# Research Papers — 2026-02 · bundle page 206 of 210 > Full-text markdown of papers #10251–10300 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/206 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/205.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/207.md) ### Toward Scalable Audio Description Quality Control: A Workflow for Evaluating Human and VLM Raters Authors: Lana Do, Gio Jung, Juvenal Francisco Barajas, Andrew Taylor Scott, Shasta Ihorn, Alexander Mario Blum, Vassilis Athitsos, Ilmi Yoon Published: 2026-02-01 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2602.01390v3 Digital video is central to communication, education, and entertainment, but without audio description (AD), blind and low-vision users are excluded. While crowdsourced platforms and vision-language models (VLMs) expand AD production, quality is rarely checked systematically. Existing evaluations rely on NLP metrics and short-clip guidelines, leaving open the question of how to assess long-form AD quality at scale. To address this, we developed a methodological workflow using Item Response Theory to evaluate VLM and human rater proficiency against expert-established ground truth. Evaluations were based on a six-dimensional framework, grounded in professional guidelines and shaped by insights from our accessibility experts and blind consultants. Findings suggest that top-performing VLMs can approximate ground-truth ratings at levels comparable to human raters. However, qualitative analysis reveals that VLM reasoning is less reliable and actionable than that of human respondents. These insights underscore the potential of hybrid evaluation systems that leverage VLMs alongside human oversight, offering a path toward scalable AD quality control. --- ### Toward Scalable Audio Description Quality Control: A Workflow for Evaluating Human and VLM Raters Authors: Lana Do, Gio Jung, Juvenal Francisco Barajas, Andrew Taylor Scott, Shasta Ihorn, Alexander Mario Blum, Vassilis Athitsos, Ilmi Yoon Published: 2026-02-01 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2602.01390v2 Digital video is central to communication, education, and entertainment, but without audio description (AD), blind and low-vision users are excluded. While crowdsourced platforms and vision-language models (VLMs) expand AD production, quality is rarely checked systematically. Existing evaluations rely on NLP metrics and short-clip guidelines, leaving open the question of how to assess long-form AD quality at scale. To address this, we developed a methodological workflow using Item Response Theory to evaluate VLM and human rater proficiency against expert-established ground truth. Evaluations were based on a six-dimensional framework, grounded in professional guidelines and shaped by insights from our accessibility experts and blind consultants. Findings suggest that top-performing VLMs can approximate ground-truth ratings at levels comparable to human raters. However, qualitative analysis reveals that VLM reasoning is less reliable and actionable than that of human respondents. These insights underscore the potential of hybrid evaluation systems that leverage VLMs alongside human oversight, offering a path toward scalable AD quality control. --- ### The Enhanced Physics-Informed Kolmogorov-Arnold Networks: Applications of Newton's Laws in Financial Deep Reinforcement Learning (RL) Algorithms Authors: Trang Thoi, Hung Tran, Tram Thoi, Huaiyang Zhong Published: 2026-02-01 Categories: cs.CE, cs.LG arXiv: https://arxiv.org/abs/2602.01388v2 Deep Reinforcement Learning (DRL), a subset of machine learning focused on sequential decision-making, has emerged as a powerful approach for tackling financial trading problems. In finance, DRL is commonly used either to generate discrete trade signals or to determine continuous portfolio allocations. In this work, we propose a novel reinforcement learning framework for portfolio optimization that incorporates Physics-Informed Kolmogorov-Arnold Networks (PIKANs) into several DRL algorithms. The approach replaces conventional multilayer perceptrons with Kolmogorov-Arnold Networks (KANs) in both actor and critic components-utilizing learnable B-spline univariate functions to achieve parameter-efficient and more interpretable function approximation. During actor updates, we introduce a physics-informed regularization loss that promotes second-order temporal consistency between observed return dynamics and the action-induced portfolio adjustments. The proposed framework is evaluated across three equity markets-China, Vietnam, and the United States, covering both emerging and developed economies. Across all three markets, PIKAN-based agents consistently deliver higher cumulative and annualized returns, superior Sharpe and Calmar ratios, and more favorable drawdown characteristics compared to both standard DRL baselines and classical online portfolio-selection methods. This yields more stable training, higher Sharpe ratios, and superior performance compared to traditional DRL counterparts. The approach is particularly valuable in highly dynamic and noisy financial markets, where conventional DRL often suffers from instability and poor generalization. --- ### "If You're Very Clever, No One Knows You've Used It": The Social Dynamics of Developing Generative AI Literacy in the Workplace Authors: Qing Nancy Xia, Marios Constantinides, Advait Sarkar, Duncan Brumby, Anna Cox Published: 2026-02-01 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2602.01386v2 Generative AI (GenAI) tools are rapidly transforming knowledge work, making AI literacy a critical priority for organizations. However, research on AI literacy lacks empirical insight into how knowledge workers' beliefs around GenAI literacy are shaped by the social dynamics of the workplace, and how workers learn to apply GenAI tools in these environments. To address this gap, we conducted in-depth interviews with 19 knowledge workers across multiple sectors to examine how they develop GenAI competencies in real-world professional contexts. We found that, while knowledge sharing from colleagues supported learning, the ability to remove cues indicating GenAI use was perceived as validation of domain expertise. These behaviours ultimately reduced opportunities for learning via knowledge sharing and undermined transparency. To advance workplace AI literacy, we argue for fostering open dialogue, increasing visibility of user-generated knowledge, and greater emphasis on the benefits of collaborative learning for navigating rapid technological developments. --- ### PromptRL: Prompt Matters in RL for Flow-Based Image Generation Authors: Fu-Yun Wang, Han Zhang, Michael Gharbi, Hongsheng Li, Taesung Park Published: 2026-02-01 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.01382v1 Flow matching models (FMs) have revolutionized text-to-image (T2I) generation, with reinforcement learning (RL) serving as a critical post-training strategy for alignment with reward objectives. In this research, we show that current RL pipelines for FMs suffer from two underappreciated yet important limitations: sample inefficiency due to insufficient generation diversity, and pronounced prompt overfitting, where models memorize specific training formulations and exhibit dramatic performance collapse when evaluated on semantically equivalent but stylistically varied prompts. We present PromptRL (Prompt Matters in RL for Flow-Based Image Generation), a framework that incorporates language models (LMs) as trainable prompt refinement agents directly within the flow-based RL optimization loop. This design yields two complementary benefits: rapid development of sophisticated prompt rewriting capabilities and, critically, a synergistic training regime that reshapes the optimization dynamics. PromptRL achieves state-of-the-art performance across multiple benchmarks, obtaining scores of 0.97 on GenEval, 0.98 on OCR accuracy, and 24.05 on PickScore. Furthermore, we validate the effectiveness of our RL approach on large-scale image editing models, improving the EditReward of FLUX.1-Kontext from 1.19 to 1.43 with only 0.06 million rollouts, surpassing Gemini 2.5 Flash Image (also known as Nano Banana), which scores 1.37, and achieving comparable performance with ReasonNet (1.44), which relied on fine-grained data annotations along with a complex multi-stage training. Our extensive experiments empirically demonstrate that PromptRL consistently achieves higher performance ceilings while requiring over 2$\times$ fewer rollouts compared to naive flow-only RL. Our code is available at https://github.com/G-U-N/UniRL. --- ### On the Power of (Approximate) Reward Models for Inference-Time Scaling Authors: Youheng Zhu, Yiping Lu Published: 2026-02-01 Categories: cs.CL, stat.ML arXiv: https://arxiv.org/abs/2602.01381v1 Inference-time scaling has recently emerged as a powerful paradigm for improving the reasoning capability of large language models. Among various approaches, Sequential Monte Carlo (SMC) has become a particularly important framework, enabling iterative generation, evaluation, rejection, and resampling of intermediate reasoning trajectories. A central component in this process is the reward model, which evaluates partial solutions and guides the allocation of computation during inference. However, in practice, true reward models are never available. All deployed systems rely on approximate reward models, raising a fundamental question: Why and when do approximate reward models suffice for effective inference-time scaling? In this work, we provide a theoretical answer. We identify the Bellman error of the approximate reward model as the key quantity governing the effectiveness of SMC-based inference-time scaling. For a reasoning process of length $T$, we show that if the Bellman error of the approximate reward model is bounded by $O(1/T)$, then combining this reward model with SMC reduces the computational complexity