# Research Papers — 2026-02 · bundle page 205 of 210

> Full-text markdown of papers #10201–10250 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-02/page/205
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/204.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/206.md)

### PeerRank: Autonomous LLM Evaluation Through Web-Grounded, Bias-Controlled Peer Review

Authors: Yanki Margalit, Erni Avram, Ran Taig, Oded Margalit, Nurit Cohen-Inger
Published: 2026-02-01
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.02589v1

Evaluating large language models typically relies on human-authored benchmarks, reference answers, and human or single-model judgments, approaches that scale poorly, become quickly outdated, and mismatch open-world deployments that depend on web retrieval and synthesis. We introduce PeerRank, a fully autonomous end-to-end evaluation framework in which models generate evaluation tasks, answer them with category-scoped live web grounding, judge peer responses and aggregate dense peer assessments into relative performance estimates, without human supervision or gold references. PeerRank treats evaluation as a multi-agent process where each model participates symmetrically as task designer, respondent, and evaluator, while removing biased judgments. In a large-scale study over 12 commercially available models and 420 autonomously generated questions, PeerRank produces stable, discriminative rankings and reveals measurable identity and presentation biases. Rankings are robust, and mean peer scores agree with Elo. We further validate PeerRank on TruthfulQA and GSM8K, where peer scores correlate with objective accuracy. Together, these results suggest that bias-aware peer evaluation with selective web-grounded answering can scale open-world LLM assessment beyond static and human curated benchmarks.

---

### Multi-Scale Wavelet Transformers for Operator Learning of Dynamical Systems

Authors: Xuesong Wang, Michael Groom, Rafael Oliveira, He Zhao, Terence O'Kane, Edwin V. Bonilla
Published: 2026-02-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.01486v2

Recent years have seen a surge in data-driven surrogates for dynamical systems that can be orders of magnitude faster than numerical solvers. However, many machine learning-based models such as neural operators exhibit spectral bias, attenuating high-frequency components that often encode small-scale structure. This limitation is particularly damaging in applications such as weather forecasting, where misrepresented high frequencies can induce long-horizon instability. To address this issue, we propose multi-scale wavelet transformers (MSWTs), which learn system dynamics in a tokenized wavelet domain. The wavelet transform explicitly separates low- and high-frequency content across scales. MSWTs leverage a wavelet-preserving downsampling scheme that retains high-frequency features and employ wavelet-based attention to capture dependencies across scales and frequency bands. Experiments on chaotic dynamical systems show substantial error reductions and improved long horizon spectral fidelity. On the ERA5 climate reanalysis, MSWTs further reduce climatological bias, demonstrating their effectiveness in a real-world forecasting setting.

---

### Predicting and improving test-time scaling laws via reward tail-guided search

Authors: Muheng Li, Jian Qian, Wenlong Mou
Published: 2026-02-01
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.01485v1

Test-time scaling has emerged as a critical avenue for enhancing the reasoning capabilities of Large Language Models (LLMs). Though the straight-forward ''best-of-$N$'' (BoN) strategy has already demonstrated significant improvements in performance, it lacks principled guidance on the choice of $N$, budget allocation, and multi-stage decision-making, thereby leaving substantial room for optimization. While many works have explored such optimization, rigorous theoretical guarantees remain limited. In this work, we propose new methodologies to predict and improve scaling properties via tail-guided search. By estimating the tail distribution of rewards, our method predicts the scaling law of LLMs without the need for exhaustive evaluations. Leveraging this prediction tool, we introduce Scaling-Law Guided (SLG) Search, a new test-time algorithm that dynamically allocates compute to identify and exploit intermediate states with the highest predicted potential. We theoretically prove that SLG achieves vanishing regret compared to perfect-information oracles, and achieves expected rewards that would otherwise require a polynomially larger compute budget required when using BoN. Empirically, we validate our framework across different LLMs and reward models, confirming that tail-guided allocation consistently achieves higher reward yields than Best-of-$N$ under identical compute budgets. Our code is available at https://github.com/PotatoJnny/Scaling-Law-Guided-search.

---

### Causal Preference Elicitation

Authors: Edwin V. Bonilla, He Zhao, Daniel M. Steinberg
Published: 2026-02-01
Categories: cs.LG, cs.AI, stat.ME
arXiv: https://arxiv.org/abs/2602.01483v2

We propose causal preference elicitation, a Bayesian framework for expert-in-the-loop causal discovery that actively queries local edge relations to concentrate a posterior over directed acyclic graphs (DAGs). From any black-box observational posterior, we model noisy expert judgments with a three-way likelihood over edge existence and direction. Posterior inference uses a flexible particle approximation, and queries are selected by an efficient expected information gain criterion on the expert's categorical response. Experiments on synthetic graphs, protein signaling data, and a human gene perturbation benchmark show faster posterior concentration and improved recovery of directed effects under tight query budgets.

---

### Community-Level Modeling of Gyral Folding Patterns for Robust and Anatomically Informed Individualized Brain Mapping

Authors: Minheng Chen, Tong Chen, Yan Zhuang, Chao Cao, Jing Zhang, Tianming Liu, Lu Zhang, Dajiang Zhu
Published: 2026-02-01
Categories: q-bio.NC, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2602.01482v1

Cortical folding exhibits substantial inter-individual variability while preserving stable anatomical landmarks that enable fine-scale characterization of cortical organization. Among these, the three-hinge gyrus (3HG) serves as a key folding primitive, showing consistent topology yet meaningful variations in morphology, connectivity, and function. Existing landmark-based methods typically model each 3HG independently, ignoring that 3HGs form higher-order folding communities that capture mesoscale structure. This simplification weakens anatomical representation and makes one-to-one matching sensitive to positional variability and noise. We propose a spectral graph representation learning framework that models community-level folding units rather than isolated landmarks. Each 3HG is encoded using a dual-profile representation combining surface topology and structural connectivity. Subject-specific spectral clustering identifies coherent folding communities, followed by topological refinement to preserve anatomical continuity. For cross-subject correspondence, we introduce Joint Morphological-Geometric Matching, jointly optimizing geometric and morphometric similarity. Across over 1000 Human Connectome Project subjects, the resulting communities show reduced morphometric variance, stronger modular organization, improved hemispheric consistency, and superior alignment compared with atlas-based and landmark-based or embedding-based baselines. These findings demonstrate that community-level modeling provides a robust and anatomically grounded framework for individualized cortical characterization and reliable cross-subject correspondence.

---

### Rod Flow: A Continuous-Time Model for Gradient Descent at the Edge of Stability

Authors: Eric Regis, Sinho Chewi
Published: 2026-02-01
Categories: cs.LG, cs.AI, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2602.01480v1

How can we understand gradient-based training over non-convex landscapes? The edge of stability phenomenon, introduced in Cohen et al. (2021), indicates that the answer is not so simple: namely, gradient descent (GD) with large step sizes often diverges away from the gradient flow. In this regime, the "Central Flow", recently proposed in Cohen et al. (2025), provides an accurate ODE approximation to the GD dynamics over many architectures. In this work, we propose Rod Flow, an alternative ODE approximation, which carries the following advantages: (1) it rests on a principled derivation stemming from a physical picture of GD iterates as an extended one-dimensional object -- a "rod"; (2) it better captures GD dynamics for simple toy examples and matches the accuracy of Central Flow for representative neural network architectures, and (3) is explicit and cheap to compute. Theoretically, we prove that Rod Flow correctly predicts the critical sharpness threshold and explains self-stabilization in quartic potentials. We validate our theory with a range of numerical experiments.

