# Research Papers — 2026-01 · bundle page 1 of 189 > Full-text markdown of papers #1–50 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 [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/2.md) ### Exploring Structural Complexity in Normative RAG with Graph-based approaches: A case study on the ETSI Standards Authors: Aiman Al Masoud, Marco Arazzi, Simone Germani, Antonino Nocera Published: 2026-01-31 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.09868v1 Industrial standards and normative documents exhibit intricate hierarchical structures, domain-specific lexicons, and extensive cross-referential dependencies, which making it challenging to process them directly by Large Language Models (LLMs). While Retrieval-Augmented Generation (RAG) provides a computationally efficient alternative to LLM fine-tuning, standard "vanilla" vector-based retrieval may fail to capture the latent structural and relational features intrinsic in normative documents. With the objective of shedding light on the most promising technique for building high-performance RAG solutions for normative, standards, and regulatory documents, this paper investigates the efficacy of Graph RAG architectures, which represent information as interconnected nodes, thus moving from simple semantic similarity toward a more robust, relation-aware retrieval mechanism. Despite the promise of graph-based techniques, there is currently a lack of empirical evidence as to which is the optimal indexing strategy for technical standards. Therefore, to help solve this knowledge gap, we propose a specialized RAG methodology tailored to the unique structure and lexical characteristics of standards and regulatory documents. Moreover, to keep our investigation grounded, we focus on well-known public standards, such as the ETSI EN 301 489 series. We evaluate several lightweight and low-latency strategies designed to embed document structure directly into the retrieval workflow. The considered approaches are rigorously tested against a custom synthesized Q&A dataset, facilitating a quantitative performance analysis. Our experimental results demonstrate that the incorporation of structural and lexical information into the index can enhance, at least to some extent, retrieval performance, providing a scalable framework for automated normative and standards elaboration. --- ### SRBench: A Comprehensive Benchmark for Sequential Recommendation with Large Language Models Authors: Jianhong Li, Zeheng Qian, Wangze Ni, Haoyang Li, Hongwei Yao, Yang Bai, Kui Ren Published: 2026-01-31 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2604.09553v1 LLM development has aroused great interest in Sequential Recommendation (SR) applications. However, comprehensive evaluation of SR models remains lacking due to the limitations of the existing benchmarks: 1) an overemphasis on accuracy, ignoring other real-world demands (e.g., fairness); 2) existing datasets fail to unleash LLMs' potential, leading to unfair comparison between Neural-Network-based SR (NN-SR) models and LLM-based SR (LLM-SR) models; and 3) no reliable mechanism for extracting task-specific answers from unstructured LLM outputs. To address these limitations, we propose SRBench, a comprehensive SR benchmark with three core designs: 1) a multi-dimensional framework covering accuracy, fairness, stability and efficiency, aligned with practical demands; 2) a unified input paradigm via prompt engineering to boost LLM-SR performance and enable fair comparisons between models; 3) a novel prompt-extractor-coupled extraction mechanism, which captures answers from LLM outputs through prompt-enforced output formatting and a numeric-oriented extractor. We have used SRBench to evaluate 13 mainstream models and discovered some meaningful insights (e.g., LLM-SR models overfocus on item popularity but lack deep understanding of item quality). Concisely, SRBench enables fair and comprehensive assessments for SR models, underpinning future research and practical application. --- ### MCERF: Advancing Multimodal LLM Evaluation of Engineering Documentation with Enhanced Retrieval Authors: Kiarash Naghavi Khanghah, Hoang Anh Nguyen, Anna C. Doris, Amir Mohammad Vahedi, Daniele Grandi, Faez Ahmed, Hongyi Xu Published: 2026-01-31 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.09552v2 Engineering rulebooks and technical standards contain multimodal information like dense text, tables, and illustrations that are challenging for retrieval augmented generation (RAG) systems. Building upon the DesignQA framework (1), which relied on full-text ingestion and text-based retrieval, this work establishes a Multimodal ColPali Enhanced Retrieval and Reasoning Framework (MCERF), a system that couples a multimodal retriever with large language model reasoning for accurate and efficient question answering from engineering documents. The system employs the ColPali, which retrieves both textual and visual information, and multiple retrieval and reasoning strategies: (i) Hybrid Lookup mode for explicit rule mentions, (ii) Vision to Text fusion for figure and table guided queries, (iii) High Reasoning LLM mode for complex multi modal questions, and (iv) SelfConsistency decision to stabilize responses. The modular framework design provides a reusable template for future multimodal systems regardless of underlying model architecture. Furthermore, this work establishes and compares two routing approaches: a single case routing approach and a multi-agent system, both of which dynamically allocate queries to optimal pipelines. Evaluation on the DesignQA benchmark illustrates that this system improves average accuracy across all tasks with a relative gain of +41.1% from baseline RAG best results, which is a significant improvement in multimodal and reasoning-intensive tasks without complete rulebook ingestion. This shows how vision language retrieval, modular reasoning, and adaptive routing enable scalable document comprehension in engineering use cases. --- ### Supporting Calibrated Reliance in Human-AI Collaboration: Different Strategies for Different Tasks Authors: Ruth Cohen, Lu Feng, Ayala Bloch, Sarit Kraus Published: 2026-01-31 Categories: cs.HC, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.03237v2 As AI systems increasingly support human decision making, a central challenge is determining what information helps people recognize when to rely on AI predictions and when to question or override them. Across three controlled human-subject studies spanning abstract visual reasoning with RAVEN matrices and deductive logical reasoning with LSAT problems, we examine how different forms of AI support affect human--AI team performance. A multi-stage reveal study shows that AI predictions and explanations can affect objective accuracy and subjective confidence differently. In visual reasoning, LLM explanations do not improve accuracy beyond the predicted answer alone, and no additional support format significantly outperforms prediction-only support; predicted probabilities show the highest descriptive accuracy and error recovery, while a derived selective-automation policy provides a higher-performing reference benchmark. In language-based logical reasoning, by contrast, LLM explanations yield the highest accuracy and error recovery, outperforming expert-written explanations and probability-based support. These results show that no single support strategy is universally effective. Human--AI interfaces should instead be designed to support calibrated reliance and effective error recovery by matching the form of assistance to the task and the evidence available to users. --- ### BLADE: Better Language Answers through Dialogue and Explanations Authors: Chathuri Jayaweera, Phoebe Huang, Bonnie J. Dorr Published: 2026-01-31 Categories: cs.HC, cs.CL arXiv: https://arxiv.org/abs/2604.03236v2 Large language model (LLM)-based educational assistants often provide direct answers offering little incentive for students to explore or engage with course materials. We present BLADE (Better Language Answers through Dialogue and Explanations), a retrieval-augmented generation (RAG) based conversational assistant grounded in course-specific content that guides students toward relevant materials through citation-grounded dialogue rather than delivering unsourced solutions. We evaluate BLADE in an advanced undergraduate NLP course with extensive instructional resources, where locating and synthesizing relevant material is a central challenge. During quizzes, students are assigned to one of three conditions: BLADE only, direct course materials only, or both; we measure performance and resource usage. Results show that students consistently select BLADE over direct materials when both are available, and that quiz performance is highest when students use BLADE alone. In contrast, simultaneous use of both resources is associated with significantly lower performance, suggesting that combining modalities may introduce cognitive load without benefit. These findings show the potential of RAG-based assistants as a citation-grounded interface for applying course content under open-book exam-like conditions, while cautioning that adding direct-material access does not necessarily help, and may hinder, in-task performance. --- ### CoEditor++: Instruction-based Visual Editing via Cognitive Reasoning Authors: Minheng Ni, Yutao Fan, Zhengyuan Yang, Yeli Shen, Yuxiang Wei, Yaowen Zhang, Lijuan Wang, Lei Zhang, Wangmeng Zuo Published: 2026-01-31 Categories: cs.HC, cs.CV arXiv: https://arxiv.org/abs/2603.05518v1 Recent advances in large multimodal models (LMMs) have enabled instruction-based image editing, allowing users to modify visual content via natural language descriptions. However, existing approaches often struggle with high-level semantic reasoning and visual consistency, particularly under ambiguous or complex instructions. To address these challenges, we propose CoEditor++, a cognitively structured, training-free framework that decomposes editing into "what to edit" and "how to edit" through two cognitive stages with