of reasoning from exponential in $T$ to polynomial in $T$. This yields an exponential improvement in inference efficiency despite using only approximate rewards. --- ### WAKESET: A Large-Scale, High-Reynolds Number Flow Dataset for Machine Learning of Turbulent Wake Dynamics Authors: Zachary Cooper-Baldock, Paulo E. Santos, Russell S. A. Brinkworth, Karl Sammut Published: 2026-02-01 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2602.01379v2 Machine learning (ML) offers transformative potential for computational fluid dynamics (CFD), promising to accelerate simulations, improve turbulence modelling, and enable real-time flow prediction and control-capabilities that could fundamentally change how engineers approach fluid dynamics problems. However, the exploration of ML in fluid dynamics is critically hampered by the scarcity of large, diverse, and high-fidelity datasets suitable for training robust models. This limitation is particularly acute for highly turbulent flows, which dominate practical engineering applications yet remain computationally prohibitive to simulate at scale. High-Reynolds number turbulent datasets are essential for ML models to learn the complex, multi-scale physics characteristic of real-world flows, enabling generalisation beyond the simplified, low-Reynolds number regimes often represented in existing datasets. This paper introduces WAKESET, a novel, large-scale CFD dataset of highly turbulent flows, designed to address this critical gap. The dataset captures the complex hydrodynamic interactions during the underwater recovery of an autonomous underwater vehicle by a larger extra-large uncrewed underwater vehicle. It comprises 1,091 high-fidelity Reynolds-Averaged Navier-Stokes simulations, augmented to 4,364 instances, covering a wide operational envelope of speeds (up to Reynolds numbers of 1.09 x 10^8) and turning angles. This work details the motivation for this new dataset by reviewing existing resources, outlines the hydrodynamic modelling and validation underpinning its creation, and describes its structure. The dataset's focus on a practical engineering problem, its scale, and its high turbulence characteristics make it a valuable resource for developing and benchmarking ML models for flow field prediction, surrogate modelling, and autonomous navigation in complex underwater environments. --- ### Context Dependence and Reliability in Autoregressive Language Models Authors: Poushali Sengupta, Shashi Raj Pandey, Sabita Maharjan, Frank Eliassen Published: 2026-02-01 Categories: cs.CL, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2602.01378v1 Large language models (LLMs) generate outputs by utilizing extensive context, which often includes redundant information from prompts, retrieved passages, and interaction history. In critical applications, it is vital to identify which context elements actually influence the output, as standard explanation methods struggle with redundancy and overlapping context. Minor changes in input can lead to unpredictable shifts in attribution scores, undermining interpretability and raising concerns about risks like prompt injection. This work addresses the challenge of distinguishing essential context elements from correlated ones. We introduce RISE (Redundancy-Insensitive Scoring of Explanation), a method that quantifies the unique influence of each input relative to others, minimizing the impact of redundancies and providing clearer, stable attributions. Experiments demonstrate that RISE offers more robust explanations than traditional methods, emphasizing the importance of conditional information for trustworthy LLM explanations and monitoring. --- ### Robust Sublinear Convergence Rates for Iterative Bregman Projections Authors: Gabriel Peyré Published: 2026-02-01 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2602.01372v2 Entropic regularization provides a simple way to approximate linear programs whose constraints split into two or more tractable blocks. The resulting objectives are amenable to cyclic Kullback-Leibler (KL) Bregman projections, with Sinkhorn-type algorithms for optimal transport, matrix scaling, and barycenters as canonical examples. This paper gives a general blueprint for proving $O(1/k)$ dual convergence rate with a constant that scales only linearly in $1/γ$, where $γ$ is the entropic regularization parameter. We call such rates "robust", because this mild dependence on $γ$ underpins favorable complexity bounds for approximating the unregularized problem via alternating KL projections. The blueprint reduces the proof to a uniform primal bound and a dual bound for a quotient norm induced by the constraint split. To make these inputs usable, we propose two helper results, which rely on the non-expansiveness of the dual iterations in this quotient dual norm. Instantiating this blueprint for graph-structured transport yields a new flow-Sinkhorn algorithm for the Wasserstein-1 distance on graphs. It achieves $\varepsilon$-additive accuracy on the transshipment cost in $O(p\,\mathrm{diameter}^3/\varepsilon^{4})$ arithmetic operations (up to logarithmic factors), where $p$ is the number of edges. We also provide a machine-checked Lean formalization of the core blueprint and its graph-$\mathrm{W}_1$ instantiation. --- ### PolyGen: Fully Synthetic Vision-Language Training via Multi-Generator Ensembles Authors: Leonardo Brusini, Cristian Sbrolli, Eugenio Lomurno, Toshihiko Yamasaki, Matteo Matteucci Published: 2026-02-01 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.01370v1 Synthetic data offers a scalable solution for vision-language pre-training, yet current state-of-the-art methods typically rely on scaling up a single generative backbone, which introduces generator-specific spectral biases and limits feature diversity. In this work, we introduce PolyGen, a framework that redefines synthetic data construction by prioritizing manifold coverage and compositional rigor over simple dataset size. PolyGen employs a Polylithic approach to train on the intersection of architecturally distinct generators, effectively marginalizing out model-specific artifacts. Additionally, we introduce a Programmatic Hard Negative curriculum that enforces fine-grained syntactic understanding. By structurally reallocating the same data budget from unique captions to multi-source variations, PolyGen achieves a more robust feature space, outperforming the leading single-source baseline (SynthCLIP) by +19.0% on aggregate multi-task benchmarks and on the SugarCrepe++ compositionality benchmark (+9.1%). These results demonstrate that structural diversity is a more data-efficient scaling law than simply increasing the volume of single-source samples. --- ### Exposing and Defending the Achilles' Heel of Video Mixture-of-Experts Authors: Songping Wang, Qinglong Liu, Yueming Lyu, Ning Li, Ziwen He, Caifeng Shan Published: 2026-02-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01369v1 Mixture-of-Experts (MoE) has demonstrated strong performance in video understanding tasks, yet its adversarial robustness remains underexplored. Existing attack methods often treat MoE as a unified architecture, overlooking the independent and collaborative weaknesses of key components such as routers and expert modules. To fill this gap, we propose Temporal Lipschitz-Guided Attacks (TLGA) to thoroughly investigate component-level vulnerabilities in video MoE models. We first design attacks on the router, revealing its independent weaknesses. Building on this, we introduce Joint Temporal Lipschitz-Guided Attacks (J-TLGA), which collaboratively perturb both routers and experts. This joint attack significantly amplifies adversarial effects and exposes the Achilles' Heel (collaborative weaknesses) of the MoE architecture. Based on these insights, we further propose Joint Temporal Lipschitz Adversarial Training (J-TLAT). J-TLAT performs joint training to further defend against collaborative weaknesses, enhancing component-wise robustness. Our framework is plug-and-play and reduces inference cost by more than 60% compared with dense models. It consistently enhances adversarial robustness across diverse datasets and architectures, effectively mitigating both the independent and collaborative weaknesses of MoE. --- ### Deep Variational Contrastive Learning for Joint Risk Stratification and Time-to-Event Estimation Authors: Pinar Erbil, Alberto Archetti, Eugenio Lomurno, Matteo Matteucci Published: 2026-02-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01367v1 Survival analysis is essential for clinical decision-making, as it allows practitioners to estimate time-to-event outcomes, stratify patient risk profiles, and guide treatment planning. Deep learning has revolutionized this field with unprecedented predictive capabilities but faces a fundamental trade-off between performance and interpretability. While neural networks achieve high accuracy, their black-box nature limits clinical adoption. Conversely, deep clustering-based methods that stratify patients into interpretable risk groups typically sacrifice predictive power. We propose CONVERSE (CONtrastive Variational Ensemble for Risk Stratification and Estimation), a deep survival model that bridges this gap by unifying variational autoencoders with contrastive learning for interpretable risk stratification. CONVERSE combines variational embeddings with multiple intra- and inter-cluster contrastive losses. Self-paced learning progressively incorporates samples from easy to hard, improving training stability. The model supports cluster-specific survival heads, enabling accurate ensemble predictions. Comprehensive evaluation on four benchmark datasets demonstrates that CONVERSE achieves competitive or superior performance compared to existing deep survival methods, while maintaining meaningful patient stratification. --- ### When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for Reasoning Authors: Wang