# Research Papers — 2026-02 · bundle page 3 of 210 > Full-text markdown of papers #101–150 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/3 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/2.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/4.md) ### SSKG Hub: An Expert-Guided Platform for LLM-Empowered Sustainability Standards Knowledge Graphs Authors: Chaoyue He, Xin Zhou, Xinjia Yu, Lei Zhang, Yan Zhang, Yi Wu, Lei Xiao, Liangyue Li, Di Wang, Hong Xu, Xiaoqiao Wang, Wei Liu et al. Published: 2026-02-28 Categories: cs.CL, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2603.00669v1 Sustainability disclosure standards (e.g., GRI, SASB, TCFD, IFRS S2) are comprehensive yet lengthy, terminology-dense, and highly cross-referential, hindering structured analysis and downstream use. We present SSKG Hub (Sustainability Standards Knowledge Graph Hub), a research prototype and interactive web platform that transforms standards into auditable knowledge graphs (KGs) through an LLM-centered, expert-guided pipeline. The system integrates automatic standard identification, configurable chunking, standard-specific prompting, robust triple parsing, and provenance-aware Neo4j storage with fine-grained audit metadata. LLM extraction produces a provenance-linked Draft KG, which is reviewed, curated, and formally promoted to a Certified KG through meta-expert adjudication. A role-based governance framework covering read-only guest access, expert review and CRUD operations, meta-expert certification, and administrative oversight ensures traceability and accountability across draft and certified states. Beyond graph exploration and triple-level evidence tracing, SSKG Hub supports cross-KG fusion, KG-driven tasks, and dedicated modules for insights and curated resources. We validate the platform through a comprehensive expert-led KG review case study that demonstrates end-to-end curation and quality assurance. The web application is publicly available at www.sskg-hub.com. --- ### Direct low-field MRI super-resolution using undersampled k-space Authors: Daniel Tweneboah Anyimadu, Mohammed M. Abdelsamea, Ahmed Karam Eldaly Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00668v1 Low-field magnetic resonance imaging (MRI) provides affordable access to diagnostic imaging but suffers from prolonged acquisition and limited image quality. Accelerated imaging can be achieved with k-space undersampling, while super-resolution (SR) and image quality transfer (IQT) methods typically rely on spatial-domain post-processing. In this work, we propose a novel framework for reconstructing high-field MR like images directly from undersampled low-field k-space. Our approach employs a k-space dual channel U-Net that processes the real and imaginary components of undersampled k-space to restore missing frequency content. Experiments on low-field brain MRI demonstrate that our k-space-driven image enhancement consistently outperforms the counterpart spatial-domain method. Furthermore, reconstructions from undersampled k-space achieve image quality comparable to full k-space acquisitions. To the best of our knowledge, this is the first work that investigates low-field MRI SR/IQT directly from undersampled k-space. --- ### Act Like a Pathologist: Tissue-Aware Whole Slide Image Reasoning Authors: Wentao Huang, Weimin Lyu, Peiliang Lou, Qingqiao Hu, Xiaoling Hu, Shahira Abousamra, Wenchao Han, Ruifeng Guo, Jiawei Zhou, Chao Chen, Chen Wang Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00667v3 Computational pathology has advanced rapidly in recent years, driven by domain-specific image encoders and growing interest in using vision-language models to answer natural-language questions about diseases. Yet, the core problem behind pathology question-answering remains unsolved, considering that a gigapixel slide contains far more information than necessary for a given question. Pathologists naturally navigate tissue and morphology complexity by scanning broadly, and zooming in selectively according to the clinical questions. Current models, in contrast, rely on uniform patch sampling or broad attention maps, often attending equally to irrelevant regions while overlooking key visual evidence. In this work, we try to bring models closer to how humans actually examine slides. We propose a question-guided, tissue-aware, and coarse-to-fine retrieval framework, HistoSelect, that consists of two key components: a group sampler that identifies question-relevant tissue regions, followed by a patch selector that retrieves the most informative patches within those regions. By selecting only the most informative patches, our method becomes significantly more efficient: reducing visual token usage by 70% on average, while improving accuracy across three pathology QA tasks. Evaluated on 356,000 question-answer pairs, our approach outperforms existing methods and produces answers grounded in interpretable, pathologist-consistent regions. Our results suggest that bringing human-like search and attention patterns into WSI reasoning is a promising direction for building practical and reliable pathology VLMs. Code is available at https://github.com/winston52/HistoSelect. --- ### InfoPO: Information-Driven Policy Optimization for User-Centric Agents Authors: Fanqi Kong, Jiayi Zhang, Mingyi Deng, Chenglin Wu, Yuyu Luo, Bang Liu Published: 2026-02-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.00656v2 Real-world user requests to LLM agents are often underspecified. Agents must interact to acquire missing information and make correct downstream decisions. However, current multi-turn GRPO-based methods often rely on trajectory-level reward computation, which leads to credit assignment problems and insufficient advantage signals within rollout groups. A feasible approach is to identify valuable interaction turns at a fine granularity to drive more targeted learning. To address this, we introduce InfoPO (Information-Driven Policy Optimization), which frames multi-turn interaction as a process of active uncertainty reduction and computes an information-gain reward that credits turns whose feedback measurably changes the agent's subsequent action distribution compared to a masked-feedback counterfactual. It then combines this signal with task outcomes via an adaptive variance-gated fusion to identify information importance while maintaining task-oriented goal direction. Across diverse tasks, including intent clarification, collaborative coding, and tool-augmented decision making, InfoPO consistently outperforms prompting and multi-turn RL baselines. It also demonstrates robustness under user simulator shifts and generalizes effectively to environment-interactive tasks. Overall, InfoPO provides a principled and scalable mechanism for optimizing complex agent-user collaboration. Code is available at https://github.com/kfq20/InfoPO. --- ### Mema: Memory-Augmented Adapter for Enhanced Vision-Language Understanding Authors: Ying Liu, Yudong Han, Kean Shi, Liyuan Pan Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00655v2 Multimodal Large Language Models (MLLMs) have achieved remarkable performance by aligning pretrained visual representations with the linguistic knowledge embedded in Large Language Models (LLMs). However, existing approaches typically rely on final-layer visual features or learnable multi-layer fusion, which often fail to sufficiently exploit hierarchical visual cues without explicit cross-layer interaction design. In this work, we propose a Memory-Augmented Adapter (Mema) within the vision encoder. Specifically, Mema maintains a stateful memory that accumulates hierarchical visual representations across layers, with its evolution conditioned on both query embeddings and step-wise visual features. A portion of this memory is selectively injected into token representations via a feedback mechanism, thereby mitigating the attenuation of fine-grained visual cues from shallow layers. Designed as a lightweight and plug-and-play module, Mema integrates seamlessly into pretrained vision encoders without modifying the vanilla backbone architecture. Only a minimal set of additional parameters requires training, enabling adaptive visual feature refinement while reducing training overhead. Extensive experiments across multiple benchmarks demonstrate that Mema consistently improves performance, validating its effectiveness in complex multimodal reasoning tasks. The code have been released at https://github.com/Sisiliu312/Mema. --- ### RC-GeoCP: Geometric Consensus for 4D Radar-Camera Collaborative Perception Authors: Xiaokai Bai, Lianqing Zheng, Runwei Guan, Siyuan Cao, Songkai Wang, Huiliang Shen Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00654v4 Collaborative perception (CP) extends sensing range through feature sharing, but most systems remain LiDAR-centric. Camera and 4D radar sensing combines dense semantics with lower-cost range--velocity measurements, yet exploiting their complementarity across agents remains difficult. Camera depth ambiguity produces spatially diffuse BEV evidence, while sparse transmission couples the choice of evidence to its subsequent contribution. Separate acquisition and aggregation objectives can assign conflicting source preferences to the retained evidence. We propose RC-GeoCP, connecting radar-grounded representation with persistent receiver--source attribution. Geometric Structure Rectification (GSR) uses radar-conditioned deformable sampling and gated calibration to construct grounded BEV features before communication. On these features, Uncertainty-Aware Communication (UAC) combines receiver demand with semantic confidence and radar support in a pre-delivery responsibility field that selects sparse support within fixed quotas. The Consensus-Driven Assembler (CDA) maps the same field into a bounded source mixture, carrying acquisition preferences into assembly. Persistent attribution coordinates spatial selection and source weighting across sparse transmission. Across two datasets and three aggregation backbones, RC-GeoCP consistently improves detection. Its sparse model retains 98.6%/96.6% of dense AP@0.7 at 10.88/4.95 MB per link. Code will be released. --- ### RC-GeoCP: Geometric Consensus for Radar-Camera Collaborative Perception Authors: Xiaokai Bai, Lianqing Zheng, Runwei Guan, Siyuan Cao, Songkai Wang, Huiliang Shen Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00654v3 Collaborative perception (CP) improves