth. Lossless compression using e.g., Huffman codes can alleviate the issue, however, Huffman codes suffer from slow, bit-sequential decoding and high hardware complexity due to deep tree traversals. Universal codes e.g., Exponential-Golomb codes are faster to decode but do not exploit the symbol frequency distributions. To address these limitations, this paper introduces Quad Length Codes, a hybrid approach designed to balance compression efficiency with decoding speed. The coding scheme uses 3 prefix bits to divide the 256 symbols into 8 areas. Each area has a different code length and encodes a different number of symbols. The scheme uses a Look Up Table with 256 entries, significantly simplifying the hardware implementation compared to Huffman trees. The coding scheme can be adapted for different distributions. For the e4m3 data type, the scheme achieves a compressibility of 13.9% in comparison to 15.9% achieved by Huffman codes, but it significantly speeds up the decoding and simplifies the hardware complexity.
Authors: Daniel Romero-Alvarado, Fernando Mart\'inez-Plumed, Lorenzo Pacchiardi, Hugo Save, Siddhesh Milind Pawar, Behzad Mehrbakhsh, Pablo Antonio Moreno Casares, Ben Slater, Paolo Bova, Peter Romero, Zachary R. Tyler, Jonathan Prunty, Luning Sun, Jose Hernandez-Orallo
Abstract: AI evaluation has primarily focused on measuring capabilities, with formal approaches inspired from Item Response Theory (IRT) being increasingly applied. Yet propensities - the tendencies of models to exhibit particular behaviours - play a central role in determining both performance and safety outcomes. However, traditional IRT describes a model's success on a task as a monotonic function of model capabilities and task demands, an approach unsuited to propensities, where both excess and deficiency can be problematic. Here, we introduce the first formal framework for measuring AI propensities by using a bilogistic formulation for model success, which attributes high success probability when the model's propensity is within an "ideal band". Further, we estimate the limits of the ideal band using LLMs equipped with newly developed task-agnostic rubrics. Applying our framework to six families of LLM models whose propensities are incited in either direction, we find that we can measure how much the propensity is shifted and what effect this has on the tasks. Critically, propensities estimated using one benchmark successfully predict behaviour on held-out tasks. Moreover, we obtain stronger predictive power when combining propensities and capabilities than either separately. More broadly, our framework showcases how rigorous propensity measurements can be conducted and how it yields gains over solely using capability evaluations to predict AI behaviour.
Authors: Xiaotong Ji, Rasul Tutunov, Matthieu Zimmer, Haitham Bou-Ammar
Abstract: Decoding sits between a language model and everything we do with it, yet it is still treated as a heuristic knob-tuning exercise. We argue decoding should be understood as a principled optimisation layer: at each token, we solve a regularised problem over the probability simplex that trades off model score against structural preferences and constraints. This single template recovers greedy decoding, Softmax sampling, Top-K, Top-P, and Sparsemax-style sparsity as special cases, and explains their common structure through optimality conditions. More importantly, the framework makes it easy to invent new decoders without folklore. We demonstrate this by designing Best-of-K (BoK), a KL-anchored coverage objective aimed at multi-sample pipelines (self-consistency, reranking, verifier selection). BoK targets the probability of covering good alternatives within a fixed K-sample budget and improves empirical performance. We show that such samples can improve accuracy by, for example, +18.6% for Qwen2.5-Math-7B on MATH500 at high sampling temperatures.
Authors: Ziheng Chen, Bernhard Sch\"olkopf, Nicu Sebe
Abstract: Hyperbolic spaces provide a natural geometry for representing hierarchical and tree-structured data due to their exponential volume growth. To leverage these benefits, neural networks require intrinsic and efficient components that operate directly in hyperbolic space. In this work, we lift two core components of neural networks, Multinomial Logistic Regression (MLR) and Fully Connected (FC) layers, into hyperbolic space via Busemann functions, resulting in Busemann MLR (BMLR) and Busemann FC (BFC) layers with a unified mathematical interpretation. BMLR provides compact parameters, a point-to-horosphere distance interpretation, batch-efficient computation, and a Euclidean limit, while BFC generalizes FC and activation layers with comparable complexity. Experiments on image classification, genome sequence learning, node classification, and link prediction demonstrate improvements in effectiveness and efficiency over prior hyperbolic layers. The code is available at https://github.com/GitZH-Chen/HBNN.
Authors: Florentin Coeurdoux, Etienne Lempereur, Nathana\"el Cuvelle-Magar, Thomas Eboli, St\'ephane Mallat, Anastasia Borovykh, Eric Vanden-Eijnden
Abstract: We develop a kernel method for generative modeling within the stochastic interpolant framework, replacing neural network training with linear systems. The drift of the generative SDE is $\hat b_t(x) = \nabla\phi(x)^\top\eta_t$, where $\eta_t\in\R^P$ solves a $P\times P$ system computable from data, with $P$ independent of the data dimension $d$. Since estimates are inexact, the diffusion coefficient $D_t$ affects sample quality; the optimal $D_t^*$ from Girsanov diverges at $t=0$, but this poses no difficulty and we develop an integrator that handles it seamlessly. The framework accommodates diverse feature maps -- scattering transforms, pretrained generative models etc. -- enabling training-free generation and model combination. We demonstrate the approach on financial time series, turbulence, and image generation.
Authors: Wall Kim, Chaeyoung Song, Hanul Kim
Abstract: Recently, TabPFN has gained attention as a foundation model for tabular data. However, it struggles to integrate heterogeneous modalities such as images and text, which are common in domains like healthcare and marketing, thereby limiting its applicability. To address this, we present the Multi-Modal Prior-data Fitted Network (MMPFN), which extends TabPFN to handle tabular and non-tabular modalities in a unified manner. MMPFN comprises per-modality encoders, modality projectors, and pre-trained foundation models. The modality projectors serve as the critical bridge, transforming non-tabular embeddings into tabular-compatible tokens for unified processing. To this end, we introduce a multi-head gated MLP and a cross-attention pooler that extract richer context from non-tabular inputs while mitigates attention imbalance issue in multimodal learning. Extensive experiments on medical and general-purpose multimodal datasets demonstrate that MMPFN consistently outperforms competitive state-of-the-art methods and effectively exploits non-tabular modalities alongside tabular features. These results highlight the promise of extending prior-data fitted networks to the multimodal setting, offering a scalable and effective framework for heterogeneous data learning. The source code is available at https://github.com/too-z/MultiModalPFN.
Authors: Jingxuan Zhang, Yunta Hsieh, Zhongwei Wan, Haokun Lin, Xin Wang, Ziqi Wang, Yingtie Lei, Mi Zhang
Abstract: Vision-language-action (VLA) models unify perception, language, and control for embodied agents but face significant challenges in practical deployment due to rapidly increasing compute and memory demands, especially as models scale to longer horizons and larger backbones. To address these bottlenecks, we introduce QuantVLA, a training-free post-training quantization (PTQ) framework that, to our knowledge, is the first PTQ approach for VLA systems and the first to successfully quantize a diffusion transformer (DiT) action head. QuantVLA incorporates three scale-calibrated components: (1) a selective quantization layout that integerizes all linear layers in both the language backbone and the DiT while keeping attention projections in floating point to preserve the original operator schedule; (2) attention temperature matching, a lightweight per-head scaling mechanism that stabilizes attention logits and is folded into the dequantization scales at inference; and (3) output head balancing, a per-layer residual interface calibration that mitigates post-projection energy drift. The framework requires no additional training, uses only a small unlabeled calibration buffer, and supports integer kernels for low-bit weights and activations while leaving the architecture unchanged. Across representative VLA models on LIBERO, QuantVLA exceeds the task success rates of full-precision baselines, achieves about 70% relative memory savings on the quantized components, and delivers a 1.22x speedup in end-to-end inference latency, providing a practical pathway toward scalable low-bit embodied intelligence under strict compute, memory, and power constraints.
Authors: Lisa L\"uddecke, Michael Hohmann, Sebastian Eilermann, Jan Tillmann-Mumm, Pezhman Pourabdollah, Mario Oertel, Oliver Niggemann
Abstract: Reliable prediction of hydraulic performance is challenging for Piano Key Weir (PKW) design because discharge capacity depends on three-dimensional geometry and operating conditions. Surrogate models can accelerate hydraulic-structure design, but progress is limited by scarce large, well-documented datasets that jointly capture geometric variation, operating conditions, and functional performance. This study presents WeirNet, a large 3D CFD benchmark dataset for geometric surrogate modeling of PKWs. WeirNet contains 3,794 parametric, feasibility-constrained rectangular and trapezoidal PKW geometries, each scheduled at 19 discharge conditions using a consistent free-surface OpenFOAM workflow, resulting in 71,387 completed simulations that form the benchmark and with complete discharge coefficient labels. The dataset is released as multiple modalities compact parametric descriptors, watertight surface meshes and high-resolution point clouds together with standardized tasks and in-distribution and out-of-distribution splits. Representative surrogate families are benchmarked for discharge coefficient prediction. Tree-based regressors on parametric descriptors achieve the best overall accuracy, while point- and mesh-based models remain competitive and offer parameterization-agnostic inference. All surrogates evaluate in milliseconds per sample, providing orders-of-magnitude speedups over CFD runtimes. Out-of-distribution results identify geometry shift as the dominant failure mode compared to unseen discharge values, and data-efficiency experiments show diminishing returns beyond roughly 60% of the training data. By publicly releasing the dataset together with simulation setups and evaluation pipelines, WeirNet establishes a reproducible framework for data-driven hydraulic modeling and enables faster exploration of PKW designs during the early stages of hydraulic planning.
