# Research Papers — 2026-01 · bundle page 53 of 189 > Full-text markdown of papers #2601–2650 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-01/page/53 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/52.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/54.md) ### PaperTok: Exploring the Use of Generative AI for Creating Short-form Videos for Research Communication Authors: Meziah Ruby Cristobal, Hyeonjeong Byeon, Tze-Yu Chen, Ruoxi Shang, Donghoon Shin, Ruican Zhong, Tony Zhou, Gary Hsieh Published: 2026-01-26 Categories: cs.HC, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.18218v1 The dissemination of scholarly research is critical, yet researchers often lack the time and skills to create engaging content for popular media such as short-form videos. To address this gap, we explore the use of generative AI to help researchers transform their academic papers into accessible video content. Informed by a formative study with science communicators and content creators (N=8), we designed PaperTok, an end-to-end system that automates the initial creative labor by generating script options and corresponding audiovisual content from a source paper. Researchers can then refine based on their preferences with further prompting. A mixed-methods user study (N=18) and crowdsourced evaluation (N=100) demonstrate that PaperTok's workflow can help researchers create engaging and informative short-form videos. We also identified the need for more fine-grained controls in the creation process. To this end, we offer implications for future generative tools that support science outreach. --- ### Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents Authors: Zhihan Liu, Lin Guan, Yixin Nie, Kai Zhang, Zhuoqun Hao, Lin Chen, Asli Celikyilmaz, Zhaoran Wang, Na Zhang Published: 2026-01-26 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.18217v1 Generalist LLM agents are often post-trained on a narrow set of environments but deployed across far broader, unseen domains. In this work, we investigate the challenge of agentic post-training when the eventual test domains are unknown. Specifically, we analyze which properties of reinforcement learning (RL) environments and modeling choices have the greatest influence on out-of-domain performance. First, we identify two environment axes that strongly correlate with cross-domain generalization: (i) state information richness, i.e., the amount of information for the agent to process from the state, and (ii) planning complexity, estimated via goal reachability and trajectory length under a base policy. Notably, domain realism and text-level similarity are not the primary factors; for instance, the simple grid-world domain Sokoban leads to even stronger generalization in SciWorld than the more realistic ALFWorld. Motivated by these findings, we further show that increasing state information richness alone can already effectively improve cross-domain robustness. We propose a randomization technique, which is low-overhead and broadly applicable: add small amounts of distractive goal-irrelevant features to the state to make it richer without altering the task. Beyond environment-side properties, we also examine several modeling choices: (a) SFT warmup or mid-training helps prevent catastrophic forgetting during RL but undermines generalization to domains that are not included in the mid-training datamix; and (b) turning on step-by-step thinking during RL, while not always improving in-domain performance, plays a crucial role in preserving generalization. --- ### PaperSearchQA: Learning to Search and Reason over Scientific Papers with RLVR Authors: James Burgess, Jan N. Hansen, Duo Peng, Yuhui Zhang, Alejandro Lozano, Min Woo Sun, Emma Lundberg, Serena Yeung-Levy Published: 2026-01-26 Categories: cs.LG, cs.AI, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2601.18207v1 Search agents are language models (LMs) that reason and search knowledge bases (or the web) to answer questions; recent methods supervise only the final answer accuracy using reinforcement learning with verifiable rewards (RLVR). Most RLVR search agents tackle general-domain QA, which limits their relevance to technical AI systems in science, engineering, and medicine. In this work we propose training agents to search and reason over scientific papers -- this tests technical question-answering, it is directly relevant to real scientists, and the capabilities will be crucial to future AI Scientist systems. Concretely, we release a search corpus of 16 million biomedical paper abstracts and construct a challenging factoid QA dataset called PaperSearchQA with 60k samples answerable from the corpus, along with benchmarks. We train search agents in this environment to outperform non-RL retrieval baselines; we also perform further quantitative analysis and observe interesting agent behaviors like planning, reasoning, and self-verification. Our corpus, datasets, and benchmarks are usable with the popular Search-R1 codebase for RLVR training and released on https://huggingface.co/collections/jmhb/papersearchqa. Finally, our data creation methods are scalable and easily extendable to other scientific domains. --- ### MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic Reasoning Authors: Juexiang Ye, Xue Li, Xinyu Yang, Chengkai Huang, Lanshun Nie, Lina Yao, Dechen Zhan Published: 2026-01-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.18204v1 Large language model-based agents operating in long-horizon interactions require memory systems that support temporal consistency, multi-hop reasoning, and evidence-grounded reuse across sessions. Existing approaches largely rely on unstructured retrieval or coarse abstractions, which often lead to temporal conflicts, brittle reasoning, and limited traceability. We propose MemWeaver, a unified memory framework that consolidates long-term agent experiences into three interconnected components: a temporally grounded graph memory for structured relational reasoning, an experience memory that abstracts recurring interaction patterns from repeated observations, and a passage memory that preserves original textual evidence. MemWeaver employs a dual-channel retrieval strategy that jointly retrieves structured knowledge and supporting evidence to construct compact yet information-dense contexts for reasoning. Experiments on the LoCoMo benchmark demonstrate that MemWeaver substantially improves multi-hop and temporal reasoning accuracy while reducing input context length by over 95\% compared to long-context baselines. --- ### SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback Authors: Fangyuan Xu, Rujun Han, Yanfei Chen, Zifeng Wang, I-Hung Hsu, Jun Yan, Vishy Tirumalashetty, Eunsol Choi, Tomas Pfister, Chen-Yu Lee Published: 2026-01-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.18202v1 Deep search agents, which aim to answer complex questions requiring reasoning across multiple documents, can significantly speed up the information-seeking process. Collecting human annotations for this application is prohibitively expensive due to long and complex exploration trajectories. We propose an agentic pipeline that automatically generates high quality, difficulty-controlled deep search question-answer pairs for a given corpus and a target difficulty level. Our pipeline, SAGE, consists of a data generator which proposes QA pairs and a search agent which attempts to solve the generated question and provide execution feedback for the data generator. The two components interact over multiple rounds to iteratively refine the question-answer pairs until they satisfy the target difficulty level. Our intrinsic evaluation shows SAGE generates questions that require diverse reasoning strategies, while significantly increases the correctness and difficulty of the generated data. Our extrinsic evaluation demonstrates up to 23% relative performance gain on popular deep search benchmarks by training deep search agents with our synthetic data. Additional experiments show that agents trained on our data can adapt from fixed-corpus retrieval to Google Search at inference time, without further training. --- ### HeterCSI: Channel-Adaptive Heterogeneous CSI Pretraining Framework for Generalized Wireless Foundation Models Authors: Chenyu Zhang, Xinchen Lyu, Chenshan Ren, Shuhan Liu, Qimei Cui, Xiaofeng Tao Published: 2026-01-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.18200v1 Wireless foundation models promise transformative capabilities for channel state information (CSI) processing across diverse 6G network applications, yet face fundamental challenges due to the inherent dual heterogeneity of CSI across both scale and scenario dimensions. However, current pretraining approaches either constrain inputs to fixed dimensions or isolate training by scale, limiting the generalization and scalability of wireless foundation models. In this paper, we propose HeterCSI, a channel-adaptive pretraining framework that reconciles training efficiency with robust cross-scenario generalization via a new understanding of gradient dynamics in heterogeneous CSI pretraining. Our key insight reveals that CSI scale heterogeneity primarily causes destructive gradient interference, while scenario diversity actually promotes constructive gradient alignment when properly managed. Specifically, we formulate heterogeneous CSI batch construction as a partitioning optimization problem that minimizes zero-padding overhead while preserving scenario diversity. To solve this, we develop a scale-aware adaptive batching strategy that aligns CSI samples of similar scales, and design a double-masking mechanism to isolate valid signals from padding artifacts. Extensive experiments on 12 datasets demonstrate that HeterCSI establishes a generalized foundation model without scenario-specific finetuning, achieving superior average performance over full-shot baselines. Compared to the state-of-the-art zero-shot benchmark WiFo, it reduces NMSE by 7.19 dB, 4.08 dB, and 5.27 dB for CSI reconstruction, time-domain, and frequency-domain prediction, respectively. The proposed HeterCSI framework also reduces training latency by 53% compared to existing approaches while improving generalization performance by 1.53 dB on average. --- ### GAIA: A Data Flywheel System for Training GUI Test-Time