scene understanding through multi-agent information sharing, yet LiDAR-centric systems remain costly and vulnerable in adverse weather. Camera--4D radar offers a practical alternative, but their synergy is still underexplored in CP. We introduce RC-GeoCP, which promotes low-cost, weather-resilient, and geometrically stable radar from an ego-level auxiliary cue to a cross-agent collaboration anchor. To resolve misalignment caused by depth ambiguity and spatial dispersion across agents, RC-GeoCP establishes an ego-normalized geometric consensus: the same radar-derived reliability prior is reused to ground local BEV features, select complementary messages, and weight received evidence. Specifically, Geometric Structure Rectification (GSR) aligns visual semantics with geometry derived from radar to generate spatially grounded, geometry-consistent representations. Uncertainty-Aware Communication (UAC) then serves as an information filter that inherits rectified features from GSR, leveraging inter agent disagreement to steer selective communication toward the most informative regions. Finally, the Consensus-Driven Assembler (CDA) aggregates multi-agent information via ego-normalized geometric anchors to form a spatially coherent representation. We establish a unified radar-camera CP evaluation protocol on V2X-Radar and V2X-R, demonstrating a strong accuracy--communication trade-off. Code will be released soon. --- ### Exploring 3D Dataset Pruning Authors: Xiaohan Zhao, Xinyi Shang, Jiacheng Liu, Zhiqiang Shen Published: 2026-02-28 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.00651v1 Dataset pruning has been widely studied for 2D images to remove redundancy and accelerate training, while particular pruning methods for 3D data remain largely unexplored. In this work, we study dataset pruning for 3D data, where its observed common long-tail class distribution nature make optimization under conventional evaluation metrics Overall Accuracy (OA) and Mean Accuracy (mAcc) inherently conflicting, and further make pruning particularly challenging. To address this, we formulate pruning as approximating the full-data expected risk with a weighted subset, which reveals two key errors: coverage error from insufficient representativeness and prior-mismatch bias from inconsistency between subset-induced class weights and target metrics. We propose representation-aware subset selection with per-class retention quotas for long-tail coverage, and prior-invariant teacher supervision using calibrated soft labels and embedding-geometry distillation. The retention quota also serves as a switch to control the OA-mAcc trade-off. Extensive experiments on 3D datasets show that our method can improve both metrics across multiple settings while adapting to different downstream preferences. Our code is available at https://github.com/XiaohanZhao123/3D-Dataset-Pruning. --- ### Position: Evaluation of Visual Processing Should Be Human-Centered, Not Metric-Centered Authors: Jinfan Hu, Fanghua Yu, Zhiyuan You, Xiang Yin, Hongyu An, Xinqi Lin, Chao Dong, Jinjin Gu Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00643v2 This position paper argues that the evaluation of modern visual processing systems should no longer be driven primarily by single-metric image quality assessment benchmarks, particularly in the era of generative and perception-oriented methods. Image restoration exemplifies this divergence: while objective IQA metrics enable reproducible, scalable evaluation, they have increasingly drifted apart from human perception and user preferences. We contend that this mismatch risks constraining innovation and misguiding research progress across visual processing tasks. Rather than rejecting metrics altogether, this paper calls for a rebalancing of evaluation paradigms, advocating a more human-centered, context-aware, and fine-grained approach to assessing the visual models' outcomes. --- ### RAIE: Region-Aware Incremental Preference Editing with LoRA for LLM-based Recommendation Authors: Jin Zeng, Yupeng Qi, Hui Li, Chengming Li, Ziyu Lyu, Lixin Cui, Lu Bai Published: 2026-02-28 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2603.00638v2 Large language models (LLMs) are increasingly adopted as the backbone of recommender systems. However, user-item interactions in real-world scenarios are non-stationary, making preference drift over time inevitable. Existing model update strategies mainly rely on global fine-tuning or pointwise editing, but they face two fundamental challenges: (i) imbalanced update granularity, where global updates perturb behaviors unrelated to the target while pointwise edits fail to capture broader preference shifts; (ii) unstable incremental updates, where repeated edits interfere with prior adaptations, leading to catastrophic forgetting and inconsistent recommendations. To address these issues, we propose Region-Aware Incremental Editing (RAIE), a plug-in framework that freezes the backbone model and performs region-level updates. RAIE first constructs semantically coherent preference regions via spherical k-means in the representation space. It then assigns incoming sequences to regions via confidence-aware gating and performs three localized edit operations - Update, Expand, and Add - to dynamically revise the affected region. Each region is equipped with a dedicated Low-Rank Adaptation (LoRA) module, which is trained only on the region's updated data. During inference, RAIE routes each user sequence to its corresponding region and activates the region-specific adapter for prediction. Experiments on two benchmark datasets under a time-sliced protocol that segments data into Set-up (S), Finetune (F), and Test (T) show that RAIE significantly outperforms state-of-the-art baselines while effectively mitigating forgetting. These results demonstrate that region-aware editing offers an accurate and scalable mechanism for continual adaptation in dynamic recommendation scenarios. Our code is available at https://github.com/fengaogao/RAIE. --- ### Retrodictive Forecasting: A Proof-of-Concept for Exploiting Temporal Asymmetry in Time Series Prediction Authors: Cedric Damour Published: 2026-02-28 Categories: cs.LG, physics.ao-ph, stat.ML arXiv: https://arxiv.org/abs/2603.00636v1 We propose a retrodictive forecasting paradigm for time series: instead of predicting the future from the past, we identify the future that best explains the observed present via inverse MAP optimization over a Conditional Variational Autoencoder (CVAE). This conditioning is a statistical modeling choice for Bayesian inversion; it does not assert that future events cause past observations. The approach is theoretically grounded in an information-theoretic arrow-of-time measure: the symmetrized Kullback-Leibler divergence between forward and time-reversed trajectory ensembles provides both the conceptual rationale and an operational GO/NO-GO diagnostic for applicability. We implement the paradigm as MAP inference over an inverse CVAE with a learned RealNVP normalizing-flow prior and evaluate it on six time series cases: four synthetic processes with controlled temporal asymmetry and two ERA5 reanalysis datasets (wind speed and solar irradiance). The work makes four contributions: (i) a formal retrodictive inference formulation; (ii) an inverse CVAE architecture; (iii) a model-free irreversibility diagnostic; and (iv) a falsifiable validation protocol with four pre-specified predictions. All pre-specified predictions are empirically supported: the diagnostic correctly classifies all six cases; the learned flow prior improves over an isotropic Gaussian baseline on GO cases; the inverse MAP yields no spurious advantage on time-reversible dynamics; and on irreversible GO cases, it achieves competitive or superior RMSE relative to forward baselines, with a statistically significant 17.7% reduction over a forward MLP on ERA5 solar irradiance. These results provide a structured proof-of-concept that retrodictive forecasting can constitute a viable alternative to conventional forward prediction when statistical time-irreversibility is present and exploitable. --- ### BLUFF: Benchmarking the Detection of False and Synthetic Content across 58 Low-Resource Languages Authors: Jason Lucas, Matt Murtagh-White, Adaku Uchendu, Ali Al-Lawati, Michiharu Yamashita, Dominik Macko, Ivan Srba, Robert Moro, Dongwon Lee Published: 2026-02-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.00634v1 Multilingual falsehoods threaten information integrity worldwide, yet detection benchmarks remain confined to English or a few high-resource languages, leaving low-resource linguistic communities without robust defense tools. We introduce BLUFF, a comprehensive benchmark for detecting false and synthetic content, spanning 79 languages with over 202K samples, combining human-written fact-checked content (122K+ samples across 57 languages) and LLM-generated content (79K+ samples across 71 languages). BLUFF uniquely covers both high-resource "big-head" (20) and low-resource "long-tail" (59) languages, addressing critical gaps in multilingual research on detecting false and synthetic content. Our dataset features four content types (human-written, LLM-generated, LLM-translated, and hybrid human-LLM text), bidirectional translation (English$\leftrightarrow$X), 39 textual modification techniques (36 manipulation tactics for fake news, 3 AI-editing strategies for real news), and varying edit intensities generated using 19 diverse LLMs. We present AXL-CoI (Adversarial Cross-Lingual Agentic Chainof-Interactions), a novel multi-agentic framework for controlled fake/real news generation, paired with mPURIFY, a quality filtering pipeline ensuring dataset integrity. Experiments reveal state-of-theart detectors suffer up to 25.3% F1 degradation on low-resource versus high-resource languages. BLUFF provides the research community with a multilingual benchmark, extensive linguistic-oriented benchmark evaluation, comprehensive documentation, and opensource tools to advance equitable falsehood detection. Dataset and code are available at: https://jsl5710.github.io/BLUFF/ --- ### Stop Treating Collisions Equally: Qualification-Aware Semantic ID Learning for Recommendation at Industrial Scale Authors: Zheng Hu, Yuxin Chen, Yongsen Pan, Xu Yuan, Yuting Yin, Daoyuan Wang, Boyang Xia, Zefei Luo, Hongyang Wang, Songhao Ni, Dongxu Liang, Jun Wang et al. Published: 2026-02-28 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2603.00632v1 