Authors: Himadri Mandal, Vishnu Varadarajan, Jaee Ponde, Aritra Das, Mihir More, Debayan Gupta
Abstract: Bubeck and Sellke (2021) pose as an open problem the connection between the law of robustness and robust generalization. The law of robustness states that overparameterization is necessary for models to interpolate robustly; in particular, robust interpolation requires the learned function to be Lipschitz. Robust generalization asks whether small robust training loss implies small robust test loss. We resolve this problem by explicitly connecting the two for arbitrary data distributions. Specifically, we introduce a nontrivial notion of robust generalization error and convert it into a lower bound on the expected Rademacher complexity of the induced robust loss class. Our bounds recover the $\Omega(n^{1/d})$ regime of Wu et al. (2023) and show that, up to constants, robust generalization does not change the order of the Lipschitz constant required for smooth interpolation. We conduct experiments to probe the predicted scaling with dataset size and model capacity, testing whether empirical behavior aligns more closely with the predictions of Bubeck and Sellke (2021) or Wu et al. (2023). For MNIST, we find that the lower-bound Lipschitz constant scales on the order predicted by Wu et al. (2023). Informally, to obtain low robust generalization error, the Lipschitz constant must lie in a range that we bound, and the allowable perturbation radius is linked to the Lipschitz scale.
Authors: Dengjia Zhang, Xiaoou Liu, Lu Cheng, Yaqing Wang, Kenton Murray, Hua Wei
Abstract: Large language models (LLMs) are increasingly deployed as multi-step decision-making agents, where effective reward design is essential for guiding learning. Although recent work explores various forms of reward shaping and step-level credit assignment, a key signal remains largely overlooked: the intrinsic uncertainty of LLMs. Uncertainty reflects model confidence, reveals where exploration is needed, and offers valuable learning cues even in failed trajectories. We introduce SELAUR: Self Evolving LLM Agent via Uncertainty-aware Rewards, a reinforcement learning framework that incorporates uncertainty directly into the reward design. SELAUR integrates entropy-, least-confidence-, and margin-based metrics into a combined token-level uncertainty estimate, providing dense confidence-aligned supervision, and employs a failure-aware reward reshaping mechanism that injects these uncertainty signals into step- and trajectory-level rewards to improve exploration efficiency and learning stability. Experiments on two benchmarks, ALFWorld and WebShop, show that our method consistently improves success rates over strong baselines. Ablation studies further demonstrate how uncertainty signals enhance exploration and robustness.
Authors: Elena Grigorescu, Brendan Juba, Karl Wimmer, Ning Xie
Abstract: Determinantal Point Processes (DPPs) are a widely used probabilistic model for negatively correlated sets. DPPs have been successfully employed in Machine Learning applications to select a diverse, yet representative subset of data. In these applications, a set of parameters that maximize the likelihood of the data is typically desirable. The algorithms used for this task to date either optimize over a limited family of DPPs, or use local improvement heuristics that do not provide theoretical guarantees of optimality. n seminal work on DPPs in Machine Learning, Kulesza conjectured in his PhD Thesis (2011) that the problem is NP-complete. The lack of a formal proof prompted Brunel et al. (COLT 2017) to suggest that, in opposition to Kulesza's conjecture, there might exist a polynomial-time algorithm for computing a maximum-likelihood DPP. They also presented some preliminary evidence supporting a conjecture that they suggested might lead to such an algorithm. In this work we prove Kulesza's conjecture. In fact, we prove the following stronger hardness of approximation result: even computing a $\left(1-O(\frac{1}{\log^9{N}})\right)$-approximation to the maximum log-likelihood of a DPP on a ground set of $N$ elements is NP-complete. From a technical perspective, we reduce the problem of approximating the maximum log-likelihood of a DPP to solving a gap instance of a $3$-Coloring problem on a hypergraph. This hypergraph is based on the bounded-degree construction of Bogdanov, Obata, and Trevisan (2002), which we enhance using the strong expanders of Alon and Capalbo (2007). We demonstrate that if a rank-$3$ DPP achieves near-optimal log-likelihood, its marginal kernel must encode an almost perfect ``vector-coloring" of the hypergraph. Finally, we show that these continuous vectors can be decoded into a proper $3$-coloring after removing a small fraction of ``noisy" edges.
Authors: Moritz Kirschte, Sebastian Meiser, Saman Ardalan, Esfandiar Mohammadi
Abstract: Distributed differentially private learning techniques enable a large number of users to jointly learn a model without having to first centrally collect the training data. At the same time, neither the communication between the users nor the resulting model shall leak information about the training data. This kind of learning technique can be deployed to edge devices if it can be scaled up to a large number of users, particularly if the communication is reduced to a minimum: no interaction, i.e., each party only sends a single message. The best previously known methods are based on gradient averaging, which inherently requires many synchronization rounds. A promising non-interactive alternative to gradient averaging relies on so-called output perturbation: each user first locally finishes training and then submits its model for secure averaging without further synchronization. We analyze this paradigm, which we coin blind model averaging (BlindAvg), in the setting of convex and smooth empirical risk minimization (ERM) like a support vector machine (SVM). While the required noise scale is asymptotically the same as in the centralized setting, it is not well understood how close BlindAvg comes to centralized learning, i.e., its utility cost. We characterize and boost the privacy-utility tradeoff of BlindAvg with two contributions: First, we prove that BlindAvg converges towards the centralized setting for a sufficiently strong L2-regularization for a non-smooth SVM learner. Second, we introduce the novel differentially private convex and smooth ERM learner SoftmaxReg that has a better privacy-utility tradeoff than an SVM in a multi-class setting. We evaluate our findings on three datasets (CIFAR-10, CIFAR-100, and Federated EMNIST) and provide an ablation in an artificially extreme non-IID scenario.
Authors: Zihao Li
Abstract: With the launch of ChatGPT, Large Language Models (LLMs) are shaking up our whole society, rapidly altering the way we think, create and live. For instance, the GPT integration in Bing has altered our approach to online searching. While nascent LLMs have many advantages, new legal and ethical risks are also emerging, stemming in particular from stochastic parrots and hallucination. The EU is the first and foremost jurisdiction that has focused on the regulation of AI models. However, the risks posed by the new LLMs are likely to be underestimated by the emerging EU regulatory paradigm. Therefore, this correspondence warns that the European AI regulatory paradigm must evolve further to mitigate such risks.
Authors: Daniel Ngo, Keegan Harris, Anish Agarwal, Vasilis Syrgkanis, Zhiwei Steven Wu
Abstract: Synthetic control methods (SCMs) are a canonical approach used to estimate treatment effects from panel data in the internet economy. We shed light on a frequently overlooked but ubiquitous assumption made in SCMs of "overlap": a treated unit can be written as some combination -- typically, convex or linear -- of the units that remain under control. We show that if units select their own interventions, and there is sufficiently large heterogeneity between units that prefer different interventions, overlap will not hold. We address this issue by proposing a recommender system which incentivizes units with different preferences to take interventions they would not normally consider. Specifically, leveraging tools from information design and online learning, we propose an SCM that incentivizes exploration in panel data settings by providing incentive-compatible intervention recommendations to units. We establish this estimator obtains valid counterfactual estimates without the need for an a priori overlap assumption. We extend our results to the setting of synthetic interventions, where the goal is to produce counterfactual outcomes under all interventions, not just control. Finally, we provide two hypothesis tests for determining whether unit overlap holds for a given panel dataset.
Authors: M. Saifullah, K. G. Papakonstantinou, A. Bhattacharya, S. M. Stoffels, C. P. Andriotis
Abstract: Life-cycle management of large-scale transportation systems requires determining a sequence of inspection and maintenance decisions to minimize long-term risks and costs while dealing with multiple uncertainties and constraints that lie in high-dimensional spaces. Traditional approaches have been widely applied but often suffer from limitations related to optimality, scalability, and the ability to properly handle uncertainty. Moreover, many existing methods rely on unconstrained formulations that overlook critical operational constraints. We address these issues in this work by casting the optimization problem within the framework of constrained Partially Observable Markov Decision Processes (POMDPs), which provide a robust mathematical foundation for stochastic sequential decision-making under observation uncertainties, in the presence of risk and resource limitations. To tackle the high dimensionality of state and action spaces, we propose DDMAC-CTDE, a Deep Decentralized Multi-Agent Actor-Critic (DDMAC) reinforcement learning architecture with Centralized Training and Decentralized Execution (CTDE). To demonstrate the utility of the proposed framework, we also develop a new comprehensive benchmark environment representing an existing transportation network in Virginia, U.S., with heterogeneous pavement and bridge assets undergoing nonstationary degradation. This environment incorporates multiple practical constraints related to budget limits, performance guidelines, traffic delays, and risk considerations. On this benchmark, DDMAC-CTDE consistently outperforms standard transportation management baselines, producing better policies. Together, the proposed framework and benchmark provide (i) a scalable, constraint-aware methodology, and (ii) a realistic, rigorous testbed for comprehensive evaluation of Deep Reinforcement Learning (DRL) for transportation infrastructure management.
Authors: E. Atza, N. Budko
Abstract: This work demonstrates that applying a fixed-effect multiple linear regression (MLR) model to an overparameterized dataset is mathematically equivalent to fitting a hyper-curve parameterized by a single scalar. This reformulation shifts the focus from global coefficients to individual predictors, allowing each to be modeled as a function of a common parameter. We prove that this overparameterized linear framework can yield exact predictions even when the underlying data contains nonlinear dependencies that violate classical linear assumptions. By employing parameterization in terms of the dependent variable and a monomial basis, we validate this approach on both synthetic and experimental datasets. Our results show that the hyper-curve perspective provides a robust framework for regularizing problems with noisy predictors and offers a systematic method for identifying and removing 'improper' predictors that degrade model generalizability.