a reflective self-selection mechanism, enabling robust, fine-grained, and interpretable editing. Built entirely from open-sourced components, CoEditor++ requires no additional training or fine-tuning, ensuring transparency and cross-domain applicability. We evaluate CoEditor++ on SmartEdit, a widely used benchmark for general editing, and AltBear, a privacy and compliance-oriented benchmark. Experimental results show that CoEditor++ achieves state-of-the-art performance in both general editing and responsible editing tasks compared with open-sourced models that require training on specialized editing datasets maintaining significantly higher visual consistency. When compared with closed-source models such as Nano Banana Pro or GPT-4o, CoEditor++ preserves comparable instruction following while still substantially outperforming them in visual consistency. Extensive ablation studies confirm that the effectiveness of CoEditor++ benefits from its structured cognitive design rather than any specific model component. Our findings suggest the potential toward cognitive-centric instruction-based image editing. --- ### Beyond Static Instruction: A Multi-agent AI Framework for Adaptive Augmented Reality Robot Training Authors: Nicolas Leins, Jana Gonnermann-Müller, Malte Teichmann, Sebastian Pokutta Published: 2026-01-31 Categories: cs.RO, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2603.00016v2 Augmented Reality (AR) offers powerful visualization capabilities for industrial robot training, yet current interfaces remain predominantly static, failing to account for learners' diverse cognitive profiles. In this paper, we present an AR application for robot training and propose a multi-agent AI framework for future integration that bridges the gap between static visualization and pedagogical intelligence. We report on the evaluation of the baseline AR interface with 36 participants performing a robotic pick-and-place task. While overall usability was high, notable disparities in task duration and learner characteristics highlighted the necessity for dynamic adaptation. To address this, we propose a multi-agent framework that orchestrates multiple components to perform complex preprocessing of multimodal inputs (e.g., voice, physiology, robot data) and adapt the AR application to the learner's needs. By utilizing autonomous Large Language Model (LLM) agents, the proposed system would dynamically adapt the learning environment based on advanced LLM reasoning in real-time. --- ### Latent Context Compilation: Distilling Long Context into Compact Portable Memory Authors: Zeju Li, Yizhou Zhou, Qiang Xu Published: 2026-01-31 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.21221v1 Efficient long-context LLM deployment is stalled by a dichotomy between amortized compression, which struggles with out-of-distribution generalization, and Test-Time Training, which incurs prohibitive synthetic data costs and requires modifying model weights, creating stateful parameters that complicate concurrent serving. We propose Latent Context Compilation, a framework that fundamentally shifts context processing from adaptation to compilation. By utilizing a disposable LoRA module as a compiler, we distill long contexts into compact buffer tokens -- stateless, portable memory artifacts that are plug-and-play compatible with frozen base models. Crucially, we introduce a self-aligned optimization strategy that eliminates the need for synthetic context-relevant QA pairs. By regularizing context reconstruction task with context-agnostic random queries, we force compressed tokens to reside within the model's existing instruction-following manifold. Experiments with Llama-3.1-8B demonstrate that Latent Context Compilation preserves fine-grained details and reasoning capabilities where prior methods falter, effectively decoupling memory density from model parameters even at a 16x compression ratio. --- ### Field-Theoretic Memory for AI Agents: Continuous Dynamics for Context Preservation Authors: Subhadip Mitra Published: 2026-01-31 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.21220v1 We present a memory system for AI agents that treats stored information as continuous fields governed by partial differential equations rather than discrete entries in a database. The approach draws from classical field theory: memories diffuse through semantic space, decay thermodynamically based on importance, and interact through field coupling in multi-agent scenarios. We evaluate the system on two established long-context benchmarks: LoCoMo (ACL 2024) with 300-turn conversations across 35 sessions, and LongMemEval (ICLR 2025) testing multi-session reasoning over 500+ turns. On LongMemEval, the field-theoretic approach achieves significant improvements: +116% F1 on multi-session reasoning (p<0.01, d= 3.06), +43.8% on temporal reasoning (p<0.001, d= 9.21), and +27.8% retrieval recall on knowledge updates (p<0.001, d= 5.00). Multi-agent experiments show near-perfect collective intelligence (>99.8%) through field coupling. Code is available at github.com/rotalabs/rotalabs-fieldmem. --- ### Reasoning-Based Personalized Generation for Users with Sparse Data Authors: Bo Ni, Branislav Kveton, Samyadeep Basu, Subhojyoti Mukherjee, Leyao Wang, Franck Dernoncourt, Sungchul Kim, Seunghyun Yoon, Zichao Wang, Ruiyi Zhang, Puneet Mathur, Jihyung Kil et al. Published: 2026-01-31 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.21219v2 Large Language Model (LLM) personalization holds great promise for tailoring responses by leveraging personal context and history. However, real-world users usually possess sparse interaction histories with limited personal context, such as cold-start users in social platforms and newly registered customers in online E-commerce platforms, compromising the LLM-based personalized generation. To address this challenge, we introduce GraSPer (Graph-based Sparse Personalized Reasoning), a novel framework for enhancing personalized text generation under sparse context. GraSPer first augments user context by predicting items that the user would likely interact with in the future. With reasoning alignment, it then generates texts for these interactions to enrich the augmented context. In the end, it generates personalized outputs conditioned on both the real and synthetic histories, ensuring alignment with user style and preferences. Extensive experiments on three benchmark personalized generation datasets show that GraSPer achieves significant performance gain, substantially improving personalization in sparse user context settings. --- ### EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors Authors: Amin Banayeeanzade, Qingchuan Yang, Deqing Fu, Spencer Hong, Erin Babinsky, Alfy Samuel, Anoop Kumar, Robin Jia, Sai Praneeth Karimireddy Published: 2026-01-31 Categories: cs.CL, cs.AI, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2602.21218v2 High-quality data is essential for modern machine learning, yet many valuable corpora are sensitive and cannot be freely shared. Synthetic data offers a practical substitute for downstream development, and large language models (LLMs) have emerged as powerful engines for generating it. However, existing private text generation methods are severely inefficient: they are data-intensive, computationally slow, and often require large private corpora or batch sizes to achieve usable quality. We introduce EPSVec, a differentially-private lightweight alternative that steers LLM generation using *dataset vectors*--directions in activation space that capture the distributional gap between private data and public priors. EPSVec extracts and sanitizes steering vectors just once and then performs standard decoding. This decouples the privacy budget from generation, enabling arbitrarily many synthetic samples without additional privacy cost and yielding strong fidelity even in low-data regimes. Furthermore, we enhance our method by utilizing pretrained (base) models and introducing fixed-shot prompting to boost generation diversity and fidelity. Our experiments demonstrate that EPSVec outperforms existing baselines in distributional alignment and downstream utility, particularly in low-data regimes, while significantly reducing computational overhead. --- ### Test-Time Adaptation for Tactile-Vision-Language Models Authors: Chuyang Ye, Haoxian Jing, Qinting Jiang, Yixi Lin, Qiang Li, Xing Tang, Jingyan Jiang Published: 2026-01-31 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2602.15873v1 Tactile-vision-language (TVL) models are increasingly deployed in real-world robotic and multimodal perception tasks, where test-time distribution shifts are unavoidable. Existing test-time adaptation (TTA) methods provide filtering in unimodal settings but lack explicit treatment of modality-wise reliability under asynchronous cross-modal shifts, leaving them brittle when some modalities become unreliable. We study TTA for TVL models under such shifts and propose a reliability-aware framework that estimates per-modality reliability from prediction uncertainty and perturbation-based responses. This shared reliability signal is used to (i) filter unreliable test samples, (ii) adaptively fuse tactile, visual, and language features, and (iii) regularize test-time optimization with a reliability-guided objective. On the TAG-C benchmark and additional TVL scenarios, our approach consistently outperforms strong TTA baselines, achieving accuracy gains of up to 49.9\% under severe modality corruptions, underscoring the importance of explicit modality-wise reliability modeling for robust test-time adaptation. --- ### GRACE: an Agentic AI for Particle Physics Experiment Design and Simulation Authors: Justin Hill, Hong Joo Ryoo Published: 2026-01-31 Categories: hep-ex, cs.AI arXiv: https://arxiv.org/abs/2602.15039v1 We present GRACE, a simulation-native agent for autonomous experimental design in high-energy and nuclear physics. Given multimodal input in the form of a natural-language prompt or a published experimental paper, the agent extracts a structured representation