Scaling Critic Models Authors: Shaokang Wang, Pei Fu, Ruoceng Zhang, Shaojie Zhang, Xiuwen Xi, Jiahui Yang, Bin Qin, Ying Huang, Zhenbo Luo, Jian Luan Published: 2026-01-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.18197v2 While Large Vision-Language Models (LVLMs) have significantly advanced GUI agents' capabilities in parsing textual instructions, interpreting screen content, and executing tasks, a critical challenge persists: the irreversibility of agent operations-where a single erroneous action can trigger catastrophic deviations. To address this, we propose the \textbf{G}UI \textbf{A}ction Cr\textbf{i}tic's Dat\textbf{a} Flywheel System (GAIA), a training framework that enables the models to have iterative critic capabilities, which are used to improve the Test-Time Scaling (TTS) of basic GUI agents' performance. Specifically, we train an \textbf{Intuitive Critic Model} (ICM) using positive and negative action examples from a base agent first. This critic evaluates the immediate correctness of the agent's intended actions, thereby selecting operations with higher success probability. Then, the initial critic guides agent actions to collect refined positive/negative samples, initiating the self-improving cycle. The augmented data then trains a second-round critic with enhanced discernment capability. We conduct experiments on various datasets and demonstrate that the proposed ICM can improve the test-time performance of various closed-source and open-source models, and the performance can be gradually improved as the data is recycled. The code, dataset, and accompanying datasheet will be publicly released at https://github.com/SeerRay-Lab/GAIA. --- ### QualiRAG: Retrieval-Augmented Generation for Visual Quality Understanding Authors: Linhan Cao, Wei Sun, Weixia Zhang, Xiangyang Zhu, Kaiwei Zhang, Jun Jia, Dandan Zhu, Guangtao Zhai, Xiongkuo Min Published: 2026-01-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.18195v1 Visual quality assessment (VQA) is increasingly shifting from scalar score prediction toward interpretable quality understanding -- a paradigm that demands \textit{fine-grained spatiotemporal perception} and \textit{auxiliary contextual information}. Current approaches rely on supervised fine-tuning or reinforcement learning on curated instruction datasets, which involve labor-intensive annotation and are prone to dataset-specific biases. To address these challenges, we propose \textbf{QualiRAG}, a \textit{training-free} \textbf{R}etrieval-\textbf{A}ugmented \textbf{G}eneration \textbf{(RAG)} framework that systematically leverages the latent perceptual knowledge of large multimodal models (LMMs) for visual quality perception. Unlike conventional RAG that retrieves from static corpora, QualiRAG dynamically generates auxiliary knowledge by decomposing questions into structured requests and constructing four complementary knowledge sources: \textit{visual metadata}, \textit{subject localization}, \textit{global quality summaries}, and \textit{local quality descriptions}, followed by relevance-aware retrieval for evidence-grounded reasoning. Extensive experiments show that QualiRAG achieves substantial improvements over open-source general-purpose LMMs and VQA-finetuned LMMs on visual quality understanding tasks, and delivers competitive performance on visual quality comparison tasks, demonstrating robust quality assessment capabilities without any task-specific training. The code will be publicly available at https://github.com/clh124/QualiRAG. --- ### MindCine: Multimodal EEG-to-Video Reconstruction with Large-Scale Pretrained Models Authors: Tian-Yi Zhou, Xuan-Hao Liu, Bao-Liang Lu, Wei-Long Zheng Published: 2026-01-26 Categories: cs.CV, cs.HC, cs.MM arXiv: https://arxiv.org/abs/2601.18192v2 Reconstructing human dynamic visual perception from electroencephalography (EEG) signals is of great research significance since EEG's non-invasiveness and high temporal resolution. However, EEG-to-video reconstruction remains challenging due to: 1) Single Modality: existing studies solely align EEG signals with the text modality, which ignores other modalities and are prone to suffer from overfitting problems; 2) Data Scarcity: current methods often have difficulty training to converge with limited EEG-video data. To solve the above problems, we propose a novel framework MindCine to achieve high-fidelity video reconstructions on limited data. We employ a multimodal joint learning strategy to incorporate beyond-text modalities in the training stage and leverage a pre-trained large EEG model to relieve the data scarcity issue for decoding semantic information, while a Seq2Seq model with causal attention is specifically designed for decoding perceptual information. Extensive experiments demonstrate that our model outperforms state-of-the-art methods both qualitatively and quantitatively. Additionally, the results underscore the effectiveness of the complementary strengths of different modalities and demonstrate that leveraging a large-scale EEG model can further enhance reconstruction performance by alleviating the challenges associated with limited data. --- ### Multi-Perspective Subimage CLIP with Keyword Guidance for Remote Sensing Image-Text Retrieval Authors: Yifan Li, Shiying Wang, Jianqiang Huang Published: 2026-01-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.18190v1 Vision-Language Pre-training (VLP) models like CLIP have significantly advanced Remote Sensing Image-Text Retrieval (RSITR). However, existing methods predominantly rely on coarse-grained global alignment, which often overlooks the dense, multi-scale semantics inherent in overhead imagery. Moreover, adapting these heavy models via full fine-tuning incurs prohibitive computational costs and risks catastrophic forgetting. To address these challenges, we propose MPS-CLIP, a parameter-efficient framework designed to shift the retrieval paradigm from global matching to keyword-guided fine-grained alignment. Specifically, we leverage a Large Language Model (LLM) to extract core semantic keywords, guiding the Segment Anything Model (SamGeo) to generate semantically relevant sub-perspectives. To efficiently adapt the frozen backbone, we introduce a Gated Global Attention (G^2A) adapter, which captures global context and long-range dependencies with minimal overhead. Furthermore, a Multi-Perspective Representation (MPR) module aggregates these local cues into robust multi-perspective embeddings. The framework is optimized via a hybrid objective combining multi-perspective contrastive and weighted triplet losses, which dynamically selects maximum-response perspectives to suppress noise and enforce precise semantic matching. Extensive experiments on the RSICD and RSITMD benchmarks demonstrate that MPS-CLIP achieves state-of-the-art performance with 35.18% and 48.40% mean Recall (mR), respectively, significantly outperforming full fine-tuning baselines and recent competitive methods. Code is available at https://github.com/Lcrucial1f/MPS-CLIP. --- ### Smooth, Sparse, and Stable: Finite-Time Exact Skeleton Recovery via Smoothed Proximal Gradients Authors: Rui Wu, Yongjun Li Published: 2026-01-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.18189v1 Continuous optimization has significantly advanced causal discovery, yet existing methods (e.g., NOTEARS) generally guarantee only asymptotic convergence to a stationary point. This often yields dense weighted matrices that require arbitrary post-hoc thresholding to recover a DAG. This gap between continuous optimization and discrete graph structures remains a fundamental challenge. In this paper, we bridge this gap by proposing the Hybrid-Order Acyclicity Constraint (AHOC) and optimizing it via the Smoothed Proximal Gradient (SPG-AHOC). Leveraging the Manifold Identification Property of proximal algorithms, we provide a rigorous theoretical guarantee: the Finite-Time Oracle Property. We prove that under standard identifiability assumptions, SPG-AHOC recovers the exact DAG support (structure) in finite iterations, even when optimizing a smoothed approximation. This result eliminates structural ambiguity, as our algorithm returns graphs with exact zero entries without heuristic truncation. Empirically, SPG-AHOC achieves state-of-the-art accuracy and strongly corroborates the finite-time identification theory. --- ### \textsc{NaVIDA}: Vision-Language Navigation with Inverse Dynamics Augmentation Authors: Weiye Zhu, Zekai Zhang, Xiangchen Wang, Hewei Pan, Teng Wang, Tiantian Geng, Rongtao Xu, Feng Zheng Published: 2026-01-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.18188v2 Vision-and-Language Navigation (VLN) requires agents to interpret natural language instructions and act coherently in visually rich environments. However, most existing methods rely on reactive state-action mappings without explicitly action-grounded visual dynamics modeling. Lacking awareness of how actions transform subsequent visual observations, agents cannot plan actions rationally, leading to unstable behaviors, weak generalization, and cumulative error along trajectory. To address these issues, we introduce \textsc{NaVIDA} (\textbf{Nav}igation with \textbf{I}nverse \textbf{D}ynamics \textbf{A}ugmentation), a lightweight VLN framework that incorporates inverse dynamics supervision (IDS) as an explicit objective to embed action-grounded visual dynamics into policy learning. By jointly optimizing this visual dynamics with instruction-conditioned action prediction in a shared representation and action space, \textsc{NaVIDA} provides additional structured supervision that regularizes learning and leads to more stable and consistent navigation. To structure this supervision and extend the effective planning range, \textsc{NaVIDA} employs hierarchical probabilistic action chunking (HPAC), which organizes trajectories into multi-step chunks and provides discriminative, longer-range visual-change cues. Extensive experiments show that \textsc{NaVIDA} achieves superior navigation performance compared to state-of-the-art methods with fewer parameters (3B vs. 8B). Real-world robot evaluations further validate the practical feasibility and effectiveness of our approach. --- ### VIBEVOICE-ASR Technical Report Authors: Zhiliang Peng, Jianwei Yu, Yaoyao Chang, Zilong Wang, Li Dong, Yingbo