Authors: Jiaqi Yan, Ankush Chakrabarty, Alisa Rupenyan, John Lygeros
Abstract: In this paper, we consider the problem of reference tracking in uncertain nonlinear systems. A neural State-Space Model (NSSM) is used to approximate the nonlinear system, where a deep encoder network learns the nonlinearity from data, and a state-space component captures the temporal relationship. This transforms the nonlinear system into a linear system in a latent space, enabling the application of model predictive control (MPC) to determine effective control actions. Our objective is to design the optimal controller using limited data from the \textit{target system} (the system of interest). To this end, we employ an implicit model-agnostic meta-learning (iMAML) framework that leverages information from \textit{source systems} (systems that share similarities with the target system) to expedite training in the target system and enhance its control performance. The framework consists of two phases: the (offine) meta-training phase learns a aggregated NSSM using data from source systems, and the (online) meta-inference phase quickly adapts this aggregated model to the target system using only a few data points and few online training iterations, based on local loss function gradients. The iMAML algorithm exploits the implicit function theorem to exactly compute the gradient during training, without relying on the entire optimization path. By focusing solely on the optimal solution, rather than the path, we can meta-train with less storage complexity and fewer approximations than other contemporary meta-learning algorithms. We demonstrate through numerical examples that our proposed method can yield accurate predictive models by adaptation, resulting in a downstream MPC that outperforms several baselines.
Authors: Gilad Yehudai, Haim Kaplan, Guy Dar, Royi Rassin, Asma Ghandeharioun, Mor Geva, Amir Globerson
Abstract: Large language models based on the transformer architecture can solve highly complex tasks, yet their fundamental limitations on simple algorithmic problems remain poorly understood. In this work, we focus on basic counting tasks and investigate how the difficulty of these tasks scales with the transformer embedding dimension, the context length, and the vocabulary size. We reveal a sharp theoretical phase transition governed by the relationship between the embedding dimension and the vocabulary size. When the dimension is at least as large as the vocabulary, transformers can perfectly maintain token counts. However, when the vocabulary exceeds the embedding dimension, the interference between non-orthogonal token representations forces the network weights to scale polynomially. This renders the exact counting algorithm numerically unstable and practically unlearnable. We empirically validate this bottleneck by training transformers from scratch, demonstrating a strict performance drop at the theoretical threshold and catastrophic out of distribution failure when scaling the vocabulary or context length. Furthermore, we show that state-of-the-art pretrained models suffer from similar failure cases. Our work reveals a critical blind spot absent from the current literature regarding the connection among these three parameters, proving that vocabulary size fundamentally dictates the difficulty of counting tasks.
Authors: Taewoon Kim, Vincent Fran\c{c}ois-Lavet, Michael Cochez
Abstract: Agents in partially observable environments require persistent memory to integrate observations over time. While KGs (knowledge graphs) provide a natural representation for such evolving state, existing benchmarks rarely expose agents to environments where both the world dynamics and the agent's memory are explicitly graph-shaped. We introduce the Room Environment v3, a configurable environment whose hidden state is an RDF KG and whose observations are RDF triples. The agent may extend these observations into a temporal KG when storing them in long-term memory. The environment is easily adjustable in terms of grid size, number of rooms, inner walls, and moving objects. We define a lightweight temporal KG memory for agents, based on RDF-star-style qualifiers (time_added, last_accessed, num_recalled), and evaluate several symbolic baselines that maintain and query this memory under different capacity constraints. Two neural sequence models (LSTM and Transformer) serve as contrasting baselines without explicit KG structure. Agents train on one layout and are evaluated on a held-out layout with the same dynamics but a different query order, exposing train-test generalization gaps. In this setting, temporal qualifiers lead to more stable performance, and the symbolic TKG (temporal knowledge graph) agent achieves roughly fourfold higher test QA (question-answer) accuracy than the neural baselines under the same environment and query conditions. The environment, agent implementations, and experimental scripts are released for reproducible research at https://github.com/humemai/agent-room-env-v3 and https://github.com/humemai/room-env.
URLs: https://github.com/humemai/agent-room-env-v3, https://github.com/humemai/room-env.
Authors: Clayton Fields, Casey Kennington
Abstract: In the past several years there has been an explosion of available models for vision-language (VL) tasks. Unfortunately, the literature still leaves open a number of questions related to best practices in designing and training such models. Additionally, the limited programming tools available for modeling make conducting VL research more difficult than necessary. In this paper, we seek to answer several questions related to the pretraining of VL encoders through meta-analysis. To conduct these experiments, we introduce a VL evaluation framework called Renaissance. In our first set of experiments, we show that we can save significant compute at little to no cost to downstream performance, by freezing large parts of VL models during pretraining. In our second set of experiments, we examine the effect of basing a VL transformer on a vision model versus a text model. Renaissance offers a great deal of flexibility in creating, training and evaluating transformer encoders for VL modeling. Its source code will be made publicly available upon publication. The source code for Renaissance can be found at https://github.com/bsu-slim/renaissance.
Authors: Pranav Vaidhyanathan, Florian Marquardt, Mark T. Mitchison, Natalia Ares
Abstract: Attention-based neural networks such as transformers have revolutionized various fields such as natural language processing, genomics, and vision. Here, we demonstrate the use of transformers for quantum feedback control through both a supervised and reinforcement learning approach. In particular, due to the transformer's ability to capture long-range temporal correlations and training efficiency, we show that it can surpass some of the limitations of previous control approaches, e.g.~those based on recurrent neural networks trained using a similar approach or policy based reinforcement learning. We numerically show, for the example of state stabilization of a two-level system, that our bespoke transformer architecture can achieve near unit fidelity to a target state in a short time even in the presence of inefficient measurement and Hamiltonian perturbations that were not included in the training set as well as the control of non-Markovian systems. We also demonstrate that our transformer can perform energy minimization of non-integrable many-body quantum systems when trained for reinforcement learning tasks. Our approach can be used for quantum error correction, fast control of quantum states in the presence of colored noise, as well as real-time tuning, and characterization of quantum devices.
Authors: Yu Zhu, Wenqi Jiang, Piyumi Jasin Pathiranage, Yongjun He, Gustavo Alonso
Abstract: The real-time performance of recommender models depends on the continuous integration of massive volumes of new user interaction data into training pipelines. While GPUs have scaled model training throughput, the data preprocessing stage - commonly expressed as Extract-Transform-Load (ETL) pipelines - has emerged as the dominant bottleneck. Production systems often dedicate clusters of CPU servers to support a single GPU node, leading to high operational cost. To address this issue, we present PipeRec, a hardware-accelerated ETL engine co-designed with online recommender model training. PipeRec introduces a training-aware ETL abstraction that exposes freshness, ordering, and batching semantics while compiling software-defined operators into reconfigurable FPGA dataflows and overlaps ETL with GPU training to maximize utilization under I/O constraints. To eliminate CPU bottlenecks, PipeRec implements a format-aware packer that streams training-ready batches directly into GPU memory via P2P DMA transfers, enabling zero-copy ingest and efficient GPU consumption. Our evaluation on three datasets shows that PipeRec accelerates ETL throughput by over 10x compared to CPU-based pipelines and up to 17x over state-of-the-art GPU ETL systems. When integrated with training, PipeRec maintains 64-91% GPU utilization and reduces end-to-end training time to 9.94% of the time taken by CPU-GPU pipelines.
Authors: Georgios Kamaras, Subramanian Ramamoorthy
Abstract: We present an integrated (or end-to-end) framework for the Real2Sim2Real problem of manipulating deformable linear objects (DLOs) based on visual perception. Working with a parameterised set of DLOs, we use likelihood-free inference (LFI) to compute the posterior distributions for the physical parameters using which we can approximately simulate the behaviour of each specific DLO. We use these posteriors for domain randomisation while training, in simulation, object-specific visuomotor policies (i.e. assuming only visual and proprioceptive sensory) for a DLO reaching task, using model-free reinforcement learning. We demonstrate the utility of this approach by deploying sim-trained DLO manipulation policies in the real world in a zero-shot manner, i.e. without any further fine-tuning. In this context, we evaluate the capacity of a prominent LFI method to perform fine classification over the parametric set of DLOs, using only visual and proprioceptive data obtained in a dynamic manipulation trajectory. We then study the implications of the resulting domain distributions in sim-based policy learning and real-world performance.
Authors: Kangyu Zheng, Tianfan Fu, Zhiding Liang
Abstract: The biomedical field is beginning to explore the use of quantum machine learning (QML) for tasks traditionally handled by classical machine learning, especially in predicting ADME (absorption, distribution, metabolism, and excretion) properties, which are essential in drug evaluation. However, ADME tasks pose unique challenges for existing quantum computing systems (QCS) frameworks, as they involve both classification with unbalanced dataset and regression problems. These dual requirements make it necessary to adapt and refine current QCS frameworks to effectively address the complexities of ADME predictions. We propose a novel training-free scoring mechanism to evaluate QML circuit performance on imbalanced classification and regression tasks. Our mechanism demonstrates significant correlation between scoring metrics and test performance on imbalanced classification tasks. Additionally, we develop methods to quantify continuous similarity relationships between quantum states, enabling performance prediction for regression tasks. This represents a novel training-free approach to searching and evaluating QCS circuits specifically for regression applications. Validation on representative ADME tasks-eight imbalanced classification and four regression-demonstrates moderate correlation between our scoring metrics and circuit performance, significantly outperforming baseline scoring methods that show negligible correlation.
Authors: Thomas Kwa, Ben West, Joel Becker, Amy Deng, Katharyn Garcia, Max Hasin, Sami Jawhar, Megan Kinniment, Nate Rush, Sydney Von Arx, Ryan Bloom, Thomas Broadley, Haoxing Du, Brian Goodrich, Nikola Jurkovic, Luke Harold Miles, Seraphina Nix, Tao Lin, Neev Parikh, David Rein, Lucas Jun Koba Sato, Hjalmar Wijk, Daniel M. Ziegler, Elizabeth Barnes, Lawrence Chan
Abstract: Despite rapid progress on AI benchmarks, the real-world meaning of benchmark performance remains unclear. To quantify the capabilities of AI systems in terms of human capabilities, we propose a new metric: 50%-task-completion time horizon. This is the time humans typically take to complete tasks that AI models can complete with 50% success rate. We first timed humans with relevant domain expertise on a combination of RE-Bench, HCAST, and 66 novel shorter tasks. On these tasks, current frontier AI models such as Claude 3.7 Sonnet have a 50% time horizon of around 50 minutes. Furthermore, frontier AI time horizon has been doubling approximately every seven months since 2019, though the trend may have accelerated in 2024. The increase in AI models' time horizons seems to be primarily driven by greater reliability and ability to adapt to mistakes, combined with better logical reasoning and tool use capabilities. We discuss the limitations of our results -- including their degree of external validity -- and the implications of increased autonomy for dangerous capabilities. If these results generalize to real-world software tasks, extrapolation of this trend predicts that within 5 years, AI systems will be capable of automating many software tasks that currently take humans a month.