of the experiment, constructs a runnable toy simulation, and autonomously explores design modifications using first-principles Monte Carlo methods. Unlike agentic systems focused on operational control or execution of predefined procedures, GRACE addresses the upstream problem of experimental design: proposing non-obvious modifications to detector geometry, materials, and configurations that improve physics performance under physical and practical constraints. The agent evaluates candidate designs through repeated simulation, physics-motivated utility functions, and budget-aware escalation from fast parametric models to full Geant4 simulations, while maintaining strict reproducibility and provenance tracking. We demonstrate the framework on historical experimental setups, showing that the agent can identify optimization directions that align with known upgrade priorities, using only baseline simulation inputs. We also conducted a benchmark in which the agent identified the setup and proposed improvements from a suite of natural language prompts, with some supplied with a relevant physics research paper, of varying high energy physics (HEP) problem settings. This work establishes experimental design as a constrained search problem under physical law and introduces a new benchmark for autonomous, simulation-driven scientific reasoning in complex instruments. --- ### Responsible AI in Business Authors: Stephan Sandfuchs, Diako Farooghi, Janis Mohr, Sarah Grewe, Markus Lemmen, Jörg Frochte Published: 2026-01-31 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2602.13244v1 Artificial intelligence (AI) and Machine Learning (ML) have moved from research and pilot projects into everyday business operations, with generative AI accelerating adoption across processes, products, and services. This paper introduces the concept of Responsible AI for organizational practice, with a particular focus on small and medium-sized enterprises. It structures Responsible AI along four focal areas that are central for introducing and operating AI systems in a legally compliant, comprehensible, sustainable, and data-sovereign manner. First, it discusses the EU AI Act as a risk-based regulatory framework, including the distinction between provider and deployer roles and the resulting obligations such as risk assessment, documentation, transparency requirements, and AI literacy measures. Second, it addresses Explainable AI as a basis for transparency and trust, clarifying key notions such as transparency, interpretability, and explainability and summarizing practical approaches to make model behavior and decisions more understandable. Third, it covers Green AI, emphasizing that AI systems should be evaluated not only by performance but also by energy and resource consumption, and outlines levers such as model reuse, resource-efficient adaptation, continuous learning, model compression, and monitoring. Fourth, it examines local models (on-premise and edge) as an operating option that supports data protection, control, low latency, and strategic independence, including domain adaptation via fine-tuning and retrieval-augmented generation. The paper concludes with a consolidated set of next steps for establishing governance, documentation, secure operation, sustainability considerations, and an implementation roadmap. --- ### Judging the Judges: Human Validation of Multi-LLM Evaluation for High-Quality K--12 Science Instructional Materials Authors: Peng He, Zhaohui Li, Zeyuan Wang, Jinjun Xiong, Tingting Li Published: 2026-01-31 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2602.13243v1 Designing high-quality, standards-aligned instructional materials for K--12 science is time-consuming and expertise-intensive. This study examines what human experts notice when reviewing AI-generated evaluations of such materials, aiming to translate their insights into design principles for a future GenAI-based instructional material design agent. We intentionally selected 12 high-quality curriculum units across life, physical, and earth sciences from validated programs such as OpenSciEd and Multiple Literacies in Project-based Learning. Using the EQuIP rubric with 9 evaluation items, we prompted GPT-4o, Claude, and Gemini to produce numerical ratings and written rationales for each unit, generating 648 evaluation outputs. Two science education experts independently reviewed all outputs, marking agreement (1) or disagreement (0) for both scores and rationales, and offering qualitative reflections on AI reasoning. This process surfaces patterns in where LLM judgments align with or diverge from expert perspectives, revealing reasoning strengths, gaps, and contextual nuances. These insights will directly inform the development of a domain-specific GenAI agent to support the design of high-quality instructional materials in K--12 science education. --- ### A Gradient Boosted Mixed-Model Machine Learning Framework for Vessel Speed in the U.S. Arctic Authors: Mauli Pant, Linda Fernandez, Indranil Sahoo Published: 2026-01-31 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2602.12292v1 Understanding how environmental and operational conditions influence vessel speed is crucial for characterizing navigational conditions in the Arctic. We analyzed Automatic Identification System (AIS) data from 2010-2019 to examine vessel speed over ground (SOG). Over half of the AIS records showed zero SOG, and treating zero and positive SOG as a single continuous process can obscure important patterns. We therefore applied a two-stage machine learning framework, first modeling the probability of SOG greater than zero and then modeling SOG conditional on being positive. AIS observations were integrated with sea ice concentration, course over ground, wind, bathymetric depth, distance to coast, vessel group, and navigational status. Gradient boosted decision trees with random effects captured nonlinear environmental responses while accounting for repeated observations. The positive SOG classifier achieved strong discrimination (AUC = 0.85), while the conditional speed model explained approximately 77 percent of out-of-fold variance. SHAP values quantified covariate effects by decomposing model predictions into additive contributions from individual variables. Distance to coast and bathymetric depth were dominant determinants of both the likelihood and magnitude of vessel speed, while changes in course, vessel group, and navigational status introduced secondary variation. Wind and sea ice effects were modest. Together, these results empirically characterize Arctic vessel operating regimes relevant to speed management and corridor-level assessment. --- ### Gaussian-Constrained LeJEPA Representations for Unsupervised Scene Discovery and Pose Consistency Authors: Mohsen Mostafa Published: 2026-01-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.07016v1 Unsupervised 3D scene reconstruction from unstructured image collections remains a fundamental challenge in computer vision, particularly when images originate from multiple unrelated scenes and contain significant visual ambiguity. The Image Matching Challenge 2025 (IMC2025) highlights these difficulties by requiring both scene discovery and camera pose estimation under real-world conditions, including outliers and mixed content. This paper investigates the application of Gaussian-constrained representations inspired by LeJEPA (Joint Embedding Predictive Architecture) to address these challenges. We present three progressively refined pipelines, culminating in a LeJEPA-inspired approach that enforces isotropic Gaussian constraints on learned image embeddings. Rather than introducing new theoretical guarantees, our work empirically evaluates how these constraints influence clustering consistency and pose estimation robustness in practice. Experimental results on IMC2025 demonstrate that Gaussian-constrained embeddings can improve scene separation and pose plausibility compared to heuristic-driven baselines, particularly in visually ambiguous settings. These findings suggest that theoretically motivated representation constraints offer a promising direction for bridging self-supervised learning principles and practical structure-from-motion pipelines. --- ### Robust and Real-Time Bangladeshi Currency Recognition: A Dual-Stream MobileNet and EfficientNet Approach Authors: Subreena, Mohammad Amzad Hossain, Mirza Raquib, Saydul Akbar Murad, Farida Siddiqi Prity, Muhammad Hanif, Nick Rahimi Published: 2026-01-31 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2602.07015v2 Accurate currency recognition is essential for assistive technologies, particularly for visually impaired individuals who rely on others to identify banknotes. This dependency puts them at risk of fraud and exploitation. To address these challenges, we first build a new Bangladeshi banknote dataset that includes both controlled and real-world scenarios, ensuring a more comprehensive and diverse representation. Next, to enhance the dataset's robustness, we incorporate four additional datasets, including public benchmarks, to cover various complexities and improve the model's generalization. To overcome the limitations of current recognition models, we propose a novel hybrid CNN architecture that combines MobileNetV3-Large and EfficientNetB0 for efficient feature extraction. This is followed by an effective multilayer perceptron (MLP) classifier to improve performance while keeping computational costs low, making the system suitable for resource-constrained devices. The experimental results show that the proposed model achieves 97.95% accuracy on controlled datasets, 92.84% on complex backgrounds, and 94.98% accuracy when combining all datasets. The model's performance is thoroughly evaluated using five-fold cross-validation and seven metrics: accuracy, precision, recall, F1-score, Cohen's Kappa, MCC, and AUC. Additionally, explainable AI methods like LIME and SHAP are incorporated to enhance transparency and interpretability. --- ### Vectra: A New Metric, Dataset, and Model for Visual Quality Assessment