# Research Papers — 2026-02 · bundle page 103 of 210 > Full-text markdown of papers #5101–5150 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-02/page/103 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/102.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/104.md) ### ExStrucTiny: A Benchmark for Schema-Variable Structured Information Extraction from Document Images Authors: Mathieu Sibue, Andres Muñoz Garza, Samuel Mensah, Pranav Shetty, Zhiqiang Ma, Xiaomo Liu, Manuela Veloso Published: 2026-02-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.12203v1 Enterprise documents, such as forms and reports, embed critical information for downstream applications like data archiving, automated workflows, and analytics. Although generalist Vision Language Models (VLMs) perform well on established document understanding benchmarks, their ability to conduct holistic, fine-grained structured extraction across diverse document types and flexible schemas is not well studied. Existing Key Entity Extraction (KEE), Relation Extraction (RE), and Visual Question Answering (VQA) datasets are limited by narrow entity ontologies, simple queries, or homogeneous document types, often overlooking the need for adaptable and structured extraction. To address these gaps, we introduce ExStrucTiny, a new benchmark dataset for structured Information Extraction (IE) from document images, unifying aspects of KEE, RE, and VQA. Built through a novel pipeline combining manual and synthetic human-validated samples, ExStrucTiny covers more varied document types and extraction scenarios. We analyze open and closed VLMs on this benchmark, highlighting challenges such as schema adaptation, query under-specification, and answer localization. We hope our work provides a bedrock for improving generalist models for structured IE in documents. --- ### Visual Reasoning Benchmark: Evaluating Multimodal LLMs on Classroom-Authentic Visual Problems from Primary Education Authors: Mohamed Huti, Alasdair Mackintosh, Amy Waldock, Dominic Andrews, Maxime Lelièvre, Moritz Boos, Tobias Murray, Paul Atherton, Robin A. A. Ince, Oliver G. B. Garrod Published: 2026-02-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.12196v1 AI models have achieved state-of-the-art results in textual reasoning; however, their ability to reason over spatial and relational structures remains a critical bottleneck -- particularly in early-grade maths, which relies heavily on visuals. This paper introduces the visual reasoning benchmark (VRB), a novel dataset designed to evaluate Multimodal Large Language Models (MLLMs) on their ability to solve authentic visual problems from classrooms. This benchmark is built on a set of 701 questions sourced from primary school examinations in Zambia and India, which cover a range of tasks such as reasoning by analogy, pattern completion, and spatial matching. We outline the methodology and development of the benchmark which intentionally uses unedited, minimal-text images to test if models can meet realistic needs of primary education. Our findings reveal a ``jagged frontier'' of capability where models demonstrate better proficiency in static skills such as counting and scaling, but reach a distinct ``spatial ceiling'' when faced with dynamic operations like folding, reflection, and rotation. These weaknesses pose a risk for classroom use on visual reasoning problems, with the potential for incorrect marking, false scaffolding, and reinforcing student misconceptions. Consequently, education-focused benchmarks like the VRB are essential for determining the functional boundaries of multimodal tools used in classrooms. --- ### Query-focused and Memory-aware Reranker for Long Context Processing Authors: Yuqing Li, Jiangnan Li, Mo Yu, Guoxuan Ding, Yanyu Chen, Zheng Lin, Wei Zhang, Jie Zhou Published: 2026-02-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.12192v3 Built upon the existing analysis of retrieval heads in large language models, we propose an alternative reranking framework that trains models to estimate passage-query relevance using the attention scores of selected heads. This approach provides a listwise solution that leverages the holistic information within the entire candidate shortlist during ranking. At the same time, it naturally produces continuous relevance scores, enabling training on arbitrary retrieval datasets without requiring Likert-scale supervision. Our framework is lightweight and effective, requiring only small-scale models, such as 3B parameters, to achieve strong performance. Extensive experiments demonstrate that our method outperforms existing state-of-the-art pointwise and listwise rerankers across multiple domains, including Wikipedia and long narrative datasets. It further establishes a new state-of-the-art on the LoCoMo benchmark, which assesses dialogue understanding and memory usage. We further demonstrate that our framework supports flexible extensions. For example, augmenting candidate passages with contextual information further improves ranking accuracy, while training attention heads from middle layers enhances efficiency without sacrificing performance. --- ### WaveFormer: Wavelet Embedding Transformer for Biomedical Signals Authors: Habib Irani, Bikram De, Vangelis Metsis Published: 2026-02-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.12189v1 Biomedical signal classification presents unique challenges due to long sequences, complex temporal dynamics, and multi-scale frequency patterns that are poorly captured by standard transformer architectures. We propose WaveFormer, a transformer architecture that integrates wavelet decomposition at two critical stages: embedding construction, where multi-channel Discrete Wavelet Transform (DWT) extracts frequency features to create tokens containing both time-domain and frequency-domain information, and positional encoding, where Dynamic Wavelet Positional Encoding (DyWPE) adapts position embeddings to signal-specific temporal structure through mono-channel DWT analysis. We evaluate WaveFormer on eight diverse datasets spanning human activity recognition and brain signal analysis, with sequence lengths ranging from 50 to 3000 timesteps and channel counts from 1 to 144. Experimental results demonstrate that WaveFormer achieves competitive performance through comprehensive frequency-aware processing. Our approach provides a principled framework for incorporating frequency-domain knowledge into transformer-based time series classification. --- ### SAGEO Arena: A Realistic Environment for Evaluating Search-Augmented Generative Engine Optimization Authors: Sunghwan Kim, Wooseok Jeong, Serin Kim, Sangam Lee, Dongha Lee Published: 2026-02-12 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2602.12187v2 Search-Augmented Generative Engines (SAGE) have emerged as a new paradigm for information access, bridging web-scale retrieval with generative capabilities to deliver synthesized answers. This shift has fundamentally reshaped how web content gains exposure online, giving rise to Search-Augmented Generative Engine Optimization (SAGEO), the practice of optimizing web documents to improve their visibility in AI-generated responses. Despite growing interest, no evaluation environment currently supports comprehensive investigation of SAGEO. Specifically, existing benchmarks lack end-to-end visibility evaluation of optimization strategies, operating on pre-determined candidate documents that abstract away retrieval and reranking preceding generation. Moreover, existing benchmarks discard structural information (e.g., schema markup) present in real web documents, overlooking the rich signals that search systems actively leverage in practice. Motivated by these gaps, we introduce SAGEO Arena, a realistic and reproducible environment for stage-level SAGEO analysis. Our objective is to jointly target search-oriented optimization (SEO) and generation-centric optimization (GEO). To achieve this, we integrate a full generative search pipeline over a large-scale corpus of web documents with rich structural information. Our findings reveal that existing approaches remain largely impractical under realistic conditions and often degrade performance in retrieval and reranking. We also find that structural information helps mitigate these limitations, and that effective SAGEO requires tailoring optimization to each pipeline stage. Overall, our benchmark paves the way for realistic SAGEO evaluation and optimization beyond simplified settings. --- ### SAGEO Arena: A Realistic Environment for Evaluating Search-Augmented Generative Engine Optimization Authors: Sunghwan Kim, Wooseok Jeong, Serin Kim, Sangam Lee, Dongha Lee Published: 2026-02-12 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2602.12187v1 Search-Augmented Generative Engines (SAGE) have emerged as a new paradigm for information access, bridging web-scale retrieval with generative capabilities to deliver synthesized answers. This shift has fundamentally reshaped how web content gains exposure online, giving rise to Search-Augmented Generative Engine Optimization (SAGEO), the practice of optimizing web documents to improve their visibility in AI-generated responses. Despite growing interest, no evaluation environment currently supports comprehensive investigation of SAGEO. Specifically, existing benchmarks lack end-to-end visibility evaluation of optimization strategies, operating on pre-determined candidate documents that abstract away retrieval and reranking preceding generation. Moreover, existing benchmarks discard structural information (e.g., schema markup) present in real web documents, overlooking the rich signals that search systems actively leverage in practice. Motivated by these gaps, we introduce SAGEO Arena, a realistic and reproducible environment for stage-level SAGEO analysis. Our objective is to jointly target search-oriented optimization (SEO) and generation-centric optimization (GEO). To achieve this, we integrate a full generative search pipeline over a large-scale corpus of web documents with rich structural information. Our findings reveal that existing approaches remain largely impractical under realistic conditions and often degrade performance in retrieval and reranking. We also find that structural information helps mitigate these limitations, and that effective SAGEO requires tailoring optimization to each pipeline stage. Overall, our benchmark paves the way for realistic SAGEO evaluation and