Yang, Shouren Wang, Chaoda Song, Chuang Ma, Xinpeng Li, Nengbo Wang, Kaixiong Zhou, Vipin Chaudhary, Xiaotian Han Published: 2026-02-01 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.01365v1 Group Relative Policy Optimization (GRPO) has become a key technique for improving reasoning abilities in large language models, yet its behavior under different domain sequencing strategies is poorly understood. In particular, the impact of sequential (one domain at a time) versus mixed-domain (multiple domain at a time) training in GRPO has not been systematically studied. We provide the first systematic analysis of training-order effects across math, science, logic, and puzzle reasoning tasks. We found (1) single-domain generalization is highly asymmetric: training on other domains improves math reasoning by approximately 25\% accuracy, while yielding negligible transfer to logic and puzzle; (2) cross-domain interactions are highly order-dependent: training in the order math$\rightarrow$science achieves 83\% / 41\% accuracy on math / science, while reversing the order to science$\rightarrow$math degrades performance to 77\% / 25\%; (3) no single strategy is universally optimal in multi-domain training: sequential training favors math (up to 84\%), mixed training favors science and logic, and poor ordering can incur large performance gaps (from 70\% to 56\%). Overall, our findings demonstrate that GRPO under multi-domain settings exhibits pronounced asymmetry, order sensitivity, and strategy dependence, highlighting the necessity of domain-aware and order-aware training design. --- ### Causally Disentangled Contrastive Learning for Multilingual Speaker Embeddings Authors: Mariëtte Olijslager, Seyed Sahand Mohammadi Ziabari, Ali Mohammed Mansoor Alsahag Published: 2026-02-01 Categories: cs.SD, cs.CL, eess.AS arXiv: https://arxiv.org/abs/2602.01363v1 Self-supervised speaker embeddings are widely used in speaker verification systems, but prior work has shown that they often encode sensitive demographic attributes, raising fairness and privacy concerns. This paper investigates the extent to which demographic information, specifically gender, age, and accent, is present in SimCLR-trained speaker embeddings and whether such leakage can be mitigated without severely degrading speaker verification performance. We study two debiasing strategies: adversarial training through gradient reversal and a causal bottleneck architecture that explicitly separates demographic and residual information. Demographic leakage is quantified using both linear and nonlinear probing classifiers, while speaker verification performance is evaluated using ROC-AUC and EER. Our results show that gender information is strongly and linearly encoded in baseline embeddings, whereas age and accent are weaker and primarily nonlinearly represented. Adversarial debiasing reduces gender leakage but has limited effect on age and accent and introduces a clear trade-off with verification accuracy. The causal bottleneck further suppresses demographic information, particularly in the residual representation, but incurs substantial performance degradation. These findings highlight fundamental limitations in mitigating demographic leakage in self-supervised speaker embeddings and clarify the trade-offs inherent in current debiasing approaches. --- ### Balancing Understanding and Generation in Discrete Diffusion Models Authors: Yue Liu, Yuzhong Zhao, Zheyong Xie, Qixiang Ye, Jianbin Jiao, Yao Hu, Shaosheng Cao, Yunfan Liu Published: 2026-02-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.01362v1 In discrete generative modeling, two dominant paradigms demonstrate divergent capabilities: Masked Diffusion Language Models (MDLM) excel at semantic understanding and zero-shot generalization, whereas Uniform-noise Diffusion Language Models (UDLM) achieve strong few-step generation quality, yet neither attains balanced performance across both dimensions. To address this, we propose XDLM, which bridges the two paradigms via a stationary noise kernel. XDLM offers two key contributions: (1) it provides a principled theoretical unification of MDLM and UDLM, recovering each paradigm as a special case; and (2) an alleviated memory bottleneck enabled by an algebraic simplification of the posterior probabilities. Experiments demonstrate that XDLM advances the Pareto frontier between understanding capability and generation quality. Quantitatively, XDLM surpasses UDLM by 5.4 points on zero-shot text benchmarks and outperforms MDLM in few-step image generation (FID 54.1 vs. 80.8). When scaled to tune an 8B-parameter large language model, XDLM achieves 15.0 MBPP in just 32 steps, effectively doubling the baseline performance. Finally, analysis of training dynamics reveals XDLM's superior potential for long-term scaling. Code is available at https://github.com/MzeroMiko/XDLM --- ### PaAno: Patch-Based Representation Learning for Time-Series Anomaly Detection Authors: Jinju Park, Seokho Kang Published: 2026-02-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01359v3 Although recent studies on time-series anomaly detection have increasingly adopted ever-larger neural network architectures such as transformers and foundation models, they incur high computational costs and memory usage, making them impractical for real-time and resource-constrained scenarios. Moreover, they often fail to demonstrate significant performance gains over simpler methods under rigorous evaluation protocols. In this study, we propose Patch-based representation learning for time-series Anomaly detection (PaAno), a lightweight yet effective method for fast and efficient time-series anomaly detection. PaAno extracts short temporal patches from time-series training data and uses a 1D convolutional neural network to embed each patch into a vector representation. The model is trained using a combination of triplet loss and pretext loss to ensure the embeddings capture informative temporal patterns from input patches. During inference, the anomaly score at each time step is computed by comparing the embeddings of its surrounding patches to those of normal patches extracted from the training time-series. Evaluated on the TSB-AD benchmark, PaAno achieved state-of-the-art performance, significantly outperforming existing methods, including those based on heavy architectures, on both univariate and multivariate time-series anomaly detection across various range-wise and point-wise performance measures. --- ### Towards knowledge-based workflows: a semantic approach to atomistic simulations for mechanical and thermodynamic properties Authors: Abril Azocar Guzman, Hoang-Thien Luu, Sarath Menon, Tilmann Hickel, Nina Merkert, Stefan Sandfeld Published: 2026-02-01 Categories: cond-mat.mtrl-sci, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2602.01358v1 Mechanical and thermodynamic properties, including the influence of crystal defects, are critical for evaluating materials in engineering applications. Molecular dynamics simulations provide valuable insight into these mechanisms at the atomic scale. However, current practice often relies on fragmented scripts with inconsistent metadata and limited provenance, which hinders reproducibility, interoperability, and reuse. FAIR data principles and workflow-based approaches offer a path to address these limitations. We present reusable atomistic workflows that incorporate metadata annotation aligned with application ontologies, enabling automatic provenance capture and FAIR-compliant data outputs. The workflows cover key mechanical and thermodynamic quantities, including equation of state, elastic tensors, mechanical loading, thermal properties, defect formation energies, and nanoindentation. We demonstrate validation of structure-property relations such as the Hall-Petch effect and show that the workflows can be reused across different interatomic potentials and materials within a coherent semantic framework. The approach provides AI-ready simulation data, supports emerging agentic AI workflows, and establishes a generalizable blueprint for knowledge-based mechanical and thermodynamic simulations. --- ### Your Self-Play Algorithm is Secretly an Adversarial Imitator: Understanding LLM Self-Play through the Lens of Imitation Learning Authors: Shangzhe Li, Xuchao Zhang, Chetan Bansal, Weitong Zhang Published: 2026-02-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.01357v2 Self-play post-training methods has emerged as an effective approach for finetuning large language models and turn the weak language model into strong language model without preference data. However, the theoretical foundations for self-play finetuning remain underexplored. In this work, we tackle this by connecting self-play finetuning with adversarial imitation learning by formulating finetuning procedure as a min-max game between the model and a regularized implicit reward player parameterized by the model itself. This perspective unifies self-play imitation and general preference alignment within a common framework. Under this formulation, we present a game-theoretic analysis showing that the self-play finetuning will converge to it's equilibrium. Guided by this theoretical formulation, we propose a new self-play imitation finetuning algorithm based on the $χ^2$-divergence variational objective with bounded rewards and improved stability. Experiments on various of language model finetuning tasks demonstrate consistent improvements over existing self-play methods and validate our theoretical insights. --- ### Aggregation Queries over Unstructured Text: Benchmark and Agentic Method Authors: Haojia Zhu, Qinyuan Xu, Haoyu Li, Yuxi Liu, Hanchen Qiu, Jiaoyan Chen, Jiahui Jin Published: 2026-02-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.01355v2 Aggregation query over free text is a long-standing yet underexplored problem. Unlike ordinary question answering, aggregate queries require exhaustive evidence