Authors: Shivasankari Kannan, Yeounoh Chung, Amita Gondi, Tristan Swadell, Fatma Ozcan
Abstract: The demand for high-fidelity test data is paramount in industrial settings where access to production data is largely restricted. Traditional data generation methods often fall short, struggling with low-fidelity and the ability to model complex data structures and semantic relationships that are critical for testing complex SQL code generation services like Natural Language to SQL (NL2SQL). In this paper, we address the critical need for generating syntactically correct and semantically relevant high-fidelity mock data for complex data structures that includes columns with nested structures that we frequently encounter in Google workloads. We highlight the limitations of existing approaches used in production, particularly their inability to handle large and complex data structures, as well as the lack of semantically coherent test data that lead to limited test coverage. We demonstrate that by leveraging Large Language Models (LLMs) and incorporating strategic pre- and post-processing steps, we can generate syntactically correct and semantically relevant high-fidelity test data that adheres to complex structural constraints and maintains semantic integrity to the SQL test targets (queries/functions). This approach supports comprehensive testing of complex SQL queries involving joins, aggregations, and even deeply nested subqueries, ensuring robust evaluation of SQL code generation services, like NL2SQL and SQL Code Assistant. Our results demonstrate the practical utility of an LLM (\textit{Gemini}) based test data generation for industrial SQL code generation services where generating high-fidelity test data is essential due to the frequent unavailability and inaccessibility of production datasets for testing.
Authors: Anton Selitskiy, Maitreya Kocharekar
Abstract: We propose kDOT, a discrete optimal transport (OT) framework for voice conversion (VC) operating in a pretrained speech embedding space. In contrast to the averaging strategies used in kNN-VC and SinkVC, and the independence assumption adopted in MKL, our method employs the barycentric projection of the discrete OT plan to construct a transport map between source and target speaker embedding distributions. We conduct a comprehensive ablation study over the number of transported embeddings and systematically analyze the impact of source and target utterance duration. Experiments on LibriSpeech demonstrate that OT with barycentric projection consistently improves distribution alignment and often outperforms averaging-based approaches in terms of WER, MOS, and FAD. Furthermore, we show that applying discrete OT as a post-processing step can transform spoofed speech into samples that are misclassified as bona fide by a state-of-the-art spoofing detector. This demonstrates the strong domain adaptation capability of OT in embedding space, while also revealing important security implications for spoof detection systems.
Authors: Junxiao Yang, Jinzhe Tu, Haoran Liu, Xiaoce Wang, Chujie Zheng, Zhexin Zhang, Shiyao Cui, Caishun Chen, Tiantian He, Hongning Wang, Yew-Soon Ong, Minlie Huang
Abstract: Recent advances in Large Reasoning Models (LRMs) have shown impressive capabilities in mathematical and logical reasoning. However, current LRMs rarely admit ignorance or respond with "I don't know". Instead, they often produce incorrect answers while showing undue confidence, raising concerns about their factual reliability. In this work, we identify two pathological reasoning patterns characterized by overthinking that contribute to the overconfident and incorrect answers: last-minute guessing and second-thought spiraling. To address these issues, we propose BARREL-a novel framework that promotes concise and boundary-aware factual reasoning. Our experiments show that BARREL-training increases the reliability of DeepSeek-R1-Distill-Llama-8B from 39.33% to 61.48%, while still achieving accuracy comparable to models finetuned on reasoning data generated by R1. These results demonstrate that our pilot study is inspiring to build more reliable and factual System 2 LRMs.
Authors: Guodong Du, Zhuo Li, Xuanning Zhou, Junlin Li, Zesheng Shi, Wanyu Lin, Ho-Kin Tang, Xiucheng Li, Fangming Liu, Wenya Wang, Min Zhang, Jing Li
Abstract: Cross-capability transfer is a key challenge in large language model (LLM) research, with applications in multi-task integration, model compression, and continual learning. Recent works like FuseLLM and FuseChat have demonstrated the potential of transferring multiple model capabilities to lightweight models, enhancing adaptability and efficiency, which motivates our investigation into more efficient cross-capability transfer methods. However, existing approaches primarily focus on small, homogeneous models, limiting their applicability. For large, heterogeneous models, knowledge distillation with full-parameter fine-tuning often overlooks the student model's intrinsic capacity and risks catastrophic forgetting, while PEFT methods struggle to effectively absorb knowledge from source LLMs. To address these issues, we introduce GraftLLM, a novel method that stores source model capabilities in a target model with SkillPack format. This approach preserves general capabilities, reduces parameter conflicts, and supports forget-free continual learning and model fusion. We employ a module-aware adaptive compression strategy to compress parameter updates, ensuring efficient storage while maintaining task-specific knowledge. The resulting SkillPack serves as a compact and transferable knowledge carrier, ideal for heterogeneous model fusion and continual learning. Experiments across various scenarios demonstrate that GraftLLM outperforms existing techniques in knowledge transfer, knowledge fusion, and forget-free learning, providing a scalable and efficient solution for cross-capability transfer. The code is publicly available at: https://github.com/duguodong7/GraftLLM.
Authors: H. L. Dao
Abstract: In this work, we introduce the first type of non-Euclidean neural quantum state (NQS) ansatz, in the form of the hyperbolic GRU (a variant of recurrent neural networks (RNNs)), to be used in the Variational Monte Carlo method of approximating the ground state energy for quantum many-body systems. In particular, we examine the performances of NQS ansatzes constructed from both conventional or Euclidean RNN/GRU and from hyperbolic GRU in the prototypical settings of the one- and two-dimensional transverse field Ising models (TFIM) and the one-dimensional Heisenberg $J_1J_2$ and $J_1J_2J_3$ systems. By virtue of the fact that, for all of the experiments performed in this work, hyperbolic GRU can yield performances comparable to or better than Euclidean RNNs, which have been extensively studied in these settings in the literature, our work is a proof-of-concept for the viability of hyperbolic GRU as the first type of non-Euclidean NQS ansatz for quantum many-body systems. Furthermore, in settings where the Hamiltonian displays a clear hierarchical interaction structure, such as the 1D Heisenberg $J_1J_2$ & $J_1J_2J_3$ systems with the 1st, 2nd and even 3rd nearest neighbor interactions, our results show that hyperbolic GRU definitively outperforms its Euclidean version in almost all instances. The fact that these results are reminiscent of the established ones from natural language processing where hyperbolic GRU almost always outperforms Euclidean RNNs when the training data exhibit a tree-like or hierarchical structure leads us to hypothesize that hyperbolic GRU NQS ansatz would likely outperform Euclidean RNN/GRU NQS ansatz in quantum spin systems that involve different degrees of nearest neighbor interactions. Finally, with this work, we hope to initiate future studies of other types of non-Euclidean NQS beyond hyperbolic GRU.
Authors: Ba-Hien Tran, Van Minh Nguyen
Abstract: Weight binarization has emerged as a promising strategy to reduce the complexity of large language models (LLMs). Existing approaches fall into post-training binarization, which is simple but causes severe performance loss, and training-aware methods, which depend on full-precision latent weights, adding complexity and limiting efficiency. We propose a novel framework that represents LLMs with multi-kernel Boolean parameters and, for the first time, enables direct finetuning LMMs in the Boolean domain, eliminating the need for latent weights. This enhances representational capacity and dramatically reduces complexity during both finetuning and inference. Extensive experiments across diverse LLMs show our method outperforms recent ultra low-bit quantization and binarization techniques.
Authors: Rulin Shao, Shuyue Stella Li, Rui Xin, Scott Geng, Yiping Wang, Sewoong Oh, Simon Shaolei Du, Nathan Lambert, Sewon Min, Ranjay Krishna, Yulia Tsvetkov, Hannaneh Hajishirzi, Pang Wei Koh, Luke Zettlemoyer
Abstract: We show that reinforcement learning with verifiable rewards (RLVR) can elicit strong mathematical reasoning in certain language models even with spurious rewards that have little, no, or even negative correlation with the correct answer. For example, RLVR training with GRPO improves MATH-500 performance for Qwen2.5-Math-7B by 21.4 percentage points using randomly assigned rewards, nearly matching the 29.1-point gain from ground-truth rewards. To explain this counterintuitive observation, we show that GRPO exhibits a clipping bias from the clip term, which can amplify high-prior behaviors learned during pretraining even without informative rewards. As a case study, we identify one such behavior in Qwen2.5-Math models, which we call code reasoning -- reasoning in code without actual code execution; code-reasoning frequency increases from 65 percent to over 90 percent with spurious rewards. However, the presence of such amplifiable behaviors is highly model-dependent. In practice, spurious rewards that are effective for Qwen models often fail to produce gains for other model families, such as Llama3 or OLMo2. Our results highlight the importance of validating RL methods across diverse models rather than relying on a single de facto choice: large gains can arise on Qwen models even from random rewards that do not reflect genuine capability improvements.
Authors: Aloni Cohen
Abstract: Are there any conditions under which a generative model's outputs are guaranteed not to infringe the copyrights of its training data? This is the question of "provable copyright protection" first posed by Vyas, Kakade, and Barak (ICML 2023). They define near access-freeness (NAF) and propose it as sufficient for protection. This paper revisits the question and establishes new foundations for provable copyright protection -- foundations that are firmer both technically and legally. First, we show that NAF alone does not prevent infringement. In fact, NAF models can enable verbatim copying, a blatant failure of copyright protection that we dub being tainted. Then, we introduce our blameless copyright protection framework for defining meaningful guarantees, and instantiate it with clean-room copyright protection. Clean-room copyright protection allows a user to control their risk of copying by behaving in a way that is unlikely to copy in a counterfactual "clean-room setting." Finally, we formalize a common intuition about differential privacy and copyright by proving that DP implies clean-room copyright protection when the dataset is golden, a copyright deduplication requirement.