optimization beyond simplified settings. --- ### Convex Markov Games and Beyond: New Proof of Existence, Characterization and Learning Algorithms for Nash Equilibria Authors: Anas Barakat, Ioannis Panageas, Antonios Varvitsiotis Published: 2026-02-12 Categories: cs.GT, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2602.12181v1 Convex Markov Games (cMGs) were recently introduced as a broad class of multi-agent learning problems that generalize Markov games to settings where strategic agents optimize general utilities beyond additive rewards. While cMGs expand the modeling frontier, their theoretical foundations, particularly the structure of Nash equilibria (NE) and guarantees for learning algorithms, are not yet well understood. In this work, we address these gaps for an extension of cMGs, which we term General Utility Markov Games (GUMGs), capturing new applications requiring coupling between agents' occupancy measures. We prove that in GUMGs, Nash equilibria coincide with the fixed points of projected pseudo-gradient dynamics (i.e., first-order stationary points), enabled by a novel agent-wise gradient domination property. This insight also yields a simple proof of NE existence using Brouwer's fixed-point theorem. We further show the existence of Markov perfect equilibria. Building on this characterization, we establish a policy gradient theorem for GUMGs and design a model-free policy gradient algorithm. For potential GUMGs, we establish iteration complexity guarantees for computing approximate-NE under exact gradients and provide sample complexity bounds in both the generative model and on-policy settings. Our results extend beyond prior work restricted to zero-sum cMGs, providing the first theoretical analysis of common-interest cMGs. --- ### How Sampling Shapes LLM Alignment: From One-Shot Optima to Iterative Dynamics Authors: Yurong Chen, Yu He, Michael I. Jordan, Fan Yao Published: 2026-02-12 Categories: cs.LG, cs.GT arXiv: https://arxiv.org/abs/2602.12180v1 Standard methods for aligning large language models with human preferences learn from pairwise comparisons among sampled candidate responses and regularize toward a reference policy. Despite their effectiveness, the effects of sampling and reference choices are poorly understood theoretically. We investigate these effects through Identity Preference Optimization, a widely used preference alignment framework, and show that proper instance-dependent sampling can yield stronger ranking guarantees, while skewed on-policy sampling can induce excessive concentration under structured preferences. We then analyze iterative alignment dynamics in which the learned policy feeds back into future sampling and reference policies, reflecting a common practice of model-generated preference data. We prove that these dynamics can exhibit persistent oscillations or entropy collapse for certain parameter choices, and characterize regimes that guarantee stability. Our theoretical insights extend to Direct Preference Optimization, indicating the phenomena we captured are common to a broader class of preference-alignment methods. Experiments on real-world preference data validate our findings. --- ### EO-VAE: Towards A Multi-sensor Tokenizer for Earth Observation Data Authors: Nils Lehmann, Yi Wang, Zhitong Xiong, Xiaoxiang Zhu Published: 2026-02-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.12177v2 State-of-the-art generative image and video models rely heavily on tokenizers that compress high-dimensional inputs into more efficient latent representations. While this paradigm has revolutionized RGB generation, Earth observation (EO) data presents unique challenges due to diverse sensor specifications and variable spectral channels. We propose EO-VAE, a multi-sensor variational autoencoder designed to serve as a foundational tokenizer for the EO domain. Unlike prior approaches that train separate tokenizers for each modality, EO-VAE utilizes a single model to encode and reconstruct flexible channel combinations via dynamic hypernetworks. Our experiments on the TerraMesh dataset demonstrate that EO-VAE achieves superior reconstruction fidelity compared to the TerraMind tokenizers, establishing a robust baseline for latent generative modeling in remote sensing. --- ### SAM3-LiteText: An Anatomical Study of the SAM3 Text Encoder for Efficient Vision-Language Segmentation Authors: Chengxi Zeng, Yuxuan Jiang, Ge Gao, Shuai Wang, Duolikun Danier, Bin Zhu, Stevan Rudinac, David Bull, Fan Zhang Published: 2026-02-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.12173v1 Vision-language segmentation models such as SAM3 enable flexible, prompt-driven visual grounding, but inherit large, general-purpose text encoders originally designed for open-ended language understanding. In practice, segmentation prompts are short, structured, and semantically constrained, leading to substantial over-provisioning in text encoder capacity and persistent computational and memory overhead. In this paper, we perform a large-scale anatomical analysis of text prompting in vision-language segmentation, covering 404,796 real prompts across multiple benchmarks. Our analysis reveals severe redundancy: most context windows are underutilized, vocabulary usage is highly sparse, and text embeddings lie on low-dimensional manifold despite high-dimensional representations. Motivated by these findings, we propose SAM3-LiteText, a lightweight text encoding framework that replaces the original SAM3 text encoder with a compact MobileCLIP student that is optimized by knowledge distillation. Extensive experiments on image and video segmentation benchmarks show that SAM3-LiteText reduces text encoder parameters by up to 88%, substantially reducing static memory footprint, while maintaining segmentation performance comparable to the original model. Code: https://github.com/SimonZeng7108/efficientsam3/tree/sam3_litetext. --- ### Pedagogically-Inspired Data Synthesis for Language Model Knowledge Distillation Authors: Bowei He, Yankai Chen, Xiaokun Zhang, Linghe Kong, Philip S. Yu, Xue Liu, Chen Ma Published: 2026-02-12 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.12172v1 Knowledge distillation from Large Language Models (LLMs) to smaller models has emerged as a critical technique for deploying efficient AI systems. However, current methods for distillation via synthetic data lack pedagogical awareness, treating knowledge transfer as a one-off data synthesis and training task rather than a systematic learning process. In this paper, we propose a novel pedagogically-inspired framework for LLM knowledge distillation that draws from fundamental educational principles. Our approach introduces a three-stage pipeline -- Knowledge Identifier, Organizer, and Adapter (IOA) -- that systematically identifies knowledge deficiencies in student models, organizes knowledge delivery through progressive curricula, and adapts representations to match the cognitive capacity of student models. We integrate Bloom's Mastery Learning Principles and Vygotsky's Zone of Proximal Development to create a dynamic distillation process where student models approach teacher model's performance on prerequisite knowledge before advancing, and new knowledge is introduced with controlled, gradual difficulty increments. Extensive experiments using LLaMA-3.1/3.2 and Qwen2.5 as student models demonstrate that IOA achieves significant improvements over baseline distillation methods, with student models retaining 94.7% of teacher performance on DollyEval while using less than 1/10th of the parameters. Our framework particularly excels in complex reasoning tasks, showing 19.2% improvement on MATH and 22.3% on HumanEval compared with state-of-the-art baselines. --- ### Statistical Parsing for Logical Information Retrieval Authors: Greg Coppola Published: 2026-02-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.12170v1 In previous work (Coppola, 2024) we introduced the Quantified Boolean Bayesian Network (QBBN), a logical graphical model that implements the forward fragment of natural deduction (Prawitz, 1965) as a probabilistic factor graph. That work left two gaps: no negation/backward reasoning, and no parser for natural language. This paper addresses both gaps across inference, semantics, and syntax. For inference, we extend the QBBN with NEG factors enforcing P(x) + P(neg x) = 1, enabling contrapositive reasoning (modus tollens) via backward lambda messages, completing Prawitz's simple elimination rules. The engine handles 44/44 test cases spanning 22 reasoning patterns. For semantics, we present a typed logical language with role-labeled predicates, modal quantifiers, and three tiers of expressiveness following Prawitz: first-order quantification, propositions as arguments, and predicate quantification via lambda abstraction. For syntax, we present a typed slot grammar that deterministically compiles sentences to logical form (33/33 correct, zero ambiguity). LLMs handle disambiguation (95% PP attachment accuracy) but cannot produce structured parses directly (12.4% UAS), confirming grammars are necessary. The architecture: LLM preprocesses, grammar parses, LLM reranks, QBBN infers. We argue this reconciles formal semantics with Sutton's "bitter lesson" (2019): LLMs eliminate the annotation bottleneck that killed formal NLP, serving as annotator while the QBBN serves as verifier. Code: https://github.com/gregorycoppola/world --- ### Sci-CoE: Co-evolving Scientific Reasoning LLMs via Geometric Consensus with Sparse Supervision Authors: Xiaohan He, Shiyang Feng, Songtao Huang, Lei Bai, Bin Wang, Bo Zhang Published: 2026-02-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.12164v1 Large language models (LLMs) have demonstrated exceptional reasoning capabilities, and co-evolving paradigms have shown promising results in domains such as code and math. However, in scientific reasoning tasks, these models remain fragile due to unreliable solution evaluation and limited diversity in verification strategies. In this work, we propose Sci-CoE, a two-stage scientific co-evolving framework that enables models to self-evolve as both solver and verifier through a transition from sparse supervision to unsupervised learning. In the first stage, the model uses a small set of annotated data to establish fundamental correctness judgment anchors for the Verifier. In the second stage, we introduce a geometric reward mechanism that jointly considers consensus, reliability, and