Semantic IDs (SIDs) are compact discrete representations derived from multimodal item features, serving as a unified abstraction for ID-based and generative recommendation. However, learning high-quality SIDs remains challenging due to two issues. (1) Collision problem: the quantized token space is prone to collisions, in which semantically distinct items are assigned identical or overly similar SID compositions, resulting in semantic entanglement. (2) Collision-signal heterogeneity: collisions are not uniformly harmful. Some reflect genuine conflicts between semantically unrelated items, while others stem from benign redundancy or systematic data effects. To address these challenges, we propose Qualification-Aware Semantic ID Learning (QuaSID), an end-to-end framework that learns collision-qualified SIDs by selectively repelling qualified conflict pairs and scaling the repulsion strength by collision severity. QuaSID consists of two mechanisms: Hamming-guided Margin Repulsion, which translates low-Hamming SID overlaps into explicit, severity-scaled geometric constraints on the encoder space; and Conflict-Aware Valid Pair Masking, which masks protocol-induced benign overlaps to denoise repulsion supervision. In addition, QuaSID incorporates a dual-tower contrastive objective to inject collaborative signals into tokenization. Experiments on public benchmarks and industrial data validate QuaSID. On public datasets, QuaSID consistently outperforms strong baselines, improving top-K ranking quality by 5.9% over the best baseline while increasing SID composition diversity. In an online A/B test on Kuaishou e-commerce with a 5% traffic split, QuaSID increases ranking GMV-S2 by 2.38% and improves completed orders on cold-start retrieval by up to 6.42%. Finally, we show that the proposed repulsion loss is plug-and-play and enhances a range of SID learning frameworks across datasets. --- ### LiTS: A Modular Framework for LLM Tree Search Authors: Xinzhe Li, Yaguang Tao Published: 2026-02-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.00631v2 LiTS is a modular Python framework for LLM reasoning via tree search. It decomposes tree search into three reusable components (Policy, Transition, and RewardModel) that plug into algorithms like MCTS and BFS. A decorator-based registry enables domain experts to extend to new domains by registering components, and algorithmic researchers to implement custom search algorithms. We demonstrate composability on MATH500 (language reasoning), Crosswords (environment planning), and MapEval (tool use), showing that components and algorithms are orthogonal: components are reusable across algorithms within each task type, and algorithms work across all components and domains. We also report a mode-collapse finding: in infinite action spaces, LLM policy diversity (not reward quality) is the bottleneck for effective tree search. A demonstration video is available at https://youtu.be/nRGX43YrR3I. The package is released under the Apache 2.0 license at https://github.com/xinzhel/lits-llm, including installation instructions and runnable examples that enable users to reproduce the demonstrated workflows. --- ### Adapt Data to Model: Adaptive Transformation Optimization for Domain-shared Time Series Foundation Models Authors: Yunzhong Qiu, Zhiyao Cen, Zhongyi Pei, Chen Wang, Jianmin Wang Published: 2026-02-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.00629v1 Large time series models (LTMs) have emerged as powerful tools for universal forecasting, yet they often struggle with the inherent diversity and nonstationarity of real-world time series data, leading to an unsatisfactory trade-off between forecasting accuracy and generalization. Rather than continually finetuning new LTM instances for each domain, we propose a data-centric framework, time-series adaptive transformation optimization (TATO), that enables a single frozen pre-trained LTM to adapt to diverse downstream domains through an optimally configured transformation pipeline. Specifically, TATO constructs three representative types of transformations, including context slicing, scale normalization, and outlier correction, to help LTMs better align with target domain characteristics. To ensure robustness, we incorporate carefully selected time series augmentations and a two-stage ranking mechanism that filters out pipelines underperforming on specific metrics. Extensive experiments on state-of-the-art LTMs and widely used datasets demonstrate that TATO consistently and significantly improves domain-adaptive forecasting performance, achieving a maximum reduction in MSE of 65.4\% and an average reduction of 13.6\%. Moreover, TATO is highly efficient, typically completing optimization in under 2 minutes, making it practical for real-world deployment. The source code is available at https://github.com/thulab/TATO. --- ### IDER: IDempotent Experience Replay for Reliable Continual Learning Authors: Zhanwang Liu, Yuting Li, Haoyuan Gao, Yexin Li, Linghe Kong, Lichao Sun, Weiran Huang Published: 2026-02-28 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.00624v2 Catastrophic forgetting, the tendency of neural networks to forget previously learned knowledge when learning new tasks, has been a major challenge in continual learning (CL). To tackle this challenge, CL methods have been proposed and shown to reduce forgetting. Furthermore, CL models deployed in mission-critical settings can benefit from uncertainty awareness by calibrating their predictions to reliably assess their confidences. However, existing uncertainty-aware continual learning methods suffer from high computational overhead and incompatibility with mainstream replay methods. To address this, we propose idempotent experience replay (IDER), a novel approach based on the idempotent property where repeated function applications yield the same output. Specifically, we first adapt the training loss to make model idempotent on current data streams. In addition, we introduce an idempotence distillation loss. We feed the output of the current model back into the old checkpoint and then minimize the distance between this reprocessed output and the original output of the current model. This yields a simple and effective new baseline for building reliable continual learners, which can be seamlessly integrated with other CL approaches. Extensive experiments on different CL benchmarks demonstrate that IDER consistently improves prediction reliability while simultaneously boosting accuracy and reducing forgetting. Our results suggest the potential of idempotence as a promising principle for deploying efficient and trustworthy continual learning systems in real-world applications.Our code is available at https://github.com/YutingLi0606/Idempotent-Continual-Learning. --- ### TraceSIR: A Multi-Agent Framework for Structured Analysis and Reporting of Agentic Execution Traces Authors: Shu-Xun Yang, Cunxiang Wang, Haoke Zhang, Wenbo Yu, Lindong Wu, Jiayi Gui, Dayong Yang, Yukuo Cen, Zhuoer Feng, Bosi Wen, Yidong Wang, Lucen Zhong et al. Published: 2026-02-28 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.00623v1 Agentic systems augment large language models with external tools and iterative decision making, enabling complex tasks such as deep research, function calling, and coding. However, their long and intricate execution traces make failure diagnosis and root cause analysis extremely challenging. Manual inspection does not scale, while directly applying LLMs to raw traces is hindered by input length limits and unreliable reasoning. Focusing solely on final task outcomes further discards critical behavioral information required for accurate issue localization. To address these issues, we propose TraceSIR, a multi-agent framework for structured analysis and reporting of agentic execution traces. TraceSIR coordinates three specialized agents: (1) StructureAgent, which introduces a novel abstraction format, TraceFormat, to compress execution traces while preserving essential behavioral information; (2) InsightAgent, which performs fine-grained diagnosis including issue localization, root cause analysis, and optimization suggestions; (3) ReportAgent, which aggregates insights across task instances and generates comprehensive analysis reports. To evaluate TraceSIR, we construct TraceBench, covering three real-world agentic scenarios, and introduce ReportEval, an evaluation protocol for assessing the quality and usability of analysis reports aligned with industry needs. Experiments show that TraceSIR consistently produces coherent, informative, and actionable reports, significantly outperforming existing approaches across all evaluation dimensions. Our project and video are publicly available at https://github.com/SHU-XUN/TraceSIR. --- ### Piecing Together Cross-Document Coreference Resolution Datasets: Systematic Dataset Analysis and Unification Authors: Anastasia Zhukova, Terry Ruas, Jan Philip Wahle, Bela Gipp Published: 2026-02-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.00621v2 Research in CDCR remains fragmented due to heterogeneous dataset formats, varying annotation standards, and the predominance of the CDCR definition as the event coreference resolution (ECR). To address these challenges, we introduce uCDCR, a unified dataset that consolidates diverse publicly available English CDCR corpora across various domains into a consistent format, which we analyze with standardized metrics and evaluation protocols. uCDCR incorporates both entity and event coreference, corrects known inconsistencies, and enriches datasets with missing attributes to facilitate reproducible research. We establish a cohesive framework for fair, interpretable, and cross-dataset analysis in CDCR and compare the datasets on their lexical properties, e.g., lexical composition of the annotated mentions, lexical diversity and ambiguity metrics, discuss the annotation rules and principles that lead to high lexical diversity, and examine how these metrics influence performance on the same-head-lemma baseline. Our dataset analysis shows that ECB+, the state-of-the-art benchmark for CDCR, has one of the lowest lexical diversities, and its CDCR complexity, measured by the same-head-lemma baseline, lies in the middle among all uCDCR datasets. Moreover, comparing document and mention distributions between ECB+ and uCDCR shows that using all uCDCR datasets for model training and evaluation