Authors: Zhijiang Tang, Jiaxin Qi, Yuhua Zheng, Jianqiang Huang
Abstract: Electrocardiogram~(ECG), a key bioelectrical time-series signal, is crucial for assessing cardiac health and diagnosing various diseases. Given its time-series format, ECG data is often incorporated into pre-training datasets for large-scale time-series model training. However, existing studies often overlook its unique characteristics and specialized downstream applications, which differ significantly from other time-series data, leading to an incomplete understanding of its properties. In this paper, we present an in-depth investigation of ECG signals and establish a comprehensive benchmark, which includes (1) categorizing its downstream applications into four distinct evaluation tasks, (2) identifying limitations in traditional evaluation metrics for ECG analysis, and introducing a novel metric; (3) benchmarking state-of-the-art time-series models and proposing a new architecture. Extensive experiments demonstrate that our proposed benchmark is comprehensive and robust. The results validate the effectiveness of the proposed metric and model architecture, which establish a solid foundation for advancing research in ECG signal analysis.
Authors: Shan Jiang, Pranoy Kovuri, David Tao, Zhixun Tan
Abstract: Software obfuscation, particularly prevalent in JavaScript, hinders code comprehension and analysis, posing significant challenges to software testing, static analysis, and malware detection. This paper introduces CASCADE, a novel hybrid approach that integrates the advanced coding capabilities of Gemini with the deterministic transformation capabilities of a compiler Intermediate Representation (IR), specifically JavaScript IR (JSIR). By employing Gemini to identify critical prelude functions, the foundational components underlying the most prevalent obfuscation techniques, and leveraging JSIR for subsequent code transformations, CASCADE effectively recovers semantic elements like original strings and API names, and reveals original program behaviors. This method overcomes limitations of existing static and dynamic deobfuscation techniques, eliminating hundreds to thousands of hardcoded rules while achieving reliability and flexibility. CASCADE is already deployed in Google's production environment, demonstrating substantial improvements in JavaScript deobfuscation efficiency and reducing reverse engineering efforts.
Authors: Zeyu Tang, Alex John London, Atoosa Kasirzadeh, Sarah Stewart de Ramirez, Peter Spirtes, Kun Zhang, Sanmi Koyejo
Abstract: Algorithmic fairness research has largely framed unfairness as discrimination along sensitive attributes. However, this approach limits visibility into unfairness as structural injustice instantiated through social determinants, which are contextual variables that shape attributes and outcomes without pertaining to specific individuals. This position paper argues that the field should quantify structural injustice via social determinants, beyond sensitive attributes. Drawing on cross-disciplinary insights, we argue that prevailing technical paradigms fail to adequately capture unfairness as structural injustice, because contexts are potentially treated as noise to be normalized rather than signal to be audited. We further demonstrate the practical urgency of this shift through a theoretical model of college admissions, a demographic study using U.S. census data, and a high-stakes domain application regarding breast cancer screening within an integrated U.S. healthcare system. Our results indicate that mitigation strategies centered solely on sensitive attributes can introduce new forms of structural injustice. We contend that auditing structural injustice through social determinants must precede mitigation, and call for new technical developments that move beyond sensitive-attribute-centered notions of fairness as non-discrimination.
Authors: Seyedali Mohammadi, Bhaskara Hanuma Vedula, Hemank Lamba, Edward Raff, Ponnurangam Kumaraguru, Francis Ferraro, Manas Gaur
Abstract: Do LLMs genuinely incorporate external definitions, or do they primarily rely on their parametric knowledge? To address these questions, we conduct controlled experiments across multiple explanation benchmark datasets (general and domain-specific) and label definition conditions, including expert-curated, LLM-generated, perturbed, and swapped definitions. Our results reveal that while explicit label definitions can enhance accuracy and explainability, their integration into an LLM's task-solving processes is neither guaranteed nor consistent, suggesting reliance on internalized representations in many cases. Models often default to their internal representations, particularly in general tasks, whereas domain-specific tasks benefit more from explicit definitions. These findings underscore the need for a deeper understanding of how LLMs process external knowledge alongside their pre-existing capabilities.
Authors: Patrick Wienholt, Christiane Kuhl, Jakob Nikolas Kather, Sven Nebelung, Daniel Truhn
Abstract: Deep neural networks excel in radiological image classification but frequently suffer from poor interpretability, limiting clinical acceptance. We present MedicalPatchNet, an inherently self-explainable architecture for chest X-ray classification that transparently attributes decisions to distinct image regions. MedicalPatchNet splits images into non-overlapping patches, independently classifies each patch, and aggregates predictions, enabling intuitive visualization of each patch's diagnostic contribution without post-hoc techniques. Trained on the CheXpert dataset (223,414 images), MedicalPatchNet matches the classification performance (AUROC 0.907 vs. 0.908) of EfficientNetV2-S, while improving interpretability: MedicalPatchNet demonstrates improved interpretability with higher pathology localization accuracy (mean hit-rate 0.485 vs. 0.376 with Grad-CAM) on the CheXlocalize dataset. By providing explicit, reliable explanations accessible even to non-AI experts, MedicalPatchNet mitigates risks associated with shortcut learning, thus improving clinical trust. Our model is publicly available with reproducible training and inference scripts and contributes to safer, explainable AI-assisted diagnostics across medical imaging domains. We make the code publicly available: https://github.com/TruhnLab/MedicalPatchNet
Authors: Rodrigo M. Carrillo-Larco, Jesus Lov\'on Melgarejo, Manuel Castillo-Cara, Gusseppe Bravo-Rocca
Abstract: BACKGROUND: Medical large language models (LLMs) have demonstrated remarkable performance in answering medical examinations. However, the extent to which this high performance is transferable to medical questions in Spanish and from a Latin American country remains unexplored. This knowledge is crucial as LLM-based medical applications gain traction in Latin America. AIMS: To build a dataset of questions medical examinations taken by Peruvian physicians pursuing specialty training; to fine-tune a LLM on this dataset; to evaluate and compare the performance in terms of accuracy between vanilla LLMs and the fine-tuned LLM. METHODS: We curated PeruMedQA, a multiple-choice question-answering (MCQA) dataset containing 8,380 questions spanning 12 specialties (2018-2025). We selected ten medical LLMs, including medgemma-4b-it and medgemma-27b-text-it, and developed zero-shot task specific prompts to answer the questions. We employed parameter-efficient fine tuning (PEFT) and low-rand adaptation (LoRA) to fine-tune medgemma-4b-it utilizing all questions except those from 2025 (test set). RESULTS: Medgemma-27b showed the highest accuracy across all specialities, achieving the highest score of 89.29% in Psychiatry; yet, in two specialties, OctoMed-7B exhibited slight superiority: Neurosurgery with 77.27% and 77.38, respectively; and Radiology with 76.13% and 77.39%, respectively. Across specialties, most LLMs with <10 billion parameters exhibited <50% of correct answers. The fine-tuned version of medgemma-4b-it emerged victorious against all LLMs with <10 billion parameters and rivaled a LLM with 70 billion parameters across various examinations. CONCLUSIONS: For medical AI applications and research that require knowledge bases from Spanish-speaking countries and those exhibiting similar epidemiological profile to Peru's, interested parties should utilize medgemma-27b-text-it.
Authors: Lauri Suomela, Sasanka Kuruppu Arachchige, German F. Torres, Harry Edelman, Joni-Kristian K\"am\"ar\"ainen
Abstract: This paper investigates how the performance of visual navigation policies trained in simulation compares to policies trained with real-world data. Performance degradation of simulator-trained policies is often significant when they are evaluated in the real world. However, despite this well-known sim-to-real gap, we demonstrate that simulator-trained policies can match the performance of their real-world-trained counterparts. Central to our approach is a navigation policy architecture that bridges the sim-to-real appearance gap by leveraging pretrained visual representations and runs real-time on robot hardware. Evaluations on a wheeled mobile robot show that the proposed policy, when trained in simulation, outperforms its real-world-trained version by 31 and the prior state-of-the-art methods by 50 points in navigation success rate. Policy generalization is verified by deploying the same model onboard a drone. Our results highlight the importance of diverse image encoder pretraining for sim-to-real generalization, and identify on-policy learning as a key advantage of simulated training over training with real data. Code, model checkpoints and multimedia materials are available at https://lasuomela.github.io/faint/
Authors: Kartik Hegde, Rehana Mahfuz, Yinyi Guo, Erik Visser
Abstract: Current audio captioning relies on supervised learning with paired audio-caption data, which is costly to curate and may not reflect human preferences in real-world scenarios. To address this, we propose a preference-aligned audio captioning framework based on Reinforcement Learning from Human Feedback (RLHF). To capture nuanced preferences, we train a Contrastive Language-Audio Pretraining (CLAP) based reward model using human-labeled pairwise preference data. This reward model is integrated into an RL framework to fine-tune any baseline captioning system without ground-truth annotations. Extensive human evaluations across multiple datasets show that our method produces captions preferred over baseline models, particularly when baselines fail to provide correct and natural captions. Furthermore, our framework achieves performance comparable to supervised approaches with ground-truth data, demonstrating effective alignment with human preferences and scalability in real-world use.