collection and systems are required to "find all," not merely "find one." Existing paradigms such as Text-to-SQL and Retrieval-Augmented Generation fail to achieve this completeness. In this work, we formalize entity-level aggregation querying over text in a corpus-bounded setting with strict completeness requirement. To enable principled evaluation, we introduce AGGBench, a benchmark designed to evaluate completeness-oriented aggregation under realistic large-scale corpus. To accompany the benchmark, we propose DFA (Disambiguation--Filtering--Aggregation), a modular agentic baseline that decomposes aggregation querying into interpretable stages and exposes key failure modes related to ambiguity, filtering, and aggregation. Empirical results show that DFA consistently improves aggregation evidence coverage over strong RAG and agentic baselines. The data and code are available in \href{https://anonymous.4open.science/r/DFA-A4C1}. --- ### T2M Mamba: Motion Periodicity-Saliency Coupling Approach for Stable Text-Driven Motion Generation Authors: Xingzu Zhan, Chen Xie, Honghang Chen, Yixun Lin, Xiaochun Mai Published: 2026-02-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01352v1 Text-to-motion generation, which converts motion language descriptions into coherent 3D human motion sequences, has attracted increasing attention in fields, such as avatar animation and humanoid robotic interaction. Though existing models have achieved significant fidelity, they still suffer from two core limitations: (i) They treat motion periodicity and keyframe saliency as independent factors, overlooking their coupling and causing generation drift in long sequences. (ii) They are fragile to semantically equivalent paraphrases, where minor synonym substitutions distort textual embeddings, propagating through the decoder and producing unstable or erroneous motions. In this work, we propose T2M Mamba to address these limitations by (i) proposing Periodicity-Saliency Aware Mamba, which utilizes novel algorithms for keyframe weight estimation via enhanced Density Peaks Clustering and motion periodicity estimation via FFT-accelerated autocorrelation to capture coupled dynamics with minimal computational overhead, and (ii) constructing a Periodic Differential Cross-modal Alignment Module (PDCAM) to enhance robust alignment of textual and motion embeddings. Extensive experiments on HumanML3D and KIT-ML datasets have been conducted, confirming the effectiveness of our approach, achieving an FID of 0.068 and consistent gains on all other metrics. --- ### Does Faithfulness-Guided Alignment Hurt Accuracy? Unlocking Accurate and Faithful Post-Retrieval Reasoning Authors: Yu Liu, Wenxiao Zhang, Diandian Guo, Cong Cao, Fangfang Yuan, Qiang Sun, Yanbing Liu, Jin B. Hong, Zhiyuan Ma Published: 2026-02-01 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.01348v3 Retrieval-augmented generation (RAG) can achieve strong answer accuracy on multi-hop questions, but outcome-level rewards often leave reasoning traces weakly grounded and difficult to audit. Under noisy retrieval, models may exhibit right-answer-wrong-reason failures, where the final answer is correct but the supporting rationale exploits shortcuts or unsupported evidence. We therefore ask whether faithfulness-guided alignment hurts answer accuracy in post-retrieval reasoning. To study this question, we propose CRAFT (Calibrated Reasoning with Answer-Faithful Traces), a reinforcement learning framework for the response-generation stage of retrieval-augmented multi-hop question answering. CRAFT trains models to produce structured reasoning traces with configurable auditability, while combining deterministic rewards for format compliance, answer correctness, and citation validity with a judge-based reward for semantic faithfulness. Experiments across model scales and benchmarks show that CRAFT unlocks task-specific reasoning capacity from 1.5B upward, improving both answer accuracy and Faithfulness; at 0.5B, performance remains sharply template-dependent. At 7B, CRAFT improves Faithfulness over the Base model in all evaluated settings and remains competitive with strong closed-source models. Code is available at https://github.com/Ameame1/CRAFT. --- ### Model Specific Task Similarity for Vision Language Model Selection via Layer Conductance Authors: Wei Yang, Hong Xie, Tao Tan, Xin Li, Defu Lian, Enhong Chen Published: 2026-02-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.01346v2 While open sourced Vision-Language Models (VLMs) have proliferated, selecting the optimal pretrained model for a specific downstream task remains challenging. Exhaustive evaluation is often infeasible due to computational constraints and data limitations in few shot scenarios. Existing selection methods fail to fully address this: they either rely on data-intensive proxies or use symmetric textual descriptors that neglect the inherently directional and model-specific nature of transferability. To address this problem, we propose a framework that grounds model selection in the internal functional dynamics of the visual encoder. Our approach represents each task via layer wise conductance and derives a target-conditioned block importance distribution through entropy regularized alignment. Building on this, we introduce Directional Conductance Divergence (DCD), an asymmetric metric that quantifies how effectively a source task covers the target's salient functional blocks. This allows for predicting target model rankings by aggregating source task ranks without direct inference. Experimental results on 48 VLMs across 21 datasets demonstrate that our method outperforms state-of-the-art baselines, achieving a 14.7% improvement in NDCG@5 over SWAB. --- ### Model Specific Task Similarity for Vision Language Model Selection via Layer Conductance Authors: Wei Yang, Hong Xie, Tao Tan, Xin Li, Defu Lian, Enhong Chen Published: 2026-02-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.01346v1 While open sourced Vision-Language Models (VLMs) have proliferated, selecting the optimal pretrained model for a specific downstream task remains challenging. Exhaustive evaluation is often infeasible due to computational constraints and data limitations in few shot scenarios. Existing selection methods fail to fully address this: they either rely on data-intensive proxies or use symmetric textual descriptors that neglect the inherently directional and model-specific nature of transferability. To address this problem, we propose a framework that grounds model selection in the internal functional dynamics of the visual encoder. Our approach represents each task via layer wise conductance and derives a target-conditioned block importance distribution through entropy regularized alignment. Building on this, we introduce Directional Conductance Divergence (DCD), an asymmetric metric that quantifies how effectively a source task covers the target's salient functional blocks. This allows for predicting target model rankings by aggregating source task ranks without direct inference. Experimental results on 48 VLMs across 21 datasets demonstrate that our method outperforms state-of-the-art baselines, achieving a 14.7% improvement in NDCG@5 over SWAB. --- ### Adaptive Visual Autoregressive Acceleration via Dual-Linkage Entropy Analysis Authors: Yu Zhang, Jingyi Liu, Feng Liu, Duoqian Miao, Qi Zhang, Kexue Fu, Changwei Wang, Longbing Cao Published: 2026-02-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01345v2 Visual AutoRegressive modeling (VAR) suffers from substantial computational cost due to the massive token count involved. Failing to account for the continuous evolution of modeling dynamics, existing VAR token reduction methods face three key limitations: heuristic stage partition, non-adaptive schedules, and limited acceleration scope, thereby leaving significant acceleration potential untapped. Since entropy variation intrinsically reflects the transition of predictive uncertainty, it offers a principled measure to capture modeling dynamics evolution. Therefore, we propose NOVA, a training-free token reduction acceleration framework for VAR models via entropy analysis. NOVA adaptively determines the acceleration activation scale during inference by online identifying the inflection point of scale entropy growth. Through scale-linkage and layer-linkage ratio adjustment, NOVA dynamically computes distinct token reduction ratios for each scale and layer, pruning low-entropy tokens while reusing the cache derived from the residuals at the prior scale to accelerate inference and maintain generation quality. Extensive experiments and analyses validate NOVA as a simple yet effective training-free acceleration framework. --- ### Adaptive Quantum-Safe Cryptography for 6G Vehicular Networks via Context-Aware Optimization Authors: Poushali Sengupta, Mayank Raikwar, Sabita Maharjan, Frank Eliassen, Yan Zhang Published: 2026-02-01 Categories: cs.CR, cs.AI, stat.AP arXiv: https://arxiv.org/abs/2602.01342v1 Powerful quantum computers in the future may be able to break the security used for communication between vehicles and other devices (Vehicle-to-Everything, or V2X). New security methods called post-quantum cryptography can help protect these systems, but they often require more computing power and can slow down communication, posing a challenge for fast 6G vehicle networks. In this paper, we propose an adaptive post-quantum cryptography (PQC) framework that predicts short-term mobility and channel variations and dynamically selects suitable lattice-, code-, or hash-based PQC configurations using a predictive multi-objective evolutionary algorithm (APMOEA) to meet vehicular latency and security constraints.However, frequent cryptographic reconfiguration in dynamic vehicular environments introduces new attack surfaces during algorithm transitions. A secure monotonic-upgrade protocol prevents downgrade, replay, and desynchronization