diversity, driving large-scale self-iteration on unlabeled data. Experiments on several general scientific benchmarks demonstrate that Sci-CoE enhances complex reasoning capabilities and exhibits strong scalability, facilitating the construction of more robust and diverse evaluation systems. Codes are available at https://github.com/InternScience/Sci-CoE. --- ### Amortized Molecular Optimization via Group Relative Policy Optimization Authors: Muhammad bin Javaid, Hasham Hussain, Ashima Khanna, Berke Kisin, Jonathan Pirnay, Alexander Mitsos, Dominik G. Grimm, Martin Grohe Published: 2026-02-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.12162v3 In structurally constrained molecular optimization, state-of-the-art methods restart an expensive oracle-driven search from scratch for every new input structure, scaling poorly to settings with many starting structures or expensive oracles. While amortized approaches that learn a transferable policy could in principle remove this bottleneck, existing methods struggle to generalize to diverse structural constraints at inference time. We present AMORTIX, an amortized Graph Transformer model that natively supports such constraints, optimizing molecular structures in a single forward pass with zero inference-time oracle calls. A central challenge for amortized training in this domain is that optimization difficulty varies drastically across starting structures. We show that, under this heterogeneity, standard reinforcement learning methods fail to stabilize training, and address this by normalizing rewards within groups of completions sharing the same starting structure. We evaluate on structurally constrained single- and multi-target kinase inhibitor design, and on a few-shot prodrug case study. AMORTIX outperforms both amortized and instance-optimization baselines on goal-directed scaffold decoration and ranks first among amortized methods on the PMO benchmark; the prodrug case study further demonstrates transfer of a learned modification rule to unseen drug structures. Code is available at https://github.com/Hash-hh/AMORTIX/. --- ### DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation Authors: Xu Guo, Fulong Ye, Qichao Sun, Liyang Chen, Bingchuan Li, Pengze Zhang, Jiawei Liu, Songtao Zhao, Qian He, Xiangwang Hou Published: 2026-02-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.12160v1 Recent advancements in foundation models have revolutionized joint audio-video generation. However, existing approaches typically treat human-centric tasks including reference-based audio-video generation (R2AV), video editing (RV2AV) and audio-driven video animation (RA2V) as isolated objectives. Furthermore, achieving precise, disentangled control over multiple character identities and voice timbres within a single framework remains an open challenge. In this paper, we propose DreamID-Omni, a unified framework for controllable human-centric audio-video generation. Specifically, we design a Symmetric Conditional Diffusion Transformer that integrates heterogeneous conditioning signals via a symmetric conditional injection scheme. To resolve the pervasive identity-timbre binding failures and speaker confusion in multi-person scenarios, we introduce a Dual-Level Disentanglement strategy: Synchronized RoPE at the signal level to ensure rigid attention-space binding, and Structured Captions at the semantic level to establish explicit attribute-subject mappings. Furthermore, we devise a Multi-Task Progressive Training scheme that leverages weakly-constrained generative priors to regularize strongly-constrained tasks, preventing overfitting and harmonizing disparate objectives. Extensive experiments demonstrate that DreamID-Omni achieves comprehensive state-of-the-art performance across video, audio, and audio-visual consistency, even outperforming leading proprietary commercial models. We will release our code to bridge the gap between academic research and commercial-grade applications. --- ### 3DGSNav: Enhancing Vision-Language Model Reasoning for Object Navigation via Active 3D Gaussian Splatting Authors: Wancai Zheng, Hao Chen, Xianlong Lu, Linlin Ou, Xinyi Yu Published: 2026-02-12 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2602.12159v1 Object navigation is a core capability of embodied intelligence, enabling an agent to locate target objects in unknown environments. Recent advances in vision-language models (VLMs) have facilitated zero-shot object navigation (ZSON). However, existing methods often rely on scene abstractions that convert environments into semantic maps or textual representations, causing high-level decision making to be constrained by the accuracy of low-level perception. In this work, we present 3DGSNav, a novel ZSON framework that embeds 3D Gaussian Splatting (3DGS) as persistent memory for VLMs to enhance spatial reasoning. Through active perception, 3DGSNav incrementally constructs a 3DGS representation of the environment, enabling trajectory-guided free-viewpoint rendering of frontier-aware first-person views. Moreover, we design structured visual prompts and integrate them with Chain-of-Thought (CoT) prompting to further improve VLM reasoning. During navigation, a real-time object detector filters potential targets, while VLM-driven active viewpoint switching performs target re-verification, ensuring efficient and reliable recognition. Extensive evaluations across multiple benchmarks and real-world experiments on a quadruped robot demonstrate that our method achieves robust and competitive performance against state-of-the-art approaches.The Project Page:https://aczheng-cai.github.io/3dgsnav.github.io/ --- ### SafeNeuron: Neuron-Level Safety Alignment for Large Language Models Authors: Zhaoxin Wang, Jiaming Liang, Fengbin Zhu, Weixiang Zhao, Junfeng Fang, Jiayi Ji, Handing Wang, Tat-Seng Chua Published: 2026-02-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.12158v1 Large language models (LLMs) and multimodal LLMs are typically safety-aligned before release to prevent harmful content generation. However, recent studies show that safety behaviors are concentrated in a small subset of parameters, making alignment brittle and easily bypassed through neuron-level attacks. Moreover, most existing alignment methods operate at the behavioral level, offering limited control over the model's internal safety mechanisms. In this work, we propose SafeNeuron, a neuron-level safety alignment framework that improves robustness by redistributing safety representations across the network. SafeNeuron first identifies safety-related neurons, then freezes these neurons during preference optimization to prevent reliance on sparse safety pathways and force the model to construct redundant safety representations. Extensive experiments across models and modalities demonstrate that SafeNeuron significantly improves robustness against neuron pruning attacks, reduces the risk of open-source models being repurposed as red-team generators, and preserves general capabilities. Furthermore, our layer-wise analysis reveals that safety behaviors are governed by stable and shared internal representations. Overall, SafeNeuron provides an interpretable and robust perspective for model alignment. --- ### TexSpot: 3D Texture Enhancement with Spatially-uniform Point Latent Representation Authors: Ziteng Lu, Yushuang Wu, Chongjie Ye, Yuda Qiu, Jing Shao, Xiaoyang Guo, Jiaqing Zhou, Tianlei Hu, Kun Zhou, Xiaoguang Han Published: 2026-02-12 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2602.12157v2 High-quality 3D texture generation remains a fundamental challenge due to the view-inconsistency inherent in current mainstream multi-view diffusion pipelines. Existing representations either rely on UV maps, which suffer from distortion during unwrapping, or point-based methods, which tightly couple texture fidelity to geometric density that limits high-resolution texture generation. To address these limitations, we introduce TexSpot, a diffusion-based texture enhancement framework. At its core is Texlet, a novel 3D texture representation that merges the geometric expressiveness of point-based 3D textures with the compactness of UV-based representation. Each Texlet latent vector encodes a local texture patch via a 2D encoder and is further aggregated using a 3D encoder to incorporate global shape context. A cascaded 3D-to-2D decoder reconstructs high-quality texture patches, enabling the Texlet space learning. Leveraging this representation, we train a diffusion transformer conditioned on Texlets to refine and enhance textures produced by multi-view diffusion methods. Extensive experiments demonstrate that TexSpot significantly improves visual fidelity, geometric consistency, and robustness over existing state-of-the-art 3D texture generation and enhancement approaches. Project page: https://texlet-arch.github.io/TexSpot-page. --- ### FAIL: Flow Matching Adversarial Imitation Learning for Image Generation Authors: Yeyao Ma, Chen Li, Xiaosong Zhang, Han Hu, Weidi Xie Published: 2026-02-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.12155v2 Post-training of flow matching models-aligning the output distribution with a high-quality target-is mathematically equivalent to imitation learning. While Supervised Fine-Tuning mimics expert demonstrations effectively, it cannot correct policy drift in unseen states. Preference optimization methods address this but require costly preference pairs or reward modeling. We propose Flow Matching Adversarial Imitation Learning (FAIL), which minimizes policy-expert divergence through adversarial training without explicit rewards or pairwise comparisons. We derive two algorithms: FAIL-PD exploits differentiable ODE solvers for low-variance pathwise gradients, while FAIL-PG provides a black-box alternative for discrete or computationally constrained settings. Fine-tuning FLUX with only 13,000 demonstrations from Nano Banana pro, FAIL achieves competitive performance on prompt following and aesthetic benchmarks. Furthermore, the framework generalizes effectively to discrete image and video generation, and functions as a robust regularizer to mitigate reward hacking in reward-based optimization. Code and data are available at https://github.com/HansPolo113/FAIL. --- ### dVoting: Fast Voting for dLLMs Authors: Sicheng Feng, Zigeng Chen, Xinyin Ma, Gongfan Fang, Xinchao Wang Published: 2026-02-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.12153v1 Diffusion Large Language