---

### Ebisu: Benchmarking Large Language Models in Japanese Finance

Authors: Xueqing Peng, Ruoyu Xiang, Fan Zhang, Mingzi Song, Mingyang Jiang, Yan Wang, Lingfei Qian, Taiki Hara, Yuqing Guo, Jimin Huang, Junichi Tsujii, Sophia Ananiadou
Published: 2026-02-01
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.01479v1

Japanese finance combines agglutinative, head-final linguistic structure, mixed writing systems, and high-context communication norms that rely on indirect expression and implicit commitment, posing a substantial challenge for LLMs. We introduce Ebisu, a benchmark for native Japanese financial language understanding, comprising two linguistically and culturally grounded, expert-annotated tasks: JF-ICR, which evaluates implicit commitment and refusal recognition in investor-facing Q&A, and JF-TE, which assesses hierarchical extraction and ranking of nested financial terminology from professional disclosures. We evaluate a diverse set of open-source and proprietary LLMs spanning general-purpose, Japanese-adapted, and financial models. Results show that even state-of-the-art systems struggle on both tasks. While increased model scale yields limited improvements, language- and domain-specific adaptation does not reliably improve performance, leaving substantial gaps unresolved. Ebisu provides a focused benchmark for advancing linguistically and culturally grounded financial NLP. All datasets and evaluation scripts are publicly released.

---

### Density-Informed Pseudo-Counts for Calibrated Evidential Deep Learning

Authors: Pietro Carlotti, Nevena Gligić, Arya Farahi
Published: 2026-02-01
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.01477v3

Evidential Deep Learning (EDL) is a popular framework for uncertainty-aware classification that models predictive uncertainty via Dirichlet distributions parameterized by neural networks. Despite its popularity, its theoretical foundations and behavior under distributional shift remain poorly understood. In this work, we provide a principled statistical interpretation by proving that EDL training corresponds to amortized variational inference in a hierarchical Bayesian model with a tempered pseudo-likelihood. This perspective reveals a major drawback: standard EDL conflates epistemic and aleatoric uncertainty, leading to systematic overconfidence on out-of-distribution (OOD) inputs. To address this, we introduce Density-Informed Pseudo-count EDL (DIP-EDL), a new parametrization that decouples class prediction from the magnitude of uncertainty by separately estimating the conditional label distribution and the marginal covariate density. This separation preserves evidence in high-density regions while shrinking predictions toward a uniform prior for OOD data. Theoretically, we prove that DIP-EDL achieves asymptotic concentration. Empirically, we show that our method enhances interpretability and improves robustness and uncertainty calibration under distributional shift.

---

### Learning to Guide Local Search for MPE Inference in Probabilistic Graphical Models

Authors: Brij Malhotra, Shivvrat Arya, Tahrima Rahman, Vibhav Giridhar Gogate
Published: 2026-02-01
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.01475v1

Most Probable Explanation (MPE) inference in Probabilistic Graphical Models (PGMs) is a fundamental yet computationally challenging problem arising in domains such as diagnosis, planning, and structured prediction. In many practical settings, the graphical model remains fixed while inference must be performed repeatedly for varying evidence patterns. Stochastic Local Search (SLS) algorithms scale to large models but rely on myopic best-improvement rule that prioritizes immediate likelihood gains and often stagnate in poor local optima. Heuristics such as Guided Local Search (GLS+) partially alleviate this limitation by modifying the search landscape, but their guidance cannot be reused effectively across multiple inference queries on the same model. We propose a neural amortization framework for improving local search in this repeated-query regime. Exploiting the fixed graph structure, we train an attention-based network to score local moves by predicting their ability to reduce Hamming distance to a near-optimal solution. Our approach integrates seamlessly with existing local search procedures, using this signal to balance short-term likelihood gains with long-term promise during neighbor selection. We provide theoretical intuition linking distance-reducing move selection to improved convergence behavior, and empirically demonstrate consistent improvements over SLS and GLS+ on challenging high-treewidth benchmarks in the amortized inference setting.

---

### Legal Infrastructure for Transformative AI Governance

Authors: Gillian K. Hadfield
Published: 2026-02-01
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.01474v1

Most of our AI governance efforts focus on substance: what rules do we want in place? What limits or checks do we want to impose on AI development and deployment? But a key role for law is not only to establish substantive rules but also to establish legal and regulatory infrastructure to generate and implement rules. The transformative nature of AI calls especially for attention to building legal and regulatory frameworks. In this PNAS Perspective piece I review three examples I have proposed: the creation of registration regimes for frontier models; the creation of registration and identification regimes for autonomous agents; and the design of regulatory markets to facilitate a role for private companies to innovate and deliver AI regulatory services.

---

### ConPress: Learning Efficient Reasoning from Multi-Question Contextual Pressure

Authors: Jie Deng, Shining Liang, Jun Li, Hongzhi Li, Yutao Xie
Published: 2026-02-01
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.01472v2

Large reasoning models (LRMs) typically solve reasoning-intensive tasks by generating long chain-of-thought (CoT) traces, leading to substantial inference overhead. We identify a reproducible inference-time phenomenon, termed Self-Compression: when multiple independent and answerable questions are presented within a single prompt, the model spontaneously produces shorter reasoning traces for each question. This phenomenon arises from multi-question contextual pressure during generation and consistently manifests across models and benchmarks. Building on this observation, we propose ConPress (Learning from Contextual Pressure), a lightweight self-supervised fine-tuning approach. ConPress constructs multi-question prompts to induce self-compression, samples the resulting model outputs, and parses and filters per-question traces to obtain concise yet correct reasoning trajectories. These trajectories are directly used for supervised fine-tuning, internalizing compressed reasoning behavior in single-question settings without external teachers, manual pruning, or reinforcement learning. With only 8k fine-tuning examples, ConPress reduces reasoning token usage by 59% on MATH500 and 33% on AIME25, while maintaining competitive accuracy.

---

### P-EAGLE: Parallel-Drafting EAGLE with Scalable Training

Authors: Mude Hui, Xin Huang, Jaime Campos Salas, Yue Sun, Nathan Pemberton, Xiang Song, Ashish Khetan, George Karypis
Published: 2026-02-01
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.01469v1

Reasoning LLMs produce longer outputs, requiring speculative decoding drafters trained on extended sequences. Parallel drafting - predicting multiple tokens per forward pass - offers latency benefits over sequential generation, but training complexity scales quadratically with the product of sequence length and parallel positions, rendering long-context training impractical. We present P(arallel)-EAGLE, which transforms EAGLE from autoregressive to parallel multi-token prediction via a learnable shared hidden state. To scale training to long contexts, we develop a framework featuring attention mask pre-computation and sequence partitioning techniques, enabling gradient accumulation within individual sequences for parallel-prediction training. We implement P-EAGLE in vLLM and demonstrate speedups of 1.10-1.36x over autoregressive EAGLE-3 across GPT-OSS 120B, 20B, and Qwen3-Coder 30B.

---

### A Statistical Theory of Gated Attention through the Lens of Hierarchical Mixture of Experts

Authors: Viet Nguyen, Tuan Minh Pham, Thinh Cao, Tan Dinh, Huy Nguyen, Nhat Ho, Alessandro Rinaldo
Published: 2026-02-01
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.01468v1

Self-attention has greatly contributed to the success of the widely used Transformer architecture by enabling learning from data with long-range dependencies. In an effort to improve performance, a gated attention model that leverages a gating mechanism within the multi-head self-attention has recently been proposed as a promising alternative. Gated attention has been empirically demonstrated to increase the expressiveness of low-rank mapping in standard attention and even to eliminate the attention sink phenomenon. Despite its efficacy, a clear theoretical understanding of gated attention's benefits remains lacking in the literature. To close this gap, we rigorously show that each entry in a gated attention matrix or a multi-head self-attention matrix can be written as a hierarchical mixture of experts. By recasting learning as an expert estimation problem, we demonstrate that gated attention is more sample-efficient than multi-head self-attention. In particular, while the former needs only a polynomial number of data points to estimate an expert, the latter requires exponentially many data points to achieve the same estimation error. Furthermore, our analysis also provides a theoretical justification for why gated attention yields higher performance when a gate is placed at the output of the scaled dot product attention or the value map rather than at other positions in the multi-head self-attention architecture.