in E-Commerce In-Image Machine Translation Authors: Qingyu Wu, Yuxuan Han, Haijun Li, Zhao Xu, Jianshan Zhao, Xu Jin, Longyue Wang, Weihua Luo Published: 2026-01-31 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.07014v1 In-Image Machine Translation (IIMT) powers cross-border e-commerce product listings; existing research focuses on machine translation evaluation, while visual rendering quality is critical for user engagement. When facing context-dense product imagery and multimodal defects, current reference-based methods (e.g., SSIM, FID) lack explainability, while model-as-judge approaches lack domain-grounded, fine-grained reward signals. To bridge this gap, we introduce Vectra, to the best of our knowledge, the first reference-free, MLLM-driven visual quality assessment framework for e-commerce IIMT. Vectra comprises three components: (1) Vectra Score, a multidimensional quality metric system that decomposes visual quality into 14 interpretable dimensions, with spatially-aware Defect Area Ratio (DAR) quantification to reduce annotation ambiguity; (2) Vectra Dataset, constructed from 1.1M real-world product images via diversity-aware sampling, comprising a 2K benchmark for system evaluation, 30K reasoning-based annotations for instruction tuning, and 3.5K expert-labeled preferences for alignment and evaluation; and (3) Vectra Model, a 4B-parameter MLLM that generates both quantitative scores and diagnostic reasoning. Experiments demonstrate that Vectra achieves state-of-the-art correlation with human rankings, and our model outperforms leading MLLMs, including GPT-5 and Gemini-3, in scoring performance. The dataset and model will be released upon acceptance. --- ### Steering to Say No: Configurable Refusal via Activation Steering in Vision Language Models Authors: Jiaxi Yang, Shicheng Liu, Yuchen Yang, Dongwon Lee Published: 2026-01-31 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.07013v1 With the rapid advancement of Vision Language Models (VLMs), refusal mechanisms have become a critical component for ensuring responsible and safe model behavior. However, existing refusal strategies are largely \textit{one-size-fits-all} and fail to adapt to diverse user needs and contextual constraints, leading to either under-refusal or over-refusal. In this work, we firstly explore the challenges mentioned above and develop \textbf{C}onfigurable \textbf{R}efusal in \textbf{VLM}s (\textbf{CR-VLM}), a robust and efficient approach for {\em configurable} refusal based on activation steering. CR-VLM consists of three integrated components: (1) extracting a configurable refusal vector via a teacher-forced mechanism to amplify the refusal signal; (2) introducing a gating mechanism that mitigates over-refusal by preserving acceptance for in-scope queries; and (3) designing a counterfactual vision enhancement module that aligns visual representations with refusal requirements. Comprehensive experiments across multiple datasets and various VLMs demonstrate that CR-VLM achieves effective, efficient, and robust configurable refusals, offering a scalable path toward user-adaptive safety alignment in VLMs. --- ### A General Model for Retinal Segmentation and Quantification Authors: Zhonghua Wang, Lie Ju, Sijia Li, Wei Feng, Sijin Zhou, Ming Hu, Jianhao Xiong, Xiaoying Tang, Yifan Peng, Mingquan Lin, Yaodong Ding, Yong Zeng et al. Published: 2026-01-31 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.07012v1 Retinal imaging is fast, non-invasive, and widely available, offering quantifiable structural and vascular signals for ophthalmic and systemic health assessment. This accessibility creates an opportunity to study how quantitative retinal phenotypes relate to ocular and systemic diseases. However, such analyses remain difficult at scale due to the limited availability of public multi-label datasets and the lack of a unified segmentation-to-quantification pipeline. We present RetSAM, a general retinal segmentation and quantification framework for fundus imaging. It delivers robust multi-target segmentation and standardized biomarker extraction, supporting downstream ophthalmologic studies and oculomics correlation analyses. Trained on over 200,000 fundus images, RetSAM supports three task categories and segments five anatomical structures, four retinal phenotypic patterns, and more than 20 distinct lesion types. It converts these segmentation results into over 30 standardized biomarkers that capture structural morphology, vascular geometry, and degenerative changes. Trained with a multi-stage strategy using both private and public fundus data, RetSAM achieves superior segmentation performance on 17 public datasets. It improves on prior best methods by 3.9 percentage points in DSC on average, with up to 15 percentage points on challenging multi-task benchmarks, and generalizes well across diverse populations, imaging devices, and clinical settings. The resulting biomarkers enable systematic correlation analyses across major ophthalmic diseases, including diabetic retinopathy, age-related macular degeneration, glaucoma, and pathologic myopia. Together, RetSAM transforms fundus images into standardized, interpretable quantitative phenotypes, enabling large-scale ophthalmic research and translation. --- ### MAU-GPT: Enhancing Multi-type Industrial Anomaly Understanding via Anomaly-aware and Generalist Experts Adaptation Authors: Zhuonan Wang, Zhenxuan Fan, Siwen Tan, Yu Zhong, Yuqian Yuan, Haoyuan Li, Hao Jiang, Wenqiao Zhang, Feifei Shao, Hongwei Wang, Jun Xiao Published: 2026-01-31 Categories: cs.CV, cs.AI, eess.IV arXiv: https://arxiv.org/abs/2602.07011v2 As industrial manufacturing scales, automating fine-grained product image analysis has become critical for quality control. However, existing approaches are hindered by limited dataset coverage and poor model generalization across diverse and complex anomaly patterns. To address these challenges, we introduce MAU-Set, a comprehensive dataset for Multi-type industrial Anomaly Understanding. It spans multiple industrial domains and features a hierarchical task structure, ranging from binary classification to complex reasoning. Alongside this dataset, we establish a rigorous evaluation protocol to facilitate fair and comprehensive model assessment. Building upon this foundation, we further present MAU-GPT, a domain-adapted multimodal large model specifically designed for industrial anomaly understanding. It incorporates a novel AMoE-LoRA mechanism that unifies anomaly-aware and generalist experts adaptation, enhancing both understanding and reasoning across diverse defect classes. Extensive experiments show that MAU-GPT consistently outperforms prior state-of-the-art methods across all domains, demonstrating strong potential for scalable and automated industrial inspection. --- ### Deep networks learn to parse uniform-depth context-free languages from local statistics Authors: Jack T. Parley, Francesco Cagnetta, Matthieu Wyart Published: 2026-01-31 Categories: stat.ML, cond-mat.dis-nn, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.06065v4 Understanding how the structure of language can be learned from sentences alone is a central question in both cognitive science and machine learning. Studies of the internal representations of Large Language Models (LLMs) support their ability to parse text when predicting the next word, while representing semantic notions independently of surface form. Yet, which data statistics make these feats possible, and how much data is required, remain largely unknown. Probabilistic context-free grammars (PCFGs) provide a tractable testbed for studying these questions. However, prior work has focused either on the post-hoc characterization of the parsing-like algorithms used by trained networks; or on the learnability of PCFGs with fixed syntax, where parsing is unnecessary. Here, we (i) introduce a tunable class of PCFGs in which both the degree of ambiguity and the correlation structure across scales can be controlled; (ii) provide a learning mechanism -- an inference algorithm inspired by the structure of deep convolutional networks -- that links learnability and sample complexity to specific language statistics; and (iii) validate our predictions empirically across deep convolutional and transformer-based architectures. Overall, we propose a unifying framework where correlations at different scales lift local ambiguities, enabling the emergence of hierarchical representations of the data. --- ### A Causal Perspective for Enhancing Jailbreak Attack and Defense Authors: Licheng Pan, Yunsheng Lu, Jiexi Liu, Jialing Tao, Haozhe Feng, Hui Xue, Zhixuan Chu, Kui Ren Published: 2026-01-31 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2602.04893v1 Uncovering the mechanisms behind "jailbreaks" in large language models (LLMs) is crucial for enhancing their safety and reliability, yet these mechanisms remain poorly understood. Existing studies predominantly analyze jailbreak prompts by probing latent representations, often overlooking the causal relationships between interpretable prompt features and jailbreak occurrences. In this work, we propose Causal Analyst, a framework that integrates LLMs into data-driven causal discovery to identify the direct causes of jailbreaks and leverage them for both attack and defense. We introduce a comprehensive dataset comprising 35k jailbreak attempts across seven LLMs, systematically constructed from 100 attack templates and 50 harmful queries, annotated with 37 meticulously designed human-readable prompt features. By jointly training LLM-based prompt encoding and GNN-based causal graph learning, we reconstruct causal pathways linking prompt features to jailbreak responses. Our analysis reveals that specific features, such as "Positive Character" and "Number of Task Steps", act as direct causal drivers of jailbreaks. We demonstrate the practical utility of these insights through two applications: (1) a Jailbreaking Enhancer that targets identified causal features to significantly boost attack success rates on public benchmarks, and (2) a