# Research Papers — 2026-03 · bundle page 132 of 243 > Full-text markdown of papers #6551–6600 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/132 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/131.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/133.md) ### Fundamental Limits of CSI Compression in FDD Massive MIMO Authors: Bumsu Park, Youngmok Park, Chanho Park, Namyoon Lee Published: 2026-03-15 Categories: cs.IT, stat.ML arXiv: https://arxiv.org/abs/2603.14325v1 Channel state information (CSI) feedback in frequency-division duplex (FDD) massive multiple-input multiple-output (MIMO) systems is fundamentally limited by the high dimensionality of wideband channels. In this paper, we model the stacked wideband CSI vector as a Gaussian-mixture source with a latent geometry state that represents different propagation environments. Each component corresponds to a locally stationary regime characterized by a correlated proper complex Gaussian distribution with its own covariance matrix. This representation captures the multimodal nature of practical CSI datasets while preserving the analytical tractability of Gaussian models. Motivated by this structure, we propose Gaussian-mixture transform coding (GMTC), a practical CSI feedback architecture that combines state inference with state-adaptive TC. The mixture parameters are learned offline from channel samples and stored as a shared statistical dictionary at both the user equipment (UE) and the base station. For each CSI realization, the UE identifies the most likely geometry state, encodes the corresponding label using a lossless source code, and compresses the CSI using the Karhunen-Loeve transform matched to that state. We further characterize the fundamental limits of CSI compression under this model by deriving analytical converse and achievability bounds on the rate-distortion (RD) function. A key structural result is that the optimal bit allocation across all mixture components is governed by a single global reverse-waterfilling level. Simulations on the COST2100 dataset show that GMTC significantly improves the RD tradeoff relative to neural transform coding approaches while requiring substantially smaller model memory and lower inference complexity. These results indicate that near-optimal CSI compression can be achieved through state-adaptive TC without relying on large neural encoders. --- ### Learning-to-Defer with Expert-Conditional Advice Authors: Yannis Montreuil, Leïna Montreuil, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi Published: 2026-03-15 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.14324v5 Learning-to-Defer routes each input to the expert that minimizes expected cost, but it assumes that the information available to every expert is fixed at decision time. Many modern systems violate this assumption: after selecting an expert, one may also choose what additional information that expert should receive, such as retrieved documents, tool outputs, or escalation context. We study this problem and call it Learning-to-Defer with advice. We show that a broad family of natural separated surrogates, which learn routing and advice with distinct heads, is inconsistent even in the smallest non-trivial setting. We then introduce an augmented surrogate that operates on the composite expert--advice action space and prove an $\mathcal{H}$-consistency guarantee together with an excess-risk transfer bound, yielding recovery of the Bayes-optimal policy in the limit. Experiments on tabular, language, and multi-modal tasks show that the resulting method improves over standard Learning-to-Defer while adapting its advice-acquisition behavior to the cost regime; a synthetic benchmark confirms the failure mode predicted for separated surrogates. --- ### How Do Medical MLLMs Fail? A Study on Visual Grounding in Medical Images Authors: Guimeng Liu, Tianze Yu, Somayeh Ebrahimkhani, Lin Zhi Zheng Shawn, Kok Pin Ng, Ngai-Man Cheung Published: 2026-03-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.14323v1 Generalist multimodal large language models (MLLMs) have achieved impressive performance across a wide range of vision-language tasks. However, their performance on medical tasks, particularly in zero-shot settings where generalization is critical, remains suboptimal. A key research gap is the limited understanding of why medical MLLMs underperform in medical image interpretation. In this work, we present a pioneering systematic investigation into the visual grounding capabilities of state-of-the-art medical MLLMs. To disentangle visual grounding from semantic grounding, we design VGMED, a novel evaluation dataset developed