Hao, Yujie Tu, Chenyu Yang, Wenhui Wang, Songchen Xu, Yutao Sun, Hangbo Bao et al. Published: 2026-01-26 Categories: cs.SD, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2601.18184v2 This report presents VibeVoice-ASR, a general-purpose speech understanding framework built upon VibeVoice, designed to address the persistent challenges of context fragmentation and multi-speaker complexity in long-form audio (e.g., meetings, podcasts) that remain despite recent advancements in short-form speech recognition. Unlike traditional pipelined approaches that rely on audio chunking, VibeVoice-ASRsupports single-pass processing for up to 60 minutes of audio. It unifies Automatic Speech Recognition, Speaker Diarization, and Timestamping into a single end-to-end generation task. In addition, VibeVoice-ASR supports over 50 languages, requires no explicit language setting, and natively handles code-switching within and across utterances. Furthermore, we introduce a prompt-based context injection mechanism that allows users to supply customized conetxt, significantly improving accuracy on domain-specific terminology and polyphonic character disambiguation. --- ### Success Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success Authors: Daniel Russo Published: 2026-01-26 Categories: cs.AI, cs.LG, eess.SY, stat.ML arXiv: https://arxiv.org/abs/2601.18175v2 A widely used technique for improving policies is success conditioning, in which one collects trajectories, identifies those that achieve a desired outcome, and updates the policy to imitate the actions taken along successful trajectories. This principle appears under many names -- rejection sampling with SFT, goal-conditioned RL, Decision Transformers -- yet what optimization problem it solves, if any, has remained unclear. We prove that success conditioning exactly solves a trust-region optimization problem, maximizing policy improvement subject to a $χ^2$ divergence constraint whose radius is determined automatically by the data. This yields an identity: relative policy improvement, the magnitude of policy change, and a quantity we call action-influence -- measuring how random variation in action choices affects success rates -- are exactly equal at every state. Success conditioning thus emerges as a conservative improvement operator. Exact success conditioning cannot degrade performance or induce dangerous distribution shift, but when it fails, it does so observably, by hardly changing the policy at all. We apply our theory to the common practice of return thresholding, showing this can amplify improvement, but at the cost of potential misalignment with the true objective. --- ### YOLO-DS: Fine-Grained Feature Decoupling via Dual-Statistic Synergy Operator for Object Detection Authors: Lin Huang, Yujuan Tan, Weisheng Li, Shitai Shan, Liu Liu, Bo Liu, Linlin Shen, Jing Yu, Yue Niu Published: 2026-01-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.18172v1 One-stage object detection, particularly the YOLO series, strikes a favorable balance between accuracy and efficiency. However, existing YOLO detectors lack explicit modeling of heterogeneous object responses within shared feature channels, which limits further performance gains. To address this, we propose YOLO-DS, a framework built around a novel Dual-Statistic Synergy Operator (DSO). The DSO decouples object features by jointly modeling the channel-wise mean and the peak-to-mean difference. Building upon the DSO, we design two lightweight gating modules: the Dual-Statistic Synergy Gating (DSG) module for adaptive channel-wise feature selection, and the Multi-Path Segmented Gating (MSG) module for depth-wise feature weighting. On the MS-COCO benchmark, YOLO-DS consistently outperforms YOLOv8 across five model scales (N, S, M, L, X), achieving AP gains of 1.1% to 1.7% with only a minimal increase in inference latency. Extensive visualization, ablation, and comparative studies validate the effectiveness of our approach, demonstrating its superior capability in discriminating heterogeneous objects with high efficiency. --- ### Learning Fair Domain Adaptation with Virtual Label Distribution Authors: Yuguang Zhang, Lijun Sheng, Jian Liang, Ran He Published: 2026-01-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.18171v1 Unsupervised Domain Adaptation (UDA) aims to mitigate performance degradation when training and testing data are sampled from different distributions. While significant progress has been made in enhancing overall accuracy, most existing methods overlook performance disparities across categories-an issue we refer to as category fairness. Our empirical analysis reveals that UDA classifiers tend to favor certain easy categories while neglecting difficult ones. To address this, we propose Virtual Label-distribution-aware Learning (VILL), a simple yet effective framework designed to improve worst-case performance while preserving high overall accuracy. The core of VILL is an adaptive re-weighting strategy that amplifies the influence of hard-to-classify categories. Furthermore, we introduce a KL-divergence-based re-balancing strategy, which explicitly adjusts decision boundaries to enhance category fairness. Experiments on commonly used datasets demonstrate that VILL can be seamlessly integrated as a plug-and-play module into existing UDA methods, significantly improving category fairness. --- ### TempDiffReg: Temporal Diffusion Model for Non-Rigid 2D-3D Vascular Registration Authors: Zehua Liu, Shihao Zou, Jincai Huang, Yanfang Zhang, Chao Tong, Weixin Si Published: 2026-01-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.18168v1 Transarterial chemoembolization (TACE) is a preferred treatment option for hepatocellular carcinoma and other liver malignancies, yet it remains a highly challenging procedure due to complex intra-operative vascular navigation and anatomical variability. Accurate and robust 2D-3D vessel registration is essential to guide microcatheter and instruments during TACE, enabling precise localization of vascular structures and optimal therapeutic targeting. To tackle this issue, we develop a coarse-to-fine registration strategy. First, we introduce a global alignment module, structure-aware perspective n-point (SA-PnP), to establish correspondence between 2D and 3D vessel structures. Second, we propose TempDiffReg, a temporal diffusion model that performs vessel deformation iteratively by leveraging temporal context to capture complex anatomical variations and local structural changes. We collected data from 23 patients and constructed 626 paired multi-frame samples for comprehensive evaluation. Experimental results demonstrate that the proposed method consistently outperforms state-of-the-art (SOTA) methods in both accuracy and anatomical plausibility. Specifically, our method achieves a mean squared error (MSE) of 0.63 mm and a mean absolute error (MAE) of 0.51 mm in registration accuracy, representing 66.7\% lower MSE and 17.7\% lower MAE compared to the most competitive existing approaches. It has the potential to assist less-experienced clinicians in safely and efficiently performing complex TACE procedures, ultimately enhancing both surgical outcomes and patient care. Code and data are available at: \textcolor{blue}{https://github.com/LZH970328/TempDiffReg.git} --- ### Fine-Grained Emotion Detection on GoEmotions: Experimental Comparison of Classical Machine Learning, BiLSTM, and Transformer Models Authors: Ani Harutyunyan, Sachin Kumar Published: 2026-01-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.18162v1 Fine-grained emotion recognition is a challenging multi-label NLP task due to label overlap and class imbalance. In this work, we benchmark three modeling families on the GoEmotions dataset: a TF-IDF-based logistic regression system trained with binary relevance, a BiLSTM with attention, and a BERT model fine-tuned for multi-label classification. Experiments follow the official train/validation/test split, and imbalance is mitigated using inverse-frequency class weights. Across several metrics, namely Micro-F1, Macro-F1, Hamming Loss, and Subset Accuracy, we observe that logistic regression attains the highest Micro-F1 of 0.51, while BERT achieves the best overall balance surpassing the official paper's reported results, reaching Macro-F1 0.49, Hamming Loss 0.036, and Subset Accuracy 0.36. This suggests that frequent emotions often rely on surface lexical cues, whereas contextual representations improve performance on rarer emotions and more ambiguous examples. --- ### Agentic Very Long Video Understanding Authors: Aniket Rege, Arka Sadhu, Yuliang Li, Kejie Li, Ramya Korlakai Vinayak, Yuning Chai, Yong Jae Lee, Hyo Jin Kim Published: 2026-01-26 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.18157v3 The advent of always-on personal AI assistants, enabled by all-day wearable devices such as smart glasses, demands a new level of contextual understanding, one that goes beyond short, isolated events to encompass the continuous, longitudinal stream of egocentric video. Achieving this vision requires advances in long-horizon video understanding, where systems must interpret and recall visual and audio information spanning days or even weeks. Existing methods, including large language models and retrieval-augmented generation, are constrained by limited context windows and lack the ability to perform compositional, multi-hop reasoning over very long video streams. In this work, we address these challenges through EGAgent, an enhanced agentic framework centered on entity scene graphs, which represent people, places, objects, and their relationships over time. Our system equips a planning agent with tools for structured search and reasoning over these graphs, as well as hybrid visual and audio search capabilities, enabling detailed, cross-modal, and temporally coherent reasoning. Experiments on the EgoLifeQA and Video-MME (Long) datasets show that our method achieves state-of-the-art performance on EgoLifeQA (57.5%) and competitive performance on Video-MME (Long) (74.1%) for complex longitudinal video understanding tasks. Code is available at https://github.com/facebookresearch/egagent. --- ### Beyond Pairwise Comparisons: A Distributional Test of Distinctiveness for Machine-Generated Works in Intellectual Property Law Authors: Anirban