Guardrail Advisor that utilizes the learned causal graph to extract true malicious intent from obfuscated queries. Extensive experiments, including baseline comparisons and causal structure validation, confirm the robustness of our causal analysis and its superiority over non-causal approaches. Our results suggest that analyzing jailbreak features from a causal perspective is an effective and interpretable approach for improving LLM reliability. Our code is available at https://github.com/Master-PLC/Causal-Analyst. --- ### DINO-AD: Unsupervised Anomaly Detection with Frozen DINO-V3 Features Authors: Jiayu Huo, Jingyuan Hong, Liyun Chen Published: 2026-01-31 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2602.03870v1 Unsupervised anomaly detection (AD) in medical images aims to identify abnormal regions without relying on pixel-level annotations, which is crucial for scalable and label-efficient diagnostic systems. In this paper, we propose a novel anomaly detection framework based on DINO-V3 representations, termed DINO-AD, which leverages self-supervised visual features for precise and interpretable anomaly localization. Specifically, we introduce an embedding similarity matching strategy to select a semantically aligned support image and a foreground-aware K-means clustering module to model the distribution of normal features. Anomaly maps are then computed by comparing the query features with clustered normal embeddings through cosine similarity. Experimental results on both the Brain and Liver datasets demonstrate that our method achieves superior quantitative performance compared with state-of-the-art approaches, achieving AUROC scores of up to 98.71. Qualitative results further confirm that our framework produces clearer and more accurate anomaly localization. Extensive ablation studies validate the effectiveness of each proposed component, highlighting the robustness and generalizability of our approach. --- ### Benchmarking Automatic Speech Recognition for Indian Languages in Agricultural Contexts Authors: Chandrashekar M S, Vineet Singh, Lakshmi Pedapudi Published: 2026-01-31 Categories: eess.AS, cs.AI, cs.CL, cs.SD arXiv: https://arxiv.org/abs/2602.03868v2 The digitization of agricultural advisory services in India requires robust Automatic Speech Recognition (ASR) systems capable of accurately transcribing domain-specific terminology in multiple Indian languages. This paper presents a benchmarking framework for evaluating ASR performance in agricultural contexts across Hindi, Telugu, and Odia languages. We introduce evaluation metrics including Agriculture Weighted Word Error Rate (AWWER) and domain-specific utility scoring to complement traditional metrics. Our evaluation of 10,934 audio recordings, each transcribed by up to 10 ASR models, reveals performance variations across languages and models, with Hindi achieving the best overall performance (WER: 16.2%) while Odia presents the greatest challenges (best WER: 35.1%, achieved only with speaker diarization). We characterize audio quality challenges inherent to real-world agricultural field recordings and demonstrate that speaker diarization with best-speaker selection can substantially reduce WER for multi-speaker recordings (upto 66% depending on the proportion of multi-speaker audio). We identify recurring error patterns in agricultural terminology and provide practical recommendations for improving ASR systems in low-resource agricultural domains. The study establishes baseline benchmarks for future agricultural ASR development. --- ### Agentic Observability: Automated Alert Triage for Adobe E-Commerce Authors: Aprameya Bharadwaj, Kyle Tu Published: 2026-01-31 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2602.02585v1 Modern enterprise systems exhibit complex interdependencies that make observability and incident response increasingly challenging. Manual alert triage, which typically involves log inspection, API verification, and cross-referencing operational knowledge bases, remains a major bottleneck in reducing mean recovery time (MTTR). This paper presents an agentic observability framework deployed within Adobe's e-commerce infrastructure that autonomously performs alert triage using a ReAct paradigm. Upon alert detection, the agent dynamically identifies the affected service, retrieves and analyzes correlated logs across distributed systems, and plans context-dependent actions such as handbook consultation, runbook execution, or retrieval-augmented analysis of recently deployed code. Empirical results from production deployment indicate a 90% reduction in mean time to insight compared to manual triage, while maintaining comparable diagnostic accuracy. Our results show that agentic AI enables an order-of-magnitude reduction in triage latency and a step-change in resolution accuracy, marking a pivotal shift toward autonomous observability in enterprise operations. --- ### Constitutional Spec-Driven Development: Enforcing Security by Construction in AI-Assisted Code Generation Authors: Srinivas Rao Marri Published: 2026-01-31 Categories: cs.SE, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2602.02584v1 The proliferation of AI-assisted "vibe coding" enables rapid software development but introduces significant security risks, as Large Language Models (LLMs) prioritize functional correctness over security. We present Constitutional Spec-Driven Development, a methodology that embeds non-negotiable security principles into the specification layer, ensuring AI-generated code adheres to security requirements by construction rather than inspection. Our approach introduces a Constitution: a versioned, machine-readable document encoding security constraints derived from Common Weakness Enumeration (CWE)/MITRE Top 25 vulnerabilities and regulatory frameworks. We demonstrate the methodology through a banking microservices application, selected as a representative example domain due to its stringent regulatory and security requirements, implementing customer management, account operations, and transaction processing. The methodology itself is domain-agnostic. The implementation addresses 10 critical CWE vulnerabilities through constitutional constraints with full traceability from principles to code locations. Our case study shows that constitutional constraints reduce security defects by 73% compared to unconstrained AI generation while maintaining developer velocity. We contribute a formal framework for constitutional security, a complete development methodology, and empirical evidence that proactive security specification outperforms reactive security verification in AI-assisted development workflows. --- ### Copula-Based Aggregation and Context-Aware Conformal Prediction for Reliable Renewable Energy Forecasting Authors: Alireza Moradi, Mathieu Tanneau, Reza Zandehshahvar, Pascal Van Hentenryck Published: 2026-01-31 Categories: cs.LG, stat.AP arXiv: https://arxiv.org/abs/2602.02583v1 The rapid growth of renewable energy penetration has intensified the need for reliable probabilistic forecasts to support grid operations at aggregated (fleet or system) levels. In practice, however, system operators often lack access to fleet-level probabilistic models and instead rely on site-level forecasts produced by heterogeneous third-party providers. Constructing coherent and calibrated fleet-level probabilistic forecasts from such inputs remains challenging due to complex cross-site dependencies and aggregation-induced miscalibration. This paper proposes a calibrated probabilistic aggregation framework that directly converts site-level probabilistic forecasts into reliable fleet-level forecasts in settings where system-level models cannot be trained or maintained. The framework integrates copula-based dependence modeling to capture cross-site correlations with Context-Aware Conformal Prediction (CACP) to correct miscalibration at the aggregated level. This combination enables dependence-aware aggregation while providing valid coverage and maintaining sharp prediction intervals. Experiments on large-scale solar generation datasets from MISO, ERCOT, and SPP demonstrate that the proposed Copula+CACP approach consistently achieves near-nominal coverage with significantly sharper intervals than uncalibrated aggregation baselines. --- ### Uncertainty and Fairness Awareness in LLM-Based Recommendation Systems Authors: Chandan Kumar Sah, Xiaoli Lian, Li Zhang, Tony Xu, Syed Shazaib Shah Published: 2026-01-31 Categories: cs.AI, cs.CL, cs.CY, cs.IR, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2602.02582v1 Large language models (LLMs) enable powerful zero-shot recommendations by leveraging broad contextual knowledge, yet predictive uncertainty and embedded biases threaten reliability and fairness. This paper studies how uncertainty and fairness evaluations affect the accuracy, consistency, and trustworthiness of LLM-generated recommendations. We introduce a benchmark of curated metrics and a dataset annotated for eight demographic attributes (31 categorical values) across two domains: movies and music. Through in-depth case studies, we quantify predictive uncertainty (via entropy) and demonstrate that Google DeepMind's Gemini 1.5 Flash exhibits systematic unfairness for certain sensitive attributes; measured similarity-based gaps are SNSR at 0.1363 and SNSV at 0.0507. These disparities persist under prompt perturbations such as typographical errors and multilingual inputs. We further integrate personality-aware fairness into the RecLLM evaluation pipeline to reveal personality-linked bias patterns and expose trade-offs between personalization and group fairness. We propose a novel uncertainty-aware evaluation methodology for RecLLMs, present empirical insights from deep uncertainty case studies, and introduce a personality profile-informed fairness benchmark that advances explainability and equity in LLM recommendations. Together, these contributions establish a foundation for safer, more interpretable RecLLMs and motivate future work on multi-model benchmarks and adaptive calibration for