---

### Rethinking Multinomial Logistic Mixture of Experts with Sigmoid Gating Function

Authors: Tuan Minh Pham, Thinh Cao, Viet Nguyen, Huy Nguyen, Nhat Ho, Alessandro Rinaldo
Published: 2026-02-01
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.01466v1

The sigmoid gate in mixture-of-experts (MoE) models has been empirically shown to outperform the softmax gate across several tasks, ranging from approximating feed-forward networks to language modeling. Additionally, recent efforts have demonstrated that the sigmoid gate is provably more sample-efficient than its softmax counterpart under regression settings. Nevertheless, there are three notable concerns that have not been addressed in the literature, namely (i) the benefits of the sigmoid gate have not been established under classification settings; (ii) existing sigmoid-gated MoE models may not converge to their ground-truth; and (iii) the effects of a temperature parameter in the sigmoid gate remain theoretically underexplored. To tackle these open problems, we perform a comprehensive analysis of multinomial logistic MoE equipped with a modified sigmoid gate to ensure model convergence. Our results indicate that the sigmoid gate exhibits a lower sample complexity than the softmax gate for both parameter and expert estimation. Furthermore, we find that incorporating a temperature into the sigmoid gate leads to a sample complexity of exponential order due to an intrinsic interaction between the temperature and gating parameters. To overcome this issue, we propose replacing the vanilla inner product score in the gating function with a Euclidean score that effectively removes that interaction, thereby substantially improving the sample complexity to a polynomial order.

---

### Agyn: A Multi-Agent System for Team-Based Autonomous Software Engineering

Authors: Nikita Benkovich, Vitalii Valkov
Published: 2026-02-01
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2602.01465v2

Large language models have demonstrated strong capabilities in individual software engineering tasks, yet most autonomous systems still treat issue resolution as a monolithic or pipeline-based process. In contrast, real-world software development is organized as a collaborative activity carried out by teams following shared methodologies, with clear role separation, communication, and review. In this work, we present a fully automated multi-agent system that explicitly models software engineering as an organizational process, replicating the structure of an engineering team. Built on top of agyn, an open-source platform for configuring agent teams, our system assigns specialized agents to roles such as coordination, research, implementation, and review, provides them with isolated sandboxes for experimentation, and enables structured communication. The system follows a defined development methodology for working on issues, including analysis, task specification, pull request creation, and iterative review, and operates without any human intervention. Importantly, the system was designed for real production use and was not tuned for SWE-bench. When evaluated post hoc on SWE-bench 500, it resolves 72.2% of tasks, outperforming single-agent baselines using comparable language models. Our results suggest that replicating team structure, methodology, and communication is a powerful paradigm for autonomous software engineering, and that future progress may depend as much on organizational design and agent infrastructure as on model improvements.

---

### Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient Estimator

Authors: Haoyu Han, Heng Yang
Published: 2026-02-01
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2602.01460v3

Policy-gradient methods are widely used in reinforcement learning, yet training often becomes unstable or slows down as learning progresses. We study this phenomenon through the noise-to-signal ratio (NSR) of a policy-gradient estimator, defined as the estimator variance (noise) normalized by the squared norm of the true gradient (signal). Our main result is that, for (i) finite-horizon linear systems with Gaussian policies and linear state-feedback, and (ii) finite-horizon polynomial systems with Gaussian policies and polynomial feedback, the NSR of the REINFORCE estimator can be characterized exactly-either in closed form or via numerical moment-evaluation algorithms-without approximation. For general nonlinear dynamics and expressive policies (including neural policies), we further derive a general upper bound on the variance. These characterizations enable a direct examination of how NSR varies across policy parameters and how it evolves along optimization trajectories (e.g. SGD and Adam). Across a range of examples, we find that the NSR landscape is highly non-uniform and typically increases as the policy approaches an optimum; in some regimes it blows up, which can trigger training instability and policy collapse.

---

### Understanding vision transformer robustness through the lens of out-of-distribution detection

Authors: Joey Kuang, Alexander Wong
Published: 2026-02-01
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.01459v1

Vision transformers have shown remarkable performance in vision tasks, but enabling them for accessible and real-time use is still challenging. Quantization reduces memory and inference costs at the risk of performance loss. Strides have been made to mitigate low precision issues mainly by understanding in-distribution (ID) task behaviour, but the attention mechanism may provide insight on quantization attributes by exploring out-of-distribution (OOD) situations. We investigate the behaviour of quantized small-variant popular vision transformers (DeiT, DeiT3, and ViT) on common OOD datasets. ID analyses show the initial instabilities of 4-bit models, particularly of those trained on the larger ImageNet-22k, as the strongest FP32 model, DeiT3, sharply drop 17% from quantization error to be one of the weakest 4-bit models. While ViT shows reasonable quantization robustness for ID calibration, OOD detection reveals more: ViT and DeiT3 pretrained on ImageNet-22k respectively experienced a 15.0% and 19.2% average quantization delta in AUPR-out between full precision to 4-bit while their ImageNet-1k-only counterparts experienced a 9.5% and 12.0% delta. Overall, our results suggest pretraining on large scale datasets may hinder low-bit quantization robustness in OOD detection and that data augmentation may be a more beneficial option.

---

### Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations

Authors: Yilun Kuang, Yash Dagade, Tim G. J. Rudner, Randall Balestriero, Yann LeCun
Published: 2026-02-01
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.01456v2

Joint-Embedding Predictive Architectures (JEPA) learn view-invariant representations and admit projection-based distribution matching for collapse prevention. Existing approaches regularize representations towards isotropic Gaussian distributions, but inherently favor dense representations and fail to capture the key property of sparsity observed in efficient representations. We introduce Rectified Distribution Matching Regularization (RDMReg), a sliced two-sample distribution-matching loss that aligns representations to a Rectified Generalized Gaussian (RGG) distribution. RGG enables explicit control over expected $\ell_0$ norm through rectification, while its continuous truncated component admits a maximum-entropy characterization under expected $\ell_p$ norm and support constraints. Equipping JEPAs with RDMReg yields Rectified LpJEPA, which strictly generalizes prior Gaussian-based JEPAs. Empirically, Rectified LpJEPA learns sparse, non-negative representations with favorable sparsity--performance trade-offs and competitive downstream performance on image classification benchmarks, showing that RDMReg can enforce sparsity while preserving task-relevant information.

---

### Modeling Topological Impact on Node Attribute Distributions in Attributed Graphs

Authors: Amirreza Shiralinasab Langari, Leila Yeganeh, Kim Khoa Nguyen
Published: 2026-02-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.01454v1

We investigate how the topology of attributed graphs influences the distribution of node attributes. This work offers a novel perspective by treating topology and attributes as structurally distinct but interacting components. We introduce an algebraic approach that combines a graph's topology with the probability distribution of node attributes, resulting in topology-influenced distributions. First, we develop a categorical framework to formalize how a node perceives the graph's topology. We then quantify this point of view and integrate it with the distribution of node attributes to capture topological effects. We interpret these topology-conditioned distributions as approximations of the posteriors $P(\cdot \mid v)$ and $P(\cdot \mid \mathcal{G})$. We further establish a principled sufficiency condition by showing that, on complete graphs, where topology carries no informative structure, our construction recovers the original attribute distribution. To evaluate our approach, we introduce an intentionally simple testbed model, $\textbf{ID}$, and use unsupervised graph anomaly detection as a probing task.