Mukherjee, Hannah Hanwen Chang Published: 2026-01-26 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2601.18156v1 Key doctrines, including novelty (patent), originality (copyright), and distinctiveness (trademark), turn on a shared empirical question: whether a body of work is meaningfully distinct from a relevant reference class. Yet analyses typically operationalize this set-level inquiry using item-level evidence: pairwise comparisons among exemplars. That unit-of-analysis mismatch may be manageable for finite corpora of human-created works, where it can be bridged by ad hoc aggregations. But it becomes acute for machine-generated works, where the object of evaluation is not a fixed set of works but a generative process with an effectively unbounded output space. We propose a distributional alternative: a two-sample test based on maximum mean discrepancy computed on semantic embeddings to determine if two creative processes-whether human or machine-produce statistically distinguishable output distributions. The test requires no task-specific training-obviating the need for discovery of proprietary training data to characterize the generative process-and is sample-efficient, often detecting differences with as few as 5-10 images and 7-20 texts. We validate the framework across three domains: handwritten digits (controlled images), patent abstracts (text), and AI-generated art (real-world images). We reveal a perceptual paradox: even when human evaluators distinguish AI outputs from human-created art with only about 58% accuracy, our method detects distributional distinctiveness. Our results present evidence contrary to the view that generative models act as mere regurgitators of training data. Rather than producing outputs statistically indistinguishable from a human baseline-as simple regurgitation would predict-they produce outputs that are semantically human-like yet stochastically distinct, suggesting their dominant function is as a semantic interpolator within a learned latent space. --- ### Explaining Synergistic Effects in Social Recommendations Authors: Yicong Li, Shan Jin, Qi Liu, Shuo Wang, Jiaying Liu, Shuo Yu, Qiang Zhang, Kuanjiu Zhou, Feng Xia Published: 2026-01-26 Categories: cs.SI, cs.AI arXiv: https://arxiv.org/abs/2601.18151v1 In social recommenders, the inherent nonlinearity and opacity of synergistic effects across multiple social networks hinders users from understanding how diverse information is leveraged for recommendations, consequently diminishing explainability. However, existing explainers can only identify the topological information in social networks that significantly influences recommendations, failing to further explain the synergistic effects among this information. Inspired by existing findings that synergistic effects enhance mutual information between inputs and predictions to generate information gain, we extend this discovery to graph data. We quantify graph information gain to identify subgraphs embodying synergistic effects. Based on the theoretical insights, we propose SemExplainer, which explains synergistic effects by identifying subgraphs that embody them. SemExplainer first extracts explanatory subgraphs from multi-view social networks to generate preliminary importance explanations for recommendations. A conditional entropy optimization strategy to maximize information gain is developed, thereby further identifying subgraphs that embody synergistic effects from explanatory subgraphs. Finally, SemExplainer searches for paths from users to recommended items within the synergistic subgraphs to generate explanations for the recommendations. Extensive experiments on three datasets demonstrate the superiority of SemExplainer over baseline methods, providing superior explanations of synergistic effects. --- ### FP8-RL: A Practical and Stable Low-Precision Stack for LLM Reinforcement Learning Authors: Zhaopeng Qiu, Shuang Yu, Jingqi Zhang, Shuai Zhang, Xue Huang, Jingyi Yang, Junjie Lai Published: 2026-01-26 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2601.18150v2 Reinforcement learning (RL) for large language models (LLMs) is increasingly bottlenecked by rollout (generation), where long output sequence lengths make attention and KV-cache memory dominate end-to-end step time. FP8 offers an attractive lever for accelerating RL by reducing compute cost and memory traffic during rollout, but applying FP8 in RL introduces unique engineering and algorithmic challenges: policy weights change every step (requiring repeated quantization and weight synchronization into the inference engine) and low-precision rollouts can deviate from the higher-precision policy assumed by the trainer, causing train-inference mismatch and potential instability. This report presents a practical FP8 rollout stack for LLM RL, implemented in the veRL ecosystem with support for common training backends (e.g., FSDP/Megatron-LM) and inference engines (e.g., vLLM/SGLang). We (i) enable FP8 W8A8 linear-layer rollout using blockwise FP8 quantization, (ii) extend FP8 to KV-cache to remove long-context memory bottlenecks via per-step QKV scale recalibration, and (iii) mitigate mismatch using importance-sampling-based rollout correction (token-level TIS/MIS variants). Across dense and MoE models, these techniques deliver up to 44% rollout throughput gains while preserving learning behavior comparable to BF16 baselines. --- ### Exact Minimum-Volume Confidence Set Intersection for Multinomial Outcomes Authors: Heguang Lin, Binhao Chen, Mengze Li, Daniel Pimentel-Alarcón, Matthew L. Malloy Published: 2026-01-26 Categories: stat.ML, cs.LG, stat.CO arXiv: https://arxiv.org/abs/2601.18145v1 Computation of confidence sets is central to data science and machine learning, serving as the workhorse of A/B testing and underpinning the operation and analysis of reinforcement learning algorithms. Among all valid confidence sets for the multinomial parameter, minimum-volume confidence sets (MVCs) are optimal in that they minimize average volume, but they are defined as level sets of an exact p-value that is discontinuous and difficult to compute. Rather than attempting to characterize the geometry of MVCs directly, this paper studies a practically motivated decision problem: given two observed multinomial outcomes, can one certify whether their MVCs intersect? We present a certified, tolerance-aware algorithm for this intersection problem. The method exploits the fact that likelihood ordering induces halfspace constraints in log-odds coordinates, enabling adaptive geometric partitioning of parameter space and computable lower and upper bounds on p-values over each cell. For three categories, this yields an efficient and provably sound algorithm that either certifies intersection, certifies disjointness, or returns an indeterminate result when the decision lies within a prescribed margin. We further show how the approach extends to higher dimensions. The results demonstrate that, despite their irregular geometry, MVCs admit reliable certified decision procedures for core tasks in A/B testing. --- ### Enhance the Safety in Reinforcement Learning by ADRC Lagrangian Methods Authors: Mingxu Zhang, Huicheng Zhang, Jiaming Ji, Yaodong Yang, Ying Sun Published: 2026-01-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.18142v1 Safe reinforcement learning (Safe RL) seeks to maximize rewards while satisfying safety constraints, typically addressed through Lagrangian-based methods. However, existing approaches, including PID and classical Lagrangian methods, suffer from oscillations and frequent safety violations due to parameter sensitivity and inherent phase lag. To address these limitations, we propose ADRC-Lagrangian methods that leverage Active Disturbance Rejection Control (ADRC) for enhanced robustness and reduced oscillations. Our unified framework encompasses classical and PID Lagrangian methods as special cases while significantly improving safety performance. Extensive experiments demonstrate that our approach reduces safety violations by up to 74%, constraint violation magnitudes by 89%, and average costs by 67\%, establishing superior effectiveness for Safe RL in complex environments. --- ### DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints Authors: Yinger Zhang, Shutong Jiang, Renhao Li, Jianhong Tu, Yang Su, Lianghao Deng, Xudong Guo, Chenxu Lv, Junyang Lin Published: 2026-01-26 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.18137v1 While agent evaluation has shifted toward long-horizon tasks, most benchmarks still emphasize local, step-level reasoning rather than the global constrained optimization (e.g., time and financial budgets) that demands genuine planning ability. Meanwhile, existing LLM planning benchmarks underrepresent the active information gathering and fine-grained local constraints typical of real-world settings. To address this, we introduce DeepPlanning, a challenging benchmark for practical long-horizon agent planning. It features multi-day travel planning and multi-product shopping tasks that require proactive information acquisition, local constrained reasoning, and global constrained optimization. Evaluations on DeepPlanning show that even frontier agentic LLMs struggle with these problems, highlighting the importance of reliable explicit reasoning patterns and parallel tool use for achieving better effectiveness-efficiency trade-offs. Error analysis further points to promising directions for improving agentic LLMs over long planning horizons. We open-source the code and data to support future research. --- ### Forward Consistency Learning with Gated Context Aggregation for Video Anomaly Detection Authors: Jiahao Lyu, Minghua Zhao, Xuewen Huang, Yifei Chen, Shuangli Du, Jing Hu, Cheng Shi, Zhiyong Lv Published: 2026-01-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.18135v1 As a crucial element of public security, video anomaly detection (VAD) aims to measure deviations from normal patterns for various events in real-time surveillance systems. However, most existing VAD methods rely on large-scale models to pursue extreme accuracy, limiting their feasibility on resource-limited edge devices. Moreover, mainstream prediction-based VAD detects anomalies using only single-frame future prediction errors, overlooking the richer constraints