will improve the generalizability of CDCR models. Finally, the almost identical performance on the same-head-lemma baseline, separately applied to events and entities, shows that resolving both types is a complex task and should not be steered toward ECR alone. The uCDCR dataset is available at https://huggingface.co/datasets/AnZhu/uCDCR, and the code for parsing, analyzing, and scoring the dataset is available at https://github.com/anastasia-zhukova/uCDCR. --- ### QQ: A Language Metadata Toolkit for Multilingual NLP Authors: Wessel Poelman, Yiyi Chen, Miryam de Lhoneux Published: 2026-02-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.00620v3 Multilingual NLP research increasingly involves hundreds or thousands of languages across different datasets. Managing, discovering, and reporting language metadata becomes a common hurdle at these scales. We present QQ, a metadata toolkit and browser explorer. QQ compiles language metadata sources into a graph of language varieties, scripts, regions, identifiers, names, and relations, and exposes it through a Python API, a command-line interface, and a browser-based explorer. Users can normalize identifiers, retrieve metadata, traverse relations, and discover which external resources contain a language. We demonstrate QQ on three workflows: an audit of the HuggingFace Hub, linking resources that use different identifier systems, and generating reproducible language-reporting tables. QQ supports FAIR-oriented metadata practices through versioning, open formats, and reusable interfaces. --- ### QQ: A Language Metadata Toolkit for Multilingual NLP Authors: Wessel Poelman, Yiyi Chen, Miryam de Lhoneux Published: 2026-02-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.00620v2 Multilingual NLP research increasingly involves hundreds or thousands of languages across different datasets. Managing, discovering, and reporting language metadata becomes a common hurdle at these scales. We present QQ, a metadata toolkit and browser explorer. QQ compiles language metadata sources into a graph of language varieties, scripts, regions, identifiers, names, and relations, and exposes it through a Python API, a command-line interface, and a browser-based explorer. Users can normalize identifiers, retrieve metadata, traverse relations, and discover which external resources contain a language. We demonstrate QQ on three workflows: an audit of the HuggingFace Hub, linking resources that use different identifier systems, and generating reproducible language-reporting tables. QQ supports FAIR-oriented metadata practices through versioning, open formats, and reusable interfaces. --- ### Multi-Domain Riemannian Graph Gluing for Building Graph Foundation Models Authors: Li Sun, Zhenhao Huang, Silei Chen, Lanxu Yang, Junda Ye, Sen Su, Philip S. Yu Published: 2026-02-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.00618v1 Multi-domain graph pre-training integrates knowledge from diverse domains to enhance performance in the target domains, which is crucial for building graph foundation models. Despite initial success, existing solutions often fall short of answering a fundamental question: how is knowledge integrated or transferred across domains? This theoretical limitation motivates us to rethink the consistency and transferability between model pre-training and domain adaptation. In this paper, we propose a fresh Riemannian geometry perspective, whose core idea is to merge any graph dataset into a unified, smooth Riemannian manifold, enabling a systematic understanding of knowledge integration and transfer. To achieve this, our key contribution is the theoretical establishment of neural manifold gluing, which first characterizes local geometry using an adaptive orthogonal frame and then "glues" the local pieces together into a coherent whole. Building on this theory, we present the GraphGlue framework, which supports batched pre-training with EMA prototyping and provides a transferability measure based on geometric consistence. Extensive experiments demonstrate its superior performance across diverse graph domains. Moreover, we empirically validated GraphGlue's geometric scaling law, showing that larger quantities of datasets improve model transferability by producing a smoother manifold. Codes are available at https://github.com/RiemannGraph/GraphGlue. --- ### From Literature to Hypotheses: An AI Co-Scientist System for Biomarker-Guided Drug Combination Hypothesis Generation Authors: Raneen Younis, Suvinava Basak, Lukas Chavez, Zahra Ahmadi Published: 2026-02-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.00612v1 The rapid growth of biomedical literature and curated databases has made it increasingly difficult for researchers to systematically connect biomarker mechanisms to actionable drug combination hypotheses. We present AI Co-Scientist (CoDHy), an interactive, human-in-the-loop system for biomarker-guided drug combination hypothesis generation in cancer research. CoDHy integrates structured biomedical databases and unstructured literature evidence into a task-specific knowledge graph, which serves as the basis for graph-based reasoning and hypothesis construction. The system combines knowledge graph embeddings with agent-based reasoning to generate, validate, and rank candidate drug combinations, while explicitly grounding each hypothesis in retrievable evidence. Through a web-based interface, users can configure the scientific context, inspect intermediate results, and iteratively refine hypotheses, enabling transparent and researcher-steerable exploration rather than automated decision-making. We demonstrate CoDHy as a system for exploratory hypothesis generation and decision support in translational oncology, highlighting its design, interaction workflow, and practical use cases. --- ### Exploring Spatiotemporal Feature Propagation for Video-Level Compressive Spectral Reconstruction: Dataset, Model and Benchmark Authors: Lijing Cai, Zhan Shi, Chenglong Huang, Jinyao Wu, Qiping Li, Zikang Huo, Linsen Chen, Chongde Zi, Xun Cao Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00611v1 Recently, Spectral Compressive Imaging (SCI) has achieved remarkable success, unlocking significant potential for dynamic spectral vision. However, existing reconstruction methods, primarily image-based, suffer from two limitations: (i) Encoding process masks spatial-spectral features, leading to uncertainty in reconstructing missing information from single compressed measurements, and (ii) The frame-by-frame reconstruction paradigm fails to ensure temporal consistency, which is crucial in the video perception. To address these challenges, this paper seeks to advance spectral reconstruction from the image level to the video level, leveraging the complementary features and temporal continuity across adjacent frames in dynamic scenes. Initially, we construct the first high-quality dynamic hyperspectral image dataset (DynaSpec), comprising 30 sequences obtained through frame-scanning acquisition. Subsequently, we propose the Propagation-Guided Spectral Video Reconstruction Transformer (PG-SVRT), which employs a spatial-then-temporal attention to effectively reconstruct spectral features from abundant video information, while using a bridged token to reduce computational complexity. Finally, we conduct simulation experiments to assess the performance of four SCI systems, and construct a DD-CASSI prototype for real-world data collection and benchmarking. Extensive experiments demonstrate that PG-SVRT achieves superior performance in reconstruction quality, spectral fidelity, and temporal consistency, while maintaining minimal FLOPs. Project page: https://github.com/nju-cite/DynaSpec --- ### CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction Authors: Yinghao Ma, Haiwen Xia, Hewei Gao, Weixiong Chen, Yuxin Ye, Yuchen Yang, Sungkyun Chang, Mingshuo Ding, Yizhi Li, Ruibin Yuan, Simon Dixon, Emmanouil Benetos Published: 2026-02-28 Categories: cs.SD, cs.AI, cs.LG, cs.MM, eess.AS arXiv: https://arxiv.org/abs/2603.00610v3 While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have lagged behind. In this paper, we bridge this critical gap by establishing a comprehensive ecosystem for music reward modeling under Compositional Multimodal Instruction (CMI), where the generated music may be conditioned on text descriptions, lyrics, and audio prompts. We first introduce CMI-Pref-Pseudo, a large-scale preference dataset comprising 110k pseudo-labeled samples, and CMI-Pref, a high-quality, human-annotated corpus tailored for fine-grained alignment tasks. To unify the evaluation landscape, we propose CMI-RewardBench, a unified benchmark that evaluates music reward models on heterogeneous samples across musicality, text-music alignment, and compositional instruction alignment. Leveraging these resources, we develop CMI reward models (CMI-RMs), a parameter-efficient reward model family capable of processing heterogeneous inputs. We evaluate their correlation with human judgment scores on musicality and alignment on CMI-Pref along with previous datasets. Further experiments demonstrate that CMI-RM not only correlates strongly with human judgments, but also enables effective inference-time scaling via top-k filtering. Code is available at GitHub (https://github.com/Haiwen-Xia/CMI-RewardBench). Model weights: CMI-RM (https://huggingface.co/HaiwenXia/CMI-RM). Datasets: CMI-Pref-Pseudo (https://huggingface.co/datasets/HaiwenXia/cmi-pref-pseudo) and CMI-Pref (https://huggingface.co/datasets/HaiwenXia/cmi-pref) --- ### Linking Modality Isolation in Heterogeneous Collaborative Perception Authors: Changxing Liu, Zichen Chao, Siheng Chen Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00609v1 Collaborative perception leverages data exchange among multiple agents to enhance overall perception capabilities. However, heterogeneity across agents introduces domain gaps that hinder collaboration, and this is further exacerbated by an underexplored issue: modality isolation. It arises when multiple agents with different modalities never co-occur in any training data frame, enlarging cross-modal domain gaps. Existing alignment methods rely on supervision from spatially overlapping observations, thus fail to handle modality isolation. To address this challenge, we propose CodeAlign, the first efficient, co-occurrence-free alignment framework that smoothly aligns modalities via cross-modal feature-code-feature(FCF) translation. The