# Research Papers — 2026-03 · bundle page 241 of 243 > Full-text markdown of papers #12001–12050 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03/page/241 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/240.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/242.md) ### DIVA-GRPO: Enhancing Multimodal Reasoning through Difficulty-Adaptive Variant Advantage Authors: Haowen Gao, Zhenyu Zhang, Liang Pang, Fangda Guo, Hongjian Dou, Guannan Lv, Shaoguo Liu, Tingting Gao, Huawei Shen, Xueqi Cheng Published: 2026-03-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.01106v1 Reinforcement learning (RL) with group relative policy optimization (GRPO) has become a widely adopted approach for enhancing the reasoning capabilities of multimodal large language models (MLLMs). While GRPO enables long-chain reasoning without a critic, it often suffers from sparse rewards on difficult problems and advantage vanishing when group-level rewards are too consistent for overly easy or hard problems. Existing solutions (sample expansion, selective utilization, and indirect reward design) often fail to maintain enough variance in within-group reward distributions to yield clear optimization signals. To address this, we propose DIVA-GRPO, a difficulty-adaptive variant advantage method that adjusts variant difficulty distributions from a global perspective. DIVA-GRPO dynamically assesses problem difficulty, samples variants with appropriate difficulty levels, and calculates advantages across local and global groups using difficulty-weighted and normalized scaling. This alleviates reward sparsity and advantage vanishing while improving training stability. Extensive experiments on six reasoning benchmarks demonstrate that DIVA-GRPO outperforms existing approaches in training efficiency and reasoning performance. Code: https://github.com/Siaaaaaa1/DIVA-GRPO --- ### Egocentric Co-Pilot: Web-Native Smart-Glasses Agents for Assistive Egocentric AI Authors: Sicheng Yang, Yukai Huang, Weitong Cai, Shitong Sun, Fengyi Fang, You He, Yiqiao Xie, Jiankang Deng, Hang Zhang, Jifei Song, Zhensong Zhang Published: 2026-03-01 Categories: cs.HC, cs.AI, cs.CV, cs.CY arXiv: https://arxiv.org/abs/2603.01104v1 What if accessing the web did not require a screen, a stable desk, or even free hands? For people navigating crowded cities, living with low vision, or experiencing cognitive overload, smart glasses coupled with AI agents could turn the web into an always-on assistive layer over daily life. We present Egocentric Co-Pilot, a web-native neuro-symbolic framework that runs on smart glasses and uses a Large Language Model (LLM) to orchestrate a toolbox of perception, reasoning, and web tools. An egocentric reasoning core combines Temporal Chain-of-Thought with Hierarchical Context Compression to support long-horizon question answering and decision support over continuous first-person video, far beyond a single model's context window. Additionally, a lightweight multimodal intent layer maps noisy speech and gaze into structured commands. We further implement and evaluate a cloud-native WebRTC pipeline integrating streaming speech, video, and control messages into a unified channel for smart glasses and browsers. In parallel, we deploy an on-premise WebSocket baseline, exposing concrete trade-offs between local inference and cloud offloading in terms of latency, mobility, and resource use. Experiments on Egolife and HD-EPIC demonstrate competitive or state-of-the-art egocentric QA performance, and a human-in-the-loop study on smart glasses shows higher task completion and user satisfaction than leading commercial baselines. Taken together, these results indicate that web-connected egocentric co-pilots can be a practical path toward more accessible, context-aware assistance in everyday life. By grounding operation in web-native communication primitives and modular, auditable tool use, Egocentric Co-Pilot offers a concrete blueprint for assistive, always-on web agents that support education, accessibility, and social inclusion for people who may benefit most from contextual, egocentric AI. --- ### Data-Efficient Brushstroke Generation with Diffusion Models for Oil Painting Authors: Dantong Qin, Alessandro Bozzon, Xian Yang, Xun Zhang, Yike Guo, Pan Wang Published: 2026-03-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.01103v1 Many creative multimedia systems are built upon visual primitives such as strokes or textures, which are difficult to collect at scale and fundamentally different from natural image data. This data scarcity makes it challenging for modern generative models to learn expressive and controllable primitives, limiting their use in process-aware content creation. In this work, we study the problem of learning human-like brushstroke generation from a small set of hand-drawn samples (n=470) and propose StrokeDiff, a diffusion-based framework with Smooth Regularization (SmR). SmR injects stochastic visual priors during training, providing a simple mechanism to stabilize diffusion models under sparse supervision without altering the inference process. We further show how the learned primitives can be made controllable through a Bézier-based conditioning module and integrated into a complete stroke-based painting pipeline, including prediction, generation, ordering, and compositing. This demonstrates how data-efficient primitive modeling can support expressive and structured multimedia content creation. Experiments indicate that the proposed approach produces diverse and structurally coherent brushstrokes and enables paintings with richer texture and layering, validated by both automatic metrics and human evaluation. --- ### Structure-preserving Randomized Neural Networks for Incompressible Magnetohydrodynamics Equations Authors: Yunlong Li, Fei Wang, Lingxiao Li Published: 2026-03-01 Categories: physics.flu-dyn, cs.LG, math.NA arXiv: https://arxiv.org/abs/2603.01102v1 The incompressible magnetohydrodynamic (MHD) equations are fundamental in many scientific and engineering applications. However, their strong nonlinearity and dual divergence-free constraints make them highly challenging for conventional numerical solvers. To overcome these difficulties, we propose a Structure-Preserving Randomized Neural Network (SP-RaNN) that automatically and exactly satisfies the divergence-free conditions. Unlike deep neural network (DNN) approaches that rely on expensive nonlinear and nonconvex optimization, SP-RaNN reformulates the training process into a linear least-squares system, thereby eliminating nonconvex optimization. The method linearizes the governing equations through Picard or Newton iterations, discretizes them at collocation points within the domain and on the boundaries using finite-difference schemes, and solves the resulting linear system via a linear least-squares procedure. By design, SP-RaNN preserves the intrinsic mathematical structure of the equations within a unified space-time framework, ensuring both stability and accuracy. Numerical experiments on the Navier-Stokes, Maxwell, and MHD equations demonstrate that SP-RaNN achieves higher accuracy, faster convergence, and exact enforcement of divergence-free constraints compared with both traditional numerical methods and DNN-based approaches. This structure-preserving framework provides an efficient and reliable tool for solving complex PDE systems while rigorously maintaining their underlying physical laws. --- ### SyncTrack: Rhythmic Stability and Synchronization in Multi-Track Music Generation Authors: Hongrui Wang, Fan Zhang, Zhiyuan Yu, Ziya Zhou, Xi Chen, Can Yang, Yang Wang Published: 2026-03-01 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2603.01101v1 Multi-track music generation has garnered significant research interest due to its precise mixing and remixing capabilities. However, existing models often overlook essential attributes such as rhythmic stability and synchronization, leading to a focus on differences between tracks rather than their inherent properties. In this paper, we introduce SyncTrack, a synchronous multi-track waveform music generation model designed to capture the unique characteristics of multi-track music. SyncTrack features a novel architecture that includes track-shared modules to establish a common rhythm across all tracks and track-specific modules to accommodate diverse timbres and pitch ranges. Each track-shared module employs two cross-track attention mechanisms to synchronize rhythmic information, while each track-specific module utilizes learnable instrument priors to better represent timbre and other unique features. Additionally, we enhance the evaluation of multi-track music quality by introducing rhythmic consistency through three novel metrics: Inner-track Rhythmic Stability (IRS), Cross-track Beat Synchronization (CBS), and Cross-track Beat Dispersion (CBD). Experiments demonstrate that SyncTrack significantly improves the multi-track music quality by enhancing rhythmic consistency. --- ### HeroGS: Hierarchical Guidance for Robust 3D Gaussian Splatting under Sparse Views Authors: Jiashu Li, Xumeng Han, Zhaoyang Wei, Zipeng Wang, Kuiran Wang, Guorong Li, Zhenjun Han, Jianbin Jiao Published: 2026-03-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.01099v2 3D Gaussian Splatting (3DGS) has recently emerged as a promising approach in novel view synthesis, combining photorealistic rendering with real-time efficiency. However, its success heavily relies on dense camera coverage; under sparse-view conditions, insufficient supervision leads to irregular Gaussian distributions, characterized by globally sparse coverage, blurred background, and distorted high-frequency areas. To address this, we propose HeroGS, Hierarchical Guidance for Robust 3D Gaussian Splatting, a unified framework that establishes hierarchical guidance across the image, feature, and parameter levels. At the image level, sparse supervision is