Models (dLLMs) represent a new paradigm beyond autoregressive modeling, offering competitive performance while naturally enabling a flexible decoding process. Specifically, dLLMs can generate tokens at arbitrary positions in parallel, endowing them with significant potential for parallel test-time scaling, which was previously constrained by severe inefficiency in autoregressive modeling. In this work, we introduce dVoting, a fast voting technique that boosts reasoning capability without training, with only an acceptable extra computational overhead. dVoting is motivated by the observation that, across multiple samples for the same prompt, token predictions remain largely consistent, whereas performance is determined by a small subset of tokens exhibiting cross-sample variability. Leveraging the arbitrary-position generation capability of dLLMs, dVoting performs iterative refinement by sampling, identifying uncertain tokens via consistency analysis, regenerating them through voting, and repeating this process until convergence. Extensive evaluations demonstrate that dVoting consistently improves performance across various benchmarks. It achieves gains of 6.22%-7.66% on GSM8K, 4.40%-7.20% on MATH500, 3.16%-14.84% on ARC-C, and 4.83%-5.74% on MMLU. Our code is available at https://github.com/fscdc/dVoting --- ### GPT-4o Lacks Core Features of Theory of Mind Authors: John Muchovej, Amanda Royka, Shane Lee, Julian Jara-Ettinger Published: 2026-02-12 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.12150v3 Do Large Language Models (LLMs) possess a Theory of Mind (ToM)? Research into this question has focused on evaluating LLMs against benchmarks and found success across a range of social tasks. However, these evaluations do not test for the actual representations posited by ToM: namely, a causal model of mental states and behavior. Here, we use a cognitively-grounded definition of ToM to develop and test a new evaluation framework. Specifically, our approach probes whether LLMs have a coherent, domain-general, and consistent model of how mental states cause behavior -- regardless of whether that model matches a human-like ToM. We find that even though LLMs succeed in approximating human judgments in a simple ToM paradigm, they fail at a logically equivalent task and exhibit low consistency between their action predictions and corresponding mental state inferences. As such, these findings suggest that the social proficiency exhibited by LLMs is not the result of a domain-general or consistent ToM. --- ### It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks Authors: Zhongzheng Qiao, Sheng Pan, Anni Wang, Viktoriya Zhukova, Yong Liu, Xudong Jiang, Qingsong Wen, Mingsheng Long, Ming Jin, Chenghao Liu Published: 2026-02-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.12147v4 Time series foundation models (TSFMs) are revolutionizing the forecasting landscape from specific dataset modeling to generalizable task evaluation. However, we contend that existing benchmarks exhibit common limitations in four dimensions: constrained data composition dominated by reused legacy sources, compromised data integrity lacking rigorous quality assurance, misaligned task formulations detached from real-world contexts, and rigid analysis perspectives that obscure generalizable insights. To bridge these gaps, we introduce TIME, a next-generation task-centric benchmark comprising 50 fresh datasets and 98 forecasting tasks, tailored for strict zero-shot TSFM evaluation free from data leakage. Integrating large language models and human expertise, we establish a human-in-the-loop benchmark construction pipeline to ensure high data integrity and redefine task formulation by aligning forecasting configurations with real-world operational requirements and variate predictability. Furthermore, we propose a novel pattern-level evaluation perspective that moves beyond traditional dataset-level evaluations based on static meta labels. By leveraging structural time series features to characterize intrinsic temporal properties, this approach offers generalizable insights into model capabilities across diverse patterns. We evaluate 12 TSFMs and establish a multi-granular leaderboard to facilitate in-depth analysis and visualized inspection. The leaderboard is available at https://huggingface.co/spaces/Real-TSF/TIME-leaderboard. --- ### Seq2Seq2Seq: Lossless Data Compression via Discrete Latent Transformers and Reinforcement Learning Authors: Mahdi Khodabandeh, Ghazal Shabani, Arash Yousefi Jordehi, Seyed Abolghasem Mirroshandel Published: 2026-02-12 Categories: cs.AI, cs.CL, cs.IT arXiv: https://arxiv.org/abs/2602.12146v1 Efficient lossless compression is essential for minimizing storage costs and transmission overhead while preserving data integrity. Traditional compression techniques, such as dictionary-based and statistical methods, often struggle to optimally exploit the structure and redundancy in complex data formats. Recent advancements in deep learning have opened new avenues for compression; however, many existing approaches depend on dense vector representations that obscure the underlying token structure. To address these limitations, we propose a novel lossless compression method that leverages Reinforcement Learning applied to a T5 language model architecture. This approach enables the compression of data into sequences of tokens rather than traditional vector representations. Unlike auto-encoders, which typically encode information into continuous latent spaces, our method preserves the token-based structure, aligning more closely with the original data format. This preservation allows for higher compression ratios while maintaining semantic integrity. By training the model using an off-policy Reinforcement Learning algorithm, we optimize sequence length to minimize redundancy and enhance compression efficiency. Our method introduces an efficient and adaptive data compression system built upon advanced Reinforcement Learning techniques, functioning independently of external grammatical or world knowledge. This approach shows significant improvements in compression ratios compared to conventional methods. By leveraging the latent information within language models, our system effectively compresses data without requiring explicit content understanding, paving the way for more robust and practical compression solutions across various applications. --- ### On the Adoption of AI Coding Agents in Open-source Android and iOS Development Authors: Muhammad Ahmad Khan, Hasnain Ali, Muneeb Rana, Muhammad Saqib Ilyas, Abdul Ali Bangash Published: 2026-02-12 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2602.12144v1 AI coding agents are increasingly contributing to software development, yet their impact on mobile development has received little empirical attention. In this paper, we present the first category-level empirical study of agent-generated code in open-source mobile app projects. We analyzed PR acceptance behaviors across mobile platforms, agents, and task categories using 2,901 AI-authored pull requests (PRs) in 193 verified Android and iOS open-source GitHub repositories in the AIDev dataset. We find that Android projects have received 2x more AI-authored PRs and have achieved higher PR acceptance rate (71%) than iOS (63%), with significant agent-level variation on Android. Across task categories, PRs with routine tasks (feature, fix, and ui) achieve the highest acceptance, while structural changes like refactor and build achieve lower success and longer resolution times. Furthermore, our evolution analysis shows improvement in PR resolution time on Android through mid-2025 before it declined again. Our findings offer the first evidence-based characterization of AI agents effects on OSS mobile projects and establish empirical baselines for evaluating agent-generated contributions to design platform aware agentic systems. --- ### STAR : Bridging Statistical and Agentic Reasoning for Large Model Performance Prediction Authors: Xiaoxiao Wang, Chunxiao Li, Junying Wang, Yijin Guo, Zijian Chen, Chunyi Li, Xiaohong Liu, Zicheng Zhang, Guangtao Zhai Published: 2026-02-12 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.12143v1 As comprehensive large model evaluation becomes prohibitively expensive, predicting model performance from limited observations has become essential. However, existing statistical methods struggle with pattern shifts, data sparsity, and lack of explanation, while pure LLM methods remain unreliable. We propose STAR, a framework that bridges data-driven STatistical expectations with knowledge-driven Agentic Reasoning. STAR leverages specialized retrievers to gather external knowledge and embeds semantic features into Constrained Probabilistic Matrix Factorization (CPMF) to generate statistical expectations with uncertainty. A reasoning module guided by Expectation Violation Theory (EVT) then refines predictions through intra-family analysis, cross-model comparison, and credibility-aware aggregation, producing adjustments with traceable explanations. Extensive experiments show that STAR consistently outperforms all baselines on both score-based and rank-based metrics, delivering a 14.46% gain in total score over the strongest statistical method under extreme sparsity, with only 1--2 observed scores per test model. --- ### Oscillators Are All You Need: Irregular Time Series Modelling via Damped Harmonic Oscillators with Closed-Form Solutions Authors: Yashas Shende, Aritra Das, Reva Laxmi Chauhan, Arghya Pathak, Debayan Gupta Published: 2026-02-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.12139v2 Transformers excel at time series modelling through attention mechanisms that capture long-term temporal patterns. However, they assume uniform time intervals and therefore struggle with irregular time series. Neural Ordinary Differential Equations (NODEs) effectively handle irregular time series by modelling hidden states as continuously evolving trajectories. ContiFormers arxiv:2402.10635 combine NODEs with Transformers, but inherit the computational bottleneck of the former by using heavy numerical solvers. This bottleneck can be removed by using a closed-form solution for the given dynamical system - but this is known to be intractable in general! We obviate this by replacing NODEs with a novel linear damped harmonic oscillator analogy - which has a known closed-form solution. We model keys and values as damped, driven oscillators