attacks during transitions. Theoretical results show decision stability under bounded prediction error, latency boundedness under mobility drift, and correctness under small forecast noise. These results demonstrate a practical path toward quantum-safe cryptography in future 6G vehicular networks. Through extensive experiments based on realistic mobility (LuST), weather (ERA5), and NR-V2X channel traces, we show that the proposed framework reduces end-to-end latency by up to 27\%, lowers communication overhead by up to 65\%, and effectively stabilizes cryptographic switching behavior using reinforcement learning. Moreover, under the evaluated adversarial scenarios, the monotonic-upgrade protocol successfully prevents downgrade, replay, and desynchronization attacks. --- ### MTC-VAE: Multi-Level Temporal Compression with Content Awareness Authors: Yubo Dong, Linchao Zhu Published: 2026-02-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01340v1 Latent Video Diffusion Models (LVDMs) rely on Variational Autoencoders (VAEs) to compress videos into compact latent representations. For continuous Variational Autoencoders (VAEs), achieving higher compression rates is desirable; yet, the efficiency notably declines when extra sampling layers are added without expanding the dimensions of hidden channels. In this paper, we present a technique to convert fixed compression rate VAEs into models that support multi-level temporal compression, providing a straightforward and minimal fine-tuning approach to counteract performance decline at elevated compression rates.Moreover, we examine how varying compression levels impact model performance over video segments with diverse characteristics, offering empirical evidence on the effectiveness of our proposed approach. We also investigate the integration of our multi-level temporal compression VAE with diffusion-based generative models, DiT, highlighting successful concurrent training and compatibility within these frameworks. This investigation illustrates the potential uses of multi-level temporal compression. --- ### Finding Differentially Private Second Order Stationary Points in Stochastic Minimax Optimization Authors: Difei Xu, Youming Tao, Meng Ding, Chenglin Fan, Di Wang Published: 2026-02-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.01339v1 We provide the first study of the problem of finding differentially private (DP) second-order stationary points (SOSP) in stochastic (non-convex) minimax optimization. Existing literature either focuses only on first-order stationary points for minimax problems or on SOSP for classical stochastic minimization problems. This work provides, for the first time, a unified and detailed treatment of both empirical and population risks. Specifically, we propose a purely first-order method that combines a nested gradient descent--ascent scheme with SPIDER-style variance reduction and Gaussian perturbations to ensure privacy. A key technical device is a block-wise ($q$-period) analysis that controls the accumulation of stochastic variance and privacy noise without summing over the full iteration horizon, yielding a unified treatment of both empirical-risk and population formulations. Under standard smoothness, Hessian-Lipschitzness, and strong concavity assumptions, we establish high-probability guarantees for reaching an $(α,\sqrt{ρ_Φα})$-approximate second-order stationary point with $α= \mathcal{O}( (\frac{\sqrt{d}}{n\varepsilon})^{2/3})$ for empirical risk objectives and $\mathcal{O}(\frac{1}{n^{1/3}} + (\frac{\sqrt{d}}{n\varepsilon})^{1/2})$ for population objectives, matching the best known rates for private first-order stationarity. --- ### High-accuracy sampling for diffusion models and log-concave distributions Authors: Fan Chen, Sinho Chewi, Constantinos Daskalakis, Alexander Rakhlin Published: 2026-02-01 Categories: cs.LG, math.ST, stat.ML arXiv: https://arxiv.org/abs/2602.01338v2 We present algorithms for diffusion model sampling which obtain $δ$-error in $\mathrm{polylog}(1/δ)$ steps, given access to $\widetilde O(δ)$-accurate score estimates in $L^2$. This is an exponential improvement over all previous results. Specifically, under minimal data assumptions, the complexity is $\widetilde O(d_\star \mathrm{polylog}(1/δ))$ where $d_\star$ is the intrinsic dimension of the data. Further, under a non-uniform $L$-Lipschitz condition, the complexity reduces to $\widetilde O(L \mathrm{polylog}(1/δ))$. Our approach also yields the first $\mathrm{polylog}(1/δ)$ complexity sampler for general log-concave distributions using only gradient evaluations. --- ### Beyond Pixels: Visual Metaphor Transfer via Schema-Driven Agentic Reasoning Authors: Yu Xu, Yuxin Zhang, Lin Gao, Oliver Deussen, Tong-Yee Lee, Fan Tang Published: 2026-02-01 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.01335v2 A visual metaphor constitutes a high-order form of human creativity, employing cross-domain semantic fusion to transform abstract concepts into impactful visual rhetoric. Despite the remarkable progress of generative AI, existing models remain largely confined to pixel-level instruction alignment and surface-level appearance preservation, failing to capture the underlying abstract logic necessary for genuine metaphorical generation. To bridge this gap, we introduce the task of Visual Metaphor Transfer (VMT), which challenges models to autonomously decouple the "creative essence" from a reference image and re-materialize that abstract logic onto a user-specified target subject. We propose a cognitive-inspired, multi-agent framework that operationalizes Conceptual Blending Theory (CBT) through a novel Schema Grammar ("G"). This structured representation decouples relational invariants from specific visual entities, providing a rigorous foundation for cross-domain logic re-instantiation. Our pipeline executes VMT through a collaborative system of specialized agents: a perception agent that distills the reference into a schema, a transfer agent that maintains generic space invariance to discover apt carriers, a generation agent for high-fidelity synthesis and a hierarchical diagnostic agent that mimics a professional critic, performing closed-loop backtracking to identify and rectify errors across abstract logic, component selection, and prompt encoding. Extensive experiments and human evaluations demonstrate that our method significantly outperforms SOTA baselines in metaphor consistency, analogy appropriateness, and visual creativity, paving the way for automated high-impact creative applications in advertising and media. Project page with source code and self-contained skills is at https://yuci-gpt.github.io/Beyond-Pixels/. --- ### Beyond Pixels: Visual Metaphor Transfer via Schema-Driven Agentic Reasoning Authors: Yu Xu, Yuxin Zhang, Juan Cao, Lin Gao, Chunyu Wang, Oliver Deussen, Tong-Yee Lee, Fan Tang Published: 2026-02-01 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.01335v1 A visual metaphor constitutes a high-order form of human creativity, employing cross-domain semantic fusion to transform abstract concepts into impactful visual rhetoric. Despite the remarkable progress of generative AI, existing models remain largely confined to pixel-level instruction alignment and surface-level appearance preservation, failing to capture the underlying abstract logic necessary for genuine metaphorical generation. To bridge this gap, we introduce the task of Visual Metaphor Transfer (VMT), which challenges models to autonomously decouple the "creative essence" from a reference image and re-materialize that abstract logic onto a user-specified target subject. We propose a cognitive-inspired, multi-agent framework that operationalizes Conceptual Blending Theory (CBT) through a novel Schema Grammar ("G"). This structured representation decouples relational invariants from specific visual entities, providing a rigorous foundation for cross-domain logic re-instantiation. Our pipeline executes VMT through a collaborative system of specialized agents: a perception agent that distills the reference into a schema, a transfer agent that maintains generic space invariance to discover apt carriers, a generation agent for high-fidelity synthesis and a hierarchical diagnostic agent that mimics a professional critic, performing closed-loop backtracking to identify and rectify errors across abstract logic, component selection, and prompt encoding. Extensive experiments and human evaluations demonstrate that our method significantly outperforms SOTA baselines in metaphor consistency, analogy appropriateness, and visual creativity, paving the way for automated high-impact creative applications in advertising and media. Source code will be made publicly available. --- ### What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-Zoom Authors: Yan Ma, Weiyu Zhang, Tianle Li, Linge Du, Xuyang Shen, Pengfei Liu Published: 2026-02-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01334v2 Vision tool-use reinforcement learning (RL) can equip vision language models with visual operators such as crop-and-zoom and achieves strong performance gains, yet it remains unclear whether these gains are driven by improvements in tool use or evolving intrinsic capabilities. We introduce MED (Measure--Explain--Diagnose), a coarse-to-fine framework that disentangles intrinsic capability changes from tool-induced effects, decomposes the tool-induced performance difference into gain and harm terms, and probes the mechanisms driving their evolution. Across checkpoint-level analyses in the crop-and-zoom setting on two VLMs with different tool priors and six benchmarks, we find that improvements are dominated by intrinsic learning, while tool-use RL mainly reduces tool-induced harm (e.g., fewer call-induced errors and weaker tool schema interference) and yields limited progress in tool-based correction of intrinsic failures. Overall, in the crop-and-zoom setting studied here, current vision