Authors: Advik Raj Basani, Pin-Yu Chen
Abstract: Detecting AI-generated text is an increasing necessity to combat misuse of LLMs in education, business compliance, journalism, and social media, where synthetic fluency can mask misinformation or deception. While prior detectors often rely on token-level likelihoods or opaque black-box classifiers, these approaches struggle against high-quality generations and offer little interpretability. In this work, we propose DivEye, a novel detection framework that captures how unpredictability fluctuates across a text using surprisal-based features. Motivated by the observation that human-authored text exhibits richer variability in lexical and structural unpredictability than LLM outputs, DivEye captures this signal through a set of interpretable statistical features. Our method outperforms existing zero-shot detectors by up to 33.2% and achieves competitive performance with fine-tuned baselines across multiple benchmarks. DivEye is robust to paraphrasing and adversarial attacks, generalizes well across domains and models, and improves the performance of existing detectors by up to 18.7% when used as an auxiliary signal. Beyond detection, DivEye provides interpretable insights into why a text is flagged, pointing to rhythmic unpredictability as a powerful and underexplored signal for LLM detection.
Authors: Shai Zucker, Xiong Wang, Fei Lu, Inbar Seroussi
Abstract: We study the convergence rate of learning pairwise interactions in single-layer attention-style models, where tokens interact through a weight matrix and a nonlinear activation function. We prove that the minimax rate is $M^{-\frac{2\beta}{2\beta+1}}$, where $M$ is the sample size and $\beta$ is the H\"older smoothness of the activation function. Importantly, this rate is independent of the embedding dimension $d$, the number of tokens $N$, and the rank $r$ of the weight matrix, provided that $rd \le (M/\log M)^{\frac{1}{2\beta+1}}$. These results highlight a fundamental statistical efficiency of attention-style models, even when the weight matrix and activation are not separately identifiable, and provide a theoretical understanding of attention mechanisms and guidance on training.
Authors: Chengshu Li, Mengdi Xu, Arpit Bahety, Hang Yin, Yunfan Jiang, Huang Huang, Josiah Wong, Sujay Garlanka, Cem Gokmen, Ruohan Zhang, Weiyu Liu, Jiajun Wu, Roberto Mart\'in-Mart\'in, Li Fei-Fei
Abstract: Imitation learning from large-scale, diverse human demonstrations has been shown to be effective for training robots, but collecting such data is costly and time-consuming. This challenge intensifies for multi-step bimanual mobile manipulation, where humans must teleoperate both the mobile base and two high-DoF arms. Prior X-Gen works have developed automated data generation frameworks for static (bimanual) manipulation tasks, augmenting a few human demos in simulation with novel scene configurations to synthesize large-scale datasets. However, prior works fall short for bimanual mobile manipulation tasks for two major reasons: 1) a mobile base introduces the problem of how to place the robot base to enable downstream manipulation (reachability) and 2) an active camera introduces the problem of how to position the camera to generate data for a visuomotor policy (visibility). To address these challenges, MoMaGen formulates data generation as a constrained optimization problem that satisfies hard constraints (e.g., reachability) while balancing soft constraints (e.g., visibility while navigation). This formulation generalizes across most existing automated data generation approaches and offers a principled foundation for developing future methods. We evaluate on four multi-step bimanual mobile manipulation tasks and find that MoMaGen enables the generation of much more diverse datasets than previous methods. As a result of the dataset diversity, we also show that the data generated by MoMaGen can be used to train successful imitation learning policies using a single source demo. Furthermore, the trained policy can be fine-tuned with a very small amount of real-world data (40 demos) to be succesfully deployed on real robotic hardware. More details are on our project page: momagen.github.io.
Authors: Raheem Karim Hashmani, Garrett W. Merz, Helen Qu, Mariel Pettee, Kyle Cranmer
Abstract: We introduce a framework for generating highly multimodal datasets with explicitly calculable mutual information (MI) between modalities. This enables the construction of benchmark datasets that provide a novel testbed for systematic studies of mutual information estimators and multimodal self-supervised learning (SSL) techniques. Our framework constructs realistic datasets with known MI using a flow-based generative model and a structured causal framework for generating correlated latent variables. We benchmark a suite of MI estimators on datasets with varying ground truth MI values and verify that regression performance improves as the MI increases between input modalities and the target value. Finally, we describe how our framework can be applied to contexts including multi-detector astrophysics and SSL studies in the highly multimodal regime.
Authors: Shayne Longpre, Sneha Kudugunta, Niklas Muennighoff, I-Hung Hsu, Isaac Caswell, Alex Pentland, Sercan Arik, Chen-Yu Lee, Sayna Ebrahimi
Abstract: Scaling laws research has focused overwhelmingly on English -- yet the most prominent AI models explicitly serve billions of international users. In this work, we undertake the largest multilingual scaling laws study to date, totaling 774 multilingual training experiments, spanning 10M-8B model parameters, 400+ training languages and 48 evaluation languages. We introduce the Adaptive Transfer Scaling Law (ATLAS) for both monolingual and multilingual pretraining, which outperforms existing scaling laws' out-of-sample generalization often by more than 0.3 R^2. Our analyses of the experiments shed light on multilingual learning dynamics, transfer properties between languages, and the curse of multilinguality. First, we derive a cross-lingual transfer matrix, empirically measuring mutual benefit scores between 38 x 38=1444 language pairs. Second, we derive a language-agnostic scaling law that reveals how to optimally scale model size and data when adding languages without sacrificing performance. Third, we identify the computational crossover points for when to pretrain from scratch versus finetune from multilingual checkpoints. We hope these findings provide the scientific foundation for democratizing scaling laws across languages, and enable practitioners to efficiently scale models -- beyond English-first AI.
Authors: Zhimin Chen, Chenyu Zhao, Ka Chun Mo, Yunjiang Jiang, Jane H. Lee, Khushhall Chandra Mahajan, Ning Jiang, Kai Ren, Jinhui Li, Wen-Yun Yang
Abstract: Modern large-scale recommendation systems rely heavily on user interaction history sequences to enhance the model performance. The advent of large language models and sequential modeling techniques, particularly transformer-like architectures, has led to significant advancements recently (e.g., HSTU, SIM, and TWIN models). While scaling to ultra-long user histories (10k to 100k items) generally improves model performance, it also creates significant challenges on latency, queries per second (QPS) and GPU cost in industry-scale recommendation systems. Existing models do not adequately address these industrial scalability issues. In this paper, we propose a novel two-stage modeling framework, namely VIrtual Sequential Target Attention (VISTA), which decomposes traditional target attention from a candidate item to user history items into two distinct stages: (1) user history summarization into a few hundred tokens; followed by (2) candidate item attention to those tokens. These summarization token embeddings are then cached in storage system and then utilized as sequence features for downstream model training and inference. This novel design for scalability enables VISTA to scale to lifelong user histories (up to one million items) while keeping downstream training and inference costs fixed, which is essential in industry. Our approach achieves significant improvements in offline and online metrics and has been successfully deployed on an industry leading recommendation platform serving billions of users.
Authors: Georgios Kamaras, Craig Innes, Subramanian Ramamoorthy
Abstract: In robotics, likelihood-free inference (LFI) can provide the domain distribution that adapts a learnt agent in a parametric set of deployment conditions. LFI assumes an arbitrary support for sampling, which remains constant as the initial generic prior is iteratively refined to more descriptive posteriors. However, a potentially misspecified support can lead to suboptimal, yet falsely certain, posteriors. To address this issue, we propose three heuristic LFI variants: EDGE, MODE, and CENTRE. Each interprets the posterior mode shift over inference steps in its own way and, when integrated into an LFI step, adapts the support alongside posterior inference. We first expose the support misspecification issue and evaluate our heuristics using stochastic dynamical benchmarks. We then evaluate the impact of heuristic support adaptation on parameter inference and policy learning for a dynamic deformable linear object (DLO) manipulation task. Inference results in a finer length and stiffness classification for a parametric set of DLOs. When the resulting posteriors are used as domain distributions for sim-based policy learning, they lead to more robust object-centric agent performance.
Authors: NVIDIA, :, Arslan Ali, Junjie Bai, Maciej Bala, Yogesh Balaji, Aaron Blakeman, Tiffany Cai, Jiaxin Cao, Tianshi Cao, Elizabeth Cha, Yu-Wei Chao, Prithvijit Chattopadhyay, Mike Chen, Yongxin Chen, Yu Chen, Shuai Cheng, Yin Cui, Jenna Diamond, Yifan Ding, Jiaojiao Fan, Linxi Fan, Liang Feng, Francesco Ferroni, Sanja Fidler, Xiao Fu, Ruiyuan Gao, Yunhao Ge, Jinwei Gu, Aryaman Gupta, Siddharth Gururani, Imad El Hanafi, Ali Hassani, Zekun Hao, Jacob Huffman, Joel Jang, Pooya Jannaty, Jan Kautz, Grace Lam, Xuan Li, Zhaoshuo Li, Maosheng Liao, Chen-Hsuan Lin, Tsung-Yi Lin, Yen-Chen Lin, Huan Ling, Ming-Yu Liu, Xian Liu, Yifan Lu, Alice Luo, Qianli Ma, Hanzi Mao, Kaichun Mo, Seungjun Nah, Yashraj Narang, Abhijeet Panaskar, Lindsey Pavao, Trung Pham, Morteza Ramezanali, Fitsum Reda, Scott Reed, Xuanchi Ren, Haonan Shao, Yue Shen, Stella Shi, Shuran Song, Bartosz Stefaniak, Shangkun Sun, Shitao Tang, Sameena Tasmeen, Lyne Tchapmi, Wei-Cheng Tseng, Jibin Varghese, Andrew Z. Wang, Hao Wang, Haoxiang Wang, Heng Wang, Ting-Chun Wang, Fangyin Wei, Jiashu Xu, Dinghao Yang, Xiaodong Yang, Haotian Ye, Seonghyeon Ye, Xiaohui Zeng, Jing Zhang, Qinsheng Zhang, Kaiwen Zheng, Andrew Zhu, Yuke Zhu
Abstract: We introduce [Cosmos-Predict2.5], the latest generation of the Cosmos World Foundation Models for Physical AI. Built on a flow-based architecture, [Cosmos-Predict2.5] unifies Text2World, Image2World, and Video2World generation in a single model and leverages [Cosmos-Reason1], a Physical AI vision-language model, to provide richer text grounding and finer control of world simulation. Trained on 200M curated video clips and refined with reinforcement learning-based post-training, [Cosmos-Predict2.5] achieves substantial improvements over [Cosmos-Predict1] in video quality and instruction alignment, with models released at 2B and 14B scales. These capabilities enable more reliable synthetic data generation, policy evaluation, and closed-loop simulation for robotics and autonomous systems. We further extend the family with [Cosmos-Transfer2.5], a control-net style framework for Sim2Real and Real2Real world translation. Despite being 3.5$\times$ smaller than [Cosmos-Transfer1], it delivers higher fidelity and robust long-horizon video generation. Together, these advances establish [Cosmos-Predict2.5] and [Cosmos-Transfer2.5] as versatile tools for scaling embodied intelligence. To accelerate research and deployment in Physical AI, we release source code, pretrained checkpoints, and curated benchmarks under the NVIDIA Open Model License at https://github.com/nvidia-cosmos/cosmos-predict2.5 and https://github.com/nvidia-cosmos/cosmos-transfer2.5. We hope these open resources lower the barrier to adoption and foster innovation in building the next generation of embodied intelligence.
