# Research Papers — 2026-02 · bundle page 157 of 210

> Full-text markdown of papers #7801–7850 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/157
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/156.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/158.md)

### The Story is Not the Science: Execution-Grounded Evaluation of Mechanistic Interpretability Research

Authors: Xiaoyan Bai, Alexander Baumgartner, Haojia Sun, Ari Holtzman, Chenhao Tan
Published: 2026-02-05
Categories: cs.CY, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.18458v1

Reproducibility crises across sciences highlight the limitations of the paper-centric review system in assessing the rigor and reproducibility of research. AI agents that autonomously design and generate large volumes of research outputs exacerbate these challenges. In this work, we address the growing challenges of scalability and rigor by flipping the dynamic and developing AI agents as research evaluators. We propose the first execution-grounded evaluation framework that verifies research beyond narrative review by examining code and data alongside the paper. We use mechanistic interpretability research as a testbed, build standardized research output, and develop MechEvalAgent, an automated evaluation framework that assesses the coherence of the experimental process, the reproducibility of results, and the generalizability of findings. We show that our framework achieves above 80% agreement with human judges, identifies substantial methodological problems, and surfaces 51 additional issues that human reviewers miss. Our work demonstrates the potential of AI agents to transform research evaluation and pave the way for rigorous scientific practices.

---

### Beyond single-channel agentic benchmarking

Authors: Nelu D. Radpour
Published: 2026-02-05
Categories: cs.CY, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2602.18456v1

Contemporary benchmarks for agentic artificial intelligence (AI) frequently evaluate safety through isolated task-level accuracy thresholds, implicitly treating autonomous systems as single points of failure. This single-channel paradigm diverges from established principles in safety-critical engineering, where risk mitigation is achieved through redundancy, diversity of error modes, and joint system reliability. This paper argues that evaluating AI agents in isolation systematically mischaracterizes their operational safety when deployed within human-in-the-loop environments. Using a recent laboratory safety benchmark as a case study demonstrates that even imperfect AI systems can nonetheless provide substantial safety utility by functioning as redundant audit layers against well-documented sources of human failure, including vigilance decrement, inattentional blindness, and normalization of deviance. This perspective reframes agentic safety evaluation around the reliability of the human-AI dyad rather than absolute agent accuracy, with a particular emphasis on uncorrelated error modes as the primary determinant of risk reduction. Such a shift aligns AI benchmarking with established practices in other safety-critical domains and offers a path toward more ecologically valid safety assessments.

---

### Impact of AI Search Summaries on Website Traffic: Evidence from Google AI Overviews and Wikipedia

Authors: Mehrzad Khosravi, Hema Yoganarasimhan
Published: 2026-02-05
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2602.18455v6

Search engines increasingly display AI-generated answers above organic links, potentially displacing traffic to upstream publishers. We estimate the impact of Google's AI Overviews (AIO) on Wikipedia's search traffic using AIO's staggered geographic rollout and Wikipedia's multilingual structure. Our difference-in-differences design compares monthly external-search referrals to English Wikipedia articles with referrals to the same articles in German and French, and finds that default AIO availability reduced English search traffic by 5.45% and 4.82%, respectively. Our results suggest that answer-producing digital intermediaries can materially reallocate attention away from informational publishers, with implications for content monetization, search platform design, and policy.

---

### Impact of AI Search Summaries on Website Traffic: Evidence from Google AI Overviews and Wikipedia

Authors: Mehrzad Khosravi, Hema Yoganarasimhan
Published: 2026-02-05
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2602.18455v4

Search engines increasingly display LLM-generated answers shown above organic links, shifting search from link lists to answer-first summaries. Publishers contend these summaries substitute for source pages and cannibalize traffic, while platforms argue they are complementary by directing users through included links. We estimate the causal impact of Google's AI Overview (AIO) on Wikipedia traffic by leveraging the feature's staggered geographic rollout and Wikipedia's multilingual structure. Using a difference-in-differences design, we compare English Wikipedia articles exposed to AIO to the same underlying articles in language editions (Hindi, Indonesian, Japanese, and Portuguese) that were not exposed to AIO during the observation period. Across 161,382 matched article-language pairs, AIO exposure reduces daily traffic to English articles by approximately 15%. Effects are heterogeneous: relative declines are largest for Culture articles and substantially smaller for STEM, consistent with stronger substitution when short synthesized answers satisfy informational intent. These findings provide early causal evidence that generative-answer features in search engines can materially reallocate attention away from informational publishers, with implications for content monetization, search platform design, and policy.

---

### AnCoder: Anchored Code Generation via Discrete Diffusion Models

Authors: Anton Xue, Litu Rout, Constantine Caramanis, Sanjay Shakkottai
Published: 2026-02-05
Categories: cs.LG, cs.PL
arXiv: https://arxiv.org/abs/2602.17688v1

Diffusion language models offer a compelling alternative to autoregressive code generation, enabling global planning and iterative refinement of complex program logic. However, existing approaches fail to respect the rigid structure of programming languages and, as a result, often produce broken programs that fail to execute. To address this, we introduce AnchorTree, a framework that explicitly anchors the diffusion process using structured, hierarchical priors native to code. Specifically, AnchorTree uses the abstract syntax tree to prioritize resolving syntactically and semantically salient tokens, such as keywords (e.g., if, while) and identifiers (e.g., variable names), thereby establishing a structural scaffold that guides the remaining generation. We validate this framework via AnCoder, a family of models showing that structurally anchored diffusion offers a parameter-efficient path to high-quality code generation.

---

### IRPAPERS: A Visual Document Benchmark for Scientific Retrieval and Question Answering

Authors: Connor Shorten, Augustas Skaburskas, Daniel M. Jones, Charles Pierse, Roberto Esposito, John Trengrove, Etienne Dilocker, Bob van Luijt
Published: 2026-02-05
Categories: cs.IR, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.17687v1

AI systems have achieved remarkable success in processing text and relational data, yet visual document processing remains relatively underexplored. Whereas traditional systems require OCR transcriptions to convert these visual documents into text and metadata, recent advances in multimodal foundation models offer retrieval and generation directly from document images. This raises a key question: How do image-based systems compare to established text-based methods? We introduce IRPAPERS, a benchmark of 3,230 pages from 166 scientific papers, with both an image and an OCR transcription for each page. Using 180 needle-in-the-haystack questions, we compare image- and text-based retrieval and question answering systems. Text retrieval using Arctic 2.0 embeddings, BM25, and hybrid text search achieved 46% Recall@1, 78% Recall@5, and 91% Recall@20, while image-based retrieval reaches 43%, 78%, and 93%, respectively. The two modalities exhibit complementary failures, enabling multimodal hybrid search to outperform either alone, achieving 49% Recall@1, 81% Recall@5, and 95% Recall@20. We further evaluate efficiency-performance tradeoffs with MUVERA and assess multiple multi-vector image embedding models. Among closed-source models, Cohere Embed v4 page image embeddings outperform Voyage 3 Large text embeddings and all tested open-source models, achieving 58% Recall@1, 87% Recall@5, and 97% Recall@20. For question answering, text-based RAG systems achieved higher ground-truth alignment than image-based systems (0.82 vs. 0.71), and both benefit substantially from increased retrieval depth, with multi-document retrieval outperforming oracle single-document retrieval. We analyze the complementary limitations of unimodal text and image representations and identify question types that require one modality over the other. The IRPAPERS dataset and all experimental code are publicly available.

---

### BRIDGE: Bridging Reasoning In Distillation Gap Elimination via Structure-Aware Masking

Authors: Bowen Yu, Sheng Zhang, Binhao Wang, Yi Wen, Jingtong Gao, Bowen Liu, Zimo Zhao, Shanshan Ye, Wanyu Wang, Maolin Wang, Xiangyu Zhao
Published: 2026-02-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.17686v6

Chain-of-Thought (CoT) reasoning has significantly improved LLMs' mathematical problem-solving capabilities, but distilling such capabilities into smaller models remains challenging due to the capacity mismatch between verbose teachers and compact students. Directly copying teachers' lengthy reasoning chains causes capacity overload, resulting in truncated outputs or repetitive failure. Existing remedies each sacrifice a critical property of CoT: implicit reasoning methods (e.g., compressing reasoning into hidden states) trade away interpretability and verifiability, while heuristic compression strategies (e.g., random step pruning) destroy logical integrity. To address this, we propose BRIDGE, a curriculum framework that first establishes structural understanding via masked reconstruction, then uses GRPO-based reinforcement learning to guide students in self-discovering the optimal balance between accuracy and brevity, and finally internalizes complex reasoning through teacher-guided rewriting on failure cases. On GSM8K, BRIDGE enables Qwen2.5-3B to achieve 11.29% accuracy improvement and 27.4% token reduction over the original model, outperforming instruction-tuned variants and distillation baselines. Zero-shot transfer experiments on SVAMP and MATH-500 further confirm the generalization of internalized reasoning. Our code and model checkpoints are publicly available at https://github.com/Applied-Machine-Learning-Lab/SDM2026_BRIDGE and https://huggingface.co/bowen0815/BRIDGE.