converted into pseudo-dense guidance, globally regularizing the Gaussian distributions and forming a consistent foundation for subsequent optimization. Building upon this, Feature-Adaptive Densification and Pruning (FADP) at the feature level leverages low-level features to refine high-frequency details and adaptively densifies Gaussians in background regions. The optimized distributions then support Co-Pruned Geometry Consistency (CPG) at parameter level, which guides geometric consistency through parameter freezing and co-pruning, effectively removing inconsistent splats. The hierarchical guidance strategy effectively constrains and optimizes the overall Gaussian distributions, thereby enhancing both structural fidelity and rendering quality. Extensive experiments demonstrate that HeroGS achieves high-fidelity reconstructions and consistently surpasses state-of-the-art baselines under sparse-view conditions. --- ### Differential privacy representation geometry for medical image analysis Authors: Soroosh Tayebi Arasteh, Marziyeh Mohammadi, Sven Nebelung, Daniel Truhn Published: 2026-03-01 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.01098v3 Differential privacy (DP)'s effect in medical imaging is typically evaluated only through end-to-end performance, leaving the mechanism of privacy-induced utility loss unclear. We introduce Differential Privacy Representation Geometry for Medical Imaging (DP-RGMI), a framework that interprets DP as a structured transformation of representation space and decomposes performance degradation into encoder geometry and task-head utilization. Geometry is quantified by representation displacement from initialization and spectral effective dimension, while utilization is measured as the gap between linear-probe and end-to-end utility. Across over 594,000 images from four chest X-ray datasets and multiple pretrained initializations, we show that DP is consistently associated with a utilization gap even when linear separability is largely preserved. At the same time, displacement and spectral dimension exhibit non-monotonic, initialization- and dataset-dependent reshaping, indicating that DP alters representation anisotropy rather than uniformly collapsing features. Correlation analysis reveals that the association between end-to-end performance and utilization is robust across datasets but can vary by initialization, while geometric quantities capture additional prior- and dataset-conditioned variation. These findings position DP-RGMI as a reproducible framework for diagnosing privacy-induced failure modes and informing privacy model selection. --- ### Differential privacy representation geometry for medical image analysis Authors: Soroosh Tayebi Arasteh, Marziyeh Mohammadi, Sven Nebelung, Daniel Truhn Published: 2026-03-01 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.01098v2 Differential privacy (DP)'s effect in medical imaging is typically evaluated only through end-to-end performance, leaving the mechanism of privacy-induced utility loss unclear. We introduce Differential Privacy Representation Geometry for Medical Imaging (DP-RGMI), a framework that interprets DP as a structured transformation of representation space and decomposes performance degradation into encoder geometry and task-head utilization. Geometry is quantified by representation displacement from initialization and spectral effective dimension, while utilization is measured as the gap between linear-probe and end-to-end utility. Across over 594,000 images from four chest X-ray datasets and multiple pretrained initializations, we show that DP is consistently associated with a utilization gap even when linear separability is largely preserved. At the same time, displacement and spectral dimension exhibit non-monotonic, initialization- and dataset-dependent reshaping, indicating that DP alters representation anisotropy rather than uniformly collapsing features. Correlation analysis reveals that the association between end-to-end performance and utilization is robust across datasets but can vary by initialization, while geometric quantities capture additional prior- and dataset-conditioned variation. These findings position DP-RGMI as a reproducible framework for diagnosing privacy-induced failure modes and informing privacy model selection. --- ### Understanding LoRA as Knowledge Memory: An Empirical Analysis Authors: Seungju Back, Dongwoo Lee, Naun Kang, Taehee Lee, S. K. Hong, Youngjune Gwon, Sungjin Ahn Published: 2026-03-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.01097v5 Continuous knowledge updating for pre-trained large language models (LLMs) is increasingly necessary yet remains challenging. Although inference-time methods like In-Context Learning (ICL) and Retrieval-Augmented Generation (RAG) are popular, they face constraints in context budgets, costs, and retrieval fragmentation. Departing from these context-dependent paradigms, this work investigates a parametric approach using Low-Rank Adaptation (LoRA) as a modular knowledge memory. Although few recent works examine this concept, the fundamental mechanics governing its capacity and composability remain largely unexplored. We bridge this gap through the first systematic empirical study mapping the design space of LoRA-based memory, ranging from characterizing storage capacity and optimizing internalization to scaling multi-module systems and evaluating long-context reasoning. Rather than proposing a single architecture, we provide practical guidance on the operational boundaries of LoRA memory. Overall, our findings position LoRA as the complementary axis of memory alongside RAG and ICL, offering distinct advantages. --- ### Unified Vision-Language Modeling via Concept Space Alignment Authors: Yifu Qiu, Paul-Ambroise Duquenne, Holger Schwenk Published: 2026-03-01 Categories: cs.CV, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.01096v1 We introduce V-SONAR, a vision-language embedding space extended from the text-only embedding space SONAR (Omnilingual Embeddings Team et al., 2026), which supports 1500 text languages and 177 speech languages. To construct V-SONAR, we propose a post-hoc alignment pipeline that maps the representations of an existing vision encoder into the SONAR space. We thoroughly evaluate V-SONAR and show that its embeddings achieve competitive performance on text-to-video retrieval. Equipped with the OMNISONAR text decoder, V-SONAR further surpasses state-of-the-art vision-language models on video captioning tasks, including DREAM-1K (BLEU 23.9 vs. 19.6) and PE-VIDEO (BLEU 39.0 vs. 30.0). Leveraging V-SONAR, we first demonstrate that the Large Concept Model (LCM; LCM team et al. 2024) operating in SONAR and trained with English text only, can perform both single- and multi-visual concept understanding in a zero-shot manner. Finally, we introduce V-LCM, which extends the LCM with vision-language instruction tuning. V-LCM encodes vision and language inputs into an unified sequence of latent embeddings via V-SONAR and SONAR, and it is trained with the same latent diffusion objective for next-embedding prediction as in LCM's text-only pre-training. Experiments on a large-scale multilingual and -modal instruction-tuning data mixture highlight the potential of V-LCM: V-LCM matches state-of-the-art vision-language models on tasks covering image/video captioning and question answering, while significantly outperforming them across 61 rich- to low-resource languages out of all 62 tested languages. --- ### Adaptive-Growth Randomized Neural Networks for Level-Set Computation of Multivalued Nonlinear First-Order PDEs with Hyperbolic Characteristics Authors: Haoning Dang, Shi Jin, Fei Wang Published: 2026-03-01 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2603.01093v1 This paper proposes an Adaptive-Growth Randomized Neural Network (AG-RaNN) method for computing multivalued solutions of nonlinear first-order PDEs with hyperbolic characteristics, including quasilinear hyperbolic balance laws and Hamilton--Jacobi equations. Such solutions arise in geometric optics, seismic waves, semiclassical limit of quantum dynamics and high frequency limit of linear waves, and differ markedly from the viscosity or entropic solutions. The main computational challenges lie in that the solutions are no longer functions, and become union of multiple branches, after the formation of singularities. Level-set formulations offer a systematic alternative by embedding the nonlinear dynamics into linear transport equations posed in an augmented phase space, at the price of substantially increased dimensionality. To alleviate this computational burden, we combine AG-RaNN with an adaptive collocation strategy that concentrates samples in a tubular neighborhood of the zero level set, together with a layer-growth mechanism that progressively enriches the randomized feature space. Under standard regularity assumptions on the transport field and the characteristic flow, we establish a convergence result for the AG-RaNN approximation of the level-set equations. Numerical experiments demonstrate that the proposed method can efficiently recover multivalued structures and resolve nonsmooth features in high-dimensional settings. --- ### The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions Authors: Alejandro H. Artiles, Martin Weiss, Levin Brinkmann, Iyad Rahwan, Bernhard Schölkopf, Christopher Pal, Hugo Larochelle, Anirudh Goyal, Nasim Rahaman Published: 2026-03-01 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.01092v2 Scientific discovery is constrained not only by what is true, but by what is cognitively available to the researchers currently exploring a field. Many directions are coherent in light of the literature yet unlikely to be proposed because no existing community occupies the right combination of concepts, methods, and intuitions. Modern language models inherit this bias, recombining high-density regions of the