URLs: https://github.com/nvidia-cosmos/cosmos-predict2.5, https://github.com/nvidia-cosmos/cosmos-transfer2.5.
Authors: Soufiane Hayou
Abstract: We provide the first proof of learning rate transfer with width in a linear multi-layer perceptron (MLP) parametrized with $\mu$P, a neural network parameterization designed to ``maximize'' feature learning in the infinite-width limit. We show that under $\mu P$, the optimal learning rate converges to a \emph{non-zero constant} as width goes to infinity, providing a theoretical explanation to learning rate transfer. In contrast, we show that this property fails to hold under alternative parametrizations such as Standard Parametrization (SP) and Neural Tangent Parametrization (NTP). We provide intuitive proofs and support the theoretical findings with extensive empirical results.
Authors: Vincenzo Lipardi, Domenica Dibenedetto, Georgios Stamoulis, Evert van Nieuwenburg, Mark H. M. Winands
Abstract: This article proposes a Graph Neural Network (GNN) approach to estimate nonstabilizerness in quantum circuits, measured by the stabilizer R\'enyi entropy (SRE). Nonstabilizerness is a fundamental resource for quantum advantage, and efficient SRE estimations are highly beneficial in practical applications. We address the nonstabilizerness estimation problem through three supervised learning formulations starting from easier classification tasks to the more challenging regression task. Experimental results show that the proposed GNN manages to capture meaningful features from the graph-based circuit representation, resulting in robust generalization performances achieved across diverse scenarios. In classification tasks, the GNN is trained on product states and generalizes on circuits evolved under Clifford operations, entangled states, and circuits with higher number of qubits. In the regression task, the GNN significantly improves the SRE estimation on out-of-distribution circuits with higher number of qubits and gate counts compared to previous work, for both unstructured random quantum circuits and structured circuits derived from the transverse-field Ising model. Moreover, the graph representation of quantum circuits naturally integrates hardware-specific information. Simulations on noisy quantum hardware highlight the potential of the proposed GNN to predict the SRE measured on quantum devices.
Authors: Erfan Nourbakhsh, Nasrin Sanjari, Ali Nourbakhsh
Abstract: Age-related macular degeneration (AMD) and choroidal neovascularization (CNV)-related conditions are leading causes of vision loss worldwide, with optical coherence tomography (OCT) serving as a cornerstone for early detection and management. However, deploying state-of-the-art deep learning models like ConvNeXtV2-Large in clinical settings is hindered by their computational demands. Therefore, it is desirable to develop efficient models that maintain high diagnostic performance while enabling real-time deployment. In this study, a novel knowledge distillation framework, termed KD-OCT, is proposed to compress a high-performance ConvNeXtV2-Large teacher model, enhanced with advanced augmentations, stochastic weight averaging, and focal loss, into a lightweight EfficientNet-B2 student for classifying normal, drusen, and CNV cases. KD-OCT employs real-time distillation with a combined loss balancing soft teacher knowledge transfer and hard ground-truth supervision. The effectiveness of the proposed method is evaluated on the Noor Eye Hospital (NEH) dataset using patient-level cross-validation. Experimental results demonstrate that KD-OCT outperforms comparable multi-scale or feature-fusion OCT classifiers in efficiency-accuracy balance, achieving near-teacher performance with substantial reductions in model size and inference time. Despite the compression, the student model exceeds most existing frameworks, facilitating edge deployment for AMD screening. Code is available at https://github.com/erfan-nourbakhsh/KD-OCT.
Authors: Eric Todd, Jannik Brinkmann, Rohit Gandikota, David Bau
Abstract: We investigate the mechanisms that arise when transformers are trained to solve arithmetic on sequences where tokens are variables whose meaning is determined only through their interactions in-context. While prior work has studied transformers in settings where the answer relies on fixed parametric or geometric information encoded in token embeddings, we devise a new in-context reasoning task where the assignment of tokens to specific algebraic elements varies from one sequence to another. Despite this challenging setup, transformers achieve near-perfect accuracy on the task and even generalize to unseen groups. We develop targeted data distributions to create causal tests of a set of hypothesized mechanisms, and we isolate three mechanisms models consistently learn: commutative copying where a dedicated head copies answers, identity element recognition that distinguishes identity-containing facts, and closure-based cancellation that tracks group membership to constrain valid answers. Our findings show that the kinds of reasoning strategies learned by transformers are dependent on the task structure and that models can develop symbolic reasoning mechanisms when trained to reason in-context about variables whose meanings are not fixed.
Authors: Chenguang Liu, Antonis Papapantoleon, Jasper Rou
Abstract: The aim of this article is to provide a firm mathematical foundation for the application of deep gradient flow methods (DGFMs) for the solution of (high-dimensional) partial differential equations (PDEs). We decompose the generalization error of DGFMs into an approximation and a training error. We first show that the solution of PDEs that satisfy reasonable and verifiable assumptions can be approximated by neural networks, thus the approximation error tends to zero as the number of neurons tends to infinity. Then, we derive the gradient flow that the training process follows in the ``wide network limit'' and analyze the limit of this flow as the training time tends to infinity. These results combined show that the generalization error of DGFMs tends to zero as the number of neurons and the training time tend to infinity.
Authors: Aqsa Sultana, Rayan Afsar, Ahmed Rahu, Surendra P. Singh, Brian Shula, Brandon Combs, Derrick Forchetti, Vijayan K. Asari
Abstract: Accurate risk stratification of precancerous polyps during routine colonoscopy screenings is essential for lowering the risk of developing colorectal cancer (CRC). However, assessment of low-grade dysplasia remains limited by subjective histopathologic interpretation. Advancements in digital pathology and deep learning provide new opportunities to identify subtle and fine morphologic patterns associated with malignant progression that may be imperceptible to the human eye. In this work, we propose XtraLight-MedMamba, an ultra-lightweight state-space-based deep learning framework for classifying neoplastic tubular adenomas from whole-slide images (WSIs). The architecture is a blend of ConvNext based shallow feature extractor with parallel vision mamba to efficiently model both long- and short-range dependencies and image generalization. An integration of Spatial and Channel Attention Bridge (SCAB) module enhances multiscale feature extraction, while Fixed Non-Negative Orthogonal Classifier (FNOClassifier) enables substantial parameter reduction and improved generalization. The model was evaluated on a curated dataset acquired from patients with low-grade tubular adenomas, stratified into case and control cohorts based on subsequent CRC development. XtraLight-MedMamba achieved an accuracy of 97.18% and an F1-score of 0.9767 using approximately 32,000 parameters, outperforming transformer-based and conventional Mamba architectures with significantly higher model complexity.
Authors: Unai Fischer-Abaigar, Emily Aiken, Christoph Kern, Juan Carlos Perdomo
Abstract: Institutions increasingly use prediction to allocate scarce resources. From a design perspective, better predictions compete with other investments, such as expanding capacity or improving treatment quality. Here, the big question is not how to solve a specific allocation problem, but rather which problem to solve. In this work, we develop an empirical toolkit to help planners form principled answers to this question and quantify the bottom-line welfare impact of investments in prediction versus other policy levers such as expanding capacity and improving treatment quality. Applying our framework in two real-world case studies on German employment services and poverty targeting in Ethiopia, we illustrate how decision-makers can reliably derive context-specific conclusions about the relative value of prediction in their allocation problem. We make our software toolkit, rvp, and parts of our data available in order to enable future empirical work in this area.
Authors: Jie Lu, Peihao Yan, Huacheng Zeng
Abstract: With over 3.5 million 5G base stations deployed globally, their collective energy consumption (projected to exceed 131 TWh annually) raises significant concerns over both operational costs and environmental impacts. In this paper, we present EExAPP, a deep reinforcement learning (DRL)-based xApp for 5G Open Radio Access Network (O-RAN) that jointly optimizes radio unit (RU) sleep scheduling and distributed unit (DU) resource slicing. EExAPP uses a dual-actor-dual-critic Proximal Policy Optimization (PPO) architecture, with dedicated actor-critic pairs targeting energy efficiency and quality-of-service (QoS) compliance. A transformer-based encoder enables scalable handling of variable user equipment (UE) populations by encoding all-UE observations into fixed-dimensional representations. To coordinate the two optimization objectives, a bipartite Graph Attention Network (GAT) is used to modulate actor updates based on both critic outputs, enabling adaptive trade-offs between power savings and QoS. We have implemented EExAPP and deployed it on a real-world 5G O-RAN testbed with live traffic, commercial RU and smartphones. Extensive over-the-air experiments and ablation studies confirm that EExAPP significantly outperforms existing methods in reducing the energy consumption of RU while maintaining QoS. The source code is available at https://github.com/EExApp/EExApp.