from longer-term temporal forward information. In this paper, we introduce FoGA, a lightweight VAD model that performs Forward consistency learning with Gated context Aggregation, containing about 2M parameters and tailored for potential edge devices. Specifically, we propose a Unet-based method that performs feature extraction on consecutive frames to generate both immediate and forward predictions. Then, we introduce a gated context aggregation module into the skip connections to dynamically fuse encoder and decoder features at the same spatial scale. Finally, the model is jointly optimized with a novel forward consistency loss, and a hybrid anomaly measurement strategy is adopted to integrate errors from both immediate and forward frames for more accurate detection. Extensive experiments demonstrate the effectiveness of the proposed method, which substantially outperforms state-of-the-art competing methods, running up to 155 FPS. Hence, our FoGA achieves an excellent trade-off between performance and the efficiency metric. --- ### RareAlert: Aligning heterogeneous large language model reasoning for early rare disease risk screening Authors: Xi Chen, Hongru Zhou, Huahui Yi, Shiyu Feng, Hanyu Zhou, Tiancheng He, Mingke You, Li Wang, Qiankun Li, Kun Wang, Weili Fu, Kang Li et al. Published: 2026-01-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.18132v1 Missed and delayed diagnosis remains a major challenge in rare disease care. At the initial clinical encounters, physicians assess rare disease risk using only limited information under high uncertainty. When high-risk patients are not recognised at this stage, targeted diagnostic testing is often not initiated, resulting in missed diagnosis. Existing primary care triage processes are structurally insufficient to reliably identify patients with rare diseases at initial clinical presentation and universal screening is needed to reduce diagnostic delay. Here we present RareAlert, an early screening system which predict patient-level rare disease risk from routinely available primary-visit information. RareAlert integrates reasoning generated by ten LLMs, calibrates and weights these signals using machine learning, and distils the aligned reasoning into a single locally deployable model. To develop and evaluate RareAlert, we curated RareBench, a real-world dataset of 158,666 cases covering 33 Orphanet disease categories and more than 7,000 rare conditions, including both rare and non-rare presentations. The results showed that rare disease identification can be reconceptualised as a universal uncertainty resolution process applied to the general patient population. On an independent test set, RareAlert, a Qwen3-4B based model trained with calibrated reasoning signals, achieved an AUC of 0.917, outperforming the best machine learning ensemble and all evaluated LLMs, including GPT-5, DeepSeek-R1, Claude-3.7-Sonnet, o3-mini, Gemini-2.5-Pro, and Qwen3-235B. These findings demonstrate the diversity in LLM medical reasoning and the effectiveness of aligning such reasoning in highly uncertain clinical tasks. By incorporating calibrated reasoning into a single model, RareAlert enables accurate, privacy-preserving, and scalable rare disease risk screening suitable for large-scale local deployment. --- ### RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents Authors: Jize Wang, Han Wu, Zhiyuan You, Yiming Song, Yijun Wang, Zifei Shan, Yining Li, Songyang Zhang, Xinyi Le, Cailian Chen, Xinping Guan, Dacheng Tao Published: 2026-01-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.18130v1 Mixture-of-Agents (MoA) improves LLM performance through layered collaboration, but its dense topology raises costs and latency. Existing methods employ LLM judges to filter responses, yet still require all models to perform inference before judging, failing to cut costs effectively. They also lack model selection criteria and struggle with large model pools, where full inference is costly and can exceed context limits. To address this, we propose RouteMoA, an efficient mixture-of-agents framework with dynamic routing. It employs a lightweight scorer to perform initial screening by predicting coarse-grained performance from the query, narrowing candidates to a high-potential subset without inference. A mixture of judges then refines these scores through lightweight self- and cross-assessment based on existing model outputs, providing posterior correction without additional inference. Finally, a model ranking mechanism selects models by balancing performance, cost, and latency. RouteMoA outperforms MoA across varying tasks and model pool sizes, reducing cost by 89.8% and latency by 63.6% in the large-scale model pool. --- ### Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models Authors: Kunat Pipatanakul, Pittawat Taveekitworachai Published: 2026-01-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.18129v1 Large language models (LLMs) have progressed rapidly; however, most state-of-the-art models are trained and evaluated primarily in high-resource languages such as English and Chinese, and are often developed by a small number of organizations with access to large-scale compute and data. This gatekeeping creates a practical barrier for sovereign settings in which a regional- or national-scale institution or domain owner must retain control and understanding of model weights, training data, and deployment while operating under limited resources and strict transparency constraints. To this end, we identify two core requirements: (1) adoptability, the ability to transform a base model into a general-purpose assistant, and (2) sovereign capability, the ability to perform high-stakes, region-specific tasks (e.g., legal reasoning in local languages and cultural knowledge). We investigate whether these requirements can be achieved without scaling massive instruction corpora or relying on complex preference tuning pipelines and large-scale reinforcement fine-tuning (RFT). We present Typhoon S, a minimal and open post-training recipe that combines supervised fine-tuning, on-policy distillation, and small-scale RFT. Using Thai as a representative case study, we demonstrate that our approach transforms both sovereign-adapted and general-purpose base models into instruction-tuned models with strong general performance. We further show that small-scale RFT with InK-GRPO -- an extension of GRPO that augments the GRPO loss with a next-word prediction loss -- improves Thai legal reasoning and Thai-specific knowledge while preserving general capabilities. Our results suggest that a carefully designed post-training strategy can reduce the required scale of instruction data and computation, providing a practical path toward high-quality sovereign LLMs under academic-scale resources. --- ### Nonlinear multi-study sparse factor analysis Authors: Gemma E. Moran, Anandi Krishnan Published: 2026-01-26 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2601.18128v2 High-dimensional data often exhibit variation that can be captured by lower-dimensional factors. For high-dimensional data from multiple studies, one goal is to understand which underlying factors are common to all studies, and which factors are study-specific. As a particular example, we consider platelet gene expression data from patients in different disease groups. In this data, factors correspond to clusters of genes which are co-expressed; we may expect some clusters (or biological pathways) to be active for all diseases, while some clusters are only active for a specific disease. To learn these factors, we consider a nonlinear multi-study sparse factor model, which allows for both shared and study-specific factors. To fit this model, we propose a multi-study sparse variational autoencoder. The underlying model is sparse in that each observed feature (i.e. each dimension of the data) depends on a small subset of the latent factors. In the genomics example, this means each gene is active in only a few biological processes. We prove that the latent factor distributions are identifiable (up to element-wise transformations), and that the canonical shared and study-specific support structure is identifiable. Empirically, we demonstrate our method recovers meaningful factors in the platelet gene expression data. --- ### The Limits of AI Data Transparency Policy: Three Disclosure Fallacies Authors: Judy Hanwen Shen, Ken Liu, Angelina Wang, Sarah H. Cen, Andy K. Zhang, Caroline Meinhardt, Daniel Zhang, Kevin Klyman, Rishi Bommasani, Daniel E. Ho Published: 2026-01-26 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2601.18127v1 Data transparency has emerged as a rallying cry for addressing concerns about AI: data quality, privacy, and copyright chief among them. Yet while these calls are crucial for accountability, current transparency policies often fall short of their intended aims. Similar to nutrition facts for food, policies aimed at nutrition facts for AI currently suffer from a limited consideration of research on effective disclosures. We offer an institutional perspective and identify three common fallacies in policy implementations of data disclosures for AI. First, many data transparency proposals exhibit a specification gap between the stated goals of data transparency and the actual disclosures necessary to achieve such goals. Second, reform attempts exhibit an enforcement gap between required disclosures on paper and enforcement to ensure compliance in fact. Third, policy proposals manifest an impact gap between disclosed information and meaningful changes in developer practices and public understanding. Informed by the social science on transparency, our analysis identifies affirmative paths for transparency that are effective rather than merely symbolic. --- ### Understanding Users' Privacy Reasoning and Behaviors During Chatbot Use to Support Meaningful Agency in Privacy Authors: Mohammad Hadi Nezhad, Francisco Enrique Vicente Castro, Ivon Arroyo Published: 2026-01-26 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2601.18125v1 Conversational agents (CAs) (e.g., chatbots) are increasingly used in settings where users disclose sensitive information, raising significant privacy concerns. Because privacy judgments are highly contextual, supporting users to engage in privacy-protective