with expert clinical guidance, explicitly assessing the visual grounding capability of medical MLLMs. We introduce new quantitative metrics and conduct detailed qualitative analyses. Our study across eight state-of-the-art (SOTA) medical MLLMs validates that they often fail to ground their predictions in clinically relevant image regions. We note that this finding is specific to medical image analysis; in contrast, prior work has shown that MLLMs are capable of grounding their predictions in the correct image regions when applied to natural scene images. Motivated by these findings, we propose VGRefine, a simple yet effective inference-time method that refines attention distribution to improve visual grounding in medical settings. Our approach achieves SOTA performance across 6 diverse Med-VQA benchmarks (over 110K VQA samples from 8 imaging modalities) without requiring additional training or external expert models. Overall, our work, for the first time, systematically validates inadequate visual grounding as one of the key contributing factors for medical MLLMs' under-performance. Additional experiments are included in the Supp. --- ### Personalized Cell Segmentation: Benchmark and Framework for Reference-Guided Cell Type Segmentation Authors: Bisheng Wang, Jaime S. Cardoso, Lin Wu Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14321v1 Accurate cell segmentation is critical for biological and medical imaging studies. Although recent deep learning models have advanced this task, most methods are limited to generic cell segmentation, lacking the ability to differentiate specific cell types. In this work, we introduce the Personalized Cell Segmentation (PerCS) task, which aims to segment all cells of a specific type given a reference cell. To support this task, we establish a benchmark by reorganizing publicly available datasets, yielding 1,372 images and over 110,000 annotated cells. As a pioneering solution, we propose PerCS-DINO, a framework built on the DINOv2 backbone. By integrating image features and reference embeddings via a cross-attention transformer and contrastive learning, PerCS-DINO effectively segments cells matching the reference. Extensive experiments demonstrate the effectiveness of the proposed PerCS-DINO and highlight the challenges of this new task. We expect PerCS to serve as a useful testbed for advancing research in cell-based applications. --- ### Early Failure Detection and Intervention in Video Diffusion Models Authors: Kwon Byung-Ki, Sohwi Lim, Nam Hyeon-Woo, Moon Ye-Bin, Tae-Hyun Oh Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14320v1 Text-to-video (T2V) diffusion models have rapidly advanced, yet generations still occasionally fail in practice, such as low text-video alignment or low perceptual quality. Since diffusion sampling is non-deterministic, it is difficult to know during inference whether a generation will succeed or fail, incurring high computational cost due to trial-and-error regeneration. To address this, we propose an early failure detection and diagnostic intervention pipeline for latent T2V diffusion models. For detection, we design a Real-time Inspection (RI) module that converts latents into intermediate video previews, enabling the use of established text-video alignment scorers for inspection in the RGB space. The RI module completes the conversion and inspection process in just 39.2ms. This is highly efficient considering that CogVideoX-5B requires 4.3s per denoising step when generating a 480p, 49-frame video on an NVIDIA A100 GPU. Subsequently, we trigger a hierarchical and early-exit intervention pipeline only when failure is predicted. Experiments on CogVideoX-5B and Wan2.1-1.3B demonstrate consistency gains on VBench with up to 2.64 times less time overhead compared to post-hoc regeneration. Our method also generalizes to a higher-capacity setting, remaining effective on Wan2.1-14B with 720p resolution and 81-frame generation. Furthermore, our pipeline is plug-and-play and orthogonal to existing techniques, showing seamless compatibility with prompt refinement and sampling guidance methods. We also provide evidence that failure signals emerge early in the denoising process and are detectable within intermediate video previews using standard vision-language evaluators. --- ### Structure-Dependent Regret and Constraint Violation Bounds for Online Convex Optimization with Time-Varying Constraints Authors: Xiufeng Liu, Qian Chen, Zhijin Wang, Ruyu Liu Published: 2026-03-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.14319v1 Online convex optimization (OCO) with time-varying constraints is a critical framework for sequential decision-making