literature when prompted for novel ideas. We introduce a framework that targets the complementary region, which we call the alien space of science, where directions are plausible under the structure of existing knowledge but unlikely under the distribution of existing researchers. Our method first decomposes papers into granular conceptual units and clusters them into a shared vocabulary of idea atoms. It then learns two complementary models over this vocabulary. A coherence model scores whether a combination of atoms forms a viable research direction, and an availability model scores whether any existing author community is positioned to produce a given combination. Sampling alien directions then reduces to ranking atom combinations that maximize coherence while minimizing availability. On a corpus of 16,068 peer-reviewed LLM papers from NeurIPS, ICLR, ICML, and major NLP venues, the resulting sampler explores a 3.5 - 7 x broader effective atom vocabulary than frontier LLM ideation baselines without sacrificing coherence, and produces ideas that match or exceed those baselines under blind LLM, human, and downstream experimental evaluation. By separating scientific plausibility from community availability, our framework points toward AI ideation that complements rather than merely accelerates human science, expanding exploration into coherent directions that the current community may overlook. --- ### CARD: Towards Conditional Design of Multi-agent Topological Structures Authors: Tongtong Wu, Yanming Li, Ziye Tang, Chen Jiang, Linhao Luo, Guilin Qi, Shirui Pan, Gholamreza Haffari Published: 2026-03-01 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.01089v1 Large language model (LLM)-based multi-agent systems have shown strong capabilities in tasks such as code generation and collaborative reasoning. However, the effectiveness and robustness of these systems critically depend on their communication topology, which is often fixed or statically learned, ignoring real-world dynamics such as model upgrades, API (or tool) changes, or knowledge source variability. To address this limitation, we propose CARD (Conditional Agentic Graph Designer), a conditional graph-generation framework that instantiates AMACP, a protocol for adaptive multi-agent communication. CARD explicitly incorporates dynamic environmental signals into graph construction, enabling topology adaptation at both training and runtime. Through a conditional variational graph encoder and environment-aware optimization, CARD produces communication structures that are both effective and resilient to shifts in model capability or resource availability. Empirical results on HumanEval, MATH, and MMLU demonstrate that CARD consistently outperforms static and prompt-based baselines, achieving higher accuracy and robustness across diverse conditions. The source code is available at: https://github.com/Warma10032/CARD. --- ### Can Vision Language Models Assess Graphic Design Aesthetics? A Benchmark, Evaluation, and Dataset Perspective Authors: Arctanx An, Shizhao Sun, Danqing Huang, Mingxi Cheng, Yan Gao, Ji Li, Yu Qiao, Jiang Bian Published: 2026-03-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.01083v1 Assessing the aesthetic quality of graphic design is central to visual communication, yet remains underexplored in vision language models (VLMs). We investigate whether VLMs can evaluate design aesthetics in ways comparable to humans. Prior work faces three key limitations: benchmarks restricted to narrow principles and coarse evaluation protocols, a lack of systematic VLM comparisons, and limited training data for model improvement. In this work, we introduce AesEval-Bench, a comprehensive benchmark spanning four dimensions, twelve indicators, and three fully quantifiable tasks: aesthetic judgment, region selection, and precise localization. Then, we systematically evaluate proprietary, open-source, and reasoning-augmented VLMs, revealing clear performance gaps against the nuanced demands of aesthetic assessment. Moreover, we construct a training dataset to fine-tune VLMs for this domain, leveraging human-guided VLM labeling to produce task labels at scale and indicator-grounded reasoning to tie abstract indicators to concrete design regions.Together, our work establishes the first systematic framework for aesthetic quality assessment in graphic design. Our code and dataset will be released at: \href{https://github.com/arctanxarc/AesEval-Bench}{https://github.com/arctanxarc/AesEval-Bench} --- ### Beyond Global Similarity: Towards Fine-Grained, Multi-Condition Multimodal Retrieval Authors: Xuan Lu, Kangle Li, Haohang Huang, Rui Meng, Wenjun Zeng, Xiaoyu Shen Published: 2026-03-01 Categories: cs.CV, cs.IR arXiv: https://arxiv.org/abs/2603.01082v1 Recent advances in multimodal large language models (MLLMs) have substantially expanded the capabilities of multimodal retrieval, enabling systems to align and retrieve information across visual and textual modalities. Yet, existing benchmarks largely focus on coarse-grained or single-condition alignment, overlooking real-world scenarios where user queries specify multiple interdependent constraints across modalities. To bridge this gap, we introduce MCMR (Multi-Conditional Multimodal Retrieval): a large-scale benchmark designed to evaluate fine-grained, multi-condition cross-modal retrieval under natural-language queries. MCMR spans five product domains: upper and bottom clothing, jewelry, shoes, and furniture. It also preserves rich long-form metadata essential for compositional matching. Each query integrates complementary visual and textual attributes, requiring models to jointly satisfy all specified conditions for relevance. We benchmark a diverse suite of MLLM-based multimodal retrievers and vision-language rerankers to assess their condition-aware reasoning abilities. Experimental results reveal: (i) distinct modality asymmetries across models; (ii) visual cues dominate early-rank precision, while textual metadata stabilizes long-tail ordering; and (iii) MLLM-based pointwise rerankers markedly improve fine-grained matching by explicitly verifying query-candidate consistency. Overall, MCMR establishes a challenging and diagnostic benchmark for advancing multimodal retrieval toward compositional, constraint-aware, and interpretable understanding. Our code and dataset is available at https://github.com/EIT-NLP/MCMR --- ### Super-resolution of turbulent reacting flows on complex meshes using graph neural networks Authors: Priyabrat Dash, Konduri Aditya, Christos E. Frouzakis, Mathis Bode Published: 2026-03-01 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2603.01080v1 State-of-the-art deep learning models have been extensively utilized to reconstruct small-scale structures from coarse-grained data in turbulent flows. However, their application has predominantly been restricted to structured uniform meshes, limiting their applicability to data associated with complex geometries that are typically simulated on structured non-uniform or unstructured meshes. Machine learning (ML) models based on graph neural networks (GNNs), known for their ability to process unstructured data, offer a promising alternative. In this study, we leverage the inherent flexibility of GNNs featuring message passing layers to develop a methodology for reconstructing unresolved small-scale structures from low-resolution data on complex meshes. The accuracy of the proposed approach is demonstrated using two cases: a reacting channel flow on a structured non-uniform mesh, and a reacting hydrogen fueled internal combustion (IC) engine featuring an unstructured mesh. Evaluation of results based on visual agreement, statistical metrics, and cumulative error reduction indicates the effectiveness of the method in accurately reconstructing fine-scale features. Overall, this study provides a pathway for integrating data-driven small-scale reconstruction and subgrid-scale modeling to enhance the accuracy of coarse-grained simulations on complex meshes. --- ### Kernel Methods for Stochastic Dynamical Systems with Application to Koopman Eigenfunctions: Feynman-Kac Representations and RKHS Approximation Authors: Boumediene Hamzi, Houman Owhadi, Umesh Vaidya Published: 2026-03-01 Categories: math.DS, eess.SY, math.NA, stat.ML arXiv: https://arxiv.org/abs/2603.01077v1 We extend the unified kernel framework for transport equations and Koopman eigenfunctions, developed in previous work by the authors for deterministic systems, to stochastic differential equations (SDEs). In the deterministic setting, three analytically grounded constructions-Lions-type variational principles, Green's function convolution, and resolvent operators along characteristic flows--were shown to yield identical reproducing kernels. For stochastic systems, the Koopman generator includes a second-order diffusion term, transforming the first-order hyperbolic transport equation into a second-order elliptic-parabolic PDE. This fundamental change necessitates replacing the method of characteristics with probabilistic representations based on the Feynman--Kac formula. Our main contributions include: (i) extension of all three kernel constructions to stochastic systems via Feynman--Kac path-integral representations; (ii) proof of kernel equivalence under uniform ellipticity assumptions; (iii) a collocation-based computational framework incorporating second-order differential operators; (iv) error bounds separating RKHS approximation error from Monte Carlo sampling error; (v) analysis of how diffusion affects numerical conditioning; and (vi) connections to generator EDMD, diffusion maps, and kernel analog forecasting. Numerical experiments on Ornstein--Uhlenbeck processes, nonlinear SDEs with varying diffusion strength, and multi-dimensional systems validate the theoretical developments and demonstrate that moderate diffusion can improve numerical stability through elliptic