tool-use RL learns to coexist safely with tools rather than master them. --- ### A-MapReduce: Executing Wide Search via Agentic MapReduce Authors: Mingju Chen, Guibin Zhang, Heng Chang, Yuchen Guo, Shiji Zhou Published: 2026-02-01 Categories: cs.MA, cs.CL arXiv: https://arxiv.org/abs/2602.01331v1 Contemporary large language model (LLM)-based multi-agent systems exhibit systematic advantages in deep research tasks, which emphasize iterative, vertically structured information seeking. However, when confronted with wide search tasks characterized by large-scale, breadth-oriented retrieval, existing agentic frameworks, primarily designed around sequential, vertically structured reasoning, remain stuck in expansive search objectives and inefficient long-horizon execution. To bridge this gap, we propose A-MapReduce, a MapReduce paradigm-inspired multi-agent execution framework that recasts wide search as a horizontally structured retrieval problem. Concretely, A-MapReduce implements parallel processing of massive retrieval targets through task-adaptive decomposition and structured result aggregation. Meanwhile, it leverages experiential memory to drive the continual evolution of query-conditioned task allocation and recomposition, enabling progressive improvement in large-scale wide-search regimes. Extensive experiments on five agentic benchmarks demonstrate that A-MapReduce is (i) high-performing, achieving state-of-the-art performance on WideSearch and DeepWideSearch, and delivering 5.11% - 17.50% average Item F1 improvements compared with strong baselines with OpenAI o3 or Gemini 2.5 Pro backbones; (ii) cost-effective and efficient, delivering superior cost-performance trade-offs and reducing running time by 45.8\% compared to representative multi-agent baselines. The code is available at https://github.com/mingju-c/AMapReduce. --- ### FlowCast: Trajectory Forecasting for Scalable Zero-Cost Speculative Flow Matching Authors: Divya Jyoti Bajpai, Shubham Agarwal, Apoorv Saxena, Kuldeep Kulkarni, Subrata Mitra, Manjesh Kumar Hanawal Published: 2026-02-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01329v1 Flow Matching (FM) has recently emerged as a powerful approach for high-quality visual generation. However, their prohibitively slow inference due to a large number of denoising steps limits their potential use in real-time or interactive applications. Existing acceleration methods, like distillation, truncation, or consistency training, either degrade quality, incur costly retraining, or lack generalization. We propose FlowCast, a training-free speculative generation framework that accelerates inference by exploiting the fact that FM models are trained to preserve constant velocity. FlowCast speculates future velocity by extrapolating current velocity without incurring additional time cost, and accepts it if it is within a mean-squared error threshold. This constant-velocity forecasting allows redundant steps in stable regions to be aggressively skipped while retaining precision in complex ones. FlowCast is a plug-and-play framework that integrates seamlessly with any FM model and requires no auxiliary networks. We also present a theoretical analysis and bound the worst-case deviation between speculative and full FM trajectories. Empirical evaluations demonstrate that FlowCast achieves $>2.5\times$ speedup in image generation, video generation, and editing tasks, outperforming existing baselines with no quality loss as compared to standard full generation. --- ### DreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas Authors: Zirui Wu, Lin Zheng, Zhihui Xie, Jiacheng Ye, Jiahui Gao, Shansan Gong, Yansong Feng, Zhenguo Li, Wei Bi, Guorui Zhou, Lingpeng Kong Published: 2026-02-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.01326v1 Diffusion Language Models (DLMs) present a compelling alternative to autoregressive models, offering flexible, any-order infilling without specialized prompting design. However, their practical utility is blocked by a critical limitation: the requirement of a fixed-length masked sequence for generation. This constraint severely degrades code infilling performance when the predefined mask size mismatches the ideal completion length. To address this, we propose DreamOn, a novel diffusion framework that enables dynamic, variable-length generation. DreamOn augments the diffusion process with two length control states, allowing the model to autonomously expand or contract the output length based solely on its own predictions. We integrate this mechanism into existing DLMs with minimal modifications to the training objective and no architectural changes. Built upon Dream-Coder-7B and DiffuCoder-7B, DreamOn achieves infilling performance on par with state-of-the-art autoregressive models on HumanEval-Infilling and SantaCoder-FIM and matches oracle performance achieved with ground-truth length. Our work removes a fundamental barrier to the practical deployment of DLMs, significantly advancing their flexibility and applicability for variable-length generation. Our code is available at https://github.com/DreamLM/DreamOn. --- ### PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding Authors: Panagiotis Koromilas, Andreas D. Demou, James Oldfield, Yannis Panagakis, Mihalis Nicolaou Published: 2026-02-01 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2602.01322v2 Sparse autoencoders (SAEs) interpret neural network representations by decomposing activations into sparse combinations of dictionary atoms. However, SAEs assume features combine additively through linear reconstruction, an assumption that cannot capture compositional structure: linear models cannot distinguish whether ''Starbucks'' arises from the composition of ''star'' and ''coffee'' features or merely their co-occurrence. This forces SAEs to allocate monolithic features for compound concepts rather than decomposing them into interpretable constituents. We introduce PolySAE, which extends the SAE decoder with higher-order terms to model feature interactions while preserving the linear encoder essential for interpretability. Through low-rank tensor factorization on a shared projection subspace, PolySAE captures pairwise and triple feature interactions with small parameter overhead (3% on GPT2). Across four language models and three SAE variants, PolySAE achieves an average improvement of $\sim$8% in probing F1 while maintaining comparable reconstruction error, and produces 2--10$\times$ larger Wasserstein distances between class-conditional feature distributions. Critically, learned interaction weights exhibit negligible correlation with co-occurrence frequency ($r = 0.06$ vs $r = 0.82$ for SAE feature covariance), suggesting that polynomial terms capture compositional structure largely independent of surface statistics. Finally, the learned interaction directions causally steer model outputs toward the corresponding compositional semantics. --- ### TxRay: Agentic Postmortem of Live Blockchain Attacks Authors: Ziyue Wang, Jiangshan Yu, Kaihua Qin, Dawn Song, Arthur Gervais, Liyi Zhou Published: 2026-02-01 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.01317v5 Decentralized Finance (DeFi) has turned blockchains into financial infrastructure, allowing anyone to trade, lend, and build protocols without intermediaries, but this openness exposes pools of value controlled by code. Within five years, the DeFi ecosystem has lost over 15.75B USD to reported exploits. Many exploits arise from permissionless opportunities that any participant can trigger using only public state and standard interfaces, which we call Anyone-Can-Take (ACT) opportunities. Despite on-chain transparency, postmortem analysis remains slow and manual: investigations start from limited evidence, sometimes only a single transaction hash, and must reconstruct the exploit lifecycle by recovering related transactions, contract code, and state dependencies. We present TxRay, a Large Language Model (LLM) agentic postmortem system that uses tool calls to reconstruct live ACT attacks from limited evidence. Starting from one or more seed transactions, TxRay recovers the exploit lifecycle, derives an evidence-backed root cause, and generates a runnable, self-contained Proof of Concept (PoC) that deterministically reproduces the incident. TxRay self-checks postmortems by encoding incident-specific semantic oracles as executable assertions. To evaluate PoC correctness and quality, we develop PoCEvaluator, an independent agentic execution-and-review evaluator. On 114 incidents from DeFiHackLabs, TxRay produces an expert-aligned root cause and an executable PoC for 105 incidents, achieving 92.11% end-to-end reproduction. Under PoCEvaluator, 98.1% of TxRay PoCs avoid hard-coding attacker addresses, a +22.9pp lift over DeFiHackLabs. In a live deployment, TxRay delivers validated root causes in 40 minutes and PoCs in 59 minutes at median latency. TxRay's oracle-validated PoCs enable attack imitation, improving coverage by 15.6% and 65.5% over STING and APE. --- ### Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialogues Authors: Chuanrui Hu, Tong Li, Xingze Gao, Hongda Chen, Yi Bai, Dannong Xu, Tianwei Lin, Xiaohong Li, Yunyun Han, Jian Pei, Yafeng Deng Published: 2026-02-01 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.01313v3 Long-term conversational memory in practical LLM applications is inherently collaborative: information is produced by multiple participants, scattered across groups and channels, revised over time, and implicitly grounded in roles and social context. Yet there is currently no established benchmark that evaluates memory under interaction patterns resembling real-world deployment, as existing benchmarks largely focus on dyadic or single-topic dialogues. In this paper, we introduce EverMemBench, the first benchmark designed for long-horizon collaborative memory, built from multi-party, multi-group conversations spanning over one million