actions during chatbot interactions is essential. However, enabling meaningful engagement requires a deeper understanding of how users currently reason about and manage sensitive information during realistic chatbot use scenarios. To investigate this, we qualitatively examined computer science (undergraduate and masters) students' in-the-moment disclosure and protection behaviors, as well as the reasoning underlying these behaviors, across a range of realistic chatbot tasks. Participants used a simulated ChatGPT interface with and without a privacy notice panel that intercepts message submissions, highlights potentially sensitive information, and offers privacy protective actions. The panel supports anonymization through retracting, faking, and generalizing, and surfaces two of ChatGPT's built-in privacy controls to improve their discoverability. Drawing on interaction logs, think-alouds, and survey responses, we analyzed how the panel fostered privacy awareness, encouraged protective actions, and supported context-specific reasoning about what information to protect and how. We further discuss design opportunities for tools that provide users greater and more meaningful agency in protecting sensitive information during CA interactions. --- ### Deadline-Aware, Energy-Efficient Control of Domestic Immersion Hot Water Heater Authors: Muhammad Ibrahim Khan, Bivin Pradeep, James Brusey Published: 2026-01-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.18123v2 Typical domestic immersion water heater systems are often operated continuously during winter, heating quickly rather than efficiently and ignoring predictable demand windows and ambient losses. We study deadline-aware control, where the aim is to reach a target temperature at a specified time while minimising energy consumption. We introduce an efficient Gymnasium environment that models an immersion hot water heater with first-order thermal losses and discrete on and off actions of 0 W and 6000 W applied every 120 seconds. Methods include a time-optimal bang-bang baseline, a zero-shot Monte Carlo Tree Search planner, and a Proximal Policy Optimisation policy. We report total energy consumption in watt-hours under identical physical dynamics. Across sweeps of initial temperature from 10 to 30 degrees Celsius, deadline from 30 to 90 steps, and target temperature from 40 to 80 degrees Celsius, PPO achieves the most energy-efficient performance at a 60-step horizon of 2 hours, using 3.23 kilowatt-hours, compared to 4.37 to 10.45 kilowatt-hours for bang-bang control and 4.18 to 6.46 kilowatt-hours for MCTS. This corresponds to energy savings of 26 percent at 30 steps and 69 percent at 90 steps. In a representative trajectory with a 50 kg water mass, 20 degrees Celsius ambient temperature, and a 60 degrees Celsius target, PPO consumes 54 percent less energy than bang-bang control and 33 percent less than MCTS. These results show that learned deadline-aware control reduces energy consumption under identical physical assumptions, while planners provide partial savings without training and learned policies offer near-zero inference cost once trained. --- ### Grasp-and-Lift: Executable 3D Hand-Object Interaction Reconstruction via Physics-in-the-Loop Optimization Authors: Byeonggyeol Choi, Woojin Oh, Jongwoo Lim Published: 2026-01-26 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2601.18121v1 Dexterous hand manipulation increasingly relies on large-scale motion datasets with precise hand-object trajectory data. However, existing resources such as DexYCB and HO3D are primarily optimized for visual alignment but often yield physically implausible interactions when replayed in physics simulators, including penetration, missed contact, and unstable grasps. We propose a simulation-in-the-loop refinement framework that converts these visually aligned trajectories into physically executable ones. Our core contribution is to formulate this as a tractable black-box optimization problem. We parameterize the hand's motion using a low-dimensional, spline-based representation built on sparse temporal keyframes. This allows us to use a powerful gradient-free optimizer, CMA-ES, to treat the high-fidelity physics engine as a black-box objective function. Our method finds motions that simultaneously maximize physical success (e.g., stable grasp and lift) while minimizing deviation from the original human demonstration. Compared to MANIPTRANS-recent transfer pipelines, our approach achieves lower hand and object pose errors during replay and more accurately recovers hand-object physical interactions. Our approach provides a general and scalable method for converting visual demonstrations into physically valid trajectories, enabling the generation of high-fidelity data crucial for robust policy learning. --- ### Beyond Text-to-SQL: Can LLMs Really Debug Enterprise ETL SQL? Authors: Jing Ye, Yiwen Duan, Yonghong Yu, Victor Ma, Yang Gao, Xing Chen Published: 2026-01-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.18119v2 SQL is central to enterprise data engineering, yet generating fully correct SQL code in a single attempt remains difficult, even for experienced developers and advanced text-to-SQL LLMs, often requiring multiple debugging iterations. We introduce OurBench, the first benchmark for enterprise-level SQL reasoning and debugging. Our benchmark is built on two key innovations: (1) an automated construction workflow that uses reverse engineering to systematically inject realistic bugs into large-scale SQL code, enabling scalable and diverse benchmark generation; and (2) an execution-free evaluation framework tailored to enterprise settings, providing fast, accurate, and resource-efficient assessment. OurBench comprises 469 OurBenchSyn queries featuring syntax errors with explicit error messages, and 516 OurBenchSem queries targeting semantic errors in which the code fails to meet user intent. The queries are highly complex, averaging over 140 lines and featuring deep and wide abstract syntax trees. Evaluation of nearly 30 LLMs reveals a substantial performance gap: the best-performing model, Claude-4-Sonnet, achieves only 36.46 percent accuracy on OurBenchSyn and 32.17 percent on OurBenchSem, while most models score below 20 percent. We further explore four solution strategies, identify key challenges, and outline promising directions for enterprise SQL debugging with LLMs. --- ### LungCRCT: Causal Representation based Lung CT Processing for Lung Cancer Treatment Authors: Daeyoung Kim Published: 2026-01-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.18118v1 Due to silence in early stages, lung cancer has been one of the most leading causes of mortality in cancer patients world-wide. Moreover, major symptoms of lung cancer are hard to differentiate with other respiratory disease symptoms such as COPD, further leading patients to overlook cancer progression in early stages. Thus, to enhance survival rates in lung cancer, early detection from consistent proactive respiratory system monitoring becomes crucial. One of the most prevalent and effective methods for lung cancer monitoring would be low-dose computed tomography(LDCT) chest scans, which led to remarkable enhancements in lung cancer detection or tumor classification tasks under rapid advancements and applications of computer vision based AI models such as EfficientNet or ResNet in image processing. However, though advanced CNN models under transfer learning or ViT based models led to high performing lung cancer detections, due to its intrinsic limitations in terms of correlation dependence and low interpretability due to complexity, expansions of deep learning models to lung cancer treatment analysis or causal intervention analysis simulations are still limited. Therefore, this research introduced LungCRCT: a latent causal representation learning based lung cancer analysis framework that retrieves causal representations of factors within the physical causal mechanism of lung cancer progression. With the use of advanced graph autoencoder based causal discovery algorithms with distance Correlation disentanglement and entropy-based image reconstruction refinement, LungCRCT not only enables causal intervention analysis for lung cancer treatments, but also leads to robust, yet extremely light downstream models in malignant tumor classification tasks with an AUC score of 93.91%. --- ### BEAR: Budgeted Evidence Allocation for Multi-Document Reasoning Authors: Lin Sun, Linglin Zhang, Jingang Huang, Change Jia, Zhengwei Cheng, Xiangzheng Zhang Published: 2026-01-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.18116v2 We argue that multi-document reasoning is constrained not only by how much text a model can read, but also by how limited query-time evidence budget is allocated across documents and semantic granularities. Full-context inference exposes the model to broad evidence non-selectively and at high per-query cost, while flat chunk retrieval often returns locally relevant passages that are weakly organized for cross-document synthesis. We present \textbf{BEAR}, a framework for structured evidence allocation that builds hierarchical semantic indices offline and performs coarse-to-fine evidence access at query time through complementary \emph{exploration} and \emph{recovery} paths. This coarse-to-fine design can be viewed as structured evidence allocation under a fixed evidence-context budget. Across synthetic and real-world benchmarks, BEAR performs particularly strongly on DragonBall, remains competitive with strong retrieval-based baselines on HotpotQA, and yields the best retrieval-based result on 2Wiki under our evaluated protocol, while operating under substantially smaller \emph{query-time evidence budgets} than the reported long-context references. Additional analyses suggest that the gains are associated with hierarchy as an allocation substrate together with complementary exploration and recovery, rather than semantic chunking alone. --- ### Robust Learning of a Group DRO Neuron Authors: Guyang Cao, Shuyao Li, Sushrut Karmalkar, Jelena Diakonikolas Published: 2026-01-26 Categories: cs.LG, cs.DS, math.OC arXiv: https://arxiv.org/abs/2601.18115v2 We study the problem of learning a single neuron under standard squared loss in the presence of arbitrary label noise