---

### The Horizon Threshold in Cooperative Multi-Agent Reward-Free Exploration

Authors: Idan Barnea, Orin Levy, Yishay Mansour
Published: 2026-02-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.01453v3

We study cooperative multi-agent reinforcement learning in the setting of reward-free exploration, where multiple agents jointly explore an unknown MDP in order to learn its dynamics (without observing rewards). We focus on a tabular finite-horizon MDP and adopt a phased learning framework. In each learning phase, multiple agents independently interact with the environment. More specifically, in each learning phase, each agent is assigned a policy, executes it, and observes the resulting trajectory. Our primary goal is to characterize the tradeoff between the number of learning phases and the number of agents, especially when the number of learning phases is small. Our results identify a regime change governed by the horizon $H$. When the number of learning phases equals $H$, we present a computationally efficient algorithm that uses only $\tilde{O}(S^6 H^6 A / ε^2)$ agents to obtain an $ε$ approximation of the dynamics (i.e., yields an $ε$-optimal policy for any reward function). We complement our algorithm with a lower bound showing that any algorithm restricted to $ρ< H$ phases requires at least $A^{H/ρ}$ agents to achieve constant accuracy. Thus, we show that having $Θ(H)$ learning phases is both necessary and sufficient when restricting the number of agents to be polynomial.

---

### Cross-Paradigm Evaluation of Gaze-Based Semantic Object Identification for Intelligent Vehicles

Authors: Penghao Deng, Jidong J. Yang, Jiachen Bian
Published: 2026-02-01
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.01452v1

Understanding where drivers direct their visual attention during driving, as characterized by gaze behavior, is critical for developing next-generation advanced driver-assistance systems and improving road safety. This paper tackles this challenge as a semantic identification task from the road scenes captured by a vehicle's front-view camera. Specifically, the collocation of gaze points with object semantics is investigated using three distinct vision-based approaches: direct object detection (YOLOv13), segmentation-assisted classification (SAM2 paired with EfficientNetV2 versus YOLOv13), and query-based Vision-Language Models, VLMs (Qwen2.5-VL-7b versus Qwen2.5-VL-32b). The results demonstrate that the direct object detection (YOLOv13) and Qwen2.5-VL-32b significantly outperform other approaches, achieving Macro F1-Scores over 0.84. The large VLM (Qwen2.5-VL-32b), in particular, exhibited superior robustness and performance for identifying small, safety-critical objects such as traffic lights, especially in adverse nighttime conditions. Conversely, the segmentation-assisted paradigm suffers from a "part-versus-whole" semantic gap that led to large failure in recall. The results reveal a fundamental trade-off between the real-time efficiency of traditional detectors and the richer contextual understanding and robustness offered by large VLMs. These findings provide critical insights and practical guidance for the design of future human-aware intelligent driver monitoring systems.

---

### Understanding QA generation: Extracting Parametric and Contextual Knowledge with CQA for Low Resource Bangla Language

Authors: Umme Abira Azmary, MD Ikramul Kayes, Swakkhar Shatabda, Farig Yousuf Sadeque
Published: 2026-02-01
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.01451v1

Question-Answering (QA) models for low-resource languages like Bangla face challenges due to limited annotated data and linguistic complexity. A key issue is determining whether models rely more on pre-encoded (parametric) knowledge or contextual input during answer generation, as existing Bangla QA datasets lack the structure required for such analysis. We introduce BanglaCQA, the first Counterfactual QA dataset in Bangla, by extending a Bangla dataset while integrating counterfactual passages and answerability annotations. In addition, we propose fine-tuned pipelines for encoder-decoder language-specific and multilingual baseline models, and prompting-based pipelines for decoder-only LLMs to disentangle parametric and contextual knowledge in both factual and counterfactual scenarios. Furthermore, we apply LLM-based and human evaluation techniques that measure answer quality based on semantic similarity. We also present a detailed analysis of how models perform across different QA settings in low-resource languages, and show that Chain-of-Thought (CoT) prompting reveals a uniquely effective mechanism for extracting parametric knowledge in counterfactual scenarios, particularly in decoder-only LLMs. Our work not only introduces a novel framework for analyzing knowledge sources in Bangla QA but also uncovers critical findings that open up broader directions for counterfactual reasoning in low-resource language settings.

---

### Dimension-Free Multimodal Sampling via Preconditioned Annealed Langevin Dynamics

Authors: Lorenzo Baldassari, Josselin Garnier, Knut Solna, Maarten V. de Hoop
Published: 2026-02-01
Categories: math.NA, math.PR, stat.ML
arXiv: https://arxiv.org/abs/2602.01449v2

Designing sampling algorithms for multimodal targets that remain stable under refinement of the finite-dimensional approximation of an underlying function-space problem is a central challenge. Annealed Langevin dynamics (ALD) is a natural alternative to classical Langevin in this context, since it is often observed to improve exploration across modes. Yet a gap remains between its empirical success and existing theory: under which conditions can ALD be guaranteed to remain stable across dimensions? In this paper, we bridge this gap by providing a uniform-in-dimension analysis of continuous-time ALD for Gaussian-mixture targets. Along an explicit annealing path obtained by gradually removing Gaussian smoothing from the target, we identify spectral conditions linking the smoothing covariance to the component covariances under which ALD achieves a prescribed accuracy in Kullback-Leibler divergence within a dimension-uniform time horizon. We then establish stability in a perturbative regime with imperfect initialization and approximate scores. Under a misspecified-mixture score model, we show that preconditioning ALD with an operator whose spectrum decays sufficiently fast prevents error terms from accumulating across coordinates and thereby preserves dimension-uniform control.

---

### SentiFuse: Deep Multi-model Fusion Framework for Robust Sentiment Extraction

Authors: Hieu Minh Duong, Rupa Ghosh, Cong Hoan Nguyen, Eugene Levin, Todd Gary, Long Nguyen
Published: 2026-02-01
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.01447v1

Sentiment analysis models exhibit complementary strengths, yet existing approaches lack a unified framework for effective integration. We present SentiFuse, a flexible and model-agnostic framework that integrates heterogeneous sentiment models through a standardization layer and multiple fusion strategies. Our approach supports decision-level fusion, feature-level fusion, and adaptive fusion, enabling systematic combination of diverse models. We conduct experiments on three large-scale social-media datasets: Crowdflower, GoEmotions, and Sentiment140. These experiments show that SentiFuse consistently outperforms individual models and naive ensembles. Feature-level fusion achieves the strongest overall effectiveness, yielding up to 4\% absolute improvement in F1 score over the best individual model and simple averaging, while adaptive fusion enhances robustness on challenging cases such as negation, mixed emotions, and complex sentiment expressions. These results demonstrate that systematically leveraging model complementarity yields more accurate and reliable sentiment analysis across diverse datasets and text types.