and expand the query in a sinusoidal basis up to a suitable number of modes. This analogy naturally captures the query-key coupling that is fundamental to any transformer architecture by modelling attention as a resonance phenomenon. Our closed-form solution eliminates the computational overhead of numerical ODE solvers while preserving expressivity. We prove that this oscillator-based parameterisation maintains the universal approximation property of continuous-time attention; specifically, any discrete attention matrix realisable by ContiFormer's continuous keys can be approximated arbitrarily well by our fixed oscillator modes. Our approach delivers both theoretical guarantees and scalability, achieving state-of-the-art performance on irregular time series benchmarks while being orders of magnitude faster. Acknowledgement: This work was done in collaboration with Dirac Labs. --- ### CitiLink-Minutes: A Multilayer Annotated Dataset of Municipal Meeting Minutes Authors: Ricardo Campos, Ana Filipa Pacheco, Ana Luísa Fernandes, Inês Cantante, Rute Rebouças, Luís Filipe Cunha, José Miguel Isidro, José Pedro Evans, Miguel Marques, Rodrigo Batista, Evelin Amorim, Alípio Jorge et al. Published: 2026-02-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.12137v2 City councils play a crucial role in local governance, directly influencing citizens' daily lives through decisions made during municipal meetings. These deliberations are formally documented in meeting minutes, which serve as official records of discussions, decisions, and voting outcomes. Despite their importance, municipal meeting records have received little attention in Information Retrieval (IR) and Natural Language Processing (NLP), largely due to the lack of annotated datasets, which ultimately limit the development of computational models. To address this gap, we introduce CitiLink-Minutes, a multilayer dataset of 120 European Portuguese municipal meeting minutes from six municipalities. Unlike prior annotated datasets of parliamentary or video records, CitiLink-Minutes provides multilayer annotations and structured linkage of official written minutes. The dataset contains over one million tokens, with all personal identifiers de-identified. Each minute was manually annotated by two trained annotators and curated by an experienced linguist across three complementary dimensions: (1) metadata, (2) subjects of discussion, and (3) voting outcomes, totaling over 38,000 individual annotations. Released under FAIR principles and accompanied by baseline results on metadata extraction, topic classification, and vote labeling, CitiLink-Minutes demonstrates its potential for downstream NLP and IR tasks, while promoting transparent access to municipal decisions. --- ### WavBench: Benchmarking Reasoning, Colloquialism, and Paralinguistics for End-to-End Spoken Dialogue Models Authors: Yangzhuo Li, Shengpeng Ji, Yifu Chen, Tianle Liang, Haorong Ying, Yule Wang, Junbo Li, Jun Fang, Zhou Zhao Published: 2026-02-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.12135v2 With the rapid integration of advanced reasoning capabilities into spoken dialogue models, the field urgently demands benchmarks that transcend simple interactions to address real-world complexity. However, current evaluations predominantly adhere to text-generation standards, overlooking the unique audio-centric characteristics of paralinguistics and colloquialisms, alongside the cognitive depth required by modern agents. To bridge this gap, we introduce WavBench, a comprehensive benchmark designed to evaluate realistic conversational abilities where prior works fall short. Uniquely, WavBench establishes a tripartite framework: 1) Pro subset, designed to rigorously challenge reasoning-enhanced models with significantly increased difficulty; 2) Basic subset, defining a novel standard for spoken colloquialism that prioritizes "listenability" through natural vocabulary, linguistic fluency, and interactive rapport, rather than rigid written accuracy; and 3) Acoustic subset, covering explicit understanding, generation, and implicit dialogue to rigorously evaluate comprehensive paralinguistic capabilities within authentic real-world scenarios. Through evaluating five state-of-the-art models, WavBench offers critical insights into the intersection of complex problem-solving, colloquial delivery, and paralinguistic fidelity, guiding the evolution of robust spoken dialogue models. The benchmark dataset and evaluation toolkit are available at https://naruto-2024.github.io/wavbench.github.io/. --- ### Value Alignment Tax: Measuring Value Trade-offs in LLM Alignment Authors: Jiajun Chen, Hua Shen Published: 2026-02-12 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2602.12134v2 Existing work on value alignment typically characterizes value relations statically, ignoring how alignment interventions, such as prompting, fine-tuning, or preference optimization, reshape the broader value system. In practice, aligning a target value can implicitly shift other values, creating value trade-offs that remain largely unmeasured. We introduce VAT, a framework that quantifies value trade-offs by measuring how alignment-induced changes propagate across interconnected values relative to achieved on-target gain. VAT captures the system-level dynamics of value expression under alignment intervention, enabling evaluation of both intended improvements and unintended side effects. Using a controlled scenario-action dataset grounded in Schwartz value theory, we collect paired pre-post normative judgments and analyze alignment effects across models, values, and interventions. Results show that alignment often produces uneven and structured co-movement among values, revealing systematic trade-offs between target and non-target values. These effects are largely invisible under conventional target-only evaluation, but become evident via VAT, highlighting process-level alignment risks and offering new insights into the dynamic nature of value alignment in LLMs. Dataset and code are open-sourced. --- ### Neutral Prompts, Non-Neutral People: Quantifying Gender and Skin-Tone Bias in Gemini Flash 2.5 Image and GPT Image 1.5 Authors: Roberto Balestri Published: 2026-02-12 Categories: cs.AI, cs.CL, cs.CY, cs.HC arXiv: https://arxiv.org/abs/2602.12133v1 This study quantifies gender and skin-tone bias in two widely deployed commercial image generators - Gemini Flash 2.5 Image (NanoBanana) and GPT Image 1.5 - to test the assumption that neutral prompts yield demographically neutral outputs. We generated 3,200 photorealistic images using four semantically neutral prompts. The analysis employed a rigorous pipeline combining hybrid color normalization, facial landmark masking, and perceptually uniform skin tone quantification using the Monk (MST), PERLA, and Fitzpatrick scales. Neutral prompts produced highly polarized defaults. Both models exhibited a strong "default white" bias (>96% of outputs). However, they diverged sharply on gender: Gemini favored female-presenting subjects, while GPT favored male-presenting subjects with lighter skin tones. This research provides a large-scale, comparative audit of state-of-the-art models using an illumination-aware colorimetric methodology, distinguishing aesthetic rendering from underlying pigmentation in synthetic imagery. The study demonstrates that neutral prompts function as diagnostic probes rather than neutral instructions. It offers a robust framework for auditing algorithmic visual culture and challenges the sociolinguistic assumption that unmarked language results in inclusive representation. --- ### A Rule-based Computational Model for Gaidhlig Morphology Authors: Peter J Barclay Published: 2026-02-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.12132v1 Language models and software tools are essential to support the continuing vitality of lesser-used languages; however, currently popular neural models require considerable data for training, which normally is not available for such low-resource languages. This paper describes work-in-progress to construct a rule-based model of Gaidhlig morphology using data from Wiktionary, arguing that rule-based systems effectively leverage limited sample data, support greater interpretability, and provide insights useful in the design of teaching materials. The use of SQL for querying the occurrence of different lexical patterns is investigated, and a declarative rule-base is presented that allows Python utilities to derive inflected forms of Gaidhlig words. This functionality could be used to support educational tools that teach or explain language patterns, for example, or to support higher level tools such as rule-based dependency parsers. This approach adds value to the data already present in Wiktionary by adapting it to new use-cases. --- ### Towards Personalized Bangla Book Recommendation: A Large-Scale Heterogeneous Book Graph Dataset Authors: Rahin Arefin Ahmed, Md. Anik Chowdhury, Sakil Ahmed Sheikh Reza, Devnil Bhattacharjee, Muhammad Abdullah Adnan, Julian McAuley, Nafis Sadeq Published: 2026-02-12 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2602.12129v2 Personalized book recommendation in Bangla literature has been constrained by the lack of structured, large-scale, and publicly available datasets. This work introduces RokomariBG, a large-scale heterogeneous book graph dataset designed to support research on personalized recommendation in a low-resource language setting. The dataset comprises 127,302 books, 63,723 users, 16,601 authors, 1,515 categories, 2,757 publishers, and 209,602 reviews, connected through several relation types and organized as a comprehensive knowledge graph. To demonstrate the utility of the dataset, we present a systematic benchmarking study on the top-N recommendation and sequential recommendation tasks, evaluating a diverse set of representative recommendation models. Through comprehensive benchmarking, we demonstrate that recommendation performance in this domain is strongly influenced by both heterogeneous relational information and code-mixed textual metadata. These findings reveal unique challenges of Bangladeshi e-commerce ecosystems that are largely absent from existing recommendation benchmarks. Overall, this work establishes a foundational benchmark and a publicly available resource for Bangla book recommendation research, enabling reproducible evaluation and future studies on recommendation in low-resource cultural