---

### BRIDGE: Bridging Reasoning In Distillation Gap Elimination via Structure-Aware Masking

Authors: Bowen Yu, Sheng Zhang, Binhao Wang, Yi Wen, Jingtong Gao, Bowen Liu, Zimo Zhao, Shanshan Ye, Wanyu Wang, Maolin Wang, Xiangyu Zhao
Published: 2026-02-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.17686v5

Chain-of-Thought (CoT) reasoning has significantly improved LLMs' mathematical problem-solving capabilities, but distilling such capabilities into smaller models remains challenging due to the capacity mismatch between verbose teachers and compact students. Directly copying teachers' lengthy reasoning chains causes capacity overload, resulting in truncated outputs or repetitive failure. Existing remedies each sacrifice a critical property of CoT: implicit reasoning methods (e.g., compressing reasoning into hidden states) trade away interpretability and verifiability, while heuristic compression strategies (e.g., random step pruning) destroy logical integrity. To address this, we propose BRIDGE, a curriculum framework that first establishes structural understanding via masked reconstruction, then uses GRPO-based reinforcement learning to guide students in self-discovering the optimal balance between accuracy and brevity, and finally internalizes complex reasoning through teacher-guided rewriting on failure cases. On GSM8K, BRIDGE enables Qwen2.5-3B to achieve 11.29% accuracy improvement and 27.4% token reduction over the original model, outperforming instruction-tuned variants and distillation baselines. Zero-shot transfer experiments on SVAMP and MATH-500 further confirm the generalization of internalized reasoning. Our code and model checkpoints are publicly available at https://github.com/Applied-Machine-Learning-Lab/SDM2026_BRIDGE and https://huggingface.co/bowen0815/BRIDGE.

---

### Distributed physics-informed neural networks via domain decomposition for fast flow reconstruction

Authors: Yixiao Qian, Jiaxu Liu, Zewei Xia, Song Chen, Chao Xu, Shengze Cai
Published: 2026-02-05
Categories: cs.LG, physics.flu-dyn
arXiv: https://arxiv.org/abs/2602.15883v1

Physics-Informed Neural Networks (PINNs) offer a powerful paradigm for flow reconstruction, seamlessly integrating sparse velocity measurements with the governing Navier-Stokes equations to recover complete velocity and latent pressure fields. However, scaling such models to large spatiotemporal domains is hindered by computational bottlenecks and optimization instabilities. In this work, we propose a robust distributed PINNs framework designed for efficient flow reconstruction via spatiotemporal domain decomposition. A critical challenge in such distributed solvers is pressure indeterminacy, where independent sub-networks drift into inconsistent local pressure baselines. We address this issue through a reference anchor normalization strategy coupled with decoupled asymmetric weighting. By enforcing a unidirectional information flow from designated master ranks where the anchor point lies to neighboring ranks, our approach eliminates gauge freedom and guarantees global pressure uniqueness while preserving temporal continuity. Furthermore, to mitigate the Python interpreter overhead associated with computing high-order physics residuals, we implement a high-performance training pipeline accelerated by CUDA graphs and JIT compilation. Extensive validation on complex flow benchmarks demonstrates that our method achieves near-linear strong scaling and high-fidelity reconstruction, establishing a scalable and physically rigorous pathway for flow reconstruction and understanding of complex hydrodynamics.

---

### PACT-WAM: Predicting Actions and Visual Foresight with Compact Temporal Encoding for Robot Manipulation

Authors: Yushan Liu, Jingjing Fan, Shoujie Li, Yifan Xie, Xiao-Ping Zhang, Wenbo Ding
Published: 2026-02-05
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2602.15882v2

Robot manipulation uses temporal context to select actions and visual foresight to assess their consequences, yet dense representations of past and future observations incur substantial processing costs. We introduce PACT-WAM, a world-action model that jointly generates a 16-step action trajectory and its temporally corresponding visual forecast through conditional flow sampling. Hierarchical history encoding assigns coarse spatial representations to earlier observations and finer representations to recent ones, retaining 16 observations with 256 tokens per view, 75% fewer than dense encoding of the same frames. A shared flow module jointly updates continuous action and visual states through two modality-specific heads under transition-wise causal attention, and a TiTok-VAE decoder reconstructs multi-view future images from the visual latents. Decoded forecasts also support Proposal Review (PR), a vision-language model component for execution-prefix selection and proposal rejection. Without PR, PACT-WAM achieves average success rates of 98.6%, 92.3%, and 78.0% on LIBERO, RoboTwin 2.0, and real-world Piper tasks, respectively. PR provides a test-time enhancement, raising these rates to 99.5%, 93.4%, and 86.7%. Ablations show that hierarchical history allocation and joint action-visual generation improve control success, while analyses of visual capacity and forecast-guided execution characterize the trade-offs between success and proposal-generation cost.

---

### FUTURE-VLA: Forecasting Unified Trajectories Under Real-time Execution

Authors: Jingjing Fan, Yushan Liu, Shoujie Li, Botao Ren, Siyuan Li, Xiao-Ping Zhang, Wenbo Ding, Zhidong Deng
Published: 2026-02-05
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2602.15882v1

General vision-language models increasingly support unified spatiotemporal reasoning over long video streams, yet deploying such capabilities on robots remains constrained by the prohibitive latency of processing long-horizon histories and generating high-dimensional future predictions. To bridge this gap, we present FUTURE-VLA, a unified architecture that reformulates long-horizon control and future forecasting as a monolithic sequence-generation task. Adopting a dual-sided efficiency paradigm, FUTURE-VLA leverages a temporally adaptive compression strategy to maximize spatiotemporal information density, enabling the ingestion of extensive multi-view histories while maintaining constant inference latency. Simultaneously, it performs latent-space autoregression to align actionable dynamics with reviewable visual look-aheads in a single forward pass. These real-time predictive capabilities further enable a prediction-guided Human-In-the-Loop mechanism via interactive execution gating, allowing operators to dynamically validate behaviors based on interpretable future previews. Extensive evaluations demonstrate that FUTURE-VLA establishes new state-of-the-art performance, attaining success rates of 99.2% on LIBERO, 75.4% on RoboTwin, and 78.0% on a real-world Piper platform, all with a $16\times$ extended spatiotemporal window while maintaining the inference latency of a single-frame baseline.

---

### VQ-DSC-R: Robust Vector Quantized-Enabled Digital Semantic Communication With OFDM Transmission

Authors: Jianqiao Chen, Nan Ma, Xiaodong Xu, Tingting Zhu, Huishi Song, Chen Dong, Wenkai Liu, Rui Meng, Ping Zhang
Published: 2026-02-05
Categories: cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2602.15045v1

Digital mapping of semantic features is essential for achieving interoperability between semantic communication and practical digital infrastructure. However, current research efforts predominantly concentrate on analog semantic communication with simplified channel models. To bridge these gaps, we develop a robust vector quantized-enabled digital semantic communication (VQ-DSC-R) system built upon orthogonal frequency division multiplexing (OFDM) transmission. Our work encompasses the framework design of VQ-DSC-R, followed by a comprehensive optimization study. Firstly, we design a Swin Transformer-based backbone for hierarchical semantic feature extraction, integrated with VQ modules that map the features into a shared semantic quantized codebook (SQC) for efficient index transmission. Secondly, we propose a differentiable vector quantization with adaptive noise-variance (ANDVQ) scheme to mitigate quantization errors in SQC, which dynamically adjusts the quantization process using K-nearest neighbor statistics, while exponential moving average mechanism stabilizes SQC training. Thirdly, for robust index transmission over multipath fading channel and noise, we develop a conditional diffusion model (CDM) to refine channel state information, and design an attention-based module to dynamically adapt to channel noise. The entire VQ-DSC-R system is optimized via a three-stage training strategy. Extensive experiments demonstrate superiority of VQ-DSC-R over benchmark schemes, achieving high compression ratios and robust performance in practical scenarios.