regularization. --- ### Feasible Pairings for Decentralized Integral Controllability of Non-Square Systems Authors: Yuhao Tong, Steven W. Su Published: 2026-03-01 Categories: math.OC, cs.AI arXiv: https://arxiv.org/abs/2603.01076v1 This paper investigates the determination of feasible input-output pairings for the decentralized integral controllability of non-square systems. The relevance of this problem extends beyond traditional industrial processes into modern AI research, particularly Multi-Agent Reinforcement Learning (MARL), where environments frequently act as strongly non-square mappings that evaluate high-dimensional joint action spaces via comparatively low-dimensional global rewards. To address the stability of these complex distributed architectures, we extend the concept of D-stability to non-square matrices, providing a crucial mathematical foundation. We formally define D-stability for non-square matrices as a direct generalization of the square case. By introducing the concept of ``Squared Matrices'', which are derived from specific column selections of the non-square formulation and directly correspond to candidate control pairings, we establish a fundamental link between the stability of these square sub-components and the original non-square system. Ultimately, we propose sufficient conditions under which the individual Volterra-Lyapunov stability of these squared components guarantees the extended D-stability of the non-square matrix, thereby providing a rigorous method to identify feasible pairings that ensure robust decentralized control across both classical and data-driven applications. --- ### Adaptive Augmentation-Aware Latent Learning for Robust LiDAR Semantic Segmentation Authors: Wangkai Li, Zhaoyang Li, Yuwen Pan, Rui Sun, Yujia Chen, Tianzhu Zhang Published: 2026-03-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.01074v1 Adverse weather conditions significantly degrade the performance of LiDAR point cloud semantic segmentation networks by introducing large distribution shifts. Existing augmentation-based methods attempt to enhance robustness by simulating weather interference during training. However, they struggle to fully exploit the potential of augmentations due to the trade-off between minor and aggressive augmentations. To address this, we propose A3Point, an adaptive augmentation-aware latent learning framework that effectively utilizes a diverse range of augmentations while mitigating the semantic shift, which refers to the change in the semantic meaning caused by augmentations. A3Point consists of two key components: semantic confusion prior (SCP) latent learning, which captures the model's inherent semantic confusion information, and semantic shift region (SSR) localization, which decouples semantic confusion and semantic shift, enabling adaptive optimization strategies for different disturbance levels. Extensive experiments on multiple standard generalized LiDAR segmentation benchmarks under adverse weather demonstrate the effectiveness of our method, setting new state-of-the-art results. --- ### Flow Matching-enabled Test-Time Refinement for Unsupervised Cardiac MR Registration Authors: Yunguan Fu, Wenjia Bai, Wen Yan, Matthew J Clarkson, Rhodri Huw Davies, Yipeng Hu Published: 2026-03-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.01073v2 Diffusion-based unsupervised image registration has been explored for cardiac cine MR, but expensive multi-step inference limits practical use. We propose FlowReg, a flow-matching framework in displacement field space that achieves strong registration in as few as two steps and supports further refinement with more steps. FlowReg uses warmup-reflow training: a single-step network first acts as a teacher, then a student learns to refine from arbitrary intermediate states, removing the need for a pre-trained model as in existing methods. An Initial Guess strategy feeds back the model prediction as the next starting point, improving refinement from step two onward. On ACDC and MM2 across six tasks (including cross-dataset generalization), FlowReg outperforms the state of the art on five tasks (+0.6% mean Dice score on average), with the largest gain in the left ventricle (+1.09%), and reduces LVEF estimation error on all six tasks (-2.58 percentage points), using only 0.7% extra parameters and no segmentation labels. Code is available at https://github.com/mathpluscode/FlowReg. --- ### How RL Unlocks the Aha Moment in Geometric Interleaved Reasoning Authors: Xiangxiang Zhang, Caijun Jia, Siyuan Li, Dingyu He, Xiya Xiong, Zheng Sun, Honghao He, Yuchen Wu, Bihui Yu, Linzhuang Sun, Cheng Tan, Jingxuan Wei Published: 2026-03-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.01070v2 Solving complex geometric problems inherently requires interleaved reasoning: a tight alternation between constructing diagrams and performing logical deductions. Although recent Multimodal Large Language Models (MLLMs) have demonstrated strong capabilities in visual generation and plotting, we identify a counter-intuitive and underexplored phenomenon. Naively applying Supervised Fine-Tuning (SFT) on interleaved plot-solution data leads to a substantial degradation in reasoning performance compared to text-only baselines. We argue that this failure stems from a fundamental limitation of SFT, which primarily induces distributional alignment: the model learns to reproduce the surface format of interleaved plotting but fails to internalize the causal dependency between the generated plot and reasoning steps. To overcome this limitation, we propose Faire (Functional alignment for interleaved reasoning), a reinforcement learning framework that enforces three casual constraints to move beyond superficial imitation toward functional alignment. Extensive experiments show that Faire induces a qualitative shift in model behavior in which the plotting is effectively internalized, yielding competitive performance on challenging geometric reasoning benchmarks. --- ### SHIELD8-UAV: Sequential 8-bit Hardware Implementation of a Precision-Aware 1D-F-CNN for Low-Energy UAV Acoustic Detection and Temporal Tracking Authors: Susmita Ghanta, Karan Nathwani, Rohit Chaurasiya Published: 2026-03-01 Categories: cs.AR, cs.CV, eess.SP, math.NA arXiv: https://arxiv.org/abs/2603.01069v1 Real-time unmanned aerial vehicle (UAV) acoustic detection at the edge demands low-latency inference under strict power and hardware limits. This paper presents SHIELD8-UAV, a sequential 8-bit hardware implementation of a precision-aware 1D feature-driven CNN (1D-F-CNN) accelerator for continuous acoustic monitoring. The design performs layer-wise execution on a shared multi-precision datapath, eliminating the need for replicated processing elements. A layer-sensitivity quantisation framework supports FP32, BF16, INT8, and FXP8 modes, while structured channel pruning reduces the flattened feature dimension from 35,072 to 8,704 (75%), thereby lowering serialised dense-layer cycles. The model achieves 89.91% detection accuracy in FP32 with less than 2.5% degradation in 8-bit modes. The accelerator uses 2,268 LUTs and 0.94 W power with 116 ms end-to-end latency, achieving 37.8% and 49.6% latency reduction compared with QuantMAC and LPRE, respectively, on a Pynq-Z2 FPGA, and 5-9% lower logic usage than parallel designs. ASIC synthesis in UMC 40 nm technology shows a maximum operating frequency of 1.56 GHz, 3.29 mm2 core area, and 1.65 W total power. These results demonstrate that sequential execution combined with precision-aware quantisation and serialisation-aware pruning enables practical low-energy edge inference without relying on massive parallelism. --- ### LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model Authors: Zebin You, Xiaolu Zhang, Jun Zhou, Chongxuan Li, Ji-Rong Wen Published: 2026-03-01 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.01068v1 We present \textbf{LLaDA-o}, an effective and length-adaptive omni diffusion model for multimodal understanding and generation. LLaDA-o is built on a Mixture of Diffusion (MoD) framework that decouples discrete masked diffusion for text understanding and continuous diffusion for visual generation, while coupling them through a shared, simple, and efficient attention backbone that reduces redundant computation for fixed conditions. Building on MoD, we further introduce a data-centric length adaptation strategy that enables flexible-length decoding in multimodal settings without architectural changes. Extensive experiments show that LLaDA-o achieves state-of-the-art performance among omni-diffusion models on multimodal understanding and generation benchmarks, and reaches 87.04 on DPG-Bench for text-to-image generation, supporting the effectiveness of unified omni diffusion modeling. Code is available at https://github.com/ML-GSAI/LLaDA-o. --- ### Hide&Seek: Remove Image Watermarks with Negligible Cost via Pixel-wise Reconstruction Authors: Huajie Chen, Tianqing Zhu, Hailin Yang, Yuchen Zhong, Yang Zhang, Hui Sun, Heng Xu, Zuobin Ying, Lihua Yin, Wanlei Zhou Published: 2026-03-01 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.01067v1 Watermarking has emerged as a key defense against the misuse of machine-generated images (MGIs). Yet the robustness of these protections remains underexplored. To reveal the limits of SOTA proactive image watermarking defenses, we propose HIDE&SEEK (HS), a suite of versatile and cost-effective attacks that reliably remove embedded watermarks while preserving high visual fidelity. --- ### A level-wise training scheme for learning neural multigrid smoothers with application to integral equations Authors: Lingfeng Li, Yin King Chu, Raymond Chan, Justin Wan Published: 2026-03-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.01064v1 Convolution-type integral equations commonly occur in signal processing and image processing. Discretizing these equations yields large and ill-conditioned