tokens with dense cross-topic interleaving, temporally evolving decisions, and role-conditioned personas. EverMemBench evaluates memory systems using 2400 QA pairs across three dimensions essential for real applications: fine-grained recall, memory awareness, and user profile understanding. Our evaluation reveals fundamental limitations of current systems: multi-hop reasoning collapses under multi-party attribution even with oracle evidence (26% accuracy), temporal reasoning fails without explicit version semantics beyond timestamps, and memory awareness is bottlenecked by retrieval, as similarity-based methods miss implicitly relevant information. EverMemBench thus represents a concrete step toward realistic evaluation of LLM memory and a cornerstone benchmark for developing next-generation LLMs that reason over time, roles, and collaborative interaction structure. Our benchmark and code are publicly available at https://github.com/EverMind-AI/EverMemBench. --- ### Imperfect Influence, Preserved Rankings: A Theory of TRAK for Data Attribution Authors: Han Tong, Shubhangi Ghosh, Haolin Zou, Arian Maleki Published: 2026-02-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.01312v1 Data attribution, tracing a model's prediction back to specific training data, is an important tool for interpreting sophisticated AI models. The widely used TRAK algorithm addresses this challenge by first approximating the underlying model with a kernel machine and then leveraging techniques developed for approximating the leave-one-out (ALO) risk. Despite its strong empirical performance, the theoretical conditions under which the TRAK approximations are accurate as well as the regimes in which they break down remain largely unexplored. In this paper, we provide a theoretical analysis of the TRAK algorithm, characterizing its performance and quantifying the errors introduced by the approximations on which the method relies. We show that although the approximations incur significant errors, TRAK's estimated influence remains highly correlated with the original influence and therefore largely preserves the relative ranking of data points. We corroborate our theoretical results through extensive simulations and empirical studies. --- ### Dispelling the Curse of Singularities in Neural Network Optimizations Authors: Hengjie Cao, Mengyi Chen, Yifeng Yang, Fang Dong, Ruijun Huang, Anrui Chen, Jixian Zhou, Mingzhi Dong, Yujiang Wang, Dongsheng Li, Wenyi Fang, Yuanyi Lin et al. Published: 2026-02-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.01308v2 This work investigates the optimization instability of deep neural networks from a less-explored yet insightful perspective: the emergence and amplification of singularities in the parametric space. Our analysis reveals that parametric singularities inevitably grow with gradient updates and further intensify alignment with representations, leading to increased singularities in the representation space. We show that the gradient Frobenius norms are bounded by the top singular values of the weight matrices, and as training progresses, the mutually reinforcing growth of weight and representation singularities, termed the curse of singularities, relaxes these bounds, escalating the risk of sharp loss explosions. To counter this, we propose Parametric Singularity Smoothing (PSS), a lightweight, flexible, and effective method for smoothing the singular spectra of weight matrices. Extensive experiments across diverse datasets, architectures, and optimizers demonstrate that PSS mitigates instability, restores trainability even after failure, and improves both training efficiency and generalization. --- ### DeCorStory: Gram-Schmidt Prompt Embedding Decorrelation for Consistent Storytelling Authors: Ayushman Sarkar, Zhenyu Yu, Mohd Yamani Idna Idris Published: 2026-02-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01306v1 Maintaining visual and semantic consistency across frames is a key challenge in text-to-image storytelling. Existing training-free methods, such as One-Prompt-One-Story, concatenate all prompts into a single sequence, which often induces strong embedding correlation and leads to color leakage, background blending, and identity drift. We propose DeCorStory, a training-free inference-time framework that explicitly reduces inter-frame semantic interference. DeCorStory applies Gram-Schmidt prompt embedding decorrelation to orthogonalize frame-level semantics, followed by singular value reweighting to strengthen prompt-specific information and identity-preserving cross-attention to stabilize character identity during diffusion. The method requires no model modification or fine-tuning and can be seamlessly integrated into existing diffusion pipelines. Experiments demonstrate consistent improvements in prompt-image alignment, identity consistency, and visual diversity, achieving state-of-the-art performance among training-free baselines. Code is available at: https://github.com/YuZhenyuLindy/DeCorStory --- ### StoryState: Agent-Based State Control for Consistent and Editable Storybooks Authors: Ayushman Sarkar, Zhenyu Yu, Wei Tang, Chu Chen, Kangning Cui, Mohd Yamani Idna Idris Published: 2026-02-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01305v1 Large multimodal models have enabled one-click storybook generation, where users provide a short description and receive a multi-page illustrated story. However, the underlying story state, such as characters, world settings, and page-level objects, remains implicit, making edits coarse-grained and often breaking visual consistency. We present StoryState, an agent-based orchestration layer that introduces an explicit and editable story state on top of training-free text-to-image generation. StoryState represents each story as a structured object composed of a character sheet, global settings, and per-page scene constraints, and employs a small set of LLM agents to maintain this state and derive 1Prompt1Story-style prompts for generation and editing. Operating purely through prompts, StoryState is model-agnostic and compatible with diverse generation backends. System-level experiments on multi-page editing tasks show that StoryState enables localized page edits, improves cross-page consistency, and reduces unintended changes, interaction turns, and editing time compared to 1Prompt1Story, while approaching the one-shot consistency of Gemini Storybook. Code is available at https://github.com/YuZhenyuLindy/StoryState --- ### ReDiStory: Region-Disentangled Diffusion for Consistent Visual Story Generation Authors: Ayushman Sarkar, Zhenyu Yu, Chu Chen, Wei Tang, Kangning Cui, Mohd Yamani Idna Idris Published: 2026-02-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01303v1 Generating coherent visual stories requires maintaining subject identity across multiple images while preserving frame-specific semantics. Recent training-free methods concatenate identity and frame prompts into a unified representation, but this often introduces inter-frame semantic interference that weakens identity preservation in complex stories. We propose ReDiStory, a training-free framework that improves multi-frame story generation via inference-time prompt embedding reorganization. ReDiStory explicitly decomposes text embeddings into identity-related and frame-specific components, then decorrelates frame embeddings by suppressing shared directions across frames. This reduces cross-frame interference without modifying diffusion parameters or requiring additional supervision. Under identical diffusion backbones and inference settings, ReDiStory improves identity consistency while maintaining prompt fidelity. Experiments on the ConsiStory+ benchmark show consistent gains over 1Prompt1Story on multiple identity consistency metrics. Code is available at: https://github.com/YuZhenyuLindy/ReDiStory --- ### Interaction-Consistent Object Removal via MLLM-Based Reasoning Authors: Ching-Kai Huang, Wen-Chieh Lin, Yan-Cen Lee Published: 2026-02-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01298v1 Image-based object removal often erases only the named target, leaving behind interaction evidence that renders the result semantically inconsistent. We formalize this problem as Interaction-Consistent Object Removal (ICOR), which requires removing not only the target object but also associated interaction elements, such as lighting-dependent effects, physically connected objects, targetproduced elements, and contextually linked objects. To address this task, we propose Reasoning-Enhanced Object Removal with MLLM (REORM), a reasoningenhanced object removal framework that leverages multimodal large language models to infer which elements must be jointly removed. REORM features a modular design that integrates MLLM-driven analysis, mask-guided removal, and a self-correction mechanism, along with a local-deployment variant that supports accurate editing under limited resources. To support evaluation, we introduce ICOREval, a benchmark consisting of instruction-driven removals with rich interaction dependencies. On ICOREval, REORM outperforms state-of-the-art image editing systems, demonstrating its effectiveness in producing interactionconsistent results. --- ### RE-MCDF: Closed-Loop Multi-Expert LLM Reasoning for Knowledge-Grounded Clinical Diagnosis Authors: Shaowei Shen, Xiaohong Yang, Jie Yang, Lianfen Huang, Yongcai Zhang, Yang Zou, Seyyedali Hosseinalipour Published: 2026-02-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.01297v3 Electronic medical records (EMRs), particularly in neurology, are inherently heterogeneous, sparse, and noisy, which poses significant challenges for large language models (LLMs) in clinical diagnosis. In such settings, single-agent systems are vulnerable to self-reinforcing errors, as their predictions lack independent validation and can drift toward spurious conclusions. Although recent multi-agent frameworks attempt to mitigate this