---

### Artificial Organisations

Authors: William Waites
Published: 2026-02-05
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.13275v1

Alignment research focuses on making individual AI systems reliable. Human institutions achieve reliable collective behaviour differently: they mitigate the risk posed by misaligned individuals through organisational structure. Multi-agent AI systems should follow this institutional model using compartmentalisation and adversarial review to achieve reliable outcomes through architectural design rather than assuming individual alignment. We demonstrate this approach through the Perseverance Composition Engine, a multi-agent system for document composition. The Composer drafts text, the Corroborator verifies factual substantiation with full source access, and the Critic evaluates argumentative quality without access to sources: information asymmetry enforced by system architecture. This creates layered verification: the Corroborator detects unsupported claims, whilst the Critic independently assesses coherence and completeness. Observations from 474 composition tasks (discrete cycles of drafting, verification, and evaluation) exhibit patterns consistent with the institutional hypothesis. When assigned impossible tasks requiring fabricated content, this iteration enabled progression from attempted fabrication toward honest refusal with alternative proposals--behaviour neither instructed nor individually incentivised. These findings motivate controlled investigation of whether architectural enforcement produces reliable outcomes from unreliable components. This positions organisational theory as a productive framework for multi-agent AI safety. By implementing verification and evaluation as structural properties enforced through information compartmentalisation, institutional design offers a route to reliable collective behaviour from unreliable individual components.

---

### ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs

Authors: Rohan Subramanian Thomas, Shikhar Shiromani, Abdullah Chaudhry, Ruizhe Li, Vasu Sharma, Kevin Zhu, Sunishchal Dev
Published: 2026-02-05
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.13274v1

Prompt design significantly impacts the moral competence and safety alignment of large language models (LLMs), yet empirical comparisons remain fragmented across datasets and models.We introduce ProMoral-Bench, a unified benchmark evaluating 11 prompting paradigms across four LLM families. Using ETHICS, Scruples, WildJailbreak, and our new robustness test, ETHICS-Contrast, we measure performance via our proposed Unified Moral Safety Score (UMSS), a metric balancing accuracy and safety. Our results show that compact, exemplar-guided scaffolds outperform complex multi-stage reasoning, providing higher UMSS scores and greater robustness at a lower token cost. While multi-turn reasoning proves fragile under perturbations, few-shot exemplars consistently enhance moral stability and jailbreak resistance. ProMoral-Bench establishes a standardized framework for principled, cost-effective prompt engineering.

---

### MergePipe: A Budget-Aware Parameter Management System for Scalable LLM Merging

Authors: Yuanyi Wang, Yanggan Gu, Zihao Wang, Kunxi Li, Yifan Yang, Zhaoyi Yan, Congkai Xie, Jianmin Wu, Hongxia Yang
Published: 2026-02-05
Categories: cs.DB, cs.AI, cs.DC
arXiv: https://arxiv.org/abs/2602.13273v1

Large language model (LLM) merging has become a key technique in modern LLM development pipelines, enabling the integration of multiple task- or domain-specific expert models without retraining. However, as the number of experts grows, existing merging implementations treat model parameters as unstructured files and execute merges in a stateless, one-shot manner, leading to excessive disk I/O, redundant parameter scans, and poor scalability. In this paper, we present \textbf{MergePipe}, a parameter management system for scalable LLM merging. MergePipe is the first system that treats LLM merging as a data management and execution problem, and introduces a catalog-driven abstraction over model parameters, merge plans, and execution lineage. At its core, MergePipe employs a cost-aware planner that explicitly models expert parameter I/O and enforces user-specified I/O budgets, followed by a streaming execution engine that materializes merged models under transactional guarantees. Our key insight is that while base model reads and output writes are unavoidable, expert parameter reads dominate merge cost and constitute the primary optimization target. By making expert access budget-aware throughout planning and execution, MergePipe mitigates the $O(K)$ I/O growth of naive pipelines and achieves predictable scaling behavior. Experiments show that MergePipe reduces total I/O by up to an order of magnitude and delivers up to $11\times$ end-to-end speedups (up to 90\% wall-time reduction) over state-of-the-art LLM merging pipelines.

---

### TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series Tasks

Authors: Muyan Weng, Defu Cao, Wei Yang, Yashaswi Sharma, Yan Liu
Published: 2026-02-05
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.13272v1

It is unclear whether strong forecasting performance reflects genuine temporal understanding or the ability to reason under contextual and event-driven conditions. We introduce TemporalBench, a multi-domain benchmark designed to evaluate temporal reasoning behavior under progressively richer informational settings. TemporalBench adopts a four-tier task taxonomy that examines historical structure interpretation, context-free forecasting, contextual temporal reasoning, and event-conditioned prediction across four real-world domains: retail, healthcare, energy, and physical systems. By controlling access to future targets and contextual information, the benchmark enables a diagnostic analysis of whether models can correctly interpret temporal patterns, align them with external context, and adapt predictions when conditions change. Extensive baseline experiments show that strong numerical forecasting accuracy does not reliably translate into robust contextual or event-aware temporal reasoning; instead, existing agent frameworks exhibit fragmented strengths and systematic failure modes that remain largely hidden under forecasting-only benchmarks. The TemporalBench dataset is publicly available at https://huggingface.co/datasets/Melady/TemporalBench, and we additionally provide a public leaderboard at https://huggingface.co/spaces/Melady/TemporalBench_Leaderboard.

---

### interwhen: A Generalizable Framework for Steering Reasoning Models with Test-time Verification

Authors: Vishak K Bhat, Prateek Chanda, Vijval Ekbote, Ashmit Khandelwal, Maitreyi Swaroop, Vineeth N. Balasubramanian, Subbarao Kambhampati, Nagarajan Natarajan, Amit Sharma
Published: 2026-02-05
Categories: cs.LO, cs.AI
arXiv: https://arxiv.org/abs/2602.11202v3

Reasoning models produce long traces of intermediate decisions and tool calls, making test-time verification important for ensuring correctness. Existing approaches either verify only the final answer, which misses early errors, or rely on branch-and-verify strategies that explore multiple trajectories. We introduce interwhen, a single-trajectory verification framework that steers model behavior by providing feedback on intermediate reasoning traces. It addresses two key challenges. First, given a set of verifiers, obtaining verifiable states from the reasoning trace typically requires prompt engineering or external task decomposition into fixed steps. Instead, we propose a monitoring system that periodically polls the reasoning trace and forks inference of the reasoning model to recover intermediate states. Verifiers are run asynchronously alongside generation, adding negligible overhead on correct executions and intervening only when violations occur. Second, beyond math and code, a central challenge for process verification is the scarcity of verifiers. interwhen addresses this through automatic verifier synthesis from natural-language policy documents. Given a policy, it can generate code-based verifiers, including provably correct verifiers in Lean and z3. Together, these contributions yield a plug-and-play test-time verification system that can improve task completion and policy compliance of any reasoning agent. On reasoning benchmarks where policies encode mathematical or logical constraints, interwhen achieves near-perfect accuracy for reasoning models using a fraction of the tokens of baselines. On agentic benchmarks with policy-based verifier generation, it enables improvements in task quality for SLMs without any finetuning, e.g., task completion rate of Qwen3-30B jumps from 32% to 87% on the telecom domain in tau2-bench. Code at https://github.com/microsoft/interwhen.

---

### TokaMark: A Comprehensive Benchmark for MAST Tokamak Plasma Models

Authors: Cécile Rousseau, Samuel Jackson, Rodrigo H. Ordonez-Hurtado, Nicola C. Amorisco, Tobia Boschi, George K. Holt, Andrea Loreti, Eszter Székely, Alexander Whittle, Adriano Agnello, Stanislas Pamela, Alessandra Pascale et al.
Published: 2026-02-05
Categories: physics.plasm-ph, cs.AI
arXiv: https://arxiv.org/abs/2602.10132v3

Development and operation of commercially viable fusion energy reactors such as tokamaks require accurate predictions of plasma dynamics from sparse, noisy, and incomplete sensors readings. The complexity of the underlying physics and the heterogeneity of experimental data pose formidable challenges for conventional numerical methods, and highlight the promise of modern data-native approaches. A major obstacle in realizing this potential is, however, the lack of curated, openly available datasets and standardized benchmarks. Existing fusion datasets are scarce, fragmented across institutions, facility-specific, and inconsistently annotated, which limits reproducibility and prevents a fair and scalable comparison of AI approaches. In this paper, we introduce TokaMark, a structured benchmark to evaluate AI models on real experimental data collected from the Mega Ampere Spherical Tokamak (MAST). TokaMark provides a comprehensive suite of tools designed to unify access to multi-modal fusion data and standardize evaluation protocols. The benchmark includes a curated list of 14 tasks spanning a range of physical mechanisms, exploiting a variety of diagnostics and covering multiple operational use cases. A baseline model is provided to facilitate transparent comparison and validation within a unified framework. By establishing a unified benchmark, TokaMark aims to accelerate progress in data-driven AI-based plasma modeling, contributing to the broader goal of achieving sustainable and stable fusion energy. The dataset, benchmark, documentation, and tooling are open-sourced under https://github.com/UKAEA-IBM-STFC-Fusion-FMs/tokamark_baseline.