and group-level distributional shifts, for a broad family of covariate distributions. Our goal is to identify a ''best-fit'' neuron parameterized by $\mathbf{w}_*$ that performs well under the most challenging reweighting of the groups. Specifically, we address a Group Distributionally Robust Optimization problem: given sample access to $K$ distinct distributions $\mathcal p_{(1)},\dots,\mathcal p_{(K)}$, we seek to approximate $\mathbf{w}_*$ that minimizes the worst-case objective over convex combinations of group distributions $\boldsymbolλ \in Δ_K$, where the objective is $\sum_{i \in (K)}λ_{(i)}\,\mathbb E_{(\mathbf x,y)\sim\mathcal p_{(i)}}(σ(\mathbf w\cdot\mathbf x)-y)^2 - νd_f(\boldsymbolλ,\frac{1}{K}\mathbf1)$ and $d_f$ is an $f$-divergence that imposes (optional) penalty on deviations from uniform group weights, scaled by a parameter $ν\geq 0$. We develop a computationally efficient primal-dual algorithm that outputs a vector $\widehat{\mathbf w}$ that is constant-factor competitive with $\mathbf{w}_*$ under the worst-case group weighting. Our analytical framework directly confronts the inherent nonconvexity of the loss function, providing robust learning guarantees in the face of arbitrary label corruptions and group-specific distributional shifts. The implementation of the dual extrapolation update motivated by our algorithmic framework shows promise on LLM pre-training benchmarks. --- ### MalURLBench: A Benchmark Evaluating Agents' Vulnerabilities When Processing Web URLs Authors: Dezhang Kong, Zhuxi Wu, Shiqi Liu, Zhicheng Tan, Kuichen Lu, Minghao Li, Qichen Liu, Shengyu Chu, Zhenhua Xu, Xuan Liu, Meng Han Published: 2026-01-26 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2601.18113v3 LLM-based web agents have become increasingly popular for their utility in daily life and work. However, they exhibit critical vulnerabilities when processing malicious URLs: accepting a disguised malicious URL enables subsequent access to unsafe webpages, which can cause severe damage to service providers and users. Despite this risk, no benchmark currently targets this emerging threat. To address this gap, we propose MalURLBench, the first benchmark for evaluating LLMs' vulnerabilities to malicious URLs. MalURLBench contains 61,845 attack instances spanning 10 real-world scenarios and 7 categories of real malicious websites. Experiments with 12 popular LLMs reveal that existing models struggle to detect elaborately disguised malicious URLs. We further identify and analyze key factors that impact attack success rates and propose URLGuard, a lightweight defense module. We believe this work will provide a foundational resource for advancing the security of web agents. Our code is available at https://github.com/JiangYingEr/MalURLBench. --- ### Demystifying Data-Driven Probabilistic Medium-Range Weather Forecasting Authors: Jean Kossaifi, Nikola Kovachki, Morteza Mardani, Daniel Leibovici, Suman Ravuri, Ira Shokar, Edoardo Calvello, Mohammad Shoaib Abbas, Peter Harrington, Ashay Subramaniam, Noah Brenowitz, Boris Bonev et al. Published: 2026-01-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.18111v1 The recent revolution in data-driven methods for weather forecasting has lead to a fragmented landscape of complex, bespoke architectures and training strategies, obscuring the fundamental drivers of forecast accuracy. Here, we demonstrate that state-of-the-art probabilistic skill requires neither intricate architectural constraints nor specialized training heuristics. We introduce a scalable framework for learning multi-scale atmospheric dynamics by combining a directly downsampled latent space with a history-conditioned local projector that resolves high-resolution physics. We find that our framework design is robust to the choice of probabilistic estimator, seamlessly supporting stochastic interpolants, diffusion models, and CRPS-based ensemble training. Validated against the Integrated Forecasting System and the deep learning probabilistic model GenCast, our framework achieves statistically significant improvements on most of the variables. These results suggest scaling a general-purpose model is sufficient for state-of-the-art medium-range prediction, eliminating the need for tailored training recipes and proving effective across the full spectrum of probabilistic frameworks. --- ### AttenMIA: LLM Membership Inference Attack through Attention Signals Authors: Pedram Zaree, Md Abdullah Al Mamun, Yue Dong, Ihsen Alouani, Nael Abu-Ghazaleh Published: 2026-01-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.18110v1 Large Language Models (LLMs) are increasingly deployed to enable or improve a multitude of real-world applications. Given the large size of their training data sets, their tendency to memorize training data raises serious privacy and intellectual property concerns. A key threat is the membership inference attack (MIA), which aims to determine whether a given sample was included in the model's training set. Existing MIAs for LLMs rely primarily on output confidence scores or embedding-based features, but these signals are often brittle, leading to limited attack success. We introduce AttenMIA, a new MIA framework that exploits self-attention patterns inside the transformer model to infer membership. Attention controls the information flow within the transformer, exposing different patterns for memorization that can be used to identify members of the dataset. Our method uses information from attention heads across layers and combines them with perturbation-based divergence metrics to train an effective MIA classifier. Using extensive experiments on open-source models including LLaMA-2, Pythia, and Opt models, we show that attention-based features consistently outperform baselines, particularly under the important low-false-positive metric (e.g., achieving up to 0.996 ROC AUC & 87.9% TPR@1%FPR on the WikiMIA-32 benchmark with Llama2-13b). We show that attention signals generalize across datasets and architectures, and provide a layer- and head-level analysis of where membership leakage is most pronounced. We also show that using AttenMIA to replace other membership inference attacks in a data extraction framework results in training data extraction attacks that outperform the state of the art. Our findings reveal that attention mechanisms, originally introduced to enhance interpretability, can inadvertently amplify privacy risks in LLMs, underscoring the need for new defenses. --- ### Beyond Static Datasets: Robust Offline Policy Optimization via Vetted Synthetic Transitions Authors: Pedram Agand, Mo Chen Published: 2026-01-26 Categories: cs.LG, cs.HC, cs.RO arXiv: https://arxiv.org/abs/2601.18107v1 Offline Reinforcement Learning (ORL) holds immense promise for safety-critical domains like industrial robotics, where real-time environmental interaction is often prohibitive. A primary obstacle in ORL remains the distributional shift between the static dataset and the learned policy, which typically mandates high degrees of conservatism that can restrain potential policy improvements. We present MoReBRAC, a model-based framework that addresses this limitation through Uncertainty-Aware latent synthesis. Instead of relying solely on the fixed data, MoReBRAC utilizes a dual-recurrent world model to synthesize high-fidelity transitions that augment the training manifold. To ensure the reliability of this synthetic data, we implement a hierarchical uncertainty pipeline integrating Variational Autoencoder (VAE) manifold detection, model sensitivity analysis, and Monte Carlo (MC) dropout. This multi-layered filtering process guarantees that only transitions residing within high-confidence regions of the learned dynamics are utilized. Our results on D4RL Gym-MuJoCo benchmarks reveal significant performance gains, particularly in ``random'' and ``suboptimal'' data regimes. We further provide insights into the role of the VAE as a geometric anchor and discuss the distributional trade-offs encountered when learning from near-optimal datasets. --- ### GLEN-Bench: A Graph-Language based Benchmark for Nutritional Health Authors: Jiatan Huang, Zheyuan Zhang, Tianyi Ma, Mingchen Li, Yaning Zheng, Yanfang Ye, Chuxu Zhang Published: 2026-01-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.18106v1 Nutritional interventions are important for managing chronic health conditions, but current computational methods provide limited support for personalized dietary guidance. We identify three key gaps: (1) dietary pattern studies often ignore real-world constraints such as socioeconomic status, comorbidities, and limited food access; (2) recommendation systems rarely explain why a particular food helps a given patient; and (3) no unified benchmark evaluates methods across the connected tasks needed for nutritional interventions. We introduce GLEN-Bench, the first comprehensive graph-language based benchmark for nutritional health assessment. We combine NHANES health records, FNDDS food composition data, and USDA food-access metrics to build a knowledge graph that links demographics, health conditions, dietary behaviors, poverty-related constraints, and nutrient needs. We test the benchmark using opioid use disorder, where models must detect subtle nutritional differences across disease stages. GLEN-Bench includes three linked tasks: risk detection identifies at-risk individuals from dietary and socioeconomic patterns; recommendation suggests personalized foods that meet clinical needs within resource constraints; and question answering provides graph-grounded, natural-language explanations to facilitate comprehension. We evaluate these graph-language approaches, including graph neural networks, large language models, and hybrid architectures, to establish solid baselines and identify practical design choices. Our analysis identifies clear dietary patterns linked to health risks, providing insights that can guide practical interventions. --- ### Mitigating the OWASP Top 10 For Large Language Models Applications using Intelligent Agents Authors: Mohammad Fasha, Faisal Abul Rub, Nasim Matar, Bilal Sowan, Mohammad Al Khaldy Published: 2026-01-26 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2601.18105v1 Large Language Models (LLMs) have emerged as a transformative and disruptive technology, enabling