trustworthy deployment. --- ### QuantLRM: Quantization of Large Reasoning Models via Fine-Tuning Signals Authors: Nan Zhang, Eugene Kwek, Yusen Zhang, Muyu Pan, Suhang Wang, Prasenjit Mitra, Rui Zhang Published: 2026-01-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.02581v1 Weight-only quantization is important for compressing Large Language Models (LLMs). Inspired by the spirit of classical magnitude pruning, we study whether the magnitude of weight updates during reasoning-incentivized fine-tuning can provide valuable signals for quantizing Large Reasoning Models (LRMs). We hypothesize that the smallest and largest weight updates during fine-tuning are more important than those of intermediate magnitude, a phenomenon we term "protecting both ends". Upon hypothesis validation, we introduce QuantLRM, which stands for weight quantization of LRMs via fine-tuning signals. We fit simple restricted quadratic functions on weight updates to protect both ends. By multiplying the average quadratic values with the count of zero weight updates of channels, we compute channel importance that is more effective than using activation or second-order information. We run QuantLRM to quantize various fine-tuned models (including supervised, direct preference optimization, and reinforcement learning fine-tuning) over four reasoning benchmarks (AIME-120, FOLIO, temporal sequences, and GPQA-Diamond) and empirically find that QuantLRM delivers a consistent improvement for LRMs quantization, with an average improvement of 6.55% on a reinforcement learning fine-tuned model. Also supporting non-fine-tuned LRMs, QuantLRM gathers effective signals via pseudo-fine-tuning, which greatly enhances its applicability. --- ### ProphetKV: User-Query-Driven Selective Recomputation for Efficient KV Cache Reuse in Retrieval-Augmented Generation Authors: Shihao Wang, Jiahao Chen, Yanqi Pan, Hao Huang, Yichen Hao, Xiangyu Zou, Wen Xia, Wentao Zhang, Chongyang Qiu, Pengfei Wang Published: 2026-01-31 Categories: cs.OS, cs.AI arXiv: https://arxiv.org/abs/2602.02579v3 The prefill stage of long-context Retrieval-Augmented Generation (RAG) is severely bottlenecked by computational overhead. To mitigate this, recent methods assemble pre-calculated KV caches of retrieved RAG documents (by a user query) and reprocess selected tokens to recover cross-attention between these pre-calculated KV caches. However, we identify a fundamental "crowding-out effect" in current token selection criteria: globally salient but user-query-irrelevant tokens saturate the limited recomputation budget, displacing the tokens truly essential for answering the user query and degrading inference accuracy. We propose ProphetKV, a user-query-driven KV Cache reuse method for RAG scenarios. ProphetKV dynamically prioritizes tokens based on their semantic relevance to the user query and employs a dual-stage recomputation pipeline to fuse layer-wise attention metrics into a high-utility set. By ensuring the recomputation budget is dedicated to bridging the informational gap between retrieved context and the user query, ProphetKV achieves high-fidelity attention recovery with minimal overhead. Our extensive evaluation results show that ProphetKV retains 96%-101% of full-prefill accuracy with only a 20% recomputation ratio, while achieving accuracy improvements of 8.8%-24.9% on RULER and 18.6%-50.9% on LongBench over the state-of-the-art approaches (e.g., CacheBlend, EPIC, and KVShare). --- ### Relaxed Triangle Inequality for Kullback-Leibler Divergence Between Multivariate Gaussian Distributions Authors: Shiji Xiao, Yufeng Zhang, Chubo Liu, Yan Ding, Keqin Li, Kenli Li Published: 2026-01-31 Categories: stat.ML, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2602.02577v2 The Kullback-Leibler (KL) divergence is not a proper distance metric and does not satisfy the triangle inequality, posing theoretical challenges in certain practical applications. Existing work has demonstrated that KL divergence between multivariate Gaussian distributions follows a relaxed triangle inequality. Given any three multivariate Gaussian distributions $\mathcal{N}_1, \mathcal{N}_2$, and $\mathcal{N}_3$, if $KL(\mathcal{N}_1, \mathcal{N}_2)\leq ε_1$ and $KL(\mathcal{N}_2, \mathcal{N}_3)\leq ε_2$, then $KL(\mathcal{N}_1, \mathcal{N}_3)< 3ε_1+3ε_2+2\sqrt{ε_1ε_2}+o(ε_1)+o(ε_2)$. However, the supremum of $KL(\mathcal{N}_1, \mathcal{N}_3)$ is still unknown. In this paper, we investigate the relaxed triangle inequality for the KL divergence between multivariate Gaussian distributions and give the supremum of $KL(\mathcal{N}_1, \mathcal{N}_3)$ as well as the conditions when the supremum can be attained. When $ε_1$ and $ε_2$ are small, the supremum is $ε_1+ε_2+2\sqrt{ε_1ε_2}+o(ε_1)+o(ε_2)$. Finally, we demonstrate several applications of our results in out-of-distribution detection with flow-based generative models and safe reinforcement learning. --- ### Product Interaction: An Algebraic Formalism for Deep Learning Architectures Authors: Haonan Dong, Chun-Wun Cheng, Angelica I. Aviles-Rivero Published: 2026-01-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.02573v1 In this paper, we introduce product interactions, an algebraic formalism in which neural network layers are constructed from compositions of a multiplication operator defined over suitable algebras. Product interactions provide a principled way to generate and organize algebraic expressions by increasing interaction order. Our central observation is that algebraic expressions in modern neural networks admit a unified construction in terms of linear, quadratic, and higher-order product interactions. Convolutional and equivariant networks arise as symmetry-constrained linear product interactions, while attention and Mamba correspond to higher-order product interactions. --- ### Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspective Authors: Haichuan Wang, Tao Lin, Lingkai Kong, Ce Li, Hezi Jiang, Milind Tambe Published: 2026-01-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.02572v2 Existing alignment methods directly use the reward model learned from user preference data to optimize an LLM policy, subject to KL regularization with respect to the base policy. This practice is suboptimal for maximizing user's utility because the KL regularization may cause the LLM to inherit the bias in the base policy that conflicts with user preferences. While amplifying rewards for preferred outputs can mitigate this bias, it also increases the risk of reward hacking. This tradeoff motivates the problem of optimally designing reward models under KL regularization. We formalize this reward model optimization problem as a Stackelberg game, and show that a simple reward shaping scheme can effectively approximate the optimal reward model. We empirically evaluate our method in inference-time alignment settings and demonstrate that it integrates seamlessly into existing alignment methods with minimal overhead. Our method consistently improves average reward and achieves win-tie rates exceeding 66% against all baselines, averaged across evaluation settings. --- ### Trajectory Consistency for One-Step Generation on Euler Mean Flows Authors: Zhiqi Li, Yuchen Sun, Duowen Chen, Jinjin He, Bo Zhu Published: 2026-01-31 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.02571v1 We propose \emph{Euler Mean Flows (EMF)}, a flow-based generative framework for one-step and few-step generation that enforces long-range trajectory consistency with minimal sampling cost. The key idea of EMF is to replace the trajectory consistency constraint, which is difficult to supervise and optimize over long time scales, with a principled linear surrogate that enables direct data supervision for long-horizon flow-map compositions. We derive this approximation from the semigroup formulation of flow-based models and show that, under mild regularity assumptions, it faithfully approximates the original consistency objective while being substantially easier to optimize. This formulation leads to a unified, JVP-free training framework that supports both $u$-prediction and $x_1$-prediction variants, avoiding explicit Jacobian computations and significantly reducing memory and computational overhead. Experiments on image synthesis, particle-based geometry generation, and functional generation demonstrate improved optimization stability and sample quality under fixed sampling budgets, together with approximately $50\%$ reductions in training time and memory consumption compared to existing one-step methods for image generation. --- ### DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems Authors: Haoran Ou, Kangjie Chen, Gelei Deng, Hangcheng Liu, Jie Zhang, Tianwei Zhang, Kwok-Yan Lam Published: 2026-01-31 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.02569v2 Fact-checking systems with search-enabled large language models (LLMs) have shown strong potential for verifying claims by dynamically retrieving external evidence. However, the robustness of such systems against adversarial attack remains insufficiently understood. In this work, we study adversarial claim attacks against search-enabled LLM-based fact-checking systems under a realistic input-only threat model. We propose DECEIVE-AFC, an agent-based adversarial attack framework that integrates novel claim-level attack strategies and adversarial claim validity evaluation principles. DECEIVE-AFC systematically explores adversarial attack trajectories that disrupt search behavior, evidence retrieval, and LLM-based reasoning without relying on access to evidence sources or model internals. Extensive evaluations on benchmark datasets and real-world systems demonstrate that our attacks substantially degrade verification performance, reducing accuracy from 78.7% to 53.7%, and significantly outperform existing claim-based attack baselines with strong cross-system transferability. --- ### Mitigating Task-Order Sensitivity and Forgetting via Hierarchical Second-Order Consolidation Authors: Protik Nag, Krishnan Raghavan, Vignesh Narayanan Published: 