linear systems. While the classic multigrid method is effective for solving linear systems derived from partial differential equations (PDE) problems, it fails to solve integral equations because its smoothers, which are implemented as conventional relaxation methods, are ineffective in reducing high-frequency components in the errors. We propose a novel neural multigrid scheme where learned neural operators replace classical smoothers. Unlike classical smoothers, these operators are trained offline. Once trained, the neural smoothers generalize to new right-hand-side vectors without retraining, making it an efficient solver. We design level-wise loss functions incorporating spectral filtering to emulate the multigrid frequency decomposition principle, ensuring each operator focuses on solving distinct high-frequency spectral bands. Although we focus on integral equations, the framework is generalizable to all kinds of problems, including PDE problems. Our experiments demonstrate superior efficiency over classical solvers and robust convergence across varying problem sizes and regularization weights. --- ### Unleashing VLA Potentials in Autonomous Driving via Explicit Learning from Failures Authors: Yuechen Luo, Qimao Chen, Fang Li, Shaoqing Xu, Jaxin Liu, Ziying Song, Zhi-xin Yang, Fuxi Wen Published: 2026-03-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.01063v1 Vision-Language-Action (VLA) models for autonomous driving often hit a performance plateau during Reinforcement Learning (RL) optimization. This stagnation arises from exploration capabilities constrained by previous Supervised Fine-Tuning (SFT), leading to persistent failures in long-tail scenarios. In these critical situations, all explored actions yield a zero-value driving score. This information-sparse reward signals a failure, yet fails to identify its root cause -- whether it is due to incorrect planning, flawed reasoning, or poor trajectory execution. To address this limitation, we propose VLA with Explicit Learning from Failures (ELF-VLA), a framework that augments RL with structured diagnostic feedback. Instead of relying on a vague scalar reward, our method produces detailed, interpretable reports that identify the specific failure mode. The VLA policy then leverages this explicit feedback to generate a Feedback-Guided Refinement. By injecting these corrected, high-reward samples back into the RL training batch, our approach provides a targeted gradient, which enables the policy to solve critical scenarios that unguided exploration cannot. Extensive experiments demonstrate that our method unlocks the latent capabilities of VLA models, achieving state-of-the-art (SOTA) performance on the public NAVSIM benchmark for overall PDMS, EPDMS score and high-level planning accuracy. --- ### GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant Authors: Zhuokang Shen, Yifan Wang, Hanyu Chen, Yunhang Shen, Wenxuan Huang, Gaoqi He, Jiao Xie, Rongrong Ji, Shaohui Lin Published: 2026-03-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.01059v3 Recent advances in large language models (LLMs) have enabled increasingly capable chatbots. However, most existing systems focus on single-user settings and do not generalize well to multi-user group chat interactions, where agents require more proactive and accurate intervention under complex, evolving contexts. Existing approaches typically rely on LLMs for both intervention reasoning and response generation, leading to high token consumption, limited scalability, and potential privacy risks. To address these challenges, we propose GroupGPT, a token-efficient and privacy-preserving agentic framework for multi-user chat assistant. GroupGPT adopts an edge-cloud model collaboration architecture to decouple intervention timing from response generation, enabling efficient and accurate decision-making while preserving user privacy through on-device processing of sensitive information. The framework also supports multimodal inputs, including memes, images, videos, and voice messages.To support evaluation of timing accuracy and response quality, we further introduce MUIR, a benchmark dataset for multi-user chat assistant intervention reasoning. MUIR contains 2,500 annotated group chat segments with intervention labels and rationales. We evaluate a range of models on MUIR, spanning from open-source to proprietary variants, including both LLMs and their smaller counterparts. Extensive experiments demonstrate that GroupGPT generates accurate and well-timed responses, achieving an average score of 4.72/5.0 in LLM-based evaluation, and is well-received by users across diverse group chat scenarios. Moreover, GroupGPT reduces the token usage by up to 3 times compared to baselines, while providing privacy sanitization of user messages before cloud transmission. Code is available at: https://github.com/Eliot-Shen/GroupGPT . --- ### TriMoE: Augmenting GPU with AMX-Enabled CPU and DIMM-NDP for High-Throughput MoE Inference via Offloading Authors: Yudong Pan, Yintao He, Tianhua Han, Lian Liu, Shixin Zhao, Zhirong Chen, Mengdi Wang, Cangyuan Li, Yinhe Han, Ying Wang Published: 2026-03-01 Categories: cs.AR, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2603.01058v1 To deploy large Mixture-of-Experts (MoE) models cost-effectively, offloading-based single-GPU heterogeneous inference is crucial. While GPU-CPU architectures that offload cold experts are constrained by host memory bandwidth, emerging GPU-NDP architectures utilize DIMM-NDP to offload non-hot experts. However, non-hot experts are not a homogeneous memory-bound group: a significant subset of warm experts exists is severely penalized by high GPU I/O latency yet can saturate NDP compute throughput, exposing a critical compute gap. We present TriMoE, a novel GPU-CPU-NDP architecture that fills this gap by synergistically leveraging AMX-enabled CPU to precisely map hot, warm, and cold experts onto their optimal compute units. We further introduce a bottleneck-aware expert scheduling policy and a prediction-driven dynamic relayout/rebalancing scheme. Experiments demonstrate that TriMoE achieves up to 2.83x speedup over state-of-the-art solutions. --- ### MMCOMET: A Large-Scale Multimodal Commonsense Knowledge Graph for Contextual Reasoning Authors: Eileen Wang, Hiba Arnaout, Dhita Pratama, Shuo Yang, Dangyang Liu, Jie Yang, Josiah Poon, Jeff Pan, Caren Han Published: 2026-03-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.01055v1 We present MMCOMET, the first multimodal commonsense knowledge graph (MMKG) that integrates physical, social, and eventive knowledge. MMCOMET extends the ATOMIC2020 knowledge graph to include a visual dimension, through an efficient image retrieval process, resulting in over 900K multimodal triples. This new resource addresses a major limitation of existing MMKGs in supporting complex reasoning tasks like image captioning and storytelling. Through a standard visual storytelling experiment, we show that our holistic approach enables the generation of richer, coherent, and contextually grounded stories than those produced using text-only knowledge. This resource establishes a new foundation for multimodal commonsense reasoning and narrative generation. --- ### Turning Black Box into White Box: Dataset Distillation Leaks Authors: Huajie Chen, Tianqing Zhu, Yuchen Zhong, Yang Zhang, Shang Wang, Feng He, Lefeng Zhang, Jialiang Shen, Minghao Wang, Wanlei Zhou Published: 2026-03-01 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.01053v1 Dataset distillation compresses a large real dataset into a small synthetic one, enabling models trained on the synthetic data to achieve performance comparable to those trained on the real data. Although synthetic datasets are assumed to be privacy-preserving, we show that existing distillation methods can cause severe privacy leakage because synthetic datasets implicitly encode the weight trajectories of the distilled model, they become over-informative and exploitable by adversaries. To expose this risk, we introduce the Information Revelation Attack (IRA) against state-of-the-art distillation techniques. Experiments show that IRA accurately predicts both the distillation algorithm and model architecture, and can successfully infer membership and recover sensitive samples from the real dataset. --- ### No More Maybe-Arrows: Resolving Causal Uncertainty by Breaking Symmetries Authors: Tingrui Huang, Devendra Singh Dhami Published: 2026-03-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.01052v1 The recent works on causal discovery have followed a similar trend of learning partial ancestral graphs (PAGs) since observational data constrain the true causal directed acyclic graph (DAG) only up to a Markov equivalence class. This limits their application in the majority of downstream tasks, as uncertainty in causal relations remains unresolved. We propose a new refinement framework, CausalSAGE, for converting PAGs to DAGs while respecting the underlying causal relations. The framework expands discrete variables into state-level representations, constrains the search space using structural knowledge and soft priors, and applies a unified differentiable objective for joint optimization. The final DAG is obtained by aggregating the optimized structures and enforcing acyclicity when necessary. Our experimental evaluations show that the obtained DAGs preserve the underlying causal relations while also being efficient to obtain. --- ### MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baseline Authors: Huanjin Yao, Qixiang Yin, Min Yang, Ziwang Zhao, Yibo Wang, Haotian Luo, Jingyi Zhang, Jiaxing Huang Published: 2026-03-01 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.01050v1 We aim to develop a multimodal research agent capable of explicit reasoning and planning, multi-tool invocation, and cross-modal information synthesis, enabling it to conduct deep research tasks. However, we observe