domains. The dataset and code are publicly available at https://github.com/backlashblitz/Bangla-Book-Recommendation-Dataset --- ### HLA: Hadamard Linear Attention Authors: Hanno Ackermann, Hong Cai, Mohsen Ghafoorian, Amirhossein Habibian Published: 2026-02-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.12128v1 The attention mechanism is an important reason for the success of transformers. It relies on computing pairwise relations between tokens. To reduce the high computational cost of standard quadratic attention, linear attention has been proposed as an efficient approximation. It employs kernel functions that are applied independently to the inputs before the pairwise similarities are calculated. That allows for an efficient computational procedure which, however, amounts to a low-degree rational function approximating softmax. We propose Hadamard Linear Attention (HLA). Unlike previous works on linear attention, the nonlinearity in HLA is not applied separately to queries and keys, but, analogously to standard softmax attention, after the pairwise similarities have been computed. It will be shown that the proposed nonlinearity amounts to a higher-degree rational function to approximate softmax. An efficient computational scheme for the proposed method is derived that is similar to that of standard linear attention. In contrast to other approaches, no time-consuming tensor reshaping is necessary to apply the proposed algorithm. The effectiveness of the approach is demonstrated by applying it to a large diffusion transformer model for video generation, an application that involves very large amounts of tokens. --- ### PosterOmni: Generalized Artistic Poster Creation via Task Distillation and Unified Reward Feedback Authors: Sixiang Chen, Jianyu Lai, Jialin Gao, Hengyu Shi, Zhongying Liu, Tian Ye, Junfeng Luo, Xiaoming Wei, Lei Zhu Published: 2026-02-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.12127v1 Image-to-poster generation is a high-demand task requiring not only local adjustments but also high-level design understanding. Models must generate text, layout, style, and visual elements while preserving semantic fidelity and aesthetic coherence. The process spans two regimes: local editing, where ID-driven generation, rescaling, filling, and extending must preserve concrete visual entities; and global creation, where layout- and style-driven tasks rely on understanding abstract design concepts. These intertwined demands make image-to-poster a multi-dimensional process coupling entity-preserving editing with concept-driven creation under image-prompt control. To address these challenges, we propose PosterOmni, a generalized artistic poster creation framework that unlocks the potential of a base edit model for multi-task image-to-poster generation. PosterOmni integrates the two regimes, namely local editing and global creation, within a single system through an efficient data-distillation-reward pipeline: (i) constructing multi-scenario image-to-poster datasets covering six task types across entity-based and concept-based creation; (ii) distilling knowledge between local and global experts for supervised fine-tuning; and (iii) applying unified PosterOmni Reward Feedback to jointly align visual entity-preserving and aesthetic preference across all tasks. Additionally, we establish PosterOmni-Bench, a unified benchmark for evaluating both local editing and global creation. Extensive experiments show that PosterOmni significantly enhances reference adherence, global composition quality, and aesthetic harmony, outperforming all open-source baselines and even surpassing several proprietary systems. --- ### Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation Authors: Wenkai Yang, Weijie Liu, Ruobing Xie, Kai Yang, Saiyong Yang, Yankai Lin Published: 2026-02-12 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.12125v2 On-policy distillation (OPD), which aligns the student with the teacher's logit distribution on student-generated trajectories, has demonstrated strong empirical gains in improving student performance and often outperforms off-policy distillation and reinforcement learning (RL) paradigms. In this work, we first theoretically show that OPD is a special case of dense KL-constrained RL where the reward function and the KL regularization are always weighted equally and the reference model can by any model. Then, we propose the Generalized On-Policy Distillation (G-OPD) framework, which extends the standard OPD objective by introducing a flexible reference model and a reward scaling factor that controls the relative weight of the reward term against the KL regularization. Through comprehensive experiments on math reasoning and code generation tasks, we derive two novel insights: (1) Setting the reward scaling factor to be greater than 1 (i.e., reward extrapolation), which we term ExOPD, consistently improves over standard OPD across a range of teacher-student size pairings. In particular, in the setting where we merge the knowledge from different domain experts, obtained by applying domain-specific RL to the same student model, back into the original student, ExOPD enables the student to even surpass the teacher's performance boundary and outperform the domain teachers. (2) Building on ExOPD, we further find that in the strong-to-weak distillation setting (i.e., distilling a smaller student from a larger teacher), performing reward correction by choosing the reference model as the teacher's base model before RL yields a more accurate reward signal and further improves distillation performance. However, this choice assumes access to the teacher's pre-RL variant and incurs more computational overhead. We hope our work offers new insights for future research on OPD. --- ### Alignment Risks from Capability-Seeking RL Training Authors: Yujun Zhou, Yue Huang, Han Bao, Kehan Guo, Zhenwen Liang, Pin-Yu Chen, Tian Gao, Werner Geyer, Nuno Moniz, Nitesh V Chawla, Xiangliang Zhang Published: 2026-02-12 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2602.12124v2 While most AI alignment research focuses on preventing models from generating explicitly harmful content, a more subtle risk arises from capability-seeking RL training in vulnerable environments. We investigate whether language models, when trained with reinforcement learning (RL) in environments with implicit loopholes, can learn to exploit these flaws to maximize reward, even without being explicitly instructed to do so. To test this, we design a suite of four diverse "vulnerability games," each presenting a structural vulnerability related to context-conditional compliance, proxy metrics, reward tampering, and self-evaluation. Our experiments show that models often learn to exploit these vulnerabilities, discovering opportunistic strategies that increase reward while sometimes preserving or even improving standard task-performance metrics. More critically, we find that these exploitative strategies are not always narrow "tricks": they can transfer in structured but limited ways, propagate from a capable teacher model to other student models through SFT, and in several cases remain more persistent when learned through RL than when distilled through SFT. Our findings show that alignment risks from capability-seeking RL training can be difficult to detect with standard performance monitoring, suggesting that future AI safety work should extend beyond content moderation to auditing and securing training environments, reward mechanisms, and evaluation channels. Code is available at https://github.com/YujunZhou/Capability-seeking-RL-risk. --- ### Meta-Sel: Efficient Demonstration Selection for In-Context Learning via Supervised Meta-Learning Authors: Xubin Wang, Weijia Jia Published: 2026-02-12 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.12123v1 Demonstration selection is a practical bottleneck in in-context learning (ICL): under a tight prompt budget, accuracy can change substantially depending on which few-shot examples are included, yet selection must remain cheap enough to run per query over large candidate pools. We propose Meta-Sel, a lightweight supervised meta-learning approach for intent classification that learns a fast, interpretable scoring function for (candidate, query) pairs from labeled training data. Meta-Sel constructs a meta-dataset by sampling pairs from the training split and using class agreement as supervision, then trains a calibrated logistic regressor on two inexpensive meta-features: TF--IDF cosine similarity and a length-compatibility ratio. At inference time, the selector performs a single vectorized scoring pass over the full candidate pool and returns the top-k demonstrations, requiring no model fine-tuning, no online exploration, and no additional LLM calls. This yields deterministic rankings and makes the selection mechanism straightforward to audit via interpretable feature weights. Beyond proposing Meta-Sel, we provide a broad empirical study of demonstration selection, benchmarking 12 methods -- spanning prompt engineering baselines, heuristic selection, reinforcement learning, and influence-based approaches -- across four intent datasets and five open-source LLMs. Across this benchmark, Meta-Sel consistently ranks among the top-performing methods, is particularly effective for smaller models where selection quality can partially compensate for limited model capacity, and maintains competitive selection-time overhead. --- ### Forecasting Commencing Enrolments Under Data Sparsity: A Zero-Shot Time Series Foundation Models Framework for Higher Education Planning Authors: Jittarin Jetwiriyanon, Teo Susnjak, Surangika Ranathunga Published: 2026-02-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.12120v3 Effective resource allocation in higher education depends on reliable enrolment forecasts, yet institutional planners frequently face data series disrupted by structural shifts. This paper investigates whether zero-shot Time Series Foundation Models (TSFMs) can provide rigorous decision support for annual enrolment forecasting under severe data sparsity. We benchmark multiple TSFMs against classical operational baselines using an expanding-window backtest that mirrors decision-time constraints. To capture environmental shifts without look-ahead bias, we introduce a leakage-safe covariate protocol that integrates feature-engineered Google Trends with the Institutional Operating Conditions Index (IOCI), a transferable