---

### A Meta-Knowledge-Augmented LLM Framework for Hyperparameter Optimization in Time-Series Forecasting

Authors: Ons Saadallah, Mátyás andó, Tamás Gábor Orosz
Published: 2026-02-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.01445v2

Hyperparameter optimization (HPO) plays a central role in the performance of deep learning models, yet remains computationally expensive and difficult to interpret, particularly for time-series forecasting. While Bayesian Optimization (BO) is a standard approach, it typically treats tuning tasks independently and provides limited insight into its decisions. Recent advances in large language models (LLMs) offer new opportunities to incorporate structured prior knowledge and reasoning into optimization pipelines. We introduce LLM-AutoOpt, a hybrid HPO framework that combines BO with LLM-based contextual reasoning. The framework encodes dataset meta-features, model descriptions, historical optimization outcomes, and target objectives as structured meta-knowledge within LLM prompts, using BO to initialize the search and mitigate cold-start effects. This design enables context-aware and stable hyperparameter refinement while exposing the reasoning behind optimization decisions. Experiments on a multivariate time series forecasting benchmark demonstrate that LLM-AutoOpt achieves improved predictive performance and more interpretable optimization behavior compared to BO and LLM baselines without meta-knowledge.

---

### A texture-based framework for foundational ultrasound models

Authors: Tal Grutman, Carmel Shinar, Tali Ilovitsh
Published: 2026-02-01
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2602.01444v1

Ultrasound is the most widely used medical imaging modality, yet the images it produces are fundamentally unique, arising from tissue-dependent scattering, reflection, and speed-of-sound variations that produce a constrained set of characteristic textures that differ markedly from natural-image statistics. These acoustically driven patterns make ultrasound challenging for algorithms originally designed for natural images. To bridge this gap, the field has increasingly turned to foundation models, hoping to leverage their generalization capabilities. However, these models often falter in ultrasound applications because they are not designed for ultrasound physics, they are merely trained on ultrasound data. Therefore, it is essential to integrate ultrasound-specific domain knowledge into established learning frameworks. We achieve this by reformulating self-supervised learning as a texture-analysis problem, introducing texture ultrasound semantic analysis (TUSA). Using TUSA, models learn to leverage highly scalable contrastive methods to extract true domain-specific representations directly from simple B-mode images. We train a TUSA model on a combination of open-source, simulated, and in vivo data. The latent space is compared to several larger foundation models, demonstrating that our approach gives TUSA models better generalizability for difficult downstream tasks on unique online datasets as well as a clinical eye dataset collected for this study. Our model achieves higher accuracy in detecting COVID (70%), spinal hematoma (100%) and vitreous hemorrhage (97%) and correlates more closely with quantitative parameters like liver steatosis (r = 0.83), ejection fraction (r = 0.63), and oxygen saturation (r = 0.38). We open-source the model weights and training script: https://github.com/talg2324/tusa

---

### SimGym: Traffic-Grounded Browser Agents for Offline A/B Testing in E-Commerce

Authors: Alberto Castelo, Zahra Zanjani Foumani, Ailin Fan, Keat Yang Koay, Vibhor Malik, Yuanzheng Zhu, Han Li, Meysam Feghhi, Ronie Uliana, Shuang Xie, Zhaoyu Zhang, Angelo Ocana Martins et al.
Published: 2026-02-01
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.01443v1

A/B testing remains the gold standard for evaluating e-commerce UI changes, yet it diverts traffic, takes weeks to reach significance, and risks harming user experience. We introduce SimGym, a scalable system for rapid offline A/B testing using traffic-grounded synthetic buyers powered by Large Language Model agents operating in a live browser. SimGym extracts per-shop buyer profiles and intents from production interaction data, identifies distinct behavioral archetypes, and simulates cohort-weighted sessions across control and treatment storefronts. We validate SimGym against real human outcomes from real UI changes on a major e-commerce platform under confounder control. Even without alignment post training, SimGym agents achieve state of the art alignment with observed outcome shifts and reduces experiment cycles from weeks to under an hour , enabling rapid experimentation without exposure to real buyers.

---

### Hidden Heroes and Gradient Bloats: Layer-Wise Redundancy Inverts Attribution in Transformers

Authors: Donald Ye
Published: 2026-02-01
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.01442v3

Gradient-based attribution is the workhorse of mechanistic interpretability, yet whether it reliably tracks causal importance at the component level remains largely untested. We causally evaluate this assumption across two algorithmic tasks and up to 10 random seeds, uncovering a systematic, layer-wise failure: gradient attribution consistently overvalues early-layer \textbf{Gradient Bloats} and undervalues late-layer \textbf{Hidden Heroes}. Rank correlation collapses from $ρ= 0.72$ on sequence reversal to $0.27$ on sequence sorting, reaching $ρ= -0.18$ in individual seeds. This failure stems from first-order gradient attribution's inability to detect collective redundancy: joint Bloat ablation causes $14\times$ greater damage than individual results predict. Consequently, Bloats dominate gradient rankings despite negligible functional impact, while ablating Hidden Heroes destroys OOD accuracy ($-36.4\% \pm 22.8\%$). This systematic inversion of early-layer feature extraction and late-layer computation motivates causal validation as a prerequisite for circuit-level claims.

---

### TQL: Scaling Q-Functions with Transformers by Preventing Attention Collapse

Authors: Perry Dong, Kuo-Han Hung, Alexander Swerdlow, Dorsa Sadigh, Chelsea Finn
Published: 2026-02-01
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.01439v1

Despite scale driving substantial recent advancements in machine learning, reinforcement learning (RL) methods still primarily use small value functions. Naively scaling value functions -- including with a transformer architecture, which is known to be highly scalable -- often results in learning instability and worse performance. In this work, we ask what prevents transformers from scaling effectively for value functions? Through empirical analysis, we identify the critical failure mode in this scaling: attention scores collapse as capacity increases. Our key insight is that we can effectively prevent this collapse and stabilize training by controlling the entropy of the attention scores, thereby enabling the use of larger models. To this end, we propose Transformer Q-Learning (TQL), a method that unlocks the scaling potential of transformers in learning value functions in RL. Our approach yields up to a 43% improvement in performance when scaling from the smallest to the largest network sizes, while prior methods suffer from performance degradation.

---

### CIPHER: Cryptographic Insecurity Profiling via Hybrid Evaluation of Responses

Authors: Max Manolov, Tony Gao, Siddharth Shukla, Cheng-Ting Chou, Ryan Lagasse
Published: 2026-02-01
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2602.01438v2

Large language models (LLMs) are increasingly used to assist developers with code, yet their implementations of cryptographic functionality often contain exploitable flaws. Minor design choices (e.g., static initialization vectors or missing authentication) can silently invalidate security guarantees. We introduce CIPHER(Cryptographic Insecurity Profiling via Hybrid Evaluation of Responses), a benchmark for measuring cryptographic vulnerability incidence in LLM-generated Python code under controlled security-guidance conditions. CIPHER uses insecure/neutral/secure prompt variants per task, a cryptography-specific vulnerability taxonomy, and line-level attribution via an automated scoring pipeline. Across a diverse set of widely used LLMs, we find that explicit secure prompting reduces some targeted issues but does not reliably eliminate cryptographic vulnerabilities overall. The benchmark and reproducible scoring pipeline will be publicly released upon publication.