three main challenges in developing such agents: (1) scarcity of search-intensive multimodal QA data, (2) lack of effective search trajectories, and (3) prohibitive cost of training with online search APIs. To tackle them, we first propose Hyper-Search, a hypergraph-based QA generation method that models and connects visual and textual nodes within and across modalities, enabling to generate search-intensive multimodal QA pairs that require invoking various search tools to solve. Second, we introduce DR-TTS, which first decomposes search-involved tasks into several categories according to search tool types, and respectively optimize specialized search tool experts for each tool. It then recomposes tool experts to jointly explore search trajectories via tree search, producing trajectories that successfully solve complex tasks using various search tools. Third, we build an offline search engine supporting multiple search tools, enabling agentic reinforcement learning without using costly online search APIs. With the three designs, we develop MM-DeepResearch, a powerful multimodal deep research agent, and extensive results shows its superiority across benchmarks. Code is available at https://github.com/HJYao00/MM-DeepResearch --- ### RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair Authors: Zhongqiang Pan, Chuanyi Li, Wenkang Zhong, Yi Feng, Bin Luo, Vincent Ng Published: 2026-03-01 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.01048v1 Automated program repair (APR) struggles to scale from isolated functions to full repositories, as it demands a global, task-aware understanding to locate necessary changes. Current methods, limited by context and reliant on shallow retrieval or costly agent iterations, falter on complex cross-file issues. To this end, we propose RepoRepair, a novel documentation-enhanced approach for repository-level fault localization and program repair. Our core insight is to leverage LLMs to generate hierarchical code documentation (from functions to files) for code repositories, creating structured semantic abstractions that enable LLMs to comprehend repository-level context and dependencies. Specifically, RepoRepair first employs a text-based LLM (e.g., DeepSeek-V3) to generate file/function-level code documentation for repositories, which serves as auxiliary knowledge to guide fault localization. Subsequently, based on the fault localization results and the issue description, a powerful LLM (e.g., Claude-4) attempts to repair the identified suspicious code snippets. Evaluated on SWE-bench Lite, RepoRepair achieves a 45.7% repair rate at a low cost of $0.44 per fix. On SWE-bench Multimodal, it delivers state-of-the-art performance with a 37.1% repair rate despite a higher cost of $0.56 per fix, demonstrating robust and cost-effective performance across diverse problem domains. --- ### Evaluating GFlowNet from partial episodes for stable and flexible policy-based training Authors: Puhua Niu, Shili Wu, Xiaoning Qian Published: 2026-03-01 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.01047v1 Generative Flow Networks (GFlowNets) were developed to learn policies for efficiently sampling combinatorial candidates by interpreting their generative processes as trajectories in directed acyclic graphs. In the value-based training workflow, the objective is to enforce the balance over partial episodes between the flows of the learned policy and the estimated flows of the desired policy, implicitly encouraging policy divergence minimization. The policy-based strategy alternates between estimating the policy divergence and updating the policy, but reliable estimation of the divergence under directed acyclic graphs remains a major challenge. This work bridges the two perspectives by showing that flow balance also yields a principled policy evaluator that measures the divergence, and an evaluation balance objective over partial episodes is proposed for learning the evaluator. As demonstrated on both synthetic and real-world tasks, evaluation balance not only strengthens the reliability of policy-based training but also broadens its flexibility by seamlessly supporting parameterized backward policies and enabling the integration of offline data-collection techniques. --- ### Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems Authors: Yuzhe Zhang, Feiran Liu, Yi Shan, Xinyi Huang, Xin Yang, Yueqi Zhu, Xuxin Cheng, Cao Liu, Ke Zeng, Terry Jingchen Zhang, Wenyuan Jiang Published: 2026-03-01 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2603.01045v2 Large language models are increasingly deployed in multi-agent systems to overcome context limitations by distributing information across agents. Yet whether agents can reliably compute with distributed information, rather than merely exchange it, remains an open question. We introduce SILO-BENCH, a role-agnostic benchmark of 30 algorithmic tasks across three communication complexity levels, evaluating 54 configurations over 1,620 experiments. Our experiments expose a fundamental Communication-Reasoning Gap: agents spontaneously form task-appropriate coordination topologies and exchange information actively, yet systematically fail to synthesize distributed state into correct answers. The failure is localized to the reasoning-integration stage where agents often acquire sufficient information but cannot integrate it. This coordination overhead compounds with scale, eventually eliminating parallelization gains entirely. These findings demonstrate that naively scaling agent count cannot circumvent context limitations, and SILO-BENCH provides a foundation for tracking progress toward genuinely collaborative multi-agent systems. The code is available at https://github.com/jwyjohn/acl26-silo-bench . --- ### Thoth: Mid-Training Bridges LLMs to Time Series Understanding Authors: Jiafeng Lin, Yuxuan Wang, Jialong Wu, Huakun Luo, Zhongyi Pei, Jianmin Wang Published: 2026-03-01 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.01042v1 Large Language Models (LLMs) have demonstrated remarkable success in general-purpose reasoning. However, they still struggle to understand and reason about time series data, which limits their effectiveness in decision-making scenarios that depend on temporal dynamics. In this paper, we propose Thoth, the first family of mid-trained LLMs with general-purpose time series understanding capabilities. As a pivotal intermediate stage, mid-training achieves task- and domain-agnostic alignment between time series and natural language, for which we construct Book-of-Thoth, a high-quality, time-series-centric mid-training corpus. Book-of-Thoth enables both time-series-to-text and text-to-time-series generation, equipping LLMs with a foundational grasp of temporal patterns. To better evaluate advanced reasoning capabilities, we further present KnoTS, a novel benchmark of knowledge-intensive time series understanding, designed for joint reasoning over temporal patterns and domain knowledge. Extensive experiments demonstrate that mid-training with Book-of-Thoth enables Thoth to significantly outperform its base model and advanced LLMs across a range of time series question answering benchmarks. Moreover, Thoth exhibits superior capabilities when fine-tuned under data scarcity, underscoring the effectiveness of mid-training for time series understanding. Code is available at: https://github.com/thuml/Thoth. --- ### Fed-ADE: Adaptive Learning Rate for Federated Post-adaptation under Distribution Shift Authors: Heewon Park, Mugon Joe, Miru Kim, Kyungjin Im, Minhae Kwon Published: 2026-03-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.01040v1 Federated learning (FL) in post-deployment settings must adapt to non-stationary data streams across heterogeneous clients without access to ground-truth labels. A major challenge is learning rate selection under client-specific, time-varying distribution shifts, where fixed learning rates often lead to underfitting or divergence. We propose Fed-ADE (Federated Adaptation with Distribution Shift Estimation), an unsupervised federated adaptation framework that leverages lightweight estimators of distribution dynamics. Specifically, Fed-ADE employs uncertainty dynamics estimation to capture changes in predictive uncertainty and representation dynamics estimation to detect covariate-level feature drift, combining them into a per-client, per-timestep adaptive learning rate. We provide theoretical analyses showing that our dynamics estimation approximates the underlying distribution shift and yields dynamic regret and convergence guarantees. Experiments on image and text benchmarks under diverse distribution shifts (label and covariate) demonstrate consistent improvements over strong baselines. These results highlight that distribution shift-aware adaptation enables effective and robust federated post-adaptation under real-world non-stationarity. --- ### From Intuition to Investigation: A Tool-Augmented Reasoning MLLM Framework for Generalizable Face Anti-Spoofing Authors: Haoyuan Zhang, Keyao Wang, Guosheng Zhang, Haixiao Yue, Zhiwen Tan, Siran Peng, Tianshuo Zhang, Xiao Tan, Kunbin Chen, Wei He, Jingdong Wang, Ajian Liu et al. Published: 2026-03-01 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.01038v2 Face recognition remains vulnerable to presentation attacks, calling for robust Face Anti-Spoofing (FAS) solutions. Recent MLLM-based FAS methods reformulate the binary classification task as the generation of brief textual descriptions to improve cross-domain generalization. However, their generalizability is still limited, as such descriptions mainly capture intuitive semantic cues (e.g., mask contours) while struggling to perceive fine-grained visual patterns. To address this limitation, we incorporate external visual tools into MLLMs to encourage deeper investigation of subtle spoof clues. Specifically, we propose the Tool-Augmented Reasoning FAS (TAR-FAS) framework, which