key idea is to explicitly identify the representation consistency through codebook, and directly learn mappings between modality-specific feature spaces, thereby eliminating the need for spatial correspondence. Codebooks regularize feature spaces into code spaces, providing compact yet expressive representations. With a prepared code space for each modality, CodeAlign learns FCF translations that map features to the corresponding codes of other modalities, which are then decoded back into features in the target code space, enabling effective alignment. Experiments show that, when integrating three modalities, CodeAlign requires only 8% of the training parameters of prior alignment methods, reduces communication load by 1024x, and achieves state-of-the-art perception performance on both OPV2V and DAIR-V2X dataset. Code will be released on https://github.com/cxliu0314/CodeAlign. --- ### Machine Learning Grade Prediction Using Students' Grades and Demographics Authors: Mwayi Sonkhanani, Symon Chibaya, Clement N. Nyirenda Published: 2026-02-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.00608v1 Student repetition in secondary education imposes significant resource burdens, particularly in resource-constrained contexts. Addressing this challenge, this study introduces a unified machine learning framework that simultaneously predicts pass/fail outcomes and continuous grades, a departure from prior research that treats classification and regression as separate tasks. Six models were evaluated: Logistic Regression, Decision Tree, and Random Forest for classification, and Linear Regression, Decision Tree Regressor, and Random Forest Regressor for regression, with hyperparameters optimized via exhaustive grid search. Using academic and demographic data from 4424 secondary school students, classification models achieved accuracies of up to 96%, while regression models attained a coefficient of determination of 0.70, surpassing baseline approaches. These results confirm the feasibility of early, data-driven identification of at-risk students and highlight the value of integrating dual-task prediction for more comprehensive insights. By enabling timely, personalized interventions, the framework offers a practical pathway to reducing grade repetition and optimizing resource allocation. --- ### IdGlow: Dynamic Identity Modulation for Multi-Subject Generation Authors: Honghao Cai, Xiangyuan Wang, Jing Li, Yunhao Bai, Tianze Zhou, Haohua Chen, Chao Hui, Changhao Qiao, Runqi Wang, Sijie Xu, Yuyang Hao, Zezhou Cui et al. Published: 2026-02-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.00607v2 Multi-subject image generation requires seamlessly harmonizing multiple reference identities within a coherent scene. However, existing methods relying on rigid spatial masks or localized attention often struggle with the "stability-plasticity dilemma," particularly failing in tasks that require complex structural deformations, such as identity-preserving age transformation. To address this, we present IdGlow, a mask-free, progressive two-stage framework built upon Flow Matching diffusion models. In the supervised fine-tuning (SFT) stage, we introduce task-adaptive timestep scheduling aligned with diffusion generative dynamics: a linear decay schedule that progressively relaxes constraints for natural group composition, and a temporal gating mechanism that concentrates identity injection within a critical semantic window, successfully preserving adult facial semantics without overriding child-like anatomical structures. To resolve attribute leakage and semantic ambiguity without explicit layout inputs, we further integrate a badcase-driven Vision-Language Model (VLM) for precise, context-aware prompt synthesis. In the second stage, we design a Fine-Grained Group-Level Direct Preference Optimization (DPO) with a weighted margin formulation to simultaneously eliminate multi-subject artifacts, elevate texture harmony, and recalibrate identity fidelity towards real-world distributions. Extensive experiments on two challenging benchmarks -- direct multi-person fusion and age-transformed group generation -- demonstrate that IdGlow fundamentally mitigates the stability-plasticity conflict, achieving a superior Pareto balance between state-of-the-art facial fidelity and commercial-grade aesthetic quality. --- ### Data-Centric Benchmark for Label Noise Estimation and Ranking in Remote Sensing Binary Building Segmentation Authors: Keiller Nogueira, Codrut-Andrei Diaconu, Dávid Kerekes, Jakob Gawlikowski, Cédric Léonard, Nassim Ait Ali Braham, June Moh Goo, Zichao Zeng, Zhipeng Liu, Pallavi Jain, Andrea Nascetti, Ronny Hänsch Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00604v2 High-quality pixel-level annotations are essential for the semantic segmentation of remote sensing imagery. However, such labels are expensive to obtain and often affected by noise due to the labor-intensive and time-consuming nature of pixel-wise annotation, which makes it challenging for human annotators to label every pixel accurately. Annotation errors can significantly degrade the performance and robustness of modern segmentation models, motivating the need for reliable mechanisms to identify and quantify noisy training samples. This paper introduces a novel data-centric benchmark, together with a new, publicly available binary building segmentation dataset. This specific task serves as a representative and practically relevant testbed that enables controlled experimentation with different annotation perturbations. Furthermore, we also introduce two techniques for identifying, quantifying, and ranking training samples according to their level of label noise in remote sensing semantic segmentation. Such proposed methods leverage complementary strategies based on model uncertainty, prediction consistency, and representation analysis, and consistently outperform established baselines across a range of experimental settings. The outcomes of this work are publicly available at https://github.com/keillernogueira/label_noise_segmentation. --- ### Data-Centric Benchmark for Label Noise Estimation and Ranking in Remote Sensing Image Segmentation Authors: Keiller Nogueira, Codrut-Andrei Diaconu, Dávid Kerekes, Jakob Gawlikowski, Cédric Léonard, Nassim Ait Ali Braham, June Moh Goo, Zichao Zeng, Zhipeng Liu, Pallavi Jain, Andrea Nascetti, Ronny Hänsch Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00604v1 High-quality pixel-level annotations are essential for the semantic segmentation of remote sensing imagery. However, such labels are expensive to obtain and often affected by noise due to the labor-intensive and time-consuming nature of pixel-wise annotation, which makes it challenging for human annotators to label every pixel accurately. Annotation errors can significantly degrade the performance and robustness of modern segmentation models, motivating the need for reliable mechanisms to identify and quantify noisy training samples. This paper introduces a novel Data-Centric benchmark, together with a novel, publicly available dataset and two techniques for identifying, quantifying, and ranking training samples according to their level of label noise in remote sensing semantic segmentation. Such proposed methods leverage complementary strategies based on model uncertainty, prediction consistency, and representation analysis, and consistently outperform established baselines across a range of experimental settings. The outcomes of this work are publicly available at https://github.com/keillernogueira/label_noise_segmentation. --- ### Learning to Explore: Policy-Guided Outlier Synthesis for Graph Out-of-Distribution Detection Authors: Li Sun, Lanxu Yang, Jiayu Tian, Bowen Fang, Xiaoyan Yu, Junda Ye, Peng Tang, Hao Peng, Philip S. Yu Published: 2026-02-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00602v1 Detecting out-of-distribution (OOD) graphs is crucial for ensuring the safety and reliability of Graph Neural Networks. In unsupervised graph-level OOD detection, models are typically trained using only in-distribution (ID) data, resulting in incomplete feature space characterization and weak decision boundaries. Although synthesizing outliers offers a promising solution, existing approaches rely on fixed, non-adaptive sampling heuristics (e.g., distance- or density-based), limiting their ability to explore informative OOD regions. We propose a Policy-Guided Outlier Synthesis (PGOS) framework that replaces static heuristics with a learned exploration strategy. Specifically, PGOS trains a reinforcement learning agent to navigate low-density regions in a structured latent space and sample representations that most effectively refine the OOD decision boundary. These representations are then decoded into high-quality pseudo-OOD graphs to improve detector robustness. Extensive experiments demonstrate that PGOS achieves state-of-the-art performance on multiple graph OOD and anomaly detection benchmarks. --- ### Theory of Code Space: Do Code Agents Understand Software Architecture? Authors: Grigory Sapunov Published: 2026-02-28 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.00601v4 AI code agents excel at isolated tasks yet struggle with multi-file software engineering requiring architectural understanding. We introduce Theory of Code Space (ToCS), a benchmark that evaluates whether agents can construct, maintain, and update coherent architectural beliefs during codebase exploration. Agents explore procedurally generated codebases under partial observability -- opening files under a budget -- and periodically externalize their belief state as structured JSON, producing a time-series of architectural understanding. Three findings emerge from experiments with four baselines and six frontier LLMs. First, the Active-Passive Gap is model-dependent: one model builds better maps through active exploration than from seeing all files at once, while another shows the opposite -- revealing that active exploration is itself a non-trivial capability absent from some models. Second, retaining structured belief maps in context acts as self-scaffolding for some models but not others, showing that the mechanism is model-dependent. Third, belief state maintenance varies dramatically: a smaller model maintains perfectly stable beliefs across probes while its larger sibling suffers catastrophic belief collapse -- forgetting previously-discovered components between probes. We release ToCS