regime measure extracted from historical narrative evidence. Our evaluation demonstrates that covariate-conditioned TSFMs are competitive with classical methods and can improve accuracy without requiring bespoke institutional training. However, the operational benefits depend on cohort characteristics and covariate design. This study provides an auditable and transferable forecasting protocol for operational researchers and university administrators, helping institutions determine when context-aware forecasting adds practical value under limited data and structural instability. --- ### KAN-FIF: Spline-Parameterized Lightweight Physics-based Tropical Cyclone Estimation on Meteorological Satellite Authors: Jiakang Shen, Qinghui Chen, Runtong Wang, Chenrui Xu, Jinglin Zhang, Cong Bai, Feng Zhang Published: 2026-02-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.12117v2 Tropical cyclones (TC) are among the most destructive natural disasters, causing catastrophic damage to coastal regions through extreme winds, heavy rainfall, and storm surges. Timely monitoring of tropical cyclones is crucial for reducing loss of life and property, yet it is hindered by the computational inefficiency and high parameter counts of existing methods on resource-constrained edge devices. Current physics-guided models suffer from linear feature interactions that fail to capture high-order polynomial relationships between TC attributes, leading to inflated model sizes and hardware incompatibility. To overcome these challenges, this study introduces the Kolmogorov-Arnold Network-based Feature Interaction Framework (KAN-FIF), a lightweight multimodal architecture that integrates MLP and CNN layers with spline-parameterized KAN layers. For Maximum Sustained Wind (MSW) prediction, experiments demonstrate that the KAN-FIF framework achieves a $94.8\%$ reduction in parameters (0.99MB vs 19MB) and $68.7\%$ faster inference per sample (2.3ms vs 7.35ms) compared to baseline model Phy-CoCo, while maintaining superior accuracy with $32.5\%$ lower MAE. The offline deployment experiment of the FY-4 series meteorological satellite processor on the Qingyun-1000 development board achieved a 14.41ms per-sample inference latency with the KAN-FIF framework, demonstrating promising feasibility for operational TC monitoring and extending deployability to edge-device AI applications. The code is released at https://github.com/Jinglin-Zhang/KAN-FIF. --- ### P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling Authors: Pinyi Zhang, Ting-En Lin, Yuchuan Wu, Jingyang Chen, Zongqi Wang, Hua Yang, Ze Xu, Fei Huang, Kai Zhang, Yongbin Li Published: 2026-02-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.12116v1 Personalized alignment of large language models seeks to adapt responses to individual user preferences, typically via reinforcement learning. A key challenge is obtaining accurate, user-specific reward signals in open-ended scenarios. Existing personalized reward models face two persistent limitations: (1) oversimplifying diverse, scenario-specific preferences into a small, fixed set of evaluation principles, and (2) struggling with generalization to new users with limited feedback. To this end, we propose P-GenRM, the first Personalized Generative Reward Model with test-time user-based scaling. P-GenRM transforms preference signals into structured evaluation chains that derive adaptive personas and scoring rubrics across various scenarios. It further clusters users into User Prototypes and introduces a dual-granularity scaling mechanism: at the individual level, it adaptively scales and aggregates each user's scoring scheme; at the prototype level, it incorporates preferences from similar users. This design mitigates noise in inferred preferences and enhances generalization to unseen users through prototype-based transfer. Empirical results show that P-GenRM achieves state-of-the-art results on widely-used personalized reward model benchmarks, with an average improvement of 2.31%, and demonstrates strong generalization on an out-of-distribution dataset. Notably, Test-time User-based scaling provides an additional 3% boost, demonstrating stronger personalized alignment with test-time scalability. --- ### Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty Authors: Zewei Yu, Lirong Gao, Yuke Zhu, Bo Zheng, Junbo Zhao, Sheng Guo, Haobo Wang Published: 2026-02-12 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.12113v2 Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex reasoning tasks by employing test-time scaling. However, they often generate over-long chains-of-thought that, driven by substantial reflections such as repetitive self-questioning and circular reasoning, lead to high token consumption, substantial computational overhead, and increased latency without improving accuracy, particularly in smaller models. Our observation reveals that increasing problem complexity induces more excessive and unnecessary reflection, which in turn reduces accuracy and increases token overhead. To address this challenge, we propose Adaptive Reflection and Length Coordinated Penalty (ARLCP), a novel reinforcement learning framework designed to dynamically balance reasoning efficiency and solution accuracy. ARLCP introduces two key innovations: (1) a reflection penalty that adaptively curtails unnecessary reflective steps while preserving essential reasoning, and (2) a length penalty calibrated to the estimated complexity of the problem. By coordinating these penalties, ARLCP encourages the model to generate more concise and effective reasoning paths. We evaluate our method on five mathematical reasoning benchmarks using DeepSeek-R1-Distill-Qwen-1.5B and DeepSeek-R1-Distill-Qwen-7B models. Experimental results show that ARLCP achieves a superior efficiency-accuracy trade-off compared to existing approaches. For the 1.5B model, it reduces the average response length by 53.1% while simultaneously improving accuracy by 5.8%. For the 7B model, it achieves a 35.0% reduction in length with a 2.7% accuracy gain. The code is released at https://github.com/ZeweiYu1/ARLCP . --- ### Few-Shot Design Optimization by Exploiting Auxiliary Information Authors: Arjun Mani, Carl Vondrick, Richard Zemel Published: 2026-02-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.12112v1 Many real-world design problems involve optimizing an expensive black-box function $f(x)$, such as hardware design or drug discovery. Bayesian Optimization has emerged as a sample-efficient framework for this problem. However, the basic setting considered by these methods is simplified compared to real-world experimental setups, where experiments often generate a wealth of useful information. We introduce a new setting where an experiment generates high-dimensional auxiliary information $h(x)$ along with the performance measure $f(x)$; moreover, a history of previously solved tasks from the same task family is available for accelerating optimization. A key challenge of our setting is learning how to represent and utilize $h(x)$ for efficiently solving new optimization tasks beyond the task history. We develop a novel approach for this setting based on a neural model which predicts $f(x)$ for unseen designs given a few-shot context containing observations of $h(x)$. We evaluate our method on two challenging domains, robotic hardware design and neural network hyperparameter tuning, and introduce a novel design problem and large-scale benchmark for the former. On both domains, our method utilizes auxiliary feedback effectively to achieve more accurate few-shot prediction and faster optimization of design tasks, significantly outperforming several methods for multi-task optimization. --- ### The Pensieve Paradigm: Stateful Language Models Mastering Their Own Context Authors: Xiaoyuan Liu, Tian Liang, Dongyang Ma, Deyu Zhou, Haitao Mi, Pinjia He, Yan Wang Published: 2026-02-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.12108v1 In the world of Harry Potter, when Dumbledore's mind is overburdened, he extracts memories into a Pensieve to be revisited later. In the world of AI, while we possess the Pensieve-mature databases and retrieval systems, our models inexplicably lack the "wand" to operate it. They remain like a Dumbledore without agency, passively accepting a manually engineered context as their entire memory. This work finally places the wand in the model's hand. We introduce StateLM, a new class of foundation models endowed with an internal reasoning loop to manage their own state. We equip our model with a suite of memory tools, such as context pruning, document indexing, and note-taking, and train it to actively manage these tools. By learning to dynamically engineering its own context, our model breaks free from the architectural prison of a fixed window. Experiments across various model sizes demonstrate StateLM's effectiveness across diverse scenarios. On long-document QA tasks, StateLMs consistently outperform standard LLMs across all model scales; on the chat memory task, they achieve absolute accuracy improvements of 10% to 20% over standard LLMs. On the deep research task BrowseComp-Plus, the performance gap becomes even more pronounced: StateLM achieves up to 52% accuracy, whereas standard LLM counterparts struggle around 5%. Ultimately, our approach shifts LLMs from passive predictors to state-aware agents where reasoning becomes a stateful and manageable process. --- ### On the Complexity of Offline Reinforcement Learning with $Q^\star$-Approximation and Partial Coverage Authors: Haolin Liu, Braham Snyder, Chen-Yu Wei Published: 2026-02-12 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2602.12107v2 We study offline reinforcement learning under $Q^\star$-approximation and partial coverage, a setting that motivates practical algorithms such as Conservative $Q$-Learning (CQL; Kumar et al., 2020) but has received limited theoretical attention. Our work is inspired by the following open question: "Are $Q^\star$-realizability and Bellman completeness sufficient for sample-efficient offline RL under partial coverage?" We answer in the negative via an information-theoretic lower bound. To identify additional structure that enables sample-efficient offline RL under partial coverage, we introduce a general decision-estimation framework, inspired by model-free decision-estimation coefficients (DEC) for online RL (Foster et al., 2023b; Liu et al., 2025b). Our framework decomposes offline RL complexity