reformulates the FAS task as a Chain-of-Thought with Visual Tools (CoT-VT) paradigm, allowing MLLMs to begin with intuitive observations and adaptively invoke external visual tools for fine-grained investigation. To this end, we design a tool-augmented data annotation pipeline and construct the ToolFAS-16K dataset, which contains multi-turn tool-use reasoning trajectories. Furthermore, we introduce a tool-aware FAS training pipeline, where Diverse-Tool Group Relative Policy Optimization (DT-GRPO) enables the model to autonomously learn efficient tool use. Extensive experiments under a challenging one-to-eleven cross-domain protocol demonstrate that TAR-FAS achieves SOTA performance while providing fine-grained visual investigation for trustworthy spoof detection. --- ### SMR-Net:Robot Snap Detection Based on Multi-Scale Features and Self-Attention Network Authors: Kuanxu Hou Published: 2026-03-01 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.01036v1 In robot automated assembly, snap assembly precision and efficiency directly determine overall production quality. As a core prerequisite, snap detection and localization critically affect subsequent assembly success. Traditional visual methods suffer from poor robustness and large localization errors when handling complex scenarios (e.g., transparent or low-contrast snaps), failing to meet high-precision assembly demands. To address this, this paper designs a dedicated sensor and proposes SMR-Net, an self-attention-based multi-scale object detection algorithm, to synergistically enhance detection and localization performance. SMR-Net adopts an attention-enhanced multi-scale feature fusion architecture: raw sensor data is encoded via an attention-embedded feature extractor to strengthen key snap features and suppress noise; three multi-scale feature maps are processed in parallel with standard and dilated convolution for dimension unification while preserving resolution; an adaptive reweighting network dynamically assigns weights to fused features, generating fine representations integrating details and global semantics. Experimental results on Type A and Type B snap datasets show SMR-Net outperforms traditional Faster R-CNN significantly: Intersection over Union (IoU) improves by 6.52% and 5.8%, and mean Average Precision (mAP) increases by 2.8% and 1.5% respectively. This fully demonstrates the method's superiority in complex snap detection and localization tasks. --- ### Reparameterized Tensor Ring Functional Decomposition for Multi-Dimensional Data Recovery Authors: Yangyang Xu, Junbo Ke, You-Wei Wen, Chao Wang Published: 2026-03-01 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.01034v2 Tensor Ring (TR) decomposition is a powerful tool for high-order data modeling, but is inherently restricted to discrete forms defined on fixed meshgrids. In this work, we propose a TR functional decomposition for both meshgrid and non-meshgrid data, where factors are parameterized by Implicit Neural Representations (INRs). However, optimizing this continuous framework to capture fine-scale details is intrinsically difficult. Through a frequency-domain analysis, we demonstrate that the spectral structure of TR factors determines the frequency composition of the reconstructed tensor and limits the high-frequency modeling capacity. To mitigate this, we propose a reparameterized TR functional decomposition, in which each TR factor is a structured combination of a learnable latent tensor and a fixed basis. This reparameterization is theoretically shown to improve the training dynamics of TR factor learning. We further derive a principled initialization scheme for the fixed basis and prove the Lipschitz continuity of our proposed model. Extensive experiments on image inpainting, denoising, super-resolution, and point cloud recovery demonstrate that our method achieves consistently superior performance over existing approaches. Code is available at https://github.com/YangyangXu2002/RepTRFD. --- ### Vision-Language Feature Alignment for Road Anomaly Segmentation Authors: Zhuolin He, Jiacheng Tang, Jian Pu, Xiangyang Xue Published: 2026-03-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.01029v1 Safe autonomous systems in complex environments require robust road anomaly segmentation to identify unknown obstacles. However, existing approaches often rely on pixel-level statistics to determine whether a region appears anomalous. This reliance leads to high false-positive rates on semantically normal background regions such as sky or vegetation, and poor recall of true Out-of-distribution (OOD) instances, thereby posing safety risks for robotic perception and decision-making. To address these challenges, we propose VL-Anomaly, a vision-language anomaly segmentation framework that incorporates semantic priors from pre-trained Vision-Language Models (VLMs). Specifically, we design a prompt learning-driven alignment module that adapts Mask2Forme's visual features to CLIP text embeddings of known categories, effectively suppressing spurious anomaly responses in background regions. At inference time, we further introduce a multi-source inference strategy that integrates text-guided similarity, CLIP-based image-text similarity and detector confidence, enabling more reliable anomaly prediction by leveraging complementary information sources. Extensive experiments demonstrate that VL-Anomaly achieves state-of-the-art performance on benchmark datasets including RoadAnomaly, SMIYC and Fishyscapes.Code is released on https://github.com/NickHezhuolin/VL-aligner-Road-anomaly-segment. --- ### Content-Aware Frequency Encoding for Implicit Neural Representations with Fourier-Chebyshev Features Authors: Junbo Ke, Yangyang Xu, You-Wei Wen, Chao Wang Published: 2026-03-01 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.01028v1 Implicit Neural Representations (INRs) have emerged as a powerful paradigm for various signal processing tasks, but their inherent spectral bias limits the ability to capture high-frequency details. Existing methods partially mitigate this issue by using Fourier-based features, which usually rely on fixed frequency bases. This forces multi-layer perceptrons (MLPs) to inefficiently compose the required frequencies, thereby constraining their representational capacity. To address this limitation, we propose Content-Aware Frequency Encoding (CAFE), which builds upon Fourier features through multiple parallel linear layers combined via a Hadamard product. CAFE can explicitly and efficiently synthesize a broader range of frequency bases, while the learned weights enable the selection of task-relevant frequencies. Furthermore, we extend this framework to CAFE+, which incorporates Chebyshev features as a complementary component to Fourier bases. This combination provides a stronger and more stable frequency representation. Extensive experiments across multiple benchmarks validate the effectiveness and efficiency of our approach, consistently achieving superior performance over existing methods. Our code is available at https://github.com/JunboKe0619/CAFE. --- ### RaUF: Learning the Spatial Uncertainty Field of Radar Authors: Shengpeng Wang, Kuangyu Wang, Wei Wang Published: 2026-03-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.01026v1 Millimeter-wave radar offers unique advantages in adverse weather but suffers from low spatial fidelity, severe azimuth ambiguity, and clutter-induced spurious returns. Existing methods mainly focus on improving spatial perception effectiveness via coarse-to-fine cross-modal supervision, yet often overlook the ambiguous feature-to-label mapping, which may lead to ill-posed geometric inference and pose fundamental challenges to downstream perception tasks. In this work, we propose RaUF, a spatial uncertainty field learning framework that models radar measurements through their physically grounded anisotropic properties. To resolve conflicting feature-to-label mapping, we design an anisotropic probabilistic model that learns fine-grained uncertainty. To further enhance reliability, we propose a Bidirectional Domain Attention mechanism that exploits the mutual complementarity between spatial structure and Doppler consistency, effectively suppressing spurious or multipath-induced reflections. Extensive experiments on public benchmarks and real-world datasets demonstrate that RaUF delivers highly reliable spatial detections with well-calibrated uncertainty. Moreover, downstream case studies further validate the enhanced reliability and scalability of RaUF under challenging real-world driving scenarios. --- ### One-Token Verification for Reasoning Correctness Estimation Authors: Zhan Zhuang, Xiequn Wang, Zebin Chen, Feiyang Ye, Ying Wei, Kede Ma, Yu Zhang Published: 2026-03-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.01025v1 Recent breakthroughs in large language models (LLMs) have led to notable successes in complex reasoning tasks, such as mathematical problem solving. A common strategy for improving performance is parallel thinking, in which multiple reasoning traces are generated and the final prediction is made using aggregation schemes like majority voting or best-of-$N$ decoding. However, two key challenges persist. First, multi-sample decoding incurs substantial inference latency, especially for long-form outputs. Second, effective mechanisms for reliably assessing the correctness of individual reasoning traces are still limited. To address these challenges, we introduce One-Token Verification (OTV), a computational method that estimates reasoning correctness in a single forward pass during generation. OTV is activated by a learnable token and integrated into the LLM via low-rank adaptation to probe internal reasoning signals through the key-value cache, supporting token-level correctness estimation at any stage of generation without disrupting primary reasoning. Experiments on mathematical reasoning benchmarks demonstrate that OTV consistently surpasses existing verifiers. Additionally, OTV reduces token usage by up to $90\%$ through correctness-guided early termination, prioritizing shorter, more reliable solutions. --- ### SimAB: Simulating A/B Tests with Persona-Conditioned AI Agents for Rapid Design Evaluation Authors: Tim Rieder, Marian Schneider, Mario Truss, Vitaly Tsaplin, Alina Rublea, Sinem Dere, Francisco Chicharro Sanz, Tobias Reiss, Mustafa Doga Dogan Published: 2026-03-01 Categories: cs.HC, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2603.01024v1 A/B testing is a standard method for validating design decisions, yet its reliance on real user traffic limits iteration speed and makes certain experiments impractical. We present SimAB, a system that reframes A/B testing as a fast, privacy-preserving simulation using persona-conditioned AI agents. Given design screenshots and a conversion goal, SimAB generates user personas, deploys them as agents that state their preference, aggregates results, and synthesizes rationales. Through a formative study with experimentation practitioners, we identified scenarios where traffic constraints hinder testing, including low-traffic pages, multi-variant comparisons, micro-optimizations, and privacy-sensitive contexts. Our design emphasizes speed, early feedback, actionable rationales, and audience specification. We evaluate SimAB against 47 historical A/B tests with known outcomes, achieving 67% overall accuracy, increasing to 83% for high-confidence cases. Additional experiments show robustness to naming and positional bias and demonstrate accuracy gains from personas. Practitioner feedback suggests that SimAB supports faster evaluation cycles and rapid screening of designs difficult to assess with traditional A/B tests. --- ### An Open-Source Modular Benchmark for Diffusion-Based Motion Planning in Closed-Loop Autonomous Driving Authors: Yun Li, Simon Thompson, Yidu Zhang, Ehsan Javanmardi, Manabu Tsukada Published: 2026-03-01 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.01023v1 Diffusion-based motion planners have achieved state-of-the-art results on benchmarks such as nuPlan, yet their evaluation within closed-loop production autonomous driving stacks remains largely unexplored. Existing evaluations abstract away ROS 2 communication latency and real-time scheduling constraints, while monolithic ONNX deployment freezes all solver parameters at export time. We present an open-source modular benchmark that addresses both gaps: using ONNX GraphSurgeon, we decompose a monolithic 18,398 node diffusion planner into three independently executable modules and reimplement the DPM-Solver++ denoising loop in native C++. Integrated as a ROS 2 node within Autoware, the open-source AD stack deployed on real vehicles worldwide, the system enables runtime-configurable solver parameters without model recompilation and per-step observability of the denoising process, breaking the black box of monolithic deployment. Unlike evaluations in standalone simulators such as CARLA, our benchmark operates within a production-grade stack and is validated through AWSIM closed-loop simulation. Through systematic comparison of DPM-Solver++ (first- and second-order) and DDIM across six step-count configurations (N in {3, 5, 7, 10, 15, 20}), we show that encoder caching yields a 3.2x latency reduction, and that second-order solving reduces FDE by 41% at N=3 compared to first-order. The complete codebase will be released as open-source, providing a direct path from simulation benchmarks to real-vehicle deployment. --- ### BadRSSD: Backdoor Attacks on Regularized Self-Supervised Diffusion Models Authors: Jiayao Wang, Yiping Zhang, Mohammad Maruf Hasan, Xiaoying Lei, Jiale Zhang, Junwu Zhu, Qilin Wu, Dongfang Zhao Published: 2026-03-01 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2603.01019v1 Self-supervised diffusion models learn high-quality visual representations via latent space denoising. However, their representation layer poses a distinct threat: unlike traditional attacks targeting generative outputs, its unconstrained latent semantic space allows for stealthy backdoors, permitting malicious control upon triggering. In this paper, we propose BadRSSD, the first backdoor attack targeting the representation layer of self-supervised diffusion models. Specifically, it hijacks the semantic representations of poisoned samples with triggers in Principal Component Analysis (PCA) space toward those of a target image, then controls the denoising trajectory during diffusion by applying coordinated constraints across latent, pixel, and feature distribution spaces to steer the model toward generating the specified target. Additionally, we integrate representation dispersion regularization into the constraint framework to maintain feature space uniformity, significantly enhancing attack stealth. This approach preserves normal model functionality (high utility) while achieving precise target generation upon trigger activation (high specificity). Experiments on multiple benchmark datasets demonstrate that BadRSSD substantially outperforms existing attacks in both FID and MSE metrics, reliably establishing backdoors across different architectures and configurations, and effectively resisting state-of-the-art backdoor defenses. --- ### Implementation of Licensed Plate Detection and Noise Removal in Image Processing Authors: Yiquan Gao Published: 2026-03-01 Categories: cs.CV, eess.IV, eess.SP arXiv: https://arxiv.org/abs/2603.01016v2 Car license plate recognition system is an image processing technology used to identify vehicles by capturing their Car License Plates. The car license plate recognition technology is also known as automatic number-plate recognition, automatic vehicle identification, car license plate recognition or optical character recognition for cars. In Malaysia, as the number of vehicle is increasing rapidly nowadays, a pretty great number of vehicle on the road has brought about the considerable demands of car license plate recognition system. Car license plate recognition system can be implemented in electronic parking payment system, highway toll-fee system, traffic surveillance system and as police enforcement tools. Additionally, car license plate recognition system technology also has potential to be combined with various techniques in other different fields like biology, aerospace and so on to achieve the goal of solving some specialized problems. --- ### Feature-Weighted Maximum Representative Subsampling Authors: Tony Hauptmann, Stefan Kramer Published: 2026-03-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.01013v1 In the social sciences, it is often necessary to debias studies and surveys before valid conclusions can be drawn. Debiasing algorithms enable the computational removal of bias using sample weights. However, an issue arises when only a subset of features is highly biased, while the rest is already representative. Algorithms need to strongly alter the sample distribution to manage a few highly biased features, which can in turn introduce bias into already representative variables. To address this issue, we developed a method that uses feature weights to minimize the impact of highly biased features on the computation of sample weights. Our algorithm is based on Maximum Representative Subsampling (MRS), which debiases datasets by aligning a non-representative sample with a representative one through iterative removal of elements to create a representative subsample. The new algorithm, named feature-weighted MRS (FW-MRS), decreases the emphasis on highly biased features, allowing it to retain more instances for downstream tasks. The feature weights are derived from the feature importance of a domain classifier trained to differentiate between the representative and non-representative datasets. We validated FW-MRS using eight tabular datasets, each of which we artificially biased. Biased features can be important for downstream tasks, and focusing less on them could lead to a decline in generalization. For this reason, we assessed the generalization performance of FW-MRS on downstream tasks and found no statistically significant differences. Additionally, FW-MRS was applied to a real-world dataset from the social sciences. The source code is available at https://github.com/kramerlab/FeatureWeightDebiasing. --- ### FastCode: Fast and Cost-Efficient Code Understanding and Reasoning Authors: Zhonghang Li, Zongwei Li, Yuxuan Chen, Han Shi, Jiawei Li, Jierun Chen, Haoli Bai, Chao Huang Published: 2026-03-01 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.01012v2 Repository-scale code reasoning is a cornerstone of modern AI-assisted software engineering, enabling Large Language Models (LLMs) to handle complex workflows from program comprehension to complex debugging. However, balancing accuracy with context cost remains a significant bottleneck, as existing agentic approaches often waste computational resources through inefficient, iterative full-text exploration. To address this, we introduce FastCode, a framework that decouples repository exploration from content consumption. FastCode utilizes a structural scouting mechanism to navigate a lightweight semantic-structural map of the codebase, allowing the system to trace dependencies and pinpoint relevant targets without the overhead of full-text ingestion. By leveraging structure-aware navigation tools regulated by a cost-aware policy, the framework constructs high-value contexts in a single, optimized step. Extensive evaluations on the SWE-QA, LongCodeQA, LOC-BENCH, and GitTaskBench benchmarks demonstrate that FastCode consistently outperforms state-of-the-art baselines in reasoning accuracy while significantly reducing token consumption, validating the efficiency of scouting-first strategies for large-scale code reasoning. Source code is available at https://github.com/HKUDS/FastCode. ---