as open-source software. Code: https://github.com/che-shr-cat/tocs --- ### Heterophily-Agnostic Hypergraph Neural Networks with Riemannian Local Exchanger Authors: Li Sun, Ming Zhang, Wenxin Jin, Zhongtian Sun, Zhenhao Huang, Hao Peng, Sen Su, Philip Yu Published: 2026-02-28 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.00599v1 Hypergraphs are the natural description of higher-order interactions among objects, widely applied in social network analysis, cross-modal retrieval, etc. Hypergraph Neural Networks (HGNNs) have become the dominant solution for learning on hypergraphs. Traditional HGNNs are extended from message passing graph neural networks, following the homophily assumption, and thus struggle with the prevalent heterophilic hypergraphs that call for long-range dependence modeling. In this paper, we achieve heterophily-agnostic message passing through the lens of Riemannian geometry. The key insight lies in the connection between oversquashing and hypergraph bottleneck within the framework of Riemannian manifold heat flow. Building on this, we propose the novel idea of locally adapting the bottlenecks of different subhypergraphs. The core innovation of the proposed mechanism is the design of an adaptive local (heat) exchanger. Specifically, it captures the rich long-range dependencies via the Robin condition, and preserves the representation distinguishability via source terms, thereby enabling heterophily-agnostic message passing with theoretical guarantees. Based on this theoretical foundation, we present a novel Heat-Exchanger with Adaptive Locality for Hypergraph Neural Network (HealHGNN), designed as a node-hyperedge bidirectional systems with linear complexity in the number of nodes and hyperedges. Extensive experiments on both homophilic and heterophilic cases show that HealHGNN achieves the state-of-the-art performance. --- ### UNICBench: UNIfied Counting Benchmark for MLLM Authors: Chenggang Rong, Tao Han, Zhiyuan Zhao, Yaowu Fan, Jia Wan, Song Guo, Yuan Yuan, Junyu Gao Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00595v1 Counting is a core capability for multimodal large language models (MLLMs), yet there is no unified counting dataset to rigorously evaluate this ability across image, text, and audio. We present UNICBench, a unified multimodal, multi level counting benchmark and evaluation toolkit with accurate ground truth, deterministic numeric parsing, and stratified reporting. The corpus comprises 5,300 images (5,508 QA), 872 documents (5,888 QA), and 2,069 audio clips (2,905 QA), annotated with a three level capability taxonomy and difficulty tags. Under a standardized protocol with fixed splits/prompts/seeds and modality specific matching rules, we evaluate 45 state-of-the-art MLLMs across modalities. Results show strong performance on some basic counting tasks but significant gaps on reasoning and the hardest partitions, highlighting long-tail errors and substantial headroom for improving general counting. UNICBench offers a rigorous and comparable basis for measurement and a public toolkit to accelerate progress. --- ### LangGap: Diagnosing and Closing the Language Gap in Vision-Language-Action Models Authors: Yuchen Hou, Lin Zhao Published: 2026-02-28 Categories: cs.RO, cs.AI, cs.CL, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.00592v1 Vision-Language-Action (VLA) models achieve over 95% success on standard benchmarks. However, through systematic experiments, we find that current state-of-the-art VLA models largely ignore language instructions. Prior work lacks: (1) systematic semantic perturbation diagnostics, (2) a benchmark that forces language understanding by design, and (3) linguistically diverse training data. This paper constructs the LangGap benchmark, based on a four-dimensional semantic perturbation method -- varying instruction semantics while keeping the tabletop layout fixed -- revealing language understanding deficits in π0.5. Existing benchmarks like LIBERO assign only one task per layout, underutilizing available objects and target locations; LangGap fully diversifies pick-and-place tasks under identical layouts, forcing models to truly understand language. Experiments show that targeted data augmentation can partially close the language gap -- success rate improves from 0% to 90% with single-task training, and 0% to 28% with multi-task training. However, as semantic diversity of extended tasks increases, model learning capacity proves severely insufficient; even trained tasks perform poorly. This reveals a fundamental challenge for VLA models in understanding diverse language instructions -- precisely the long-term value of LangGap. --- ### Fair in Mind, Fair in Action? A Synchronous Benchmark for Understanding and Generation in UMLLMs Authors: Yiran Zhao, Lu Zhou, Xiaogang Xu, Zhe Liu, Jiafei Wu, Liming Fang Published: 2026-02-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.00590v1 As artificial intelligence (AI) is increasingly deployed across domains, ensuring fairness has become a core challenge. However, the field faces a "Tower of Babel'' dilemma: fairness metrics abound, yet their underlying philosophical assumptions often conflict, hindering unified paradigms-particularly in unified Multimodal Large Language Models (UMLLMs), where biases propagate systemically across tasks. To address this, we introduce the IRIS Benchmark, to our knowledge the first benchmark designed to synchronously evaluate the fairness of both understanding and generation tasks in UMLLMs. Enabled by our demographic classifier, ARES, and four supporting large-scale datasets, the benchmark is designed to normalize and aggregate arbitrary metrics into a high-dimensional "fairness space'', integrating 60 granular metrics across three dimensions-Ideal Fairness, Real-world Fidelity, and Bias Inertia & Steerability (IRIS). Through this benchmark, our evaluation of leading UMLLMs uncovers systemic phenomena such as the "generation gap'', individual inconsistencies like "personality splits'', and the "counter-stereotype reward'', while offering diagnostics to guide the optimization of their fairness capabilities. With its novel and extensible framework, the IRIS benchmark is capable of integrating evolving fairness metrics, ultimately helping to resolve the "Tower of Babel'' impasse. Project Page: https://iris-benchmark-web.vercel.app/ --- ### AlignVAR: Towards Globally Consistent Visual Autoregression for Image Super-Resolution Authors: Cencen Liu, Dongyang Zhang, Wen Yin, Jielei Wang, Tianyu Li, Ji Guo, Wenbo Jiang, Guoqing Wang, Guoming Lu Published: 2026-02-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.00589v2 Visual autoregressive (VAR) models have recently emerged as a promising alternative for image generation, offering stable training, non-iterative inference, and high-fidelity synthesis through next-scale prediction. This encourages the exploration of VAR for image super-resolution (ISR), yet its application remains underexplored and faces two critical challenges: locality-biased attention, which fragments spatial structures, and residual-only supervision, which accumulates errors across scales, severely compromises global consistency of reconstructed images. To address these issues, we propose AlignVAR, a globally consistent visual autoregressive framework tailored for ISR, featuring two key components: (1) Spatial Consistency Autoregression (SCA), which applies an adaptive mask to reweight attention toward structurally correlated regions, thereby mitigating excessive locality and enhancing long-range dependencies; and (2) Hierarchical Consistency Constraint (HCC), which augments residual learning with full reconstruction supervision at each scale, exposing accumulated deviations early and stabilizing the coarse-to-fine refinement process. Extensive experiments demonstrate that AlignVAR consistently enhances structural coherence and perceptual fidelity over existing generative methods, while delivering over 10x faster inference with nearly 50% fewer parameters than leading diffusion-based approaches, establishing a new paradigm for efficient ISR. --- ### Energy-Efficient Information Representation in MNIST Classification Using Biologically Inspired Learning Authors: Patrick Stricker, Florian Röhrbein, Andreas Knoblauch Published: 2026-02-28 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2603.00588v1 Efficient representation learning is essential for optimal information storage and classification. However, it is frequently overlooked in artificial neural networks (ANNs). This neglect results in networks that can become overparameterized by factors of up to 13, increasing redundancy and energy consumption. As the demand for large language models (LLMs) and their scale increase, these issues are further highlighted, raising significant ethical and environmental concerns. We analyze our previously developed biologically inspired learning rule using information-theoretic concepts, evaluating its efficiency on the MNIST classification task. The proposed rule, which emulates the brain's structural plasticity, naturally prevents overparameterization by optimizing synaptic usage and retaining only the essential number of synapses. Furthermore, it outperforms backpropagation (BP) in terms of efficiency and storage capacity. It also eliminates the need for pre-optimization of network architecture, enhances adaptability, and reflects the brain's ability to reserve 'space' for new memories. This approach advances scalable and energy-efficient AI and provides a promising framework for developing brain-inspired models that optimize resource allocation and adaptability. --- ### Unlearning Evaluation through Subset Statistical Independence Authors: Chenhao Zhang, Muxing Li, Feng Liu, Weitong Chen, Miao Xu Published: 2026-02-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.00587v1 Evaluating machine unlearning remains challenging, as existing methods typically require retraining reference models or performing membership inference attacks, both of which rely on prior access to training configuration or supervision labels, making them impractical in realistic scenarios. Motivated by the fact that most unlearning algorithms remove a small, random subset of the training data, we propose a subset-level evaluation framework based on statistical independence. Specifically, we design a tailored use of the Hilbert-Schmidt Independence Criterion to assess whether the model outputs