issue through collaborative reasoning, their interactions are often shallow and loosely structured, failing to reflect the rigorous, evidence-driven processes used by clinical experts. More fundamentally, existing approaches largely ignore the rich logical dependencies among diseases, such as mutual exclusivity, pathological compatibility, and diagnostic confusion. This limitation prevents them from ruling out clinically implausible hypotheses, even when sufficient evidence is available. To overcome these, we propose RE-MCDF, a relation-enhanced multi-expert clinical diagnosis framework. RE-MCDF introduces a generation--verification--revision closed-loop architecture that integrates three complementary components: (i) a primary expert that generates candidate diagnoses and supporting evidence, (ii) a laboratory expert that dynamically prioritizes heterogeneous clinical indicators, and (iii) a multi-relation awareness and evaluation expert group that explicitly enforces inter-disease logical constraints. Guided by a medical knowledge graph (MKG), the first two experts adaptively reweight EMR evidence, while the expert group validates and corrects candidate diagnoses to ensure logical consistency. Extensive experiments on the neurology subset of CMEMR (NEEMRs) and on our curated dataset (XMEMRs) demonstrate that RE-MCDF consistently outperforms state-of-the-art baselines in complex diagnostic scenarios (https://github.com/shenshaowei/RE-MCDF). --- ### Interacted Planes Reveal 3D Line Mapping Authors: Zeran Ke, Bin Tan, Gui-Song Xia, Yujun Shen, Nan Xue Published: 2026-02-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.01296v1 3D line mapping from multi-view RGB images provides a compact and structured visual representation of scenes. We study the problem from a physical and topological perspective: a 3D line most naturally emerges as the edge of a finite 3D planar patch. We present LiP-Map, a line-plane joint optimization framework that explicitly models learnable line and planar primitives. This coupling enables accurate and detailed 3D line mapping while maintaining strong efficiency (typically completing a reconstruction in 3 to 5 minutes per scene). LiP-Map pioneers the integration of planar topology into 3D line mapping, not by imposing pairwise coplanarity constraints but by explicitly constructing interactions between plane and line primitives, thus offering a principled route toward structured reconstruction in man-made environments. On more than 100 scenes from ScanNetV2, ScanNet++, Hypersim, 7Scenes, and Tanks\&Temple, LiP-Map improves both accuracy and completeness over state-of-the-art methods. Beyond line mapping quality, LiP-Map significantly advances line-assisted visual localization, establishing strong performance on 7Scenes. Our code is released at https://github.com/calmke/LiPMAP for reproducible research. --- ### Best-of-Both-Worlds for Heavy-Tailed Markov Decision Processes Authors: Yu Chen, Yuhao Liu, Jiatai Huang, Yihan Du, Longbo Huang Published: 2026-02-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.01295v3 We investigate episodic Markov Decision Processes with heavy-tailed losses (HTMDPs). Existing approaches for HTMDPs are conservative in stochastic environments and lack adaptivity in adversarial regimes. In this work, we propose algorithms HT-FTRL-OM and HT-FTRL-UOB for HTMDPs that achieve Best-of-Both-Worlds (BoBW) guarantees: instance-independent regret in adversarial environments and logarithmic instance-dependent regret in self-bounding (including the stochastic case) environments. For the known transition setting, HT-FTRL-OM applies the Follow-The-Regularized-Leader (FTRL) framework over occupancy measures with novel skipping loss estimators, achieving a $\widetilde{O}(T^{1/α})$ regret bound in adversarial regimes and a ${O}(\log T)$ regret in stochastic regimes. Building upon this framework, we develop a novel algorithm HT-FTRL-UOB to tackle the more challenging unknown-transition setting. Under a mild truncative nonnegativity condition on the loss distributions, this algorithm employs a pessimistic skipping loss estimator and achieves a $\widetilde{O}(T^{1/α} + \sqrt{T})$ regret in adversarial regimes and a ${O}(\log^2(T))$ regret in stochastic regimes. Our analysis overcomes key barriers through several technical insights, including a local control mechanism for heavy-tailed shifted losses, a new suboptimal-mass propagation principle, and a novel regret decomposition that isolates transition uncertainty from heavy-tailed estimation errors and skipping bias. --- ### Dynamic Heuristic Neuromorphic Solver for the Edge User Allocation Problem with Bayesian Confidence Propagation Neural Network Authors: Kecheng Zhang, Anders Lansner, Ahsan Javed Awan, Naresh Balaji Ravichandran, Pawel Herman Published: 2026-02-01 Categories: cs.NE arXiv: https://arxiv.org/abs/2602.01294v1 We propose a neuromorphic solver for the NP-hard Edge User Allocation problem using an attractor network with Winner-Takes-All (WTA) mechanism implemented with the Bayesian Confidence Propagation Neural Network (BCPNN) framework. Unlike previous energy-based attractor networks, our solver uses dynamic heuristic biasing to guide allocations in real time and introduces a "no allocation" state to each WTA motif, achieving near-optimal performance with an empirically upper-bounded number of time steps. The approach is compatible with neuromorphic architectures and may offer improvements in energy efficiency. --- ### Gradient-Aligned Calibration for Post-Training Quantization of Diffusion Models Authors: Dung Anh Hoang, Cuong Pham anh Trung Le, Jianfei Cai, Thanh-Toan Do Published: 2026-02-01 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2602.01289v3 Diffusion models have shown remarkable performance in image synthesis by progressively estimating a smooth transition from a Gaussian distribution of noise to a real image. Unfortunately, their practical deployment is limited by slow inference speed, high memory usage, and the computational demands of the noise estimation process. Post-training quantization (PTQ) emerges as a promising solution to accelerate sampling and reduce memory overhead for diffusion models. Existing PTQ methods for diffusion models typically apply uniform weights to calibration samples across timesteps, which is sub-optimal since data at different timesteps may contribute differently to the diffusion process. Additionally, due to varying activation distributions and gradients across timesteps, a uniform quantization approach is sub-optimal. Each timestep requires a different gradient direction for optimal quantization, and treating them equally can lead to conflicting gradients that degrade performance. In this paper, we propose a novel PTQ method that addresses these challenges by assigning appropriate weights to calibration samples. Specifically, our approach learns to assign optimal weights to calibration samples to align the quantized model's gradients across timesteps, facilitating the quantization process. Extensive experiments on CIFAR-10, LSUN-Bedrooms, and ImageNet demonstrate the superiority of our method compared to other PTQ methods for diffusion models. --- ### EDIS: Diagnosing LLM Reasoning via Entropy Dynamics Authors: Chenghua Zhu, Siyan Wu, Xiangkang Zeng, Zishan Xu, Zhaolu Kang, Yifu Guo, Yuquan Lu, Junduan Huang, Guojing Zhou Published: 2026-02-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.01288v2 Entropy-based confidence signals are increasingly leveraged to improve reasoning in large language models (LLMs), yet existing approaches treat confidence as a static quantity -- typically aggregated over tokens. We show that the \emph{temporal evolution} of confidence during generation carries richer information than aggregate statistics alone. Analyzing token-level entropy trajectories, we identify characteristic patterns distinguishing correct from incorrect reasoning: erroneous solutions exhibit unstable dynamics, including burst spikes (sustained uncertainty growth) and peak-valley spikes (sharp rebounds following transient confidence). These patterns persist across models and training stages, suggesting they reflect intrinsic properties of reasoning failure rather than superficial noise. To formalize this observation, we introduce the Entropy Dynamics Instability Score (\textbf{EDIS}), a trajectory-level metric quantifying instability in entropy evolution. EDIS serves as an effective diagnostic signal for inference-time selection, substantially improving reasoning accuracy, and offers a promising direction for training-time sample curation. Our findings establish entropy dynamics as an underexplored yet informative lens for understanding and improving LLM reasoning. --- ### Multi-LLM Adaptive Conformal Inference for Reliable LLM Responses Authors: Kangjun Noh, Seongchan Lee, Ilmun Kim, Kyungwoo Song Published: 2026-02-01 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2602.01285v1 Ensuring factuality is essential for the safe use of Large Language Models (LLMs) in high-stakes domains such as medicine and law. Conformal inference provides distribution-free guarantees, but existing approaches are either overly conservative, discarding many true-claims, or rely on adaptive error rates and simple linear models that fail to capture complex group structures. To address these challenges, we reformulate conformal inference in a multiplicative filtering setting, modeling factuality as a product of claim-level scores. Our method, Multi-LLM Adaptive Conformal Inference (MACI), leverages ensembles to produce more accurate factuality-scores, which in our experiments led to higher retention, while validity is preserved through group-conditional calibration. Experiments show that MACI consistently achieves user-specified coverage with substantially higher retention and lower time cost than baselines. Our repository is available at https://github.com/MLAI-Yonsei/MACI ---