2026-01-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.02568v1 We introduce $\textbf{Hierarchical Taylor Series-based Continual Learning (HTCL)}$, a framework that couples fast local adaptation with conservative, second-order global consolidation to address the high variance introduced by random task ordering. To address task-order effects, HTCL identifies the best intra-group task sequence and integrates the resulting local updates through a Hessian-regularized Taylor expansion, yielding a consolidation step with theoretical guarantees. The approach naturally extends to an $L$-level hierarchy, enabling multiscale knowledge integration in a manner not supported by conventional single-level CL systems. Across a wide range of datasets and replay and regularization baselines, HTCL acts as a model-agnostic consolidation layer that consistently enhances performance, yielding mean accuracy gains of $7\%$ to $25\%$ while reducing the standard deviation of final accuracy by up to $68\%$ across random task permutations. --- ### IceBench-S2S: A Benchmark of Deep Learning for Challenging Subseasonal-to-Seasonal Daily Arctic Sea Ice Forecasting in Deep Latent Space Authors: Jingyi Xu, Shengnan Wang, Weidong Yang, Siwei Tu, Lei Bai, Ben Fei Published: 2026-01-31 Categories: cs.LG, cs.AI, eess.IV arXiv: https://arxiv.org/abs/2602.02567v1 Arctic sea ice plays a critical role in regulating Earth's climate system, significantly influencing polar ecological stability and human activities in coastal regions. Recent advances in artificial intelligence have facilitated the development of skillful pan-Arctic sea ice forecasting systems, where data-driven approaches showcase tremendous potential to outperform conventional physics-based numerical models in terms of accuracy, computational efficiency and forecasting lead times. Despite the latest progress made by deep learning (DL) forecasting models, most of their skillful forecasting lead times are confined to daily subseasonal scale and monthly averaged values for up to six months, which drastically hinders their deployment for real-world applications, e.g., maritime routine planning for Arctic transportation and scientific investigation. Extending daily forecasts from subseasonal to seasonal (S2S) scale is scientifically crucial for operational applications. To bridge the gap between the forecasting lead time of current DL models and the significant daily S2S scale, we introduce IceBench-S2S, the first comprehensive benchmark for evaluating DL approaches in mitigating the challenge of forecasting Arctic sea ice concentration in successive 180-day periods. It proposes a generalized framework that first compresses spatial features of daily sea ice data into a deep latent space. The temporally concatenated deep features are subsequently modeled by DL-based forecasting backbones to predict the sea ice variation at S2S scale. IceBench-S2S provides a unified training and evaluation pipeline for different backbones, along with practical guidance for model selection in polar environmental monitoring tasks. --- ### Improving Minimax Estimation Rates for Contaminated Mixture of Multinomial Logistic Experts via Expert Heterogeneity Authors: Fanqi Yan, Dung Le, Trang Pham, Huy Nguyen, Nhat Ho Published: 2026-01-31 Categories: math.ST, cs.LG arXiv: https://arxiv.org/abs/2602.00939v1 Contaminated mixture of experts (MoE) is motivated by transfer learning methods where a pre-trained model, acting as a frozen expert, is integrated with an adapter model, functioning as a trainable expert, in order to learn a new task. Despite recent efforts to analyze the convergence behavior of parameter estimation in this model, there are still two unresolved problems in the literature. First, the contaminated MoE model has been studied solely in regression settings, while its theoretical foundation in classification settings remains absent. Second, previous works on MoE models for classification capture pointwise convergence rates for parameter estimation without any guaranty of minimax optimality. In this work, we close these gaps by performing, for the first time, the convergence analysis of a contaminated mixture of multinomial logistic experts with homogeneous and heterogeneous structures, respectively. In each regime, we characterize uniform convergence rates for estimating parameters under challenging settings where ground-truth parameters vary with the sample size. Furthermore, we also establish corresponding minimax lower bounds to ensure that these rates are minimax optimal. Notably, our theories offer an important insight into the design of contaminated MoE, that is, expert heterogeneity yields faster parameter estimation rates and, therefore, is more sample-efficient than expert homogeneity. --- ### CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining Authors: I-Chun Arthur Liu, Krzysztof Choromanski, Sandy Huang, Connor Schenck Published: 2026-01-31 Categories: cs.RO, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.00937v3 Leveraging pre-trained 2D image representations in behavior cloning policies has achieved great success and has become a standard approach for robotic manipulation. However, such representations fail to capture the 3D spatial information about objects and scenes that is essential for precise manipulation. In this work, we introduce Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining (CLAMP), a novel 3D pre-training framework that utilizes point clouds and robot actions. From the merged point cloud computed from RGB-D images and camera extrinsics, we re-render multi-view four-channel image observations with depth and 3D coordinates, including dynamic wrist views, to provide clearer views of target objects for high-precision manipulation tasks. The pre-trained encoders learn to associate the 3D geometric and positional information of objects with robot action patterns via contrastive learning on large-scale simulated robot trajectories. During encoder pre-training, we pre-train a Diffusion Policy to initialize the policy weights for fine-tuning, which is essential for improving fine-tuning sample efficiency and performance. After pre-training, we fine-tune the policy on a limited amount of task demonstrations using the learned image and action representations. We demonstrate that this pre-training and fine-tuning design substantially improves learning efficiency and policy performance on unseen tasks. Furthermore, we show that CLAMP outperforms state-of-the-art baselines across six simulated tasks and five real-world tasks. The project website and videos can be found at https://clamp3d.github.io/CLAMP/. --- ### MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers Authors: Chaithanya Bandi, Razvan-Gabriel Dumitru, Ben Hertzberg, Divyansh Agarwal, Geobio Boo, Tejas Polakam, Sami Hassaan, Jeff Da, HiJae Kim, Vipul Gupta, Manasi Sharma, Andrew Park et al. Published: 2026-01-31 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2602.00933v3 The Model Context Protocol (MCP) is emerging as a standard interface through which large language model (LLM) agents discover and invoke external tools. However, existing MCP evaluations fall short along three key axes: realistic multi-step workflows with cross-server orchestration, breadth across authentic MCP servers rather than mocks, and structured, reproducible claim-level scoring disentangled from agent verbosity or style. We introduce MCP-Atlas, a benchmark for measuring tool-use competency against production MCP servers. MCP-Atlas contains 1,000 natural-language tasks written and verified by human experts spanning 36 real MCP servers and 220 tools. Prompts do not specify servers, tools, or parameters, requiring agents to identify relevant tools among semantically plausible distractors and to compose multi-step, cross-server workflows. Each task is scored with a claim-level rubric, where final answers are scored against atomic factual claims grounded in tool outputs. This answer-centric scoring permits valid alternative tool-call trajectories to receive credit. We pair this with an 11-category diagnostic taxonomy that disentangles tool-call failures from cognitive failures in task understanding, synthesis, parsing, and stopping. Evaluating 20 frontier models from six providers under matched task-level conditions, we find pass rates up to 82.2% at a 0.75 claim coverage threshold and a clear three-tier performance structure. Automated diagnostics show that 63.3% of diagnosed failures are cognitive rather than tool-call related. Notably, several high-performing models fail after successful tool execution due to premature stopping or incorrect synthesis. We release the task schema, containerized harness, claim evaluator, and a 500-task public split, while reserving a 500-task private split to preserve leaderboard integrity. The code is at https://github.com/scaleapi/mcp-atlas. --- ### Continuous-Utility Direct Preference Optimization Authors: Muhammad Ahmed Mohsin, Muhammad Umer, Ahsan Bilal, Zihao He, Muhammad Usman Rafique, Asad Aali, Muhammad Ali Jamshed, John M. Cioffi, Emily Fox Published: 2026-01-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.00931v2 Large language model reasoning is often treated as a monolithic capability, relying on binary preference supervision that fails to capture partial progress or fine-grained reasoning quality. We introduce Continuous Utility Direct Preference Optimization (CU-DPO), a framework that aligns models to a portfolio of prompt-based cognitive strategies by replacing binary labels with continuous scores that capture fine-grained reasoning quality. We prove that learning with K strategies yields a Theta(K log K) improvement in sample complexity over binary preferences, and that DPO converges to the entropy-regularized utility-maximizing policy. To exploit this signal, we propose a two-stage training pipeline: (i) strategy selection, which optimizes the model to choose the best strategy for a given problem via best-vs-all comparisons, and (ii) execution refinement, which trains the model to correctly execute the selected strategy using margin-stratified