a wide range of applications in natural language processing, machine translation, and beyond. However, this widespread integration of LLMs also raised several security concerns highlighted by the Open Web Application Security Project (OWASP), which has identified the top 10 security vulnerabilities inherent in LLM applications. Addressing these vulnerabilities is crucial, given the increasing reliance on LLMs and the potential threats to data integrity, confidentiality, and service availability. This paper presents a framework designed to mitigate the security risks outlined in the OWASP Top 10. Our proposed model leverages LLM-enabled intelligent agents, offering a new approach to proactively identify, assess, and counteract security threats in real-time. The proposed framework serves as an initial blueprint for future research and development, aiming to enhance the security measures of LLMs and protect against emerging threats in this rapidly evolving landscape. --- ### CHiRPE: A Step Towards Real-World Clinical NLP with Clinician-Oriented Model Explanations Authors: Stephanie Fong, Zimu Wang, Guilherme C. Oliveira, Xiangyu Zhao, Yiwen Jiang, Jiahe Liu, Beau-Luke Colton, Scott Woods, Martha E. Shenton, Barnaby Nelson, Zongyuan Ge, Dominic Dwyer Published: 2026-01-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.18102v1 The medical adoption of NLP tools requires interpretability by end users, yet traditional explainable AI (XAI) methods are misaligned with clinical reasoning and lack clinician input. We introduce CHiRPE (Clinical High-Risk Prediction with Explainability), an NLP pipeline that takes transcribed semi-structured clinical interviews to: (i) predict psychosis risk; and (ii) generate novel SHAP explanation formats co-developed with clinicians. Trained on 944 semi-structured interview transcripts across 24 international clinics of the AMP-SCZ study, the CHiRPE pipeline integrates symptom-domain mapping, LLM summarisation, and BERT classification. CHiRPE achieved over 90% accuracy across three BERT variants and outperformed baseline models. Explanation formats were evaluated by 28 clinical experts who indicated a strong preference for our novel concept-guided explanations, especially hybrid graph-and-text summary formats. CHiRPE demonstrates that clinically-guided model development produces both accurate and interpretable results. Our next step is focused on real-world testing across our 24 international sites. --- ### Spatial-Conditioned Reasoning in Long-Egocentric Videos Authors: James Tribble, Hao Wang, Si-En Hong, Chaoyi Zhou, Ashish Bastola, Siyu Huang, Abolfazl Razi Published: 2026-01-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.18100v2 Long-horizon egocentric video presents significant challenges for visual navigation due to viewpoint drift and the absence of persistent geometric context. Although recent vision-language models perform well on image and short-video reasoning, their spatial reasoning capability in long egocentric sequences remains limited. In this work, we study how explicit spatial signals influence VLM-based video understanding without modifying model architectures or inference procedures. We introduce Sanpo-D, a fine-grained re-annotation of the Google Sanpo dataset, and benchmark multiple VLMs on navigation-oriented spatial queries. To examine input-level inductive bias, we further fuse depth maps with RGB frames and evaluate their impact on spatial reasoning. Our results reveal a trade-off between general-purpose accuracy and spatial specialization, showing that depth-aware and spatially grounded representations can improve performance on safety-critical tasks such as pedestrian and obstruction detection. --- ### Computational Framework for Estimating Relative Gaussian Blur Kernels between Image Pairs Authors: Akbar Saadat Published: 2026-01-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.18099v1 Following the earlier verification for Gaussian model in \cite{ASaa2026}, this paper introduces a zero training forward computational framework for the model to realize it in real time applications. The framework is based on discrete calculation of the analytic expression of the defocused image from the sharper one for the application range of the standard deviation of the Gaussian kernels and selecting the best matches. The analytic expression yields multiple solutions at certain image points, but is filtered down to a single solution using similarity measures over neighboring points.The framework is structured to handle cases where two given images are partial blurred versions of each other. Experimental evaluations on real images demonstrate that the proposed framework achieves a mean absolute error (MAE) below $1.7\%$ in estimating synthetic blur values. Furthermore, the discrepancy between actual blurred image intensities and their corresponding estimates remains under $2\%$, obtained by applying the extracted defocus filters to less blurred images. --- ### Text-Pass Filter: An Efficient Scene Text Detector Authors: Chuang Yang, Haozhao Ma, Xu Han, Yuan Yuan, Qi Wang Published: 2026-01-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.18098v1 To pursue an efficient text assembling process, existing methods detect texts via the shrink-mask expansion strategy. However, the shrinking operation loses the visual features of text margins and confuses the foreground and background difference, which brings intrinsic limitations to recognize text features. We follow this issue and design Text-Pass Filter (TPF) for arbitrary-shaped text detection. It segments the whole text directly, which avoids the intrinsic limitations. It is noteworthy that different from previous whole text region-based methods, TPF can separate adhesive texts naturally without complex decoding or post-processing processes, which makes it possible for real-time text detection. Concretely, we find that the band-pass filter allows through components in a specified band of frequencies, called its passband but blocks components with frequencies above or below this band. It provides a natural idea for extracting whole texts separately. By simulating the band-pass filter, TPF constructs a unique feature-filter pair for each text. In the inference stage, every filter extracts the corresponding matched text by passing its pass-feature and blocking other features. Meanwhile, considering the large aspect ratio problem of ribbon-like texts makes it hard to recognize texts wholly, a Reinforcement Ensemble Unit (REU) is designed to enhance the feature consistency of the same text and to enlarge the filter's recognition field to help recognize whole texts. Furthermore, a Foreground Prior Unit (FPU) is introduced to encourage TPF to discriminate the difference between the foreground and background, which improves the feature-filter pair quality. Experiments demonstrate the effectiveness of REU and FPU while showing the TPF's superiority. --- ### From LLMs to LRMs: Rethinking Pruning for Reasoning-Centric Models Authors: Longwei Ding, Anhao Zhao, Fanghua Ye, Ziyang Chen, Xiaoyu Shen Published: 2026-01-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.18091v1 Large language models (LLMs) are increasingly costly to deploy, motivating extensive research on model pruning. However, most existing studies focus on instruction-following LLMs, leaving it unclear whether established pruning strategies transfer to reasoning-augmented models that explicitly generate long intermediate reasoning traces. In this work, we conduct a controlled study of pruning for both instruction-following ($\textbf{LLM-instruct}$) and reasoning-augmented ($\textbf{LLM-think}$) models. To isolate the effects of pruning, we align pruning calibration and post-pruning recovery data with each model's original training distribution, which we show yields more stable and reliable pruning behavior. We evaluate static depth pruning, static width pruning, and dynamic pruning across 17 tasks spanning classification, generation, and reasoning. Our results reveal clear paradigm-dependent differences: depth pruning outperforms width pruning on classification tasks, while width pruning is more robust for generation and reasoning. Moreover, static pruning better preserves reasoning performance, whereas dynamic pruning excels on classification and generation but remains challenging for long-chain reasoning. These findings underscore the need for pruning strategies that explicitly account for the distinct characteristics of reasoning-augmented LLMs. Our code is publicly available at https://github.com/EIT-NLP/LRM-Pruning. --- ### LatentMoE: Toward Optimal Accuracy per FLOP and Parameter in Mixture of Experts Authors: Venmugil Elango, Nidhi Bhatia, Roger Waleffe, Rasoul Shafipour, Tomer Asida, Abhinav Khattar, Nave Assaf, Maximilian Golub, Joey Guman, Tiyasa Mitra, Ritchie Zhao, Ritika Borkar et al. Published: 2026-01-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.18089v1 Mixture of Experts (MoEs) have become a central component of many state-of-the-art open-source and proprietary large language models. Despite their widespread adoption, it remains unclear how close existing MoE architectures are to optimal with respect to inference cost, as measured by accuracy per floating-point operation and per parameter. In this work, we revisit MoE design from a hardware-software co-design perspective, grounded in empirical and theoretical considerations. We characterize key performance bottlenecks across diverse deployment regimes, spanning offline high-throughput execution and online, latency-critical inference. Guided by these insights, we introduce LatentMoE, a new model architecture resulting from systematic design exploration and optimized for maximal accuracy per unit of compute. Empirical design space exploration at scales of up to 95B parameters and over a 1T-token training horizon, together with supporting theoretical analysis, shows that LatentMoE consistently outperforms standard MoE architectures in terms of accuracy per FLOP and per parameter. Given its strong performance, the LatentMoE architecture has been adopted by the flagship Nemotron-3 Super and Ultra models and scaled to substantially larger regimes, including longer token horizons and larger model sizes, as reported in Nvidia et al. (arXiv:2512.20856). ---