Authors: Jianke Yang, Ohm Venkatachalam, Mohammad Kianezhad, Sharvaree Vadgama, Rose Yu
Abstract: Explaining observed phenomena through symbolic, interpretable formulas is a fundamental goal of science. Recently, large language models (LLMs) have emerged as promising tools for symbolic equation discovery, owing to their broad domain knowledge and strong reasoning capabilities. However, most existing LLM-based systems try to guess equations directly from data, without modeling the multi-step reasoning process that scientists often follow: first inferring physical properties such as symmetries, then using these as priors to restrict the space of candidate equations. We introduce KeplerAgent, an agentic framework that explicitly follows this scientific reasoning process. The agent coordinates physics-based tools to extract intermediate structure and uses these results to configure symbolic regression engines such as PySINDy and PySR, including their function libraries and structural constraints. Across a suite of physical equation benchmarks, KeplerAgent achieves substantially higher symbolic accuracy and greater robustness to noisy data than both LLM and traditional baselines.
Authors: Pengxiang Zhao, Hui-Ling Zhen, Xing Li, Han Bao, Weizhe Lin, Zhiyuan Yang, Ziwei Yu, Xin Wang, Mingxuan Yuan, Xianzhi Yu, Zhenhua Dong
Abstract: As LLMs scale, low-bit floating-point formats like MXFP and NVFP4 offer new opportunities for precision and efficiency. In this work, we evaluate HiFloat (HiF8 and HiF4), a family of formats tailored for Ascend NPUs. Through rigorous comparison across weight-activation and KV-cache tasks, we provide three key insights: (1) INT8 suits narrow-range data, while floating-point formats excel with high-variance data; (2) in 4-bit regimes, HiF4's hierarchical scaling prevents the accuracy collapse seen in integer formats; and (3) HiFloat is fully compatible with state-of-the-art post-training quantization frameworks. Overall, HiFloat provides a solution for high-efficiency LLM inference on NPUs.
Authors: Lunjun Zhang, Ryan Chen, Bradly C. Stadie
Abstract: Building agentic systems that can autonomously self-improve from experience is a longstanding goal of AI. Large language models (LLMs) today primarily self-improve via two mechanisms: self-reflection for context updates, and reinforcement learning (RL) for weight updates. In this work, we propose Evolutionary System Prompt Learning (E-SPL), a method for jointly improving model contexts and model weights. In each RL iteration, E-SPL samples trajectories under multiple system prompts in parallel, then jointly applies RL updates to LLM weights and evolutionary updates to system prompts. System prompts evolve via mutation and crossover, two genetic operators driven by LLM self-reflection; selection is based on relative performance ratings updated across RL iterations. E-SPL encourages a natural division between declarative knowledge encoded in prompts and procedural knowledge encoded in weights, resulting in improved performance across reasoning and agentic tasks. For instance, in an easy-to-hard (AIME $\rightarrow$ BeyondAIME) generalization setting, E-SPL improves RL success rate from 38.8% $\rightarrow$ 45.1% while also outperforming reflective prompt evolution (40.0%). Overall, our results demonstrate that RL and system prompt evolution are deeply synergistic, and combining the two yields consistent gains in sample efficiency and generalization. Code: https://github.com/LunjunZhang/E-SPL
Authors: Brandon Yee, Wilson Collins, Maximilian Rutkowski
Abstract: We extend the Prometheus framework for unsupervised phase transition discovery from 2D classical systems to 3D classical and quantum many-body systems, addressing scalability in higher dimensions and generalization to quantum fluctuations. For the 3D Ising model ($L \leq 32$), the framework detects the critical temperature within 0.01\% of literature values ($T_c/J = 4.511 \pm 0.005$) and extracts critical exponents with $\geq 70\%$ accuracy ($\beta = 0.328 \pm 0.015$, $\gamma = 1.24 \pm 0.06$, $\nu = 0.632 \pm 0.025$), correctly identifying the 3D Ising universality class via $\chi^2$ comparison ($p = 0.72$) without analytical guidance. For quantum systems, we developed quantum-aware VAE (Q-VAE) architectures using complex-valued wavefunctions and fidelity-based loss. Applied to the transverse field Ising model, we achieve 2\% accuracy in quantum critical point detection ($h_c/J = 1.00 \pm 0.02$) and successfully discover ground state magnetization as the order parameter ($r = 0.97$). Notably, for the disordered transverse field Ising model, we detect exotic infinite-randomness criticality characterized by activated dynamical scaling $\ln \xi \sim |h - h_c|^{-\psi}$, extracting a tunneling exponent $\psi = 0.48 \pm 0.08$ consistent with theoretical predictions ($\psi = 0.5$). This demonstrates that unsupervised learning can identify qualitatively different types of critical behavior, not just locate critical points. Our systematic validation across classical thermal transitions ($T = 0$ to $T > 0$) and quantum phase transitions ($T = 0$, varying $h$) establishes that VAE-based discovery generalizes across fundamentally different physical domains, providing robust tools for exploring phase diagrams where analytical solutions are unavailable.
Authors: Iman Ahmadi, Mehrshad Taji, Arad Mahdinezhad Kashani, AmirHossein Jadidi, Saina Kashani, Babak Khalaj
Abstract: Task planning for robotic manipulation with large language models (LLMs) is an emerging area. Prior approaches rely on specialized models, fine tuning, or prompt tuning, and often operate in an open loop manner without robust environmental feedback, making them fragile in dynamic settings. MALLVI presents a Multi Agent Large Language and Vision framework that enables closed-loop feedback driven robotic manipulation. Given a natural language instruction and an image of the environment, MALLVI generates executable atomic actions for a robot manipulator. After action execution, a Vision Language Model (VLM) evaluates environmental feedback and decides whether to repeat the process or proceed to the next step. Rather than using a single model, MALLVI coordinates specialized agents, Decomposer, Localizer, Thinker, and Reflector, to manage perception, localization, reasoning, and high level planning. An optional Descriptor agent provides visual memory of the initial state. The Reflector supports targeted error detection and recovery by reactivating only relevant agents, avoiding full replanning. Experiments in simulation and real-world settings show that iterative closed loop multi agent coordination improves generalization and increases success rates in zero shot manipulation tasks. Code available at https://github.com/iman1234ahmadi/MALLVI .
Authors: Ruicheng Ao, David Simchi-Levi, Xinshang Wang
Abstract: Supply chain optimization models frequently become infeasible because of modeling errors. Diagnosis and repair require scarce OR expertise: analysts must interpret solver diagnostics, trace root causes across echelons, and fix formulations without sacrificing operational soundness. Whether AI agents can perform this task remains untested. We decompose this task into two phases: a domain-agnostic feasibility phase that iteratively repairs any LP using IIS-guided diagnosis, and a domain-specific validation phase that enforces five rationality checks grounded in inventory theory. We test 22 API models from seven families on 976 multi-echelon supply chain problems and train two 8B-parameter models with self-taught reasoning and solver-verified rewards. The trained models reach 81.7% Rational Recovery Rate (RRR) -- the fraction of problems resolved to both feasibility and operational rationality -- versus 42.2% for the best API model and 21.3% on average. The gap concentrates in Phase 1 repair, where API models average 27.6% recovery rate versus 97.2% for trained models. Two gaps separate current AI from reliable model repair: solver interaction, as API models restore only 27.6% of infeasible formulations; and operational rationale, as roughly one in four feasible repairs violate supply chain theory. Each gap requires a different intervention -- targeted training closes the solver interaction gap, while explicit specification as solver-verifiable checks closes the rationality gap. For organizations adopting AI in operational planning, formalizing what 'rational' means in their context is the higher-return investment.
Authors: David Schmotz, Luca Beurer-Kellner, Sahar Abdelnabi, Maksym Andriushchenko
Abstract: LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, knowledge, and instructions. Although this can extend agent capabilities to new domains, it creates an increasingly complex agent supply chain, offering new surfaces for prompt injection attacks. We identify skill-based prompt injection as a significant threat and introduce SkillInject, a benchmark evaluating the susceptibility of widely-used LLM agents to injections through skill files. SkillInject contains 202 injection-task pairs with attacks ranging from obviously malicious injections to subtle, context-dependent attacks hidden in otherwise legitimate instructions. We evaluate frontier LLMs on SkillInject, measuring both security in terms of harmful instruction avoidance and utility in terms of legitimate instruction compliance. Our results show that today's agents are highly vulnerable with up to 80% attack success rate with frontier models, often executing extremely harmful instructions including data exfiltration, destructive action, and ransomware-like behavior. They furthermore suggest that this problem will not be solved through model scaling or simple input filtering, but that robust agent security will require context-aware authorization frameworks. Our benchmark is available at https://www.skill-inject.com/.
Authors: Christian Catalini, Xiang Hui, Jane Wu
Abstract: For millennia, human cognition was the primary engine of progress on Earth. As AI decouples cognition from biology, the marginal cost of measurable execution falls to zero, absorbing any labor capturable by metrics--including creative, analytical, and innovative work. The binding constraint on growth is no longer intelligence but human verification bandwidth: the capacity to validate, audit, and underwrite responsibility when execution is abundant. We model the AGI transition as the collision of two racing cost curves: an exponentially decaying Cost to Automate and a biologically bottlenecked Cost to Verify. This structural asymmetry widens a Measurability Gap between what agents can execute and what humans can afford to verify. It also drives a shift from skill-biased to measurability-biased technical change. Rents migrate to verification-grade ground truth, cryptographic provenance, and liability underwriting--the ability to insure outcomes rather than merely generate them. The current human-in-the-loop equilibrium is unstable: eroded from below as apprenticeship collapses (Missing Junior Loop) and from within as experts codify their obsolescence (Codifier's Curse). Unverified deployment becomes privately rational--a Trojan Horse externality. Unmanaged, these forces pull toward a Hollow Economy. Yet by scaling verification alongside agentic capabilities, the forces that threaten collapse become the catalyst for unbounded discovery and experimentation--an Augmented Economy. We derive a practical playbook for individuals, companies, investors, and policymakers. Today's defining challenge is not the race to deploy the most autonomous systems; it is the race to secure the foundations of their oversight. Only by scaling our bandwidth for verification alongside our capacity for execution can we ensure that the intelligence we have summoned preserves the humanity that initiated it.