---

### Theoretical Analysis of Measure Consistency Regularization for Partially Observed Data

Authors: Yinsong Wang, Shahin Shahrampour
Published: 2026-02-01
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.01437v2

The problem of corrupted data, missing features, or missing modalities continues to plague the modern machine learning landscape. To address this issue, a class of regularization methods that enforce consistency between imputed and fully observed data has emerged as a promising approach for improving model generalization, particularly in partially observed settings. We refer to this class of methods as Measure Consistency Regularization (MCR). Despite its empirical success in various applications, such as image inpainting, data imputation and semi-supervised learning, a fundamental understanding of the theoretical underpinnings of MCR remains limited. This paper bridges this gap by offering theoretical insights into when MCR yields a more favorable finite-sample estimation-error upper bound, viewed through the lens of neural network distance. Under ideal interpolation and compatibility conditions, we show that the MCR estimation-error upper bound is no larger than vanilla supervised training and becomes strictly smaller when the mixed-sample alternative is favorable. We then extend the analysis to the non-ideal regime, where optimization and compatibility residuals can potentially offset this finite-sample advantage. Guided by these insights, we propose a novel practical diagnostic that leverages the duality gap and a calibrated drift estimator to infer the potential benefit of MCR training. We present detailed empirical evidence to support our theoretical claims and to show the effectiveness and accuracy of our practical diagnostic. We further provide simulations on real-world datasets to show the versatility of MCR under different model architectures designed for different data sources.

---

### Theoretical Analysis of Measure Consistency Regularization for Partially Observed Data

Authors: Yinsong Wang, Shahin Shahrampour
Published: 2026-02-01
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.01437v1

The problem of corrupted data, missing features, or missing modalities continues to plague the modern machine learning landscape. To address this issue, a class of regularization methods that enforce consistency between imputed and fully observed data has emerged as a promising approach for improving model generalization, particularly in partially observed settings. We refer to this class of methods as Measure Consistency Regularization (MCR). Despite its empirical success in various applications, such as image inpainting, data imputation and semi-supervised learning, a fundamental understanding of the theoretical underpinnings of MCR remains limited. This paper bridges this gap by offering theoretical insights into why, when, and how MCR enhances imputation quality under partial observability, viewed through the lens of neural network distance. Our theoretical analysis identifies the term responsible for MCR's generalization advantage and extends to the imperfect training regime, demonstrating that this advantage is not always guaranteed. Guided by these insights, we propose a novel training protocol that monitors the duality gap to determine an early stopping point that preserves the generalization benefit. We then provide detailed empirical evidence to support our theoretical claims and to show the effectiveness and accuracy of our proposed stopping condition. We further provide a set of real-world data simulations to show the versatility of MCR under different model architectures designed for different data sources.

---

### BioTamperNet: Affinity-Guided State-Space Model Detecting Tampered Biomedical Images

Authors: Soumyaroop Nandi, Prem Natarajan
Published: 2026-02-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.01435v2

We propose BioTamperNet, a novel framework for detecting duplicated regions in tampered biomedical images, leveraging affinity-guided attention inspired by State Space Model (SSM) approximations. Existing forensic models, primarily trained on natural images, often underperform on biomedical data where subtle manipulations can compromise experimental validity. To address this, BioTamperNet introduces an affinity-guided self-attention module to capture intra-image similarities and an affinity-guided cross-attention module to model cross-image correspondences. Our design integrates lightweight SSM-inspired linear attention mechanisms to enable efficient, fine-grained localization. Trained end-to-end, BioTamperNet simultaneously identifies tampered regions and their source counterparts. Extensive experiments on the benchmark bio-forensic datasets demonstrate significant improvements over competitive baselines in accurately detecting duplicated regions. Code - https://github.com/SoumyaroopNandi/BioTamperNet

---

### Phase Transitions for Feature Learning in Neural Networks

Authors: Andrea Montanari, Zihao Wang
Published: 2026-02-01
Categories: cs.LG, math.ST
arXiv: https://arxiv.org/abs/2602.01434v2

According to a popular viewpoint, neural networks learn from data by first identifying low-dimensional representations, and subsequently fitting the best model in this space. Recent works provide a formalization of this phenomenon when learning multi-index models. In this setting, we are given $n$ i.i.d. pairs $({\boldsymbol x}_i,y_i)$, where the covariate vectors ${\boldsymbol x}_i\in\mathbb{R}^d$ are isotropic, and responses $y_i$ only depend on ${\boldsymbol x}_i$ through a $k$-dimensional projection ${\boldsymbol Θ}_*^{\sf T}{\boldsymbol x}_i$. Feature learning amounts to learning the latent space spanned by ${\boldsymbol Θ}_*$. In this context, we study the gradient descent dynamics of two-layer neural networks under the proportional asymptotics $n,d\to\infty$, $n/d\toδ$, while the dimension of the latent space $k$ and the number of hidden neurons $m$ are kept fixed. Earlier work establishes that feature learning via polynomial-time algorithms is possible if $δ> δ_{\text{alg}}$, for $δ_{\text{alg}}$ a threshold depending on the data distribution, and is impossible (within a certain class of algorithms) below $δ_{\text{alg}}$. Here we derive an analogous threshold $δ_{\text{NN}}$ for two-layer networks. Our characterization of $δ_{\text{NN}}$ opens the way to study the dependence of learning dynamics on the network architecture and training algorithm. The threshold $δ_{\text{NN}}$ is determined by the following scenario. Training first visits points for which the gradient of the empirical risk is large and learns the directions spanned by these gradients. Then the gradient becomes smaller and the dynamics becomes dominated by negative directions of the Hessian. The threshold $δ_{\text{NN}}$ corresponds to a phase transition in the spectrum of the Hessian in this second phase.

---

### DCD: Decomposition-based Causal Discovery from Autocorrelated and Non-Stationary Temporal Data

Authors: Muhammad Hasan Ferdous, Md Osman Gani
Published: 2026-02-01
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2602.01433v2

Multivariate time series in domains such as finance, climate science, and healthcare often exhibit long-term trends, seasonal patterns, and short-term fluctuations, complicating causal inference under non-stationarity and autocorrelation. Existing causal discovery methods typically operate on raw observations, making them vulnerable to spurious edges and misattributed temporal dependencies. We introduce a decomposition-based causal discovery framework that separates each time series into trend, seasonal, and residual components and performs component-specific causal analysis. Trend components are assessed using stationarity tests, seasonal components using kernel-based dependence measures, and residual components using constraint-based causal discovery. The resulting component-level graphs are integrated into a unified multi-scale causal structure. This approach isolates long- and short-range causal effects, reduces spurious associations, and improves interpretability. Across extensive synthetic benchmarks and real-world climate data, our framework more accurately recovers ground-truth causal structure than state-of-the-art baselines, particularly under strong non-stationarity and temporal autocorrelation.

---

### Improving the Trade-off Between Watermark Strength and Speculative Sampling Efficiency for Language Models

Authors: Weiqing He, Xiang Li, Li Shen, Weijie Su, Qi Long
Published: 2026-02-01
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2602.01428v2

Watermarking is a principled approach for tracing the provenance of large language model (LLM) outputs, but its deployment in practice is hindered by inference inefficiency. Speculative sampling accelerates inference, with efficiency improving as the acceptance rate between draft and target models increases. Yet recent work reveals a fundamental trade-off: higher watermark strength reduces acceptance, preventing their simultaneous achievement. We revisit this trade-off and show it is not absolute. We introduce a quantitative measure of watermark strength that governs statistical detectability and is maximized when tokens are deterministic functions of pseudorandom numbers. Using this measure, we fully characterize the trade-off as a constrained optimization problem and derive explicit Pareto curves for two existing watermarking schemes. Finally, we introduce a principled mechanism that injects pseudorandomness into draft-token acceptance, ensuring maximal watermark strength while maintaining speculative sampling efficiency. Experiments further show that this approach improves detectability without sacrificing efficiency. Our findings uncover a principle that unites speculative sampling and watermarking, paving the way for their efficient and practical deployment.