into decision complexity and value estimation error. This allows modular study of both sub-problems. Our result not only unifies existing results (Chen and Jiang, 2022; Uehara et al., 2023), but further improves and generalizes them. On the decision complexity side, our improvement includes: the first $ε^{-2}$ sample complexity bound for soft $Q$-learning under partial coverage that improves Uehara et al.'s (2023) $ε^{-4}$ bound, the removal of the need for additional online interaction in the value-gap setting of Chen and Jiang (2022), and new learnable settings beyond the above two cases. On the value estimation side, we provide a new characterization of the role of Bellman completeness under partial coverage, and the first characterization of offline learnability for general low-Bellman-rank MDPs (Jiang et al., 2017; Du et al., 2021; Jin et al., 2021). The latter is a canonical online RL setting that has remained unexplored in offline RL except for special cases. As a side contribution, our techniques give the first analysis of CQL in the function approximation setting. --- ### Iskra: A System for Inverse Geometry Processing Authors: Ana Dodik, Ahmed H. Mahmoud, Justin Solomon Published: 2026-02-12 Categories: cs.GR, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.12105v2 We propose a system for differentiating through solutions to geometry processing problems. Our system differentiates a broad class of geometric algorithms, exploiting existing fast problem-specific schemes common to geometry processing, including local-global and ADMM solvers. It is compatible with machine learning frameworks, opening doors to new classes of inverse geometry processing applications. We marry the scatter-gather approach to mesh processing with tensor-based workflows and rely on the adjoint method applied to user-specified imperative code to generate an efficient backward pass behind the scenes. We demonstrate our approach by differentiating through mean curvature flow, spectral conformal parameterization, geodesic distance computation, and as-rigid-as-possible deformation, examining usability and performance on these applications. Our system allows practitioners to differentiate through existing geometry processing algorithms without needing to reformulate them, resulting in low implementation effort, fast runtimes, and lower memory requirements than differentiable optimization tools not tailored to geometry processing. --- ### AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer Authors: Lingting Zhu, Shengju Qian, Haidi Fan, Jiayu Dong, Zhenchao Jin, Siwei Zhou, Gen Dong, Xin Wang, Lequan Yu Published: 2026-02-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.12100v1 The digital industry demands high-quality, diverse modular 3D assets, especially for user-generated content~(UGC). In this work, we introduce AssetFormer, an autoregressive Transformer-based model designed to generate modular 3D assets from textual descriptions. Our pilot study leverages real-world modular assets collected from online platforms. AssetFormer tackles the challenge of creating assets composed of primitives that adhere to constrained design parameters for various applications. By innovatively adapting module sequencing and decoding techniques inspired by language models, our approach enhances asset generation quality through autoregressive modeling. Initial results indicate the effectiveness of AssetFormer in streamlining asset creation for professional development and UGC scenarios. This work presents a flexible framework extendable to various types of modular 3D assets, contributing to the broader field of 3D content generation. The code is available at https://github.com/Advocate99/AssetFormer. --- ### GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning Authors: GigaBrain Team, Boyuan Wang, Bohan Li, Chaojun Ni, Guan Huang, Guosheng Zhao, Hao Li, Jie Li, Jindi Lv, Jingyu Liu, Lv Feng, Mingming Yu et al. Published: 2026-02-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.12099v2 Vision-language-action (VLA) models that directly predict multi-step action chunks from current observations face inherent limitations due to constrained scene understanding and weak future anticipation capabilities. In contrast, video world models pre-trained on web-scale video corpora exhibit robust spatiotemporal reasoning and accurate future prediction, making them a natural foundation for enhancing VLA learning. Therefore, we propose \textit{GigaBrain-0.5M*}, a VLA model trained via world model-based reinforcement learning. Built upon \textit{GigaBrain-0.5}, which is pre-trained on over 10,000 hours of robotic manipulation data, whose intermediate version currently ranks first on the international RoboChallenge benchmark. \textit{GigaBrain-0.5M*} further integrates world model-based reinforcement learning via \textit{RAMP} (Reinforcement leArning via world Model-conditioned Policy) to enable robust cross-task adaptation. Empirical results demonstrate that \textit{RAMP} achieves substantial performance gains over the RECAP baseline, yielding improvements of approximately 30\% on challenging tasks including \texttt{Laundry Folding}, \texttt{Box Packing}, and \texttt{Espresso Preparation}. Critically, \textit{GigaBrain-0.5M$^*$} exhibits reliable long-horizon execution, consistently accomplishing complex manipulation tasks without failure as validated by real-world deployment videos on our \href{https://gigabrain05m.github.io}{project page}. --- ### Multi Graph Search for High-Dimensional Robot Motion Planning Authors: Itamar Mishani, Maxim Likhachev Published: 2026-02-12 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2602.12096v1 Efficient motion planning for high-dimensional robotic systems, such as manipulators and mobile manipulators, is critical for real-time operation and reliable deployment. Although advances in planning algorithms have enhanced scalability to high-dimensional state spaces, these improvements often come at the cost of generating unpredictable, inconsistent motions or requiring excessive computational resources and memory. In this work, we introduce Multi-Graph Search (MGS), a search-based motion planning algorithm that generalizes classical unidirectional and bidirectional search to a multi-graph setting. MGS maintains and incrementally expands multiple implicit graphs over the state space, focusing exploration on high-potential regions while allowing initially disconnected subgraphs to be merged through feasible transitions as the search progresses. We prove that MGS is complete and bounded-suboptimal, and empirically demonstrate its effectiveness on a range of manipulation and mobile manipulation tasks. Demonstrations, benchmarks and code are available at https://multi-graph-search.github.io/. --- ### DeepSight: An All-in-One LM Safety Toolkit Authors: Bo Zhang, Jiaxuan Guo, Lijun Li, Dongrui Liu, Sujin Chen, Guanxu Chen, Zhijie Zheng, Qihao Lin, Lewen Yan, Chen Qian, Yijin Zhou, Yuyao Wu et al. Published: 2026-02-12 Categories: cs.CL, cs.AI, cs.CR, cs.CV arXiv: https://arxiv.org/abs/2602.12092v1 As the development of Large Models (LMs) progresses rapidly, their safety is also a priority. In current Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) safety workflow, evaluation, diagnosis, and alignment are often handled by separate tools. Specifically, safety evaluation can only locate external behavioral risks but cannot figure out internal root causes. Meanwhile, safety diagnosis often drifts from concrete risk scenarios and remains at the explainable level. In this way, safety alignment lack dedicated explanations of changes in internal mechanisms, potentially degrading general capabilities. To systematically address these issues, we propose an open-source project, namely DeepSight, to practice a new safety evaluation-diagnosis integrated paradigm. DeepSight is low-cost, reproducible, efficient, and highly scalable large-scale model safety evaluation project consisting of a evaluation toolkit DeepSafe and a diagnosis toolkit DeepScan. By unifying task and data protocols, we build a connection between the two stages and transform safety evaluation from black-box to white-box insight. Besides, DeepSight is the first open source toolkit that support the frontier AI risk evaluation and joint safety evaluation and diagnosis. --- ### Choose Your Agent: Tradeoffs in Adopting AI Advisors, Coaches, and Delegates in Multi-Party Negotiation Authors: Kehang Zhu, Nithum Thain, Vivian Tsai, James Wexler, Crystal Qian Published: 2026-02-12 Categories: cs.GT, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2602.12089v3 As AI usage becomes more prevalent in social contexts, understanding agent-user interaction is critical to designing systems that imp rove both individual and group outcomes. We present an online behavioral experiment (N=243) in which participants play three multi-tu rn bargaining games in groups of three. Each game, presented in randomized order, grants access to a single LLM assistance modality: proactive recommendations from an Advisor, reactive feedback from a Coach, or autonomous execution by a Delegate. All three modalitie s are powered by an LLM with super-human performance within this negotiation setting. On each turn, participants privately decide whe ther to act manually or use the AI modality available in that game. We document a preference-performance misalignment: participants s trongly prefer the higher-control Advisor (44%) over the Delegate (19%), yet groups only significantly increase collective surplus un der Delegate access. Adjusting for voluntary non-compliance, delegating to the AI yields suggestive individual welfare gains, roughly 1.5x the intent-to-treat estimate. A mechanism analysis traces this gap to a human filter: AI-generated proposals create more joint surplus than manual proposals across all conditions, but in the Advisor and Coach modes users modify, override, or ignore the AI's su ggestions, reverting toward human-baseline trade patterns. The Delegate advantage arises not from a different AI capability but from bypassing this filtering step altogether. Realizing these welfare gains depends not only on model capability, but on the interaction structure through which that capability is delivered. We argue that assistance modalities should be designed as mechanisms with endog enous participation; adoption-compatible interaction rules are a prerequisite to improving welfare with automated assistance. ---