on a given subset exhibit statistical dependence, without requiring model retraining or auxiliary classifiers. Our method provides a simple, standalone evaluation procedure that aligns with unlearning workflows. Extensive experiments demonstrate that our approach reliably distinguishes in-training from out-of-training subsets and clearly differentiates unlearning effectiveness, even when existing evaluations fall short. --- ### WildActor: Unconstrained Identity-Preserving Video Generation Authors: Qin Guo, Tianyu Yang, Xuanhua He, Fei Shen, Yong Zhang, Zhuoliang Kang, Xiaoming Wei, Dan Xu Published: 2026-02-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00586v2 Production-ready human video generation requires digital actors to maintain strictly consistent full-body identities across dynamic shots, viewpoints and motions, a setting that remains challenging for existing methods. Prior methods often suffer from face-centric behavior that neglects body-level consistency, or produce copy-paste artifacts where subjects appear rigid due to pose locking. We present Actor-18M, a large-scale human video dataset designed to capture identity consistency under unconstrained viewpoints and environments. Actor-18M comprises 1.6M videos with 18M corresponding human images, covering both arbitrary views and canonical three-view representations. Leveraging Actor-18M, we propose WildActor, a framework for any-view conditioned human video generation. We introduce an Asymmetric Identity-Preserving Attention mechanism coupled with a Viewpoint-Adaptive Monte Carlo Sampling strategy that iteratively re-weights reference conditions by marginal utility for balanced manifold coverage. Evaluated on the proposed Actor-Bench, WildActor consistently preserves body identity under diverse shot compositions, large viewpoint transitions, and substantial motions, surpassing existing methods in these challenging settings. --- ### MicroVerse: A Preliminary Exploration Toward a Micro-World Simulation Authors: Rongsheng Wang, Minghao Wu, Hongru Zhou, Zhihan Yu, Zhenyang Cai, Junying Chen, Benyou Wang Published: 2026-02-28 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.00585v1 Recent advances in video generation have opened new avenues for macroscopic simulation of complex dynamic systems, but their application to microscopic phenomena remains largely unexplored. Microscale simulation holds great promise for biomedical applications such as drug discovery, organ-on-chip systems, and disease mechanism studies, while also showing potential in education and interactive visualization. In this work, we introduce MicroWorldBench, a multi-level rubric-based benchmark for microscale simulation tasks. MicroWorldBench enables systematic, rubric-based evaluation through 459 unique expert-annotated criteria spanning multiple microscale simulation task (e.g., organ-level processes, cellular dynamics, and subcellular molecular interactions) and evaluation dimensions (e.g., scientific fidelity, visual quality, instruction following). MicroWorldBench reveals that current SOTA video generation models fail in microscale simulation, showing violations of physical laws, temporal inconsistency, and misalignment with expert criteria. To address these limitations, we construct MicroSim-10K, a high-quality, expert-verified simulation dataset. Leveraging this dataset, we train MicroVerse, a video generation model tailored for microscale simulation. MicroVerse can accurately reproduce complex microscale mechanism. Our work first introduce the concept of Micro-World Simulation and present a proof of concept, paving the way for applications in biology, education, and scientific visualization. Our work demonstrates the potential of educational microscale simulations of biological mechanisms. Our data and code are publicly available at https://github.com/FreedomIntelligence/MicroVerse --- ### Super Research: Answering Highly Complex Questions with Large Language Models through Super Deep and Super Wide Research Authors: Yubo Dong, Nianhao You, Yuxuan Hou, Zixun Sun, Yue Zhang, Liang Zhang, Siyuan Zhao, Hehe Fan Published: 2026-02-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.00582v2 While Large Language Models (LLMs) have demonstrated proficiency in Deep Research or Wide Search, their capacity to solve highly complex questions-those requiring long-horizon planning, massive evidence gathering, and synthesis across heterogeneous sources-remains largely unexplored. We introduce Super Research, a task for complex autonomous research tasks that integrates (i) structured decomposition into a research plan, (ii) super wide retrieval for diverse perspectives, and (iii) super deep investigation to resolve uncertainties through iterative queries. To evaluate this capability, we curated a benchmark of 300 expert-written questions across diverse domains, each requiring up to 100+ retrieval steps and 1,000+ web pages to reconcile conflicting evidence. Super Research produces verifiable reports with fine-grained citations and intermediate artifacts (e.g., outlines and tables) to ensure traceable reasoning. Furthermore, we present a graph-anchored auditing protocol that evaluates Super Research along five dimensions: Coverage, Logical Consistency, Report Utility, Objectivity and Citation Health. While super-complex questions may be infrequent in standard applications, Super Research serves as a critical ceiling evaluation and stress test for LLM capabilities. A model's proficiency within Super Research acts as a powerful proxy for its general research competence; success here suggests the robustness necessary to navigate nearly any subordinate research task. Leaderboard is available at: https://cnsdqd-dyb.github.io/Super-Research-Benchmark/ --- ### DeepAFL: Deep Analytic Federated Learning Authors: Jianheng Tang, Yajiang Huang, Kejia Fan, Feijiang Han, Jiaxu Li, Jinfeng Xu, Run He, Anfeng Liu, Houbing Herbert Song, Huiping Zhuang, Yunhuai Liu Published: 2026-02-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00579v1 Federated Learning (FL) is a popular distributed learning paradigm to break down data silo. Traditional FL approaches largely rely on gradient-based updates, facing significant issues about heterogeneity, scalability, convergence, and overhead, etc. Recently, some analytic-learning-based work has attempted to handle these issues by eliminating gradient-based updates via analytical (i.e., closed-form) solutions. Despite achieving superior invariance to data heterogeneity, these approaches are fundamentally limited by their single-layer linear model with a frozen pre-trained backbone. As a result, they can only achieve suboptimal performance due to their lack of representation learning capabilities. In this paper, to enable representable analytic models while preserving the ideal invariance to data heterogeneity for FL, we propose our Deep Analytic Federated Learning approach, named DeepAFL. Drawing inspiration from the great success of ResNet in gradient-based learning, we design gradient-free residual blocks in our DeepAFL with analytical solutions. We introduce an efficient layer-wise protocol for training our deep analytic models layer by layer in FL through least squares. Both theoretical analyses and empirical evaluations validate our DeepAFL's superior performance with its dual advantages in heterogeneity invariance and representation learning, outperforming state-of-the-art baselines by up to 5.68%-8.42% across three benchmark datasets. --- ### Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs Authors: Jie Cao, Tianwei Lin, Zhenxuan Fan, Bo Yuan, Ziyuan Zhao, Rolan Yan, Wenqiao Zhang, Siliang Tang Published: 2026-02-28 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.00578v1 Long chain-of-thought~(CoT) has become a dominant paradigm for enhancing the reasoning capability of large reasoning models~(LRMs); however, the performance gains often come with a substantial increase in reasoning budget. Recent studies show that existing CoT paradigms tend to induce systematic overthinking, unnecessarily coupling reasoning capability with reasoning cost. Most prior approaches reduce token usage through post hoc techniques such as token compression, truncation, or length penalties, without explicitly addressing the core mechanisms of reasoning. We propose \textbf{Draft-Thinking}, which guides models to first learn a concise \textit{draft-style} reasoning structure that retains only the critical reasoning steps. Through a \textit{progressive curriculum learning}, the model stably internalizes this efficient reasoning pattern as its capability scales. Moreover, Draft-Thinking introduces adaptive prompting, which elevates reasoning depth to a flexible, model-selectable behavior. Extensive experiments demonstrate that Draft-Thinking substantially reduces reasoning budget while largely preserving reasoning performance; for example, on MATH500, it achieves an 82.6\% reduction in reasoning budget at the cost of only a 2.6\% performance drop. --- ### Efficient Long-Sequence Diffusion Modeling for Symbolic Music Generation Authors: Jinhan Xu, Xing Tang, Houpeng Yang, Haoran Zhang, Shenghua Yuan, Jiatao Chen, Tianming Xi, Jing Wang, Jiaojiao Yu, Guangli Xiang Published: 2026-02-28 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2603.00576v1 Symbolic music generation is a challenging task in multimedia generation, involving long sequences with hierarchical temporal structures, long-range dependencies, and fine-grained local details. Though recent diffusion-based models produce high quality generations, they tend to suffer from high training and inference costs with long symbolic sequences due to iterative denoising and sequence-length-related costs. To deal with such problem, we put forth a diffusing strategy named SMDIM to combine efficient global structure construction and light local refinement. SMDIM uses structured state space models to capture long range musical context at near linear cost, and selectively refines local musical details via a hybrid refinement scheme. Experiments performed on a wide range of symbolic music datasets which encompass various Western classical music, popular music and traditional folk music show that the SMDIM model outperforms the other state-of-the-art approaches on both the generation quality and the computational efficiency, and it has robust generalization to underexplored musical styles. These results show that SMDIM offers a principled