---

### Robust Generalization with Adaptive Optimal Transport Priors for Decision-Focused Learning

Authors: Haixiang Sun, Andrew L. Liu
Published: 2026-02-01
Categories: stat.ML, cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2602.01427v2

Few-shot learning requires models to generalize under limited supervision while remaining robust to distribution shifts. Existing Sinkhorn Distributionally Robust Optimization (DRO) methods provide theoretical guarantees but rely on a fixed reference distribution, which limits their adaptability. We propose a Prototype-Guided Distributionally Robust Optimization (PG-DRO) framework that learns class-adaptive priors from abundant base data via hierarchical optimal transport and embeds them into the Sinkhorn DRO formulation. This design enables few-shot information to be organically integrated into producing class-specific robust decisions that are both theoretically grounded and efficient, and further aligns the uncertainty set with transferable structural knowledge. Experiments show that PG-DRO achieves stronger robust generalization in few-shot scenarios, outperforming both standard learners and DRO baselines.

---

### One Probe Won't Catch Them All: Towards Targeted Deception Detection

Authors: Vikram Natarajan, Devina Jain, Shivam Arora, Satvik Golechha, Joseph Bloom
Published: 2026-02-01
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.01425v2

Linear probes are a promising approach for monitoring AI systems for deceptive behaviour. Previous work has shown that a linear classifier trained on a contrastive instruction pair and a simple dataset can achieve good performance. However, these probes exhibit notable failures even in straightforward scenarios, including spurious correlations and false positives on non-deceptive responses. In this paper, we demonstrate that deception detection is inherently heterogeneous: while a single universal probe achieves modest improvements (+0.032 AUC), post-hoc oracle analysis reveals substantially higher potential (+0.108 AUC) when probes are matched to specific deception types, and synthetic validation experiments suggest this ceiling is achievable a priori when the deception type is known in advance. Our findings reveal that instruction pairs capture deceptive intent rather than content-specific patterns, explaining why prompt choice dominates probe performance (70.6% of variance). Given this heterogeneity, we conclude that organizations should define their specific threat models and deploy appropriately matched probes rather than seeking a universal deception detector.

---

### Semi-supervised CAPP Transformer Learning via Pseudo-labeling

Authors: Dennis Gross, Helge Spieker, Arnaud Gotlieb, Emmanuel Stathatos, Panorios Benardos, George-Christopher Vosniakos
Published: 2026-02-01
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.01419v2

High-level Computer-Aided Process Planning (CAPP) generates manufacturing process plans from part specifications. It suffers from limited dataset availability in industry, reducing model generalization. We propose a semi-supervised learning approach to improve transformer-based CAPP transformer models without manual labeling. An oracle, trained on available transformer behaviour data, filters correct predictions from unseen parts, which are then used for one-shot retraining. Experiments on small-scale datasets with simulated ground truth across the full data distribution show consistent accuracy gains over baselines, demonstrating the method's effectiveness in data-scarce manufacturing environments.

---

### Semi-supervised CAPP Transformer Learning via Pseudo-labeling

Authors: Dennis Gross, Helge Spieker, Arnaud Gotlieb, Emmanuel Stathatos, Panorios Benardos, George-Christopher Vosniakos
Published: 2026-02-01
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.01419v1

High-level Computer-Aided Process Planning (CAPP) generates manufacturing process plans from part specifications. It suffers from limited dataset availability in industry, reducing model generalization. We propose a semi-supervised learning approach to improve transformer-based CAPP transformer models without manual labeling. An oracle, trained on available transformer behaviour data, filters correct predictions from unseen parts, which are then used for one-shot retraining. Experiments on small-scale datasets with simulated ground truth across the full data distribution show consistent accuracy gains over baselines, demonstrating the method's effectiveness in data-scarce manufacturing environments.

---

### Parabolic Position Encoding: Vision-Centric, Principled, Extrapolatable, General

Authors: Christoffer Koo Øhrstrøm, Rafael I. Cabral Muchacho, Yifei Dong, Filippos Moumtzidellis, Ronja Güldenring, Florian T. Pokorny, Lazaros Nalpantidis
Published: 2026-02-01
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.01418v2

We propose Parabolic Position Encoding (PaPE), a parabola-based position encoding for vision modalities in attention-based architectures. Given a set of vision tokens-such as from videos, event camera streams, images, or point clouds-our objective is to encode their positions while accounting for the characteristics of vision modalities. Prior works have largely extended position encodings from 1D-sequences in language to nD-structures in vision, but only with partial account of vision characteristics. We address this gap by designing PaPE from principles distilled from prior work: translation invariance, rotation invariance (PaPE-RI), distance decay, directionality, and context awareness. Extrapolation experiments on ImageNet-1K show how PaPE extrapolates remarkably well, improving in absolute terms by up to 10.5\% over the next-best encoding. Generality experiments on 8 datasets across 4 modalities show that PaPE is a general vision position encoding, as PaPE matches the best baseline on 5 datasets and exceeds all on 2 datasets. Code is available at https://github.com/DTU-PAS/parabolic-position-encoding.

---

### Importance Weighted Variational Inference without the Reparameterization Trick

Authors: Kamélia Daudel, Minh-Ngoc Tran, Cheng Zhang
Published: 2026-02-01
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.01412v1

Importance weighted variational inference (VI) approximates densities known up to a normalizing constant by optimizing bounds that tighten with the number of Monte Carlo samples $N$. Standard optimization relies on reparameterized gradient estimators, which are well-studied theoretically yet restrict both the choice of the data-generating process and the variational approximation. While REINFORCE gradient estimators do not suffer from such restrictions, they lack rigorous theoretical justification. In this paper, we provide the first comprehensive analysis of REINFORCE gradient estimators in importance weighted VI, leveraging this theoretical foundation to diagnose and resolve fundamental deficiencies in current state-of-the-art estimators. Specifically, we introduce and examine a generalized family of variational inference for Monte Carlo objectives (VIMCO) gradient estimators. We prove that state-of-the-art VIMCO gradient estimators exhibit a vanishing signal-to-noise ratio (SNR) as $N$ increases, which prevents effective optimization. To overcome this issue, we propose the novel VIMCO-$\star$ gradient estimator and show that it averts the SNR collapse of existing VIMCO gradient estimators by achieving a $\sqrt{N}$ SNR scaling instead. We demonstrate its superior empirical performance compared to current VIMCO implementations in challenging settings where reparameterized gradients are typically unavailable.

---

### SNIP: An Adaptive Mixed Precision Framework for Subbyte Large Language Model Training

Authors: Yunjie Pan, Yongyi Yang, Hanmei Yang, Scott Mahlke
Published: 2026-02-01
Categories: cs.LG, cs.AR
arXiv: https://arxiv.org/abs/2602.01410v1

Training large language models (LLMs) efficiently while preserving model quality poses significant challenges, particularly with subbyte precision supported by state-of-the-art GPUs. Current mixed-precision training approaches either apply uniform precision to all GEMM operations or rely on heuristic-based methods that fail to generalize during training, leading to suboptimal convergence and instability. To address these challenges, this paper introduces SNIP, a fine-grained adaptive mixed-precision training framework for LLM pretraining that supports subbyte precision. SNIP periodically collects statistics on activations, gradients, and optimizer states to assess the precision loss impact on model quality. We define two key metrics: loss divergence in the forward pass, caused by quantization-induced increases in training loss, and weight divergence in the backward pass, which measures error propagation through gradients affecting model updates. These metrics guide an Integer Linear Programming (ILP) problem that systematically optimizes layerwise precision to minimize overall quality loss while meeting efficiency targets. Experiments on 1B, 3B, 7B and 70B Llama-like models demonstrate that SNIP consistently outperforms existing baselines, reducing FLOPs by up to 80% while preserving model quality across different model sizes and training phases with minimal computational overhead.