pairs. On mathematical reasoning benchmarks, CU-DPO improves strategy selection accuracy from 35-46 percent to 68-78 percent across seven base models, yielding consistent downstream reasoning gains of up to 6.6 points on in-distribution datasets with effective transfer to out-of-distribution tasks. --- ### Learning Abstractions for Hierarchical Planning in Program-Synthesis Agents Authors: Zergham Ahmed, Kazuki Irie, Joshua B. Tenenbaum, Christopher J. Bates, Samuel J. Gershman Published: 2026-01-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.00929v1 Humans learn abstractions and use them to plan efficiently to quickly generalize across tasks -- an ability that remains challenging for state-of-the-art large language model (LLM) agents and deep reinforcement learning (RL) systems. Inspired by the cognitive science of how people form abstractions and intuitive theories of their world knowledge, Theory-Based RL (TBRL) systems, such as TheoryCoder, exhibit strong generalization through effective use of abstractions. However, they heavily rely on human-provided abstractions and sidestep the abstraction-learning problem. We introduce TheoryCoder-2, a new TBRL agent that leverages LLMs' in-context learning ability to actively learn reusable abstractions rather than relying on hand-specified ones, by synthesizing abstractions from experience and integrating them into a hierarchical planning process. We conduct experiments on diverse environments, including BabyAI, Minihack and VGDL games like Sokoban. We find that TheoryCoder-2 is significantly more sample-efficient than baseline LLM agents augmented with classical planning domain construction, reasoning-based planning, and prior program-synthesis agents such as WorldCoder. TheoryCoder-2 is able to solve complex tasks that the baselines fail, while only requiring minimal human prompts, unlike prior TBRL systems. --- ### Beyond What Seems Necessary: Hidden Gains from Scaling Training-Time Reasoning Length under Outcome Supervision Authors: Yihao Xue, Allan Zhang, Jianhao Huang, Amit Sahai, Baharan Mirzasoleiman Published: 2026-01-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.00927v1 Training LLMs to think and reason for longer has become a key ingredient in building state-of-the-art models that can solve complex problems previously out of reach. Recent efforts pursue this in different ways, such as RL fine-tuning to elicit long CoT or scaling latent reasoning through architectural recurrence. This makes reasoning length an important scaling knob. In this work, we identify a novel phenomenon (both theoretically and experimentally): under outcome-only supervision, out-of-distribution (OOD) performance can continue improving as training-time reasoning length (e.g., the token budget in RL, or the loop count in looped Transformers) increases, even after in-distribution (ID) performance has saturated. This suggests that robustness may require a larger budget than ID validation alone would indicate. We provide theoretical explanations via two mechanisms: (i) self-iteration can induce a stronger inductive bias in the hypothesis class, reshaping ID-optimal solutions in ways that improve OOD generalization; and (ii) when shortcut solutions that work for ID samples but not for OOD samples persist in the hypothesis class, regularization can reduce the learned solution's reliance on these shortcuts as the number of self-iterations increases. We complement the theory with empirical evidence from two realizations of scaling training-time reasoning length: increasing the number of loops in looped Transformers on a synthetic task, and increasing token budgets during RL fine-tuning of LLMs on mathematical reasoning. --- ### Supervised sparse auto-encoders for interpretable and compositional representations Authors: Ouns El Harzli, Hugo Wallner, Yoonsoo Nam, Haixuan Xavier Tao Published: 2026-01-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.00924v3 Sparse auto-encoders (SAEs) have re-emerged as a prominent method for mechanistic interpretability, yet they face two significant challenges: the non-smoothness of the $L_1$ penalty, which hinders reconstruction and scalability, and a lack of alignment between learned features and human semantics. In this paper, we address these limitations by adapting unconstrained feature models, a mathematical framework from neural collapse theory, and by supervising the task. We supervise (decoder-only) SAEs to reconstruct feature vectors by jointly learning sparse concept embeddings and decoder weights. Validated on Stable Diffusion 3.5, our approach demonstrates compositional generalization, successfully reconstructing images with concept combinations unseen during training, and enabling feature-level intervention for semantic image editing without prompt modification. --- ### On the Convergence of Jacobian-Free Backpropagation for Optimal Control Problems with Implicit Hamiltonians Authors: Eric Gelphman, Deepanshu Verma, Nicole Tianjiao Yang, Stanley Osher, Samy Wu Fung Published: 2026-01-31 Categories: math.OC, cs.LG, math.NA arXiv: https://arxiv.org/abs/2602.00921v2 Optimal feedback control with implicit Hamiltonians poses a fundamental challenge for learning-based value function methods due to the absence of closed-form optimal control laws. Recent work~\cite{gelphman2025end} introduced an implicit deep learning approach using Jacobian-Free Backpropagation (JFB) to address this setting, but only established sample-wise descent guarantees. In this paper, we establish convergence guarantees for JFB in the stochastic minibatch setting, showing that the resulting updates converge to stationary points of the expected optimal control objective. We further demonstrate scalability on substantially higher-dimensional problems, including multi-agent optimal consumption and swarm-based quadrotor and bicycle control. Together, our results provide both theoretical justification and empirical evidence for using JFB in high-dimensional optimal control with implicit Hamiltonians. --- ### Early Classification of Time Series in Non-Stationary Cost Regimes Authors: Aurélien Renault, Alexis Bondu, Antoine Cornuéjols, Vincent Lemaire Published: 2026-01-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.00918v2 Early Classification of Time Series (ECTS) addresses decision-making problems in which predictions must be made as early as possible while maintaining high accuracy. Most existing ECTS methods assume that the time-dependent decision costs governing the learning objective are known, fixed, and correctly specified. In practice, however, these costs are often uncertain and may change over time, leading to mismatches between training-time and deployment-time objectives. In this paper, we study ECTS under two practically relevant forms of cost non-stationarity: drift in the balance between misclassification and decision delay costs, and stochastic realizations of decision costs that deviate from the nominal training-time model. To address these challenges, we revisit representative ECTS approaches and adapt them to an online learning setting. Focusing on separable methods, we update only the triggering model during deployment, while keeping the classifier fixed. We propose several online adaptations and baselines, including bandit-based and RL-based approaches, and conduct controlled experiments on synthetic data to systematically evaluate robustness under cost non-stationarity. Our results demonstrate that online learning can effectively improve the robustness of ECTS methods to cost drift, with RL-based strategies exhibiting strong and stable performance across varying cost regimes. --- ### A Baseline Multimodal Approach to Emotion Recognition in Conversations Authors: Víctor Yeste, Rodrigo Rivas-Arévalo Published: 2026-01-31 Categories: cs.CL, cs.AI, cs.CY, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2602.00914v1 We present a lightweight multimodal baseline for emotion recognition in conversations using the SemEval-2024 Task 3 dataset built from the sitcom Friends. The goal of this report is not to propose a novel state-of-the-art method, but to document an accessible reference implementation that combines (i) a transformer-based text classifier and (ii) a self-supervised speech representation model, with a simple late-fusion ensemble. We report the baseline setup and empirical results obtained under a limited training protocol, highlighting when multimodal fusion improves over unimodal models. This preprint is provided for transparency and to support future, more rigorous comparisons. --- ### Do Schwartz Higher-Order Values Help Sentence-Level Human Value Detection? A Study of Hierarchical Gating and Calibration Authors: Víctor Yeste, Paolo Rosso Published: 2026-01-31 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.00913v3 Human value detection from single sentences is a sparse, imbalanced multi-label task. We study whether Schwartz higher-order (HO) categories help this setting on ValueEval'24 / ValuesML (74K English sentences) under a compute-frugal budget. Rather than proposing a new architecture, we compare direct supervised transformers, hard HO$\rightarrow$values pipelines, Presence$\rightarrow$HO$\rightarrow$values cascades, compact instruction-tuned large language models (LLMs), QLoRA, and low-cost upgrades such as threshold tuning and small ensembles. HO categories are learnable: the easiest bipolar pair, Growth vs. Self-Protection, reaches Macro-$F_1=0.58$. The most reliable gains come from calibration and ensembling: threshold tuning improves Social Focus vs. Personal Focus from $0.41$ to $0.57$ ($+0.16$), transformer soft voting lifts Growth from $0.286$ to $0.303$, and a Transformer+LLM hybrid reaches $0.353$ on Self-Protection. In contrast, hard hierarchical gating does not consistently improve the end task. Compact LLMs also underperform supervised encoders as stand-alone systems, although they sometimes add useful diversity in hybrid ensembles. Under this benchmark, the HO structure is more useful as an inductive bias than as a rigid routing rule. ---