solution for long-sequence symbolic music generation, including associated attributes that accompany the sequences. We provide a project webpage with audio examples and supplementary materials at https://3328702107.github.io/smdim-music/. --- ### SWE-Hub: A Unified Production System for Scalable, Executable Software Engineering Tasks Authors: Yucheng Zeng, Shupeng Li, Daxiang Dong, Ruijie Xu, Zimo Chen, Liwei Zheng, Yuxuan Li, Zhe Zhou, Haotian Zhao, Lun Tian, Heng Xiao, Tianshu Zhu et al. Published: 2026-02-28 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2603.00575v1 Progress in software-engineering agents is increasingly constrained by the scarcity of executable, scalable, and realistic data for training and evaluation. This scarcity stems from three fundamental challenges in existing pipelines: environments are brittle and difficult to reproduce across languages; synthesizing realistic, system-level bugs at scale is computationally expensive; and existing data predominantly consists of short-horizon repairs, failing to capture long-horizon competencies like architectural consistency. We introduce \textbf{SWE-Hub}, an end-to-end system that operationalizes the data factory abstraction by unifying environment automation, scalable synthesis, and diverse task generation into a coherent production stack. At its foundation, the \textbf{Env Agent} establishes a shared execution substrate by automatically converting raw repository snapshots into reproducible, multi-language container environments with standardized interfaces. Built upon this substrate, \textbf{SWE-Scale} engine addresses the need for high-throughput generation, combining cross-language code analysis with cluster-scale validation to synthesize massive volumes of localized bug-fix instances. \textbf{Bug Agent} generates high-fidelity repair tasks by synthesizing system-level regressions involving cross-module dependencies, paired with user-like issue reports that describe observable symptoms rather than root causes. Finally, \textbf{SWE-Architect} expands the task scope from repair to creation by translating natural-language requirements into repository-scale build-a-repo tasks. By integrating these components, SWE-Hub establishes a unified production pipeline capable of continuously delivering executable tasks across the entire software engineering lifecycle. --- ### Decoupling Stability and Plasticity for Multi-Modal Test-Time Adaptation Authors: Yongbo He, Zirun Guo, Tao Jin Published: 2026-02-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.00574v2 Adapting pretrained multi-modal models to evolving test-time distributions, known as multi-modal test-time adaptation, presents a significant challenge. Existing methods frequently encounter negative transfer in the unbiased modality and catastrophic forgetting in the biased modality. To address these challenges, we propose Decoupling Adaptation for Stability and Plasticity (DASP), a novel diagnose-then-mitigate framework. Our analysis reveals a critical discrepancy within the unified latent space: the biased modality exhibits substantially higher interdimensional redundancy (i.e., strong correlations across feature dimensions) compared to the unbiased modality. Leveraging this insight, DASP identifies the biased modality and implements an asymmetric adaptation strategy. This strategy employs a decoupled architecture where each modality-specific adapter is divided into stable and plastic components. The asymmetric mechanism works as follows: for the biased modality, which requires plasticity, the plastic component is activated and updated to capture domain-specific information, while the stable component remains fixed. Conversely, for the unbiased modality, which requires stability, the plastic component is bypassed, and the stable component is updated using KL regularization to prevent negative transfer. This asymmetric design enables the model to adapt flexibly to new domains while preserving generalizable knowledge. Comprehensive evaluations on diverse multi-modal benchmarks demonstrate that DASP significantly outperforms state-of-the-art methods. --- ### CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging Authors: Jie Cao, Zhenxuan Fan, Zhuonan Wang, Tianwei Lin, Ziyuan Zhao, Rolan Yan, Wenqiao Zhang, Feifei Shao, Hongwei Wang, Jun Xiao, Siliang Tang Published: 2026-02-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.00573v2 Large language models (LLMs) achieve remarkable performance on diverse downstream and domain-specific tasks via parameter-efficient fine-tuning (PEFT). However, existing PEFT methods, particularly MoE-LoRA architectures, suffer from limited parameter efficiency and coarse-grained adaptation due to the proliferation of LoRA experts and instance-level routing. To address these issues, we propose Core Space Mixture of LoRA (\textbf{CoMoL}), a novel MoE-LoRA framework that incorporates expert diversity, parameter efficiency, and fine-grained adaptation. Specifically, CoMoL introduces two key components: core space experts and core space routing. Core space experts store each expert in a compact core matrix, preserving diversity while controlling parameter growth. Core space routing dynamically selects and activates the appropriate core experts for each token, enabling fine-grained, input-adaptive routing. Activated core experts are then merged via a soft-merging strategy into a single core expert, which is combined with a shared LoRA to form a specialized LoRA module. Besides, the routing network is projected into the same low-rank space as the LoRA matrices, further reducing parameter overhead without compromising expressiveness. Extensive experiments demonstrate that CoMoL retains the adaptability of MoE-LoRA architectures while achieving parameter efficiency comparable to standard LoRA, consistently outperforming existing methods across multiple tasks. --- ### TopoEdge: Topology-Grounded Agentic Framework for Edge Networking Code Generation and Repair Authors: Haomin Qi, Bohan Liu, Zihan Dai, Yunkai Gao Published: 2026-02-28 Categories: cs.SE, cs.LG, cs.NI arXiv: https://arxiv.org/abs/2603.00569v1 TopoEdge is a topology-grounded, edge-deployable framework for end-to-end software-defined networking (SDN) configuration generation and repair, motivated by the brittleness of configuration artefacts under topology variation and by strict operational constraints on latency, privacy, and on-site execution. TopoEdge represents each target topology as a router-level graph and embeds it using a contrastively trained graph neural network (GNN), enabling nearest-neighbour retrieval of a verified reference configuration paired with an executable Python driver (a Topotest/pytest test script that orchestrates the emulated network and checks protocol assertions). The target topology, retrieved reference topology, and reference driver are assembled into a topology-grounded retrieval-augmented generation context (TopoRAG), which grounds a distributed, execution-centric generate--verify--repair loop coordinated by a central controller and realised by three role-specialised agents: (i) a Planning agent that produces a topology-consistent configuration plan and a per-device skeleton; (ii) a Generation agent that materialises executable configuration artefacts, including device configurations and the driver; and (iii) a Verification agent that runs the FRRouting Topotest/pytest harness, compresses failures into a compact trace, and emits localised patch directives for iterative repair. --- ### Enhancing Molecular Property Predictions by Learning from Bond Modelling and Interactions Authors: Yunqing Liu, Yi Zhou, Wenqi Fan Published: 2026-02-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00568v1 Molecule representation learning is crucial for understanding and predicting molecular properties. However, conventional atom-centric models, which treat chemical bonds merely as pairwise interactions, often overlook complex bond-level phenomena like resonance and stereoselectivity. This oversight limits their predictive accuracy for nuanced chemical behaviors. To address this limitation, we introduce \textbf{DeMol}, a dual-graph framework whose architecture is motivated by a rigorous information-theoretic analysis demonstrating the information gain from a bond-centric perspective. DeMol explicitly models molecules through parallel atom-centric and bond-centric channels. These are synergistically fused by multi-scale Double-Helix Blocks designed to learn intricate atom-atom, atom-bond, and bond-bond interactions. The framework's geometric consistency is further enhanced by a regularization term based on covalent radii to enforce chemically plausible structures. Comprehensive evaluations on diverse benchmarks, including PCQM4Mv2, OC20 IS2RE, QM9, and MoleculeNet, show that DeMol establishes a new state-of-the-art, outperforming existing methods. These results confirm the superiority of explicitly modelling bond information and interactions, paving the way for more robust and accurate molecular machine learning. --- ### Learning to Attack: A Bandit Approach to Adversarial Context Poisoning Authors: Ray Telikani, Amir H. Gandomi Published: 2026-02-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00567v1 Neural contextual bandits are vulnerable to adversarial attacks, where subtle perturbations to rewards, actions, or contexts induce suboptimal decisions. We introduce AdvBandit, a black-box adaptive attack that formulates context poisoning as a continuous-armed bandit problem, enabling the attacker to jointly learn and exploit the victim's evolving policy. The attacker requires no access to the victim's internal parameters, reward function, or gradient information; instead, it constructs a surrogate model using a maximum-entropy inverse reinforcement learning module from observed context-action pairs and optimizes perturbations against this surrogate using projected gradient descent. An upper confidence bound-aware Gaussian process guides arm selection. An attack-budget control mechanism is also introduced to limit detection risk and overhead. We provide theoretical guarantees, including sublinear attacker regret and lower bounds on victim regret linear in the number of attacks. Experiments on three real-world datasets (Yelp, MovieLens, and Disin) against various victim contextual bandits demonstrate that our attack model achieves higher cumulative victim regret than state-of-the-art baselines. ---