---

### From Pragmas to Partners: A Symbiotic Evolution of Agentic High-Level Synthesis

Authors: Niansong Zhang, Sunwoo Kim, Shreesha Srinath, Zhiru Zhang
Published: 2026-02-01
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.01401v3

The rise of large language models has sparked interest in AI-driven hardware design, raising the question: does high-level synthesis (HLS) still matter in the agentic era? We argue that HLS remains essential. While we expect mature agentic hardware systems to leverage both HLS and RTL, this paper focuses on HLS and its role in enabling agentic optimization. HLS offers faster iteration cycles, portability, and design permutability that make it a natural layer for agentic optimization. This position paper makes three contributions. First, we explain why HLS serves as a practical abstraction layer and a golden reference for agentic hardware design. Second, we identify key limitations of current HLS tools, namely inadequate performance feedback, rigid interfaces, and limited debuggability that agents are uniquely positioned to address. Third, we propose a taxonomy for the symbiotic evolution of agentic HLS, clarifying how responsibility shifts from human designers to AI agents as systems advance from copilots to autonomous design partners.

---

### Online Social Welfare Function-based Resource Allocation

Authors: Kanad Pardeshi, Samsara Foubert, Aarti Singh
Published: 2026-02-01
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.01400v1

In many real-world settings, a centralized decision-maker must repeatedly allocate finite resources to a population over multiple time steps. Individuals who receive a resource derive some stochastic utility; to characterize the population-level effects of an allocation, the expected individual utilities are then aggregated using a social welfare function (SWF). We formalize this setting and present a general confidence sequence framework for SWF-based online learning and inference, valid for any monotonic, concave, and Lipschitz-continuous SWF. Our key insight is that monotonicity alone suffices to lift confidence sequences from individual utilities to anytime-valid bounds on optimal welfare. Building on this foundation, we propose SWF-UCB, a SWF-agnostic online learning algorithm that achieves near-optimal $\tilde{O}(n+\sqrt{nkT})$ regret (for $k$ resources distributed among $n$ individuals at each of $T$ time steps). We instantiate our framework on three normatively distinct SWF families: Weighted Power Mean, Kolm, and Gini, providing bespoke oracle algorithms for each. Experiments confirm $\sqrt{T}$ scaling and reveal rich interactions between $k$ and SWF parameters. This framework naturally supports inference applications such as sequential hypothesis testing, optimal stopping, and policy evaluation.

---

### An Odd Estimator for Shapley Values

Authors: Fabian Fumagalli, Landon Butler, Justin Singh Kang, Kannan Ramchandran, R. Teal Witter
Published: 2026-02-01
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2602.01399v2

The Shapley value is a ubiquitous framework for attribution in machine learning, encompassing feature importance, data valuation, and causal inference. However, its exact computation is generally intractable, necessitating efficient approximation methods. While the most effective and popular estimators leverage the paired sampling heuristic to reduce estimation error, the theoretical mechanism driving this improvement has remained opaque. In this work, we provide an elegant and fundamental justification for paired sampling: we prove that the Shapley value depends exclusively on the odd component of the set function, and that paired sampling orthogonalizes the regression objective to filter out the irrelevant even component. Leveraging this insight, we propose OddSHAP, a novel consistent estimator that performs polynomial regression solely on the odd subspace. By utilizing the Fourier basis to isolate this subspace and employing a proxy model to identify high-impact interactions, OddSHAP overcomes the combinatorial explosion of higher-order approximations. Through an extensive benchmark, we find that OddSHAP achieves state-of-the-art estimation accuracy at larger sampling budgets.

---

### Nonlinear model reduction for transport-dominated problems

Authors: Jan S. Hesthaven, Benjamin Peherstorfer, Benjamin Unger
Published: 2026-02-01
Categories: math.NA, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2602.01397v1

This article surveys nonlinear model reduction methods that remain effective in regimes where linear reduced-space approximations are intrinsically inefficient, such as transport-dominated problems with wave-like phenomena and moving coherent structures, which are commonly associated with the Kolmogorov barrier. The article organizes nonlinear model reduction techniques around three key elements -- nonlinear parametrizations, reduced dynamics, and online solvers -- and categorizes existing approaches into transformation-based methods, online adaptive techniques, and formulations that combine generic nonlinear parametrizations with instantaneous residual minimization.

---

### Rethinking Selective Knowledge Distillation

Authors: Almog Tavor, Itay Ebenspanger, Neil Cnaan, Mor Geva
Published: 2026-02-01
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.01395v1

Growing efforts to improve knowledge distillation (KD) in large language models (LLMs) replace dense teacher supervision with selective distillation, which uses a subset of token positions, vocabulary classes, or training samples for supervision. However, it remains unclear which importance signals, selection policies, and their interplay are most effective. In this work, we revisit where and how to distill in autoregressive LLMs. We disentangle selective KD along the position, class, and sample axes and systematically compare importance signals and selection policies. Then, guided by this analysis, we identify underexplored opportunities and introduce student-entropy-guided position selection (SE-KD). Across a suite of benchmarks, SE-KD often improves accuracy, downstream task adherence, and memory efficiency over dense distillation. Extending this approach across the class and sample axes (SE-KD 3X) yields complementary efficiency gains that make offline teacher caching feasible. In practice, this reduces wall time by 70% and peak memory by 18%, while cutting storage usage by 80% over prior methods without sacrificing performance.

---

### SSNAPS: Audio-Visual Separation of Speech and Background Noise with Diffusion Inverse Sampling

Authors: Yochai Yemini, Yoav Ellinson, Rami Ben-Ari, Sharon Gannot, Ethan Fetaya
Published: 2026-02-01
Categories: eess.AS, cs.LG, cs.SD
arXiv: https://arxiv.org/abs/2602.01394v2

This paper addresses the challenge of audio-visual single-microphone speech separation and enhancement in the presence of real-world environmental noise. Our approach is based on generative inverse sampling, where we model clean speech and ambient noise with dedicated diffusion priors and jointly leverage them to recover all underlying sources. To achieve this, reformulate a recent inverse sampler to match our setting. We evaluate on mixtures of 1, 2, and 3 speakers with noise and show that, despite being entirely unsupervised, our method consistently outperforms leading supervised baselines in WER across all conditions. We further extend our framework to handle off-screen speaker separation. Moreover, the high fidelity of the separated noise component makes it suitable for downstream detection of the acoustic scene. Code and pretrained models will become available upon acceptance. Demo page: https://ssnaps2026.github.io/ssnaps2026/

---

### Relighting as a Probe of Visual Priors via Augmented Latent Intrinsics

Authors: Xiaoyan Xing, Xiao Zhang, Sezer Karaoglu, Theo Gevers, Anand Bhattad
Published: 2026-02-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.01391v2

Image-to-image relighting requires representations that separate illumination from scene properties while preserving dense geometry, material, and photometric cues. We use this task as a probe of visual priors: unlike recognition tasks that reward invariance, relighting tests whether visual features retain the information needed for light transfer. Through a controlled generative relighting framework, we find that strong semantic encoders can degrade relighting quality, exposing a semantic--photometric trade-off between abstraction and physical fidelity. We introduce Augmented Latent Intrinsics (ALI), which balances this trade-off by fusing dense, pixel-aligned visual features into a latent-intrinsic relighting model and refining it with self-supervision on unlabeled real image pairs. ALI improves relighting quality, especially on glossy, metallic, and transparent materials, and demonstrates that generative relighting is an effective tool for quantifying what visual encoders encode about the physical world.

---