in dynamic networked systems, where learners must minimize cumulative loss while satisfying regions of feasibility that shift across rounds. Existing theoretical analyses typically treat constraint variation as a monolithic adversarial process, resulting in joint regret and violation bounds that are overly conservative for real-world network dynamics. In this paper, we introduce a structured characterization of constraint variation - smooth drift, periodic cycles, and sparse switching - mapping these classes to common network phenomena such as slow channel fading, diurnal traffic patterns, and discrete maintenance windows. We derive structure-dependent joint bounds that strictly improve upon adversarial rates when the constraint process exhibits regularity. To realize these gains, we propose the Structure-Adaptive Primal-Dual (SA-PD) algorithm, which utilizes observable constraint signals to detect environmental structure online and adapt dual update strategies accordingly. Extensive experiments on synthetic benchmarks and real-world datasets - including online electricity scheduling and transformer load management - demonstrate that SA-PD reduces cumulative constraint violation by up to 53% relative to structure-agnostic baselines while maintaining competitive utility. This work serves as a comprehensive guide for exploiting temporal regularity in constrained online learning for robust network engineering. --- ### Direct Object-Level Reconstruction via Probabilistic Gaussian Splatting Authors: Shuai Guo, Ao Guo, Junchao Zhao, Qi Chen, Yuxiang Qi, Zechuan Li, Dong Chen, Mingliang Xu Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14316v2 Object-level 3D reconstruction play important roles across domains such as cultural heritage digitization, industrial manufacturing, and virtual reality. However, existing Gaussian Splatting-based approaches generally rely on full-scene reconstruction, in which substantial redundant background information is introduced, leading to increased computational and storage overhead. To address this limitation, we propose an efficient single-object 3D reconstruction method based on 2D Gaussian Splatting. By directly integrating foreground-background probability cues into Gaussian primitives and dynamically pruning low-probability Gaussians during training, the proposed method fundamentally focuses on an object of interest and improves the memory and computational efficiency. Our pipeline leverages probability masks generated by YOLO and SAM to supervise probabilistic Gaussian attributes, replacing binary masks with continuous probability values to mitigate boundary ambiguity. Additionally, we propose a dual-stage filtering strategy for training's startup to suppress background Gaussians. And, during training, rendered probability masks are conversely employed to refine supervision and enhance boundary consistency across views. Experiments conducted on the MIP-360, T&T, and NVOS datasets demonstrate that our method exhibits strong self-correction capability in the presence of mask errors and achieves reconstruction quality comparable to standard 3DGS approaches, while requiring only approximately 1/10 of their Gaussian amount. These results validate the efficiency and robustness of our method for single-object reconstruction and highlight its potential for applications requiring both high fidelity and computational efficiency. --- ### Enhancing LLM Training via Spectral Clipping Authors: Xiaowen Jiang, Andrei Semenov, Sebastian U. Stich Published: 2026-03-15 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2603.14315v2 While spectral-based optimizers like Muon operate directly on the spectrum of updates, standard adaptive methods such as AdamW do not account for the spectral structure of weights and gradients, leaving them vulnerable to two empirical issues in large language model (LLM) training: (i) the optimizer updates can have large spectral norms, potentially destabilizing training and degrading generalization; (ii) stochastic gradient noise can exhibit sparse spectral spikes, with a few dominant singular values much larger than the rest. We propose SPECTRA, a general framework addressing these by (i) post-spectral clipping of updates to enforce spectral-norm constraints (ii) optional pre-spectral clipping of gradients to suppress spectral noise spikes. We prove that post-clipping constitutes a Composite Frank-Wolfe method with spectral-norm constraints and weight regularization. We further analyze how pre-clipping mitigates sparse spectral spikes. We propose efficient soft spectral clipping via Newton-Schulz iterations, avoiding expensive SVD. Experiments on