---

### Artificial Intelligence in Open Source Software Engineering: A Foundation for Sustainability

Authors: S M Rakib UI Karim, Wenyi Lu, Sean Goggins
Published: 2026-02-05
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2602.07071v1

Open-source software (OSS) is foundational to modern digital infrastructure, yet this context for group work continues to struggle to ensure sufficient contributions in many critical cases. This literature review explores how artificial intelligence (AI) is being leveraged to address critical challenges to OSS sustainability, including maintaining contributor engagement, securing funding, ensuring code quality and security, fostering healthy community dynamics, and preventing project abandonment. Synthesizing recent interdisciplinary research, the paper identifies key applications of AI in this domain, including automated bug triaging, system maintenance, contributor onboarding and mentorship, community health analytics, vulnerability detection, and task automation. The review also examines the limitations and ethical concerns that arise from applying AI in OSS contexts, including data availability, bias and fairness, transparency, risks of misuse, and the preservation of human-centered values in collaborative development. By framing AI not as a replacement but as a tool to augment human infrastructure, this study highlights both the promise and pitfalls of AI-driven interventions. It concludes by identifying critical research gaps and proposing future directions at the intersection of AI, sustainability, and OSS, aiming to support more resilient and equitable open-source ecosystems.

---

### Hybrid Dual-Path Linear Transformations for Efficient Transformer Architectures

Authors: Vladimer Khasia
Published: 2026-02-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.07070v1

Standard Transformer architectures rely heavily on dense linear transformations, treating feature projection as a monolithic, full-rank operation. We argue that this formulation is inefficient and lacks the structural inductive bias necessary for distinguishing between local feature preservation and global context integration. To address this, we introduce the Hybrid Dual-Path Linear (HDPL) operator, which decomposes the affine transformation into two topologically distinct pathways: a sparse block-diagonal component for high-rank local processing, and a low-rank Variational Autoencoder (VAE) bottleneck for global context regularization. By "surgically" replacing specific projections (Query, Key, Value, Gate, Up) with HDPL operators while retaining standard dense layers for aggregation (Output, Down), we achieve a superior balance of efficiency and representational power. Experiments on the FineWeb-Edu dataset demonstrate that the HDPL architecture outperforms a standard Llama-style baseline, reducing validation loss while simultaneously reducing parameter count by 6.8%. Beyond immediate performance gains, we discuss how the explicit materialization of a probabilistic latent space within the Transformer backbone serves as a vital architectural affordance, offering new pathways for inference-time or hypernetwork induced control, continual adaptation, interpretability, and cross-model or cross-modal synchronization. The code is available at https://github.com/VladimerKhasia/HDPL

---

### Bird-SR: Bidirectional Reward-Guided Diffusion for Real-World Image Super-Resolution

Authors: Zihao Fan, Xin Lu, Yidi Liu, Jie Huang, Dong Li, Xueyang Fu, Baocai Yin
Published: 2026-02-05
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.07069v2

Powered by multimodal text-to-image priors, diffusion-based super-resolution excels at synthesizing intricate details; however, models trained on synthetic low-resolution (LR) and high-resolution (HR) image pairs often degrade when applied to real-world LR images due to significant distribution shifts. We propose Bird-SR, a bidirectional reward-guided diffusion framework that formulates super-resolution as trajectory-level preference optimization via reward feedback learning (ReFL), jointly leveraging synthetic LR-HR pairs and real-world LR images. For structural fidelity easily affected in ReFL, the model is directly optimized on synthetic pairs at early diffusion steps, which also facilitates structure preservation for real-world inputs under smaller distribution gap in structure levels. For perceptual enhancement, quality-guided rewards are applied to both synthetic and real LR images at the later trajectory phase. To mitigate reward hacking, the rewards for synthetic results are formulated in a relative advantage space bounded by their ground-truth counterparts, while real-world optimization is regularized via a semantic alignment constraint. Furthermore, to balance structural and perceptual learning, we introduce a dynamic fidelity-perception weighting strategy that emphasizes structure preservation at early stages and progressively shifts focus toward perceptual optimization at later diffusion steps. Extensive experiments on real-world SR benchmarks demonstrate that Bird-SR consistently outperforms state-of-the-art methods in perceptual quality while preserving structural consistency, validating its effectiveness for real-world super-resolution. Our code can be obtained at https://github.com/fanzh03/Bird-SR.

---

### MRI Cross-Modal Synthesis: A Comparative Study of Generative Models for T1-to-T2 Reconstruction

Authors: Ali Alqutayfi, Sadam Al-Azani
Published: 2026-02-05
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2602.07068v1

MRI cross-modal synthesis involves generating images from one acquisition protocol using another, offering considerable clinical value by reducing scan time while maintaining diagnostic information. This paper presents a comprehensive comparison of three state-of-the-art generative models for T1-to-T2 MRI reconstruction: Pix2Pix GAN, CycleGAN, and Variational Autoencoder (VAE). Using the BraTS 2020 dataset (11,439 training and 2,000 testing slices), we evaluate these models based on established metrics including Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index (SSIM). Our experiments demonstrate that all models can successfully synthesize T2 images from T1 inputs, with CycleGAN achieving the highest PSNR (32.28 dB) and SSIM (0.9008), while Pix2Pix GAN provides the lowest MSE (0.005846). The VAE, though showing lower quantitative performance (MSE: 0.006949, PSNR: 24.95 dB, SSIM: 0.6573), offers advantages in latent space representation and sampling capabilities. This comparative study provides valuable insights for researchers and clinicians selecting appropriate generative models for MRI synthesis applications based on their specific requirements and data constraints.

---

### Contactless estimation of continuum displacement and mechanical compressibility from image series using a deep learning based framework

Authors: A. N. Maria Antony, T. Richter, E. Gladilin
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.07065v1

Contactless and non-invasive estimation of mechanical properties of physical media from optical observations is of interest for manifold engineering and biomedical applications, where direct physical measurements are not possible. Conventional approaches to the assessment of image displacement and non-contact material probing typically rely on time-consuming iterative algorithms for non-rigid image registration and constitutive modelling using discretization and iterative numerical solving techniques, such as Finite Element Method (FEM) and Finite Difference Method (FDM), which are not suitable for high-throughput data processing. Here, we present an efficient deep learning based end-to-end approach for the estimation of continuum displacement and material compressibility directly from the image series. Based on two deep neural networks for image registration and material compressibility estimation, this framework outperforms conventional approaches in terms of efficiency and accuracy. In particular, our experimental results show that the deep learning model trained on a set of reference data can accurately determine the material compressibility even in the presence of substantial local deviations of the mapping predicted by image registration from the reference displacement field. Our findings suggest that the remarkable accuracy of the deep learning end-to-end model originates from its ability to assess higher-order cognitive features, such as the vorticity of the vector field, rather than conventional local features of the image displacement.

---

### OmniFysics: Towards Physical Intelligence Evolution via Omni-Modal Signal Processing and Network Optimization

Authors: Minghao Han, Dingkang Yang, Yue Jiang, Yizhou Liu, Lihua Zhang
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.07064v2

The autonomous evolution of networked AI systems relies heavily on robust environmental perception. However, physical understanding remains brittle in current models because key physical signals are visually ambiguous and sparsely represented in web-scale data. To bridge the gap between data-centric learning and knowledge-based physical rules, we present OmniFysics, a compact omni-modal network that unifies signal processing and understanding across images, audio, video, and text. To enable autonomous optimization and inject explicit physical knowledge, we construct a dynamic physical data engine. Within this engine, FysicsAny acts as an adaptive mechanism that produces physics-grounded supervision by mapping salient objects to verified physical attributes via hierarchical retrieval and physics-law-constrained signal verification. Concurrently, FysicsOmniCap distills web videos utilizing advanced audio-visual cross-modal signal processing, generating high-fidelity data pairs that emphasize dynamic physical cues. We optimize the OmniFysics network through staged multimodal alignment and evolutive instruction tuning, integrating latent-space flow matching for generation and an adaptive intent router for efficient execution. Experiments demonstrate that this evolutive optimization paradigm not only achieves competitive performance on standard multimodal benchmarks but also significantly advances physics-oriented evaluations.

---

### Video-based Music Generation

Authors: Serkan Sulun
Published: 2026-02-05
Categories: cs.LG, cs.AI, cs.CV, cs.MM, cs.SD
arXiv: https://arxiv.org/abs/2602.07063v1

As the volume of video content on the internet grows rapidly, finding a suitable soundtrack remains a significant challenge. This thesis presents EMSYNC (EMotion and SYNChronization), a fast, free, and automatic solution that generates music tailored to the input video, enabling content creators to enhance their productions without composing or licensing music. Our model creates music that is emotionally and rhythmically synchronized with the video. A core component of EMSYNC is a novel video emotion classifier. By leveraging pretrained deep neural networks for feature extraction and keeping them frozen while training only fusion layers, we reduce computational complexity while improving accuracy. We show the generalization abilities of our method by obtaining state-of-the-art results on Ekman-6 and MovieNet. Another key contribution is a large-scale, emotion-labeled MIDI dataset for affective music generation. We then present an emotion-based MIDI generator, the first to condition on continuous emotional values rather than discrete categories, enabling nuanced music generation aligned with complex emotional content. To enhance temporal synchronization, we introduce a novel temporal boundary conditioning method, called "boundary offset encodings," aligning musical chords with scene changes. Combining video emotion classification, emotion-based music generation, and temporal boundary conditioning, EMSYNC emerges as a fully automatic video-based music generator. User studies show that it consistently outperforms existing methods in terms of music richness, emotional alignment, temporal synchronization, and overall preference, setting a new state-of-the-art in video-based music generation.

---

### From Images to Decisions: Assistive Computer Vision for Non-Metallic Content Estimation in Scrap Metal

Authors: Daniil Storonkin, Ilia Dziub, Maksim Golyadkin, Ilya Makarov
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.07062v1

Scrap quality directly affects energy use, emissions, and safety in steelmaking. Today, the share of non-metallic inclusions (contamination) is judged visually by inspectors - an approach that is subjective and hazardous due to dust and moving machinery. We present an assistive computer vision pipeline that estimates contamination (per percent) from images captured during railcar unloading and also classifies scrap type. The method formulates contamination assessment as a regression task at the railcar level and leverages sequential data through multi-instance learning (MIL) and multi-task learning (MTL). Best results include MAE 0.27 and R2 0.83 by MIL; and an MTL setup reaches MAE 0.36 with F1 0.79 for scrap class. Also we present the system in near real time within the acceptance workflow: magnet/railcar detection segments temporal layers, a versioned inference service produces railcar-level estimates with confidence scores, and results are reviewed by operators with structured overrides; corrections and uncertain cases feed an active-learning loop for continual improvement. The pipeline reduces subjective variability, improves human safety, and enables integration into acceptance and melt-planning workflows.

---

### TACIT: Transformation-Aware Capturing of Implicit Thought

Authors: Daniel Nobrega
Published: 2026-02-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.07061v1

We present TACIT (Transformation-Aware Capturing of Implicit Thought), a diffusion-based transformer for interpretable visual reasoning. Unlike language-based reasoning systems, TACIT operates entirely in pixel space using rectified flow, enabling direct visualization of the reasoning process at each inference step. We demonstrate the approach on maze-solving, where the model learns to transform images of unsolved mazes into solutions. Key results on 1 million synthetic maze pairs include: - 192x reduction in training loss over 100 epochs - 22.7x improvement in L2 distance to ground truth - Only 10 Euler steps required (vs. 100-1000 for typical diffusion models) Quantitative analysis reveals a striking phase transition phenomenon: the solution remains invisible for 68% of the transformation (zero recall), then emerges abruptly at t=0.70 within just 2% of the process. Most remarkably, 100% of samples exhibit simultaneous emergence across all spatial regions, ruling out sequential path construction and providing evidence for holistic rather than algorithmic reasoning. This "eureka moment" pattern -- long incubation followed by sudden crystallization -- parallels insight phenomena in human cognition. The pixel-space design with noise-free flow matching provides a foundation for understanding how neural networks develop implicit reasoning strategies that operate below and before language.

---

### U-Net Based Image Enhancement for Short-time Muon Scattering Tomography

Authors: Haochen Wang, Pei Yu, Liangwen Chen, Weibo He, Yu Zhang, Yuhong Yu, Xueheng Zhang, Lei Yang, Zhiyu Sun
Published: 2026-02-05
Categories: eess.IV, cs.CV, physics.ins-det, physics.med-ph
arXiv: https://arxiv.org/abs/2602.07060v1

Muon Scattering Tomography (MST) is a promising non-invasive inspection technique, yet the practical application of short-time MST is hindered by poor image quality due to limited muon flux. To address this limitation, we propose a U-Net-based framework trained on Point of Closest Approach (PoCA) images reconstructed with simulation MST data to enhance image quality. When applied to experimental MST data, the framework significantly improves image quality, increasing the Structural Similarity Index Measure (SSIM) from 0.7232 to 0.9699 and decreasing the Learned Perceptual Image Patch Similarity (LPIPS) from 0.3604 to 0.0270. These results demonstrate that our method can effectively enhance low-statistics MST images, thereby paving the way for the practical deployment of short-time MST.

---

### Assessing Reproducibility in Evolutionary Computation: A Case Study using Human- and LLM-based Assessment

Authors: Francesca Da Ros, Tarik Začiragić, Aske Plaat, Thomas Bäck, Niki van Stein
Published: 2026-02-05
Categories: cs.NE, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2602.07059v1

Reproducibility is an important requirement in evolutionary computation, where results largely depend on computational experiments. In practice, reproducibility relies on how algorithms, experimental protocols, and artifacts are documented and shared. Despite growing awareness, there is still limited empirical evidence on the actual reproducibility levels of published work in the field. In this paper, we study the reproducibility practices in papers published in the Evolutionary Combinatorial Optimization and Metaheuristics track of the Genetic and Evolutionary Computation Conference over a ten-year period. We introduce a structured reproducibility checklist and apply it through a systematic manual assessment of the selected corpus. In addition, we propose RECAP (REproducibility Checklist Automation Pipeline), an LLM-based system that automatically evaluates reproducibility signals from paper text and associated code repositories. Our analysis shows that papers achieve an average completeness score of 0.62, and that 36.90% of them provide additional material beyond the manuscript itself. We demonstrate that automated assessment is feasible: RECAP achieves substantial agreement with human evaluators (Cohen's k of 0.67). Together, these results highlight persistent gaps in reproducibility reporting and suggest that automated tools can effectively support large-scale, systematic monitoring of reproducibility practices.

---

### Conformal changepoint localization

Authors: Rohan Hore, Aaditya Ramdas
Published: 2026-02-05
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2602.06267v2

We study the problem of offline changepoint localization in a distribution-free setting. One observes a vector of data with a single changepoint, assuming that the data before and after the changepoint are i.i.d. (or more generally exchangeable) from arbitrary and unknown distributions. The goal is to produce a finite-sample confidence set for the index at which the change occurs without making any other assumptions. Existing methods often rely on parametric assumptions, tail conditions, or asymptotic approximations, or only produce point estimates. In contrast, our distribution-free algorithm, CONformal CHangepoint localization (CONCH), only leverages exchangeability arguments to construct confidence sets with finite sample coverage. By proving a conformal Neyman--Pearson lemma, we derive principled score functions that yield informative (small) sets. Moreover, with such score functions, the normalized length of the confidence set shrinks to zero under weak assumptions. We also establish a universality result showing that any distribution-free changepoint localization method must be an instance of CONCH. Experiments suggest that CONCH delivers precise confidence sets even in challenging settings involving images or text.

---

### Is my model "mind blurting"? Interpreting the dynamics of reasoning tokens with Recurrence Quantification Analysis (RQA)

Authors: Quoc Tuan Pham, Mehdi Jafari, Flora Salim
Published: 2026-02-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.06266v1

Test-time compute is central to large reasoning models, yet analysing their reasoning behaviour through generated text is increasingly impractical and unreliable. Response length is often used as a brute proxy for reasoning effort, but this metric fails to capture the dynamics and effectiveness of the Chain of Thoughts (CoT) or the generated tokens. We propose Recurrence Quantification Analysis (RQA) as a non-textual alternative for analysing model's reasoning chains at test time. By treating token generation as a dynamical system, we extract hidden embeddings at each generation step and apply RQA to the resulting trajectories. RQA metrics, including Determinism and Laminarity, quantify patterns of repetition and stalling in the model's latent representations. Analysing 3,600 generation traces from DeepSeek-R1-Distill, we show that RQA captures signals not reflected by response length, but also substantially improves prediction of task complexity by 8\%. These results help establish RQA as a principled tool for studying the latent token generation dynamics of test-time scaling in reasoning models.

---

### Swap Regret Minimization Through Response-Based Approachability

Authors: Ioannis Anagnostides, Gabriele Farina, Maxwell Fishelson, Haipeng Luo, Jon Schneider
Published: 2026-02-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.06264v3

We consider the problem of minimizing different notions of swap regret in online optimization. These forms of regret are tightly connected to correlated equilibrium concepts in games, and have been more recently shown to guarantee non-manipulability against strategic adversaries. The only computationally efficient algorithm for minimizing linear swap regret over a general convex set in $\mathbb{R}^d$ was developed recently by Daskalakis, Farina, Fishelson, Pipis, and Schneider (STOC '25). However, it incurs a highly suboptimal regret bound of $Ω(d^4 \sqrt{T})$ and also relies on computationally intensive calls to the ellipsoid algorithm at each iteration. In this paper, we develop a significantly simpler, computationally efficient algorithm that guarantees $O(d \sqrt{T})$ linear swap regret for a general convex set that has been preconditioned via the John ellipsoid. Our algorithm leverages the powerful response-based approachability framework of Bernstein and Shimkin (JMLR~'15) -- previously overlooked in the line of work on swap regret minimization -- and simultaneously minimizes profile swap regret, which was recently shown to guarantee non-manipulability. Moreover, we establish a matching information-theoretic lower bound: any learner must incur in expectation $Ω(d \sqrt{T})$ linear swap regret for large enough $T$, even when the set is centrally symmetric. This also shows that the classic algorithm of Gordon, Greenwald, and Marks (ICML '08) is existentially optimal for minimizing linear swap regret, although it is computationally inefficient. Finally, we extend our approach to minimize regret with respect to the set of swap deviations with polynomial dimension, unifying and strengthening recent results in equilibrium computation and online learning.

---

### Can One-sided Arguments Lead to Response Change in Large Language Models?

Authors: Pedro Cisneros-Velarde
Published: 2026-02-05
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.06260v1

Polemic questions need more than one viewpoint to express a balanced answer. Large Language Models (LLMs) can provide a balanced answer, but also take a single aligned viewpoint or refuse to answer. In this paper, we study if such initial responses can be steered to a specific viewpoint in a simple and intuitive way: by only providing one-sided arguments supporting the viewpoint. Our systematic study has three dimensions: (i) which stance is induced in the LLM response, (ii) how the polemic question is formulated, (iii) how the arguments are shown. We construct a small dataset and remarkably find that opinion steering occurs across (i)-(iii) for diverse models, number of arguments, and topics. Switching to other arguments consistently decreases opinion steering.

---

### GRP-Obliteration: Unaligning LLMs With a Single Unlabeled Prompt

Authors: Mark Russinovich, Yanan Cai, Keegan Hines, Giorgio Severi, Blake Bullwinkel, Ahmed Salem
Published: 2026-02-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.06258v1

Safety alignment is only as robust as its weakest failure mode. Despite extensive work on safety post-training, it has been shown that models can be readily unaligned through post-deployment fine-tuning. However, these methods often require extensive data curation and degrade model utility. In this work, we extend the practical limits of unalignment by introducing GRP-Obliteration (GRP-Oblit), a method that uses Group Relative Policy Optimization (GRPO) to directly remove safety constraints from target models. We show that a single unlabeled prompt is sufficient to reliably unalign safety-aligned models while largely preserving their utility, and that GRP-Oblit achieves stronger unalignment on average than existing state-of-the-art techniques. Moreover, GRP-Oblit generalizes beyond language models and can also unalign diffusion-based image generation systems. We evaluate GRP-Oblit on six utility benchmarks and five safety benchmarks across fifteen 7-20B parameter models, spanning instruct and reasoning models, as well as dense and MoE architectures. The evaluated model families include GPT-OSS, distilled DeepSeek, Gemma, Llama, Ministral, and Qwen.

---

### On Randomized Algorithms in Online Strategic Classification

Authors: Chase Hutton, Adam Melrod, Han Shao
Published: 2026-02-05
Categories: cs.LG, cs.GT
arXiv: https://arxiv.org/abs/2602.06257v2

Online strategic classification studies settings in which agents strategically modify their features to obtain favorable predictions. For example, given a classifier that determines loan approval based on credit scores, applicants may open or close credit cards and bank accounts to obtain a positive prediction. The learning goal is to achieve low mistake or regret bounds despite such behavior. While randomized algorithms have the potential to offer advantages to the learner in strategic settings, they have been largely underexplored. In the realizable setting, no lower bound is known for randomized algorithms, and existing lower bound constructions for deterministic learners can be circumvented by randomization. In the agnostic setting, the best known regret upper bound is $O(T^{3/4}\log^{1/4}T|\mathcal H|)$, which is far from the standard online learning rate of $O(\sqrt{T\log|\mathcal H|})$. In this work, we provide refined bounds for online strategic classification in both settings; our bounds depend on the Littlestone dimension $\mathrm{Ldim}(\mathcal H)$ of the hypothesis class $\mathcal H$ and the maximum degree $Δ$ of the manipulation graph. In the realizable setting, we extend, for $T > \mathrm{Ldim}(\mathcal H) Δ^2$, the existing lower bound $Ω(\mathrm{Ldim}(\mathcal H) Δ)$ for deterministic learners to all learners. This yields the first lower bound that applies to randomized learners. We then provide the first randomized learner that improves the known (deterministic) upper bound of $O(\mathrm{Ldim}(\mathcal H) \cdot Δ\log Δ)$. In the agnostic setting, we give an improper randomized learner that improves the regret upper bound to $O(\sqrt{T\log|\mathcal H|})$, matching the standard online learning rate. We also show a larger lower bound for all proper learning rules, demonstrating that improperness is necessary to achieve the optimal rate.

---

### Steering Safely or Off a Cliff? Rethinking Specificity and Robustness in Inference-Time Interventions

Authors: Navita Goyal, Hal Daumé
Published: 2026-02-05
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.06256v1

Model steering, which involves intervening on hidden representations at inference time, has emerged as a lightweight alternative to finetuning for precisely controlling large language models. While steering efficacy has been widely studied, evaluations of whether interventions alter only the intended property remain limited, especially with respect to unintended changes in behaviors related to the target property. We call this notion specificity. We propose a framework that distinguishes three dimensions of specificity: general (preserving fluency and unrelated abilities), control (preserving related control properties), and robustness (preserving control properties under distribution shifts). We study two safety-critical use cases: steering models to reduce overrefusal and faithfulness hallucinations, and show that while steering achieves high efficacy and largely maintains general and control specificity, it consistently fails to preserve robustness specificity. In the case of overrefusal steering, for example, all steering methods reduce overrefusal without harming general abilities and refusal on harmful queries; however, they substantially increase vulnerability to jailbreaks. Our work provides the first systematic evaluation of specificity in model steering, showing that standard efficacy and specificity checks are insufficient, because without robustness evaluation, steering methods may appear reliable even when they compromise model safety.

---

### ASMa: Asymmetric Spatio-temporal Masking for Skeleton Action Representation Learning

Authors: Aman Anand, Amir Eskandari, Elyas Rahsno, Farhana Zulkernine
Published: 2026-02-05
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.06251v1

Self-supervised learning (SSL) has shown remarkable success in skeleton-based action recognition by leveraging data augmentations to learn meaningful representations. However, existing SSL methods rely on data augmentations that predominantly focus on masking high-motion frames and high-degree joints such as joints with degree 3 or 4. This results in biased and incomplete feature representations that struggle to generalize across varied motion patterns. To address this, we propose Asymmetric Spatio-temporal Masking (ASMa) for Skeleton Action Representation Learning, a novel combination of masking to learn a full spectrum of spatio-temporal dynamics inherent in human actions. ASMa employs two complementary masking strategies: one that selectively masks high-degree joints and low-motion, and another that masks low-degree joints and high-motion frames. These masking strategies ensure a more balanced and comprehensive skeleton representation learning. Furthermore, we introduce a learnable feature alignment module to effectively align the representations learned from both masked views. To facilitate deployment in resource-constrained settings and on low-resource devices, we compress the learned and aligned representation into a lightweight model using knowledge distillation. Extensive experiments on NTU RGB+D 60, NTU RGB+D 120, and PKU-MMD datasets demonstrate that our approach outperforms existing SSL methods with an average improvement of 2.7-4.4% in fine-tuning and up to 5.9% in transfer learning to noisy datasets and achieves competitive performance compared to fully supervised baselines. Our distilled model achieves 91.4% parameter reduction and 3x faster inference on edge devices while maintaining competitive accuracy, enabling practical deployment in resource-constrained scenarios.

---

### REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loop

Authors: Patryk Rybak, Paweł Batorski, Paul Swoboda, Przemysław Spurek
Published: 2026-02-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.06248v1

Machine unlearning for LLMs aims to remove sensitive or copyrighted data from trained models. However, the true efficacy of current unlearning methods remains uncertain. Standard evaluation metrics rely on benign queries that often mistake superficial information suppression for genuine knowledge removal. Such metrics fail to detect residual knowledge that more sophisticated prompting strategies could still extract. We introduce REBEL, an evolutionary approach for adversarial prompt generation designed to probe whether unlearned data can still be recovered. Our experiments demonstrate that REBEL successfully elicits ``forgotten'' knowledge from models that seemed to be forgotten in standard unlearning benchmarks, revealing that current unlearning methods may provide only a superficial layer of protection. We validate our framework on subsets of the TOFU and WMDP benchmarks, evaluating performance across a diverse suite of unlearning algorithms. Our experiments show that REBEL consistently outperforms static baselines, recovering ``forgotten'' knowledge with Attack Success Rates (ASRs) reaching up to 60% on TOFU and 93% on WMDP. We will make all code publicly available upon acceptance. Code is available at https://github.com/patryk-rybak/REBEL/

---

### Adaptive Sparse Möbius Transforms for Learning Polynomials

Authors: Yigit Efe Erginbas, Justin Singh Kang, Elizabeth Polito, Kannan Ramchandran
Published: 2026-02-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.06246v1

We consider the problem of exactly learning an $s$-sparse real-valued Boolean polynomial of degree $d$ of the form $f:\{ 0,1\}^n \rightarrow \mathbb{R}$. This problem corresponds to decomposing functions in the AND basis and is known as taking a Möbius transform. While the analogous problem for the parity basis (Fourier transform) $f: \{-1,1 \}^n \rightarrow \mathbb{R}$ is well-understood, the AND basis presents a unique challenge: the basis vectors are coherent, precluding standard compressed sensing methods. We overcome this challenge by identifying that we can exploit adaptive group testing to provide a constructive, query-efficient implementation of the Möbius transform (also known as Möbius inversion) for sparse functions. We present two algorithms based on this insight. The Fully-Adaptive Sparse Möbius Transform (FASMT) uses $O(sd \log(n/d))$ adaptive queries in $O((sd + n) sd \log(n/d))$ time, which we show is near-optimal in query complexity. Furthermore, we also present the Partially-Adaptive Sparse Möbius Transform (PASMT), which uses $O(sd^2\log(n/d))$ queries, trading a factor of $d$ to reduce the number of adaptive rounds to $O(d^2\log(n/d))$, with no dependence on $s$. When applied to hypergraph reconstruction from edge-count queries, our results improve upon baselines by avoiding the combinatorial explosion in the rank $d$. We demonstrate the practical utility of our method for hypergraph reconstruction by applying it to learning real hypergraphs in simulations.

---

### Inheritance Between Feedforward and Convolutional Networks via Model Projection

Authors: Nicolas Ewen, Jairo Diaz-Rodriguez, Kelly Ramsay
Published: 2026-02-05
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.06245v2

Neural-network techniques are often transferred across architecture families by analogy, but such transfer is valid only when the assumptions required by a technique are preserved. We introduce this idea as inheritance between model classes. Using a unified node-level framework with tensor-valued activations, we prove that generalized feedforward networks (GFFNs) form a strict subset of generalized convolutional networks (GCNNs), so GCNN properties transfer directly to GFFNs. The reverse direction is not automatic: standard CNN nodes use spatial kernels, while FFN nodes use one scalar weight per input contribution. We introduce model projection to recover a restricted reverse inheritance path. Projection freezes each convolutional input-channel sub-function and learns one scalar coefficient for each input-output channel contribution, giving projected CNN nodes the GFFN-style trainable structure of scalar-weighted input recombination. This inherited structure leads naturally to parameter-efficient transfer learning. Across multiple ImageNet-pretrained CNN backbones and downstream image-classification datasets, model projection is competitive with standard and PEFT baselines and provides an effective initialization for subsequent full fine-tuning.

---

### A Fast and Generalizable Fourier Neural Operator-Based Surrogate for Melt-Pool Prediction in Laser Processing

Authors: Alix Benoit, Toni Ivas, Mateusz Papierz, Asel Sagingalieva, Alexey Melnikov, Elia Iseli
Published: 2026-02-05
Categories: cs.LG, cs.CE
arXiv: https://arxiv.org/abs/2602.06241v3

High-fidelity simulations of laser welding capture complex thermo-fluid phenomena, including phase change, free-surface deformation, and keyhole dynamics, however their computational cost limits large-scale process exploration and real-time use. In this work we present the Laser Processing Fourier Neural Operator (LP-FNO), a Fourier Neural Operator (FNO) based surrogate model that learns the parametric solution operator of various laser processes from multiphysics simulations generated with FLOW-3D WELD (registered trademark). Through a novel approach of reformulating the transient problem in the moving laser frame and applying temporal averaging, the system results in a quasi-steady state setting suitable for operator learning, even in the keyhole welding regime. The proposed LP-FNO maps process parameters to three-dimensional temperature fields and melt-pool boundaries across a broad process window spanning conduction and keyhole regimes using the non-dimensional normalized enthalpy formulation. The model achieves temperature prediction errors on the order of 1% and intersection-over-union scores for melt-pool segmentation over 0.9. We demonstrate that a LP-FNO model trained on coarse-resolution data can be evaluated on finer grids, yielding accurate super-resolved predictions in mesh-converged conduction regimes, whereas discrepancies in keyhole regimes reflect unresolved dynamics in the coarse-mesh training data. These results indicate that the LP-FNO provides an efficient surrogate modeling framework for laser welding, enabling prediction of full three-dimensional fields and phase interfaces over wide parameter ranges in just tens of milliseconds, up to a hundred thousand times faster than traditional Finite Volume multi-physics software.

---

### ATEX-CF: Attack-Informed Counterfactual Explanations for Graph Neural Networks

Authors: Yu Zhang, Sean Bin Yang, Arijit Khan, Cuneyt Gurcan Akcora
Published: 2026-02-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.06240v1

Counterfactual explanations offer an intuitive way to interpret graph neural networks (GNNs) by identifying minimal changes that alter a model's prediction, thereby answering "what must differ for a different outcome?". In this work, we propose a novel framework, ATEX-CF that unifies adversarial attack techniques with counterfactual explanation generation-a connection made feasible by their shared goal of flipping a node's prediction, yet differing in perturbation strategy: adversarial attacks often rely on edge additions, while counterfactual methods typically use deletions. Unlike traditional approaches that treat explanation and attack separately, our method efficiently integrates both edge additions and deletions, grounded in theory, leveraging adversarial insights to explore impactful counterfactuals. In addition, by jointly optimizing fidelity, sparsity, and plausibility under a constrained perturbation budget, our method produces instance-level explanations that are both informative and realistic. Experiments on synthetic and real-world node classification benchmarks demonstrate that ATEX-CF generates faithful, concise, and plausible explanations, highlighting the effectiveness of integrating adversarial insights into counterfactual reasoning for GNNs.

---

### Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution

Authors: Adam Barla, Emanuele Nevali, Luca Viano, Volkan Cevher
Published: 2026-02-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.06239v3

We introduce PEPO (Pessimistic Ensemble based Preference Optimization), a single-step Direct Preference Optimization (DPO)-like algorithm to mitigate the well-known over-optimization issue in preference learning without requiring the knowledge of the data-generating distribution or learning an explicit reward model. PEPO achieves pessimism via an ensemble of preference-optimized policies trained on disjoint data subsets and then aggregates them through a worst case construction that favors the agreement across models. In the tabular setting, PEPO achieves sample complexity guarantees depending only on a single-policy concentrability coefficient, thus avoiding the all-policy concentrability which affects the guarantees of algorithms prone to over-optimization, such as DPO. The theoretical findings are corroborated by a convincing practical performance, while retaining the simplicity and the practicality of DPO-style training.

---

### RuleSmith: Multi-Agent LLMs for Automated Game Balancing

Authors: Ziyao Zeng, Chen Liu, Tianyu Liu, Hao Wang, Xiatao Sun, Fengyu Yang, Xiaofeng Liu, Zhiwen Fan
Published: 2026-02-05
Categories: cs.LG, cs.AI, cs.GT, cs.MA
arXiv: https://arxiv.org/abs/2602.06232v1

Game balancing is a longstanding challenge requiring repeated playtesting, expert intuition, and extensive manual tuning. We introduce RuleSmith, the first framework that achieves automated game balancing by leveraging the reasoning capabilities of multi-agent LLMs. It couples a game engine, multi-agent LLMs self-play, and Bayesian optimization operating over a multi-dimensional rule space. As a proof of concept, we instantiate RuleSmith on CivMini, a simplified civilization-style game containing heterogeneous factions, economy systems, production rules, and combat mechanics, all governed by tunable parameters. LLM agents interpret textual rulebooks and game states to generate actions, to conduct fast evaluation of balance metrics such as win-rate disparities. To search the parameter landscape efficiently, we integrate Bayesian optimization with acquisition-based adaptive sampling and discrete projection: promising candidates receive more evaluation games for accurate assessment, while exploratory candidates receive fewer games for efficient exploration. Experiments show that RuleSmith converges to highly balanced configurations and provides interpretable rule adjustments that can be directly applied to downstream game systems. Our results illustrate that LLM simulation can serve as a powerful surrogate for automating design and balancing in complex multi-agent environments.

---

### SR4-Fit: An Interpretable and Informative Classification Algorithm Applied to Prediction of U.S. House of Representatives Elections

Authors: Shyam Sundar Murali Krishnan, Dean Frederick Hougen
Published: 2026-02-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.06229v1

The growth of machine learning demands interpretable models for critical applications, yet most high-performing models are ``black-box'' systems that obscure input-output relationships, while traditional rule-based algorithms like RuleFit suffer from a lack of predictive power and instability despite their simplicity. This motivated our development of Sparse Relaxed Regularized Regression Rule-Fit (SR4-Fit), a novel interpretable classification algorithm that addresses these limitations while maintaining superior classification performance. Using demographic characteristics of U.S. congressional districts from the Census Bureau's American Community Survey, we demonstrate that SR4-Fit can predict House election party outcomes with unprecedented accuracy and interpretability. Our results show that while the majority party remains the strongest predictor, SR4-Fit has revealed intrinsic combinations of demographic factors that affect prediction outcomes that were unable to be interpreted in black-box algorithms such as random forests. The SR4-Fit algorithm surpasses both black-box models and existing interpretable rule-based algorithms such as RuleFit with respect to accuracy, simplicity, and robustness, generating stable and interpretable rule sets while maintaining superior predictive performance, thus addressing the traditional trade-off between model interpretability and predictive capability in electoral forecasting. To further validate SR4-Fit's performance, we also apply it to six additional publicly available classification datasets, like the breast cancer, Ecoli, page blocks, Pima Indians, vehicle, and yeast datasets, and find similar results.

---

### Do It for HER: First-Order Temporal Logic Reward Specification in Reinforcement Learning (Extended Version)

Authors: Pierriccardo Olivieri, Fausto Lasca, Alessandro Gianola, Matteo Papini
Published: 2026-02-05
Categories: cs.AI, cs.LG, cs.LO
arXiv: https://arxiv.org/abs/2602.06227v1

In this work, we propose a novel framework for the logical specification of non-Markovian rewards in Markov Decision Processes (MDPs) with large state spaces. Our approach leverages Linear Temporal Logic Modulo Theories over finite traces (LTLfMT), a more expressive extension of classical temporal logic in which predicates are first-order formulas of arbitrary first-order theories rather than simple Boolean variables. This enhanced expressiveness enables the specification of complex tasks over unstructured and heterogeneous data domains, promoting a unified and reusable framework that eliminates the need for manual predicate encoding. However, the increased expressive power of LTLfMT introduces additional theoretical and computational challenges compared to standard LTLf specifications. We address these challenges from a theoretical standpoint, identifying a fragment of LTLfMT that is tractable but sufficiently expressive for reward specification in an infinite-state-space context. From a practical perspective, we introduce a method based on reward machines and Hindsight Experience Replay (HER) to translate first-order logic specifications and address reward sparsity. We evaluate this approach to a continuous-control setting using Non-Linear Arithmetic Theory, showing that it enables natural specification of complex tasks. Experimental results show how a tailored implementation of HER is fundamental in solving tasks with complex goals.

---

### ForeHOI: Feed-forward 3D Object Reconstruction from Daily Hand-Object Interaction Videos

Authors: Yuantao Chen, Jiahao Chang, Chongjie Ye, Chaoran Zhang, Zhaojie Fang, Chenghong Li, Xiaoguang Han
Published: 2026-02-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.06226v2

The ubiquity of monocular videos capturing daily hand-object interactions presents a valuable resource for embodied intelligence. While 3D hand reconstruction from in-the-wild videos has seen significant progress, reconstructing the involved objects remains challenging due to severe occlusions and the complex, coupled motion of the camera, hands, and object. In this paper, we introduce ForeHOI, a novel feed-forward model that directly reconstructs 3D object geometry from monocular hand-object interaction videos within one minute of inference time, eliminating the need for any pre-processing steps. Our key insight is that, the joint prediction of 2D mask inpainting and 3D shape completion in a feed-forward framework can effectively address the problem of severe occlusion in monocular hand-held object videos, thereby achieving results that outperform the performance of optimization-based methods. The information exchanges between the 2D and 3D shape completion boosts the overall reconstruction quality, enabling the framework to effectively handle severe hand-object occlusion. Furthermore, to support the training of our model, we contribute the first large-scale, high-fidelity synthetic dataset of hand-object interactions with comprehensive annotations. Extensive experiments demonstrate that ForeHOI achieves state-of-the-art performance in object reconstruction, significantly outperforming previous methods with around a 100x speedup. Code and data are available at: https://github.com/Tao-11-chen/ForeHOI.

---

### BenchMarker: An Education-Inspired Toolkit for Highlighting Flaws in Multiple-Choice Benchmarks

Authors: Nishant Balepur, Bhavya Rajasekaran, Jane Oh, Michael Xie, Atrey Desai, Vipul Gupta, Steven James Moore, Eunsol Choi, Rachel Rudinger, Jordan Lee Boyd-Graber
Published: 2026-02-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.06221v2

Multiple-choice question answering (MCQA) is standard in NLP, but benchmarks lack rigorous quality control. We present BenchMarker, an education-inspired toolkit using LLM judges to flag three common MCQ flaws: 1) contamination: items appearing exactly online; 2) shortcuts: cues in the choices that enable guessing; and 3) writing errors: structural/grammatical issues based on a 19-rule education rubric. We validate BenchMarker with human annotations, then run the tool to audit 12 benchmarks, revealing: 1) flaws persist in MCQA benchmarks, especially automatically-made and crowdsourced data - we detect 47% of TruthfulQA appears online and 100% of HellaSwag violates multiple writing rules; 2) contaminated MCQs tend to inflate accuracy, while writing errors tend to lower it and change rankings beyond random; and 3) prior benchmark repairs address their targeted issues (i.e., lowering accuracy with LLM-written distractors), but inadvertently add new flaws (i.e. implausible distractors, many correct answers). Overall, flaws in MCQs degrade NLP evaluation, but education research offers a path forward. We release BenchMarker to bridge the fields and improve MCQA benchmark design.

---

### Coupled Local and Global World Models for Efficient First Order RL

Authors: Joseph Amigo, Rooholla Khorrambakht, Nicolas Mansard, Ludovic Righetti
Published: 2026-02-05
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2602.06219v2

World models offer a promising avenue for more faithfully capturing complex dynamics, including contacts and non-rigidity, as well as complex sensory information, such as visual perception, in situations where standard simulators struggle. However, these models are computationally complex to evaluate, posing a challenge for popular RL approaches that have been successfully used with simulators to solve complex locomotion tasks but yet struggle with manipulation. This paper introduces a method that bypasses simulators entirely, training RL policies inside world models learned from robots' interactions with real environments. At its core, our approach enables policy training with large-scale diffusion models via a novel decoupled first-order gradient (FoG) method: a full-scale world model generates accurate forward trajectories, while a lightweight latent-space surrogate approximates its local dynamics for efficient gradient computation. This coupling of a local and global world model ensures high-fidelity unrolling alongside computationally tractable differentiation. We demonstrate the efficacy of our method on the Push-T manipulation task, where it significantly outperforms PPO in sample efficiency. We further evaluate our approach through an ego-centric object manipulation task with a quadruped. Together, these results demonstrate that learning inside data-driven world models is a promising pathway for solving hard-to-model RL tasks in image space without reliance on hand-crafted physics simulators.

---

### Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings

Authors: Grégoire Dhimoïla, Thomas Fel, Victor Boutin, Agustin Picard
Published: 2026-02-05
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.06218v2

Vision-language models (VLMs) align images and text with remarkable success, yet the geometry of their shared embedding space remains poorly understood. To probe this geometry, we begin from the Iso-Energy Assumption, which exploits cross-modal redundancy: a concept that is truly shared should exhibit the same average energy across modalities. We operationalize this assumption with an Aligned Sparse Autoencoder (SAE) that encourages energy consistency during training while preserving reconstruction. We find that this inductive bias changes the SAE solution without harming reconstruction, giving us a representation that serves as a tool for geometric analysis. Sanity checks on controlled data with known ground truth confirm that alignment improves when Iso-Energy holds and remains neutral when it does not. Applied to foundational VLMs, our framework reveals a clear structure with practical consequences: (i) sparse bimodal atoms carry the entire cross-modal alignment signal; (ii) unimodal atoms act as modality-specific biases and fully explain the modality gap; (iii) removing unimodal atoms collapses the gap without harming performance; (iv) restricting vector arithmetic to the bimodal subspace yields in-distribution edits and improved retrieval. These findings suggest that the right inductive bias can both preserve model fidelity and render the latent geometry interpretable and actionable.

---