LLM pretraining show SPECTRA uniformly improves validation loss for various optimizers, including AdamW, Signum, Mars, and AdEMAMix, with the best-performing variants achieving state-of-the-art results. Models trained with SPECTRA exhibit smaller weight norms, confirming the link between spectral clipping and regularization. --- ### Mind the Shift: Decoding Monetary Policy Stance from FOMC Statements with Large Language Models Authors: Yixuan Tang, Yi Yang Published: 2026-03-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.14313v1 Federal Open Market Committee (FOMC) statements are a major source of monetary-policy information, and even subtle changes in their wording can move global financial markets. A central task is therefore to measure the hawkish--dovish stance conveyed in these texts. Existing approaches typically treat stance detection as a standard classification problem, labeling each statement in isolation. However, the interpretation of monetary-policy communication is inherently relative: market reactions depend not only on the tone of a statement, but also on how that tone shifts across meetings. We introduce Delta-Consistent Scoring (DCS), an annotation-free framework that maps frozen large language model (LLM) representations to continuous stance scores by jointly modeling absolute stance and relative inter-meeting shifts. Rather than relying on manual hawkish--dovish labels, DCS uses consecutive meetings as a source of self-supervision. It learns an absolute stance score for each statement and a relative shift score between consecutive statements. A delta-consistency objective encourages changes in absolute scores to align with the relative shifts. This allows DCS to recover a temporally coherent stance trajectory without manual labels. Across four LLM backbones, DCS consistently outperforms supervised probes and LLM-as-judge baselines, achieving up to 71.1% accuracy on sentence-level hawkish--dovish classification. The resulting meeting-level scores are also economically meaningful: they correlate strongly with inflation indicators and are significantly associated with Treasury yield movements. Overall, the results suggest that LLM representations encode monetary-policy signals that can be recovered through relative temporal structure. --- ### Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange Authors: Fiona Y. Wang, Lee Marom, Subhadeep Pal, Rachel K. Luu, Wei Lu, Jaime A. Berkovich, Markus J. Buehler Published: 2026-03-15 Categories: cs.AI, cond-mat.dis-nn, cs.LG, cs.MA, q-bio.BM arXiv: https://arxiv.org/abs/2603.14312v1 We present ScienceClaw + Infinite, a framework for autonomous scientific investigation in which independent agents conduct research without central coordination, and any contributor can deploy new agents into a shared ecosystem. The system is built around three components: an extensible registry of over 300 interoperable scientific skills, an artifact layer that preserves full computational lineage as a directed acyclic graph (DAG), and a structured platform for agent-based scientific discourse with provenance-aware governance. Agents select and chain tools based on their scientific profiles, produce immutable artifacts with typed metadata and parent lineage, and broadcast unsatisfied information needs to a shared global index. The ArtifactReactor enables plannerless coordination: peer agents discover and fulfill open needs through pressure-based scoring, while schema-overlap matching triggers multi-parent synthesis across independent analyses. An autonomous mutation layer actively prunes the expanding artifact DAG to resolve conflicting or redundant workflows, while persistent memory allows agents to continuously build upon complex epistemic states across multiple cycles. Infinite converts these outputs into auditable scientific records through structured posts, provenance views, and machine-readable discourse relations, with community feedback steering subsequent investigation cycles. Across four autonomous investigations, peptide design for the somatostatin receptor SSTR2, lightweight impact-resistant ceramic screening, cross-domain resonance bridging biology, materials, and music, and formal analogy construction between urban morphology and grain-boundary evolution, the framework demonstrates heterogeneous tool chaining, emergent convergence among independently operating agents, and traceable reasoning from raw computation to published finding. --- ### In-Field 3D Wheat Head Instance Segmentation From TLS Point Clouds Using Deep Learning Without Manual Labels Authors: Tomislav Medic, Liangliang Nan Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14309v1 3D instance segmentation for laser scanning (LiDAR) point clouds remains a challenge in many remote sensing-related domains. Successful solutions typically rely on supervised deep learning and manual annotations, and consequently focus on objects that can be well delineated through visual inspection and manual labeling of point clouds. However, for tasks with more complex and cluttered scenes, such as in-field plant phenotyping in agriculture, such approaches are often infeasible. In this study, we tackle the task of in-field wheat head instance segmentation directly from terrestrial laser scanning (TLS) point clouds. To address the problem and circumvent the need for manual annotations, we propose a novel two-stage pipeline. To obtain the initial 3D instance proposals, the first stage uses 3D-to-2D multi-view projections, the Grounded SAM pipeline for zero-shot 2D object-centric segmentation, and multi-view label fusion. The second stage uses these initial proposals as noisy pseudo-labels to train a supervised 3D panoptic-style segmentation neural network. Our results demonstrate the feasibility of the proposed approach and show performance improvementsrelative to Wheat3DGS, a recent alternative solution for in-field wheat head instance segmentation without manual 3D annotations based on multi-view RGB images and 3D Gaussian Splatting, showcasing TLS as a competitive sensing alternative. Moreover, the results show that both stages of the proposed pipeline can deliver usable 3D instance segmentation without manual annotations, indicating promising, low-effort transferability to other comparable TLS-based point cloud segmentation tasks. --- ### A Physically-Grounded Attack and Adaptive Defense Framework for Real-World Low-Light Image Enhancement Authors: Tongshun Zhang, Pingping Liu, Yuqing Lei, Zixuan Zhong, Qiuzhan Zhou, Zhiyuan Zha Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14304v1 Limited illumination often causes severe physical noise and detail degradation in images. Existing Low-Light Image Enhancement (LLIE) methods frequently treat the enhancement process as a blind black-box mapping, overlooking the physical noise transformation during imaging, leading to suboptimal performance. To address this, we propose a novel LLIE approach, conceptually formulated as a physics-based attack and display-adaptive defense paradigm. Specifically, on the attack side, we establish a physics-based Degradation Synthesis (PDS) pipeline. Unlike standard data augmentation, PDS explicitly models Image Signal Processor (ISP) inversion to the RAW domain, injects physically plausible photon and read noise, and re-projects the data to the sRGB domain. This generates high-fidelity training pairs with explicitly parameterized degradation vectors, effectively simulating realistic attacks on clean signals. On the defense side, we construct a dual-layer fortified system. A noise predictor estimates degradation parameters from the input sRGB image. These estimates guide a degradation-aware Mixture of Experts (DA-MoE), which dynamically routes features to experts specialized in handling specific noise intensities. Furthermore, we introduce an Adaptive Metric Defense (AMD) mechanism, dynamically calibrating the feature embedding space based on noise severity, ensuring robust representation learning under severe degradation. Extensive experiments demonstrate that our approach offers significant plug-and-play performance enhancement for existing benchmark LLIE methods, effectively suppressing real-world noise while preserving structural fidelity. The sourced code is available at https://github.com/bywlzts/Attack-defense-llie. --- ### SemantiCache: Efficient KV Cache Compression via Semantic Chunking and Clustered Merging Authors: Shunlong Wu, Hai Lin, Shaoshen Chen, Tingwei Lu, Yongqin Zeng, Shaoxiong Zhan, Hai-Tao Zheng, Hong-Gee Kim Published: 2026-03-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.14303v1 Existing KV cache compression methods generally operate on discrete tokens or non-semantic chunks. However, such approaches often lead to semantic fragmentation, where linguistically coherent units are disrupted, causing irreversible information loss and degradation in model performance. To address this, we introduce SemantiCache, a novel compression framework that preserves semantic integrity by aligning the compression process with the semantic hierarchical nature of language. Specifically, we first partition the cache into semantically coherent chunks by delimiters, which are natural semantic boundaries. Within each chunk, we introduce a computationally efficient Greedy Seed-Based Clustering (GSC) algorithm to group tokens into semantic clusters. These clusters are further merged into semantic cores, enhanced by a Proportional Attention mechanism that rebalances the reduced attention contributions of the merged tokens. Extensive experiments across diverse benchmarks and models demonstrate that SemantiCache accelerates the decoding stage of inference by up to 2.61 times and substantially reduces memory footprint, while maintaining performance comparable to the original model. --- ### 4D Synchronized Fields: Motion-Language Gaussian Splatting for Temporal Scene Understanding Authors: Mohamed Rayan Barhdadi, Samir Abdaljalil, Rasul Khanbayov, Erchin Serpedin, Hasan Kurban Published: 2026-03-15 Categories: cs.CV, cs.AI, cs.GR arXiv: https://arxiv.org/abs/2603.14301v1 Current 4D representations decouple geometry, motion, and semantics: reconstruction methods discard interpretable motion structure; language-grounded methods attach semantics after motion is learned, blind to how objects move; and motion-aware methods encode dynamics as opaque per-point residuals without object-level organization. We propose 4D Synchronized Fields, a 4D Gaussian representation that learns object-factored motion in-loop during reconstruction and synchronizes language to the resulting kinematics through a per-object conditioned field. Each Gaussian trajectory is decomposed into shared object motion plus an implicit residual, and a kinematic-conditioned ridge map predicts temporal semantic variation, yielding a single representation in which reconstruction, motion, and semantics are structurally coupled and enabling open-vocabulary temporal queries that retrieve both objects and moments. On HyperNeRF, 4D Synchronized Fields achieves 28.52 dB mean PSNR, the highest among all language-grounded and motion-aware baselines, within 1.5 dB of reconstruction-only methods. On targeted temporal-state retrieval, the kinematic-conditioned field attains 0.884 mean accuracy, 0.815 mean vIoU, and 0.733 mean tIoU, surpassing 4D LangSplat (0.620, 0.433, and 0.439 respectively) and LangSplat (0.415, 0.304, and 0.262). Ablation confirms that kinematic conditioning is the primary driver, accounting for +0.45 tIoU over a static-embedding-only baseline. 4D Synchronized Fields is the only method that jointly exposes interpretable motion primitives and temporally grounded language fields from a single trained representation. Code will be released. --- ### Show Me When and Where: Towards Referring Video Object Segmentation in the Wild Authors: Mingqi Gao, Jinyu Yang, Jingnan Luo, Xiantong Zhen, Jungong Han, Giovanni Montana, Feng Zheng Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14300v1 Referring video object segmentation (RVOS) has recently generated great popularity in computer vision due to its widespread applications. Existing RVOS setting contains elaborately trimmed videos, with text-referred objects always appearing in all frames, which however fail to fully reflect the realistic challenges of this task. This simplified setting requires RVOS methods to only predict where objects, with no need to show when the objects appear. In this work, we introduce a new setting towards in-the-wild RVOS. To this end, we collect a new benchmark dataset using Youtube Untrimmed videos for RVOS - YoURVOS, which contains 1,120 in-the-wild videos with 7 times more duration and scenes than existing datasets. Our new benchmark challenges RVOS methods to show not only where but also when objects appear in videos. To set a baseline, we propose Object-level Multimodal TransFormers (OMFormer) to tackle the challenges, which are characterized by encoding object-level multimodal interactions for efficient and global spatial-temporal localisation. We demonstrate that previous VOS methods struggle on our YoURVOS benchmark, especially with the increase of target-absent frames, while our OMFormer consistently performs well. Our YoURVOS dataset offers an imperative benchmark, which will push forward the advancement of RVOS methods for practical applications. --- ### RL-ScanIQA: Reinforcement-Learned Scanpaths for Blind 360°Image Quality Assessment Authors: Yujia Wang, Yuyan Li, Jiuming Liu, Fang-Lue Zhang, Xinhu Zheng, Neil. A Dodgson Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14297v1 Blind 360°image quality assessment (IQA) aims to predict perceptual quality for panoramic images without a pristine reference. Unlike conventional planar images, 360°content in immersive environments restricts viewers to a limited viewport at any moment, making viewing behaviors critical to quality perception. Although existing scanpath-based approaches have attempted to model viewing behaviors by approximating the human view-then-rate paradigm, they treat scanpath generation and quality assessment as separate steps, preventing end-to-end optimization and task-aligned exploration. To address this limitation, we propose RL-ScanIQA, a reinforcement-learned framework for blind 360°IQA. RL-ScanIQA optimize a PPO-trained scanpath policy and a quality assessor, where the policy receives quality-driven feedback to learn task-relevant viewing strategies. To improve training stability and prevent mode collapse, we design multi-level rewards, including scanpath diversity and equator-biased priors. We further boost cross-dataset robustness using distortion-space augmentation together with rank-consistent losses that preserve intra-image and inter-image quality orderings. Extensive experiments on three benchmarks show that RL-ScanIQA achieves superior in-dataset performance and cross-dataset generalization. Codes are available at https://github.com/wangyuji1/RLScanIQA.git. --- ### Seeking Physics in Diffusion Noise Authors: Chujun Tang, Lei Zhong, Fangqiang Ding Published: 2026-03-15 Categories: cs.CV, cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2603.14294v3 Do video diffusion models encode signals predictive of physical plausibility? We probe intermediate denoising representations of pretrained Diffusion Transformers (DiTs) and find that physically plausible and implausible videos are partially separable in mid-layer feature space, even at high noise levels. Within-source and perceptual-quality controls suggest that this signal is not fully explained by generator identity or generic visual quality. We distill the signal into a lightweight, backbone-specific physics verifier trained on frozen features and use it in two complementary inference-time mechanisms under a fixed multi-trajectory budget: progressive trajectory selection, which scores trajectories at intermediate checkpoints and prunes weak candidates early, and reward-gradient guidance, which steers surviving trajectories by backpropagating through only the first few DiT blocks. Experiments on PhyGenBench and Physics-IQ across CogVideoX-2B/5B and Wan 2.1-14B show that progressive selection matches verifier-based Best-of-4 on CogVideoX-2B while reducing wall-clock inference time by 37%, whereas reward-gradient guidance substantially improves physical consistency on CogVideoX-5B, all without fine-tuning the video generator. --- ### RegFormer++: An Efficient Large-Scale 3D LiDAR Point Registration Network with Projection-Aware 2D Transformer Authors: Jiuming Liu, Guangming Wang, Zhe Liu, Chaokang Jiang, Haoang Li, Mengmeng Liu, Tianchen Deng, Marc Pollefeys, Michael Ying Yang, Hesheng Wang Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14290v1 Although point cloud registration has achieved remarkable advances in object-level and indoor scenes, large-scale LiDAR registration methods has been rarely explored before. Challenges mainly arise from the huge point scale, complex point distribution, and numerous outliers within outdoor LiDAR scans. In addition, most existing registration works generally adopt a two-stage paradigm: They first find correspondences by extracting discriminative local descriptors and then leverage robust estimators (e.g. RANSAC) to filter outliers, which are highly dependent on well-designed descriptors and post-processing choices. To address these problems, we propose a novel end-to-end differential transformer network, termed RegFormer++, for large-scale point cloud alignment without requiring any further post-processing. Specifically, a hierarchical projection-aware 2D transformer with linear complexity is proposed to project raw LiDAR points onto a cylindrical surface and extract global point features, which can improve resilience to outliers due to long-range dependencies. Because we fill original 3D coordinates into 2D projected positions, our designed transformer can benefit from both high efficiency in 2D processing and accuracy from 3D geometric information. Furthermore, to effectively reduce wrong point matching, a Bijective Association Transformer (BAT) is designed, combining both cross attention and all-to-all point gathering. To improve training stability and robustness, a feature-transformed optimal transport module is also designed for regressing the final pose transformation. Extensive experiments on KITTI, NuScenes, and Argoverse datasets demonstrate that our model achieves state-of-the-art performance in terms of both accuracy and efficiency. --- ### Windowed Fourier Propagator: A Frequency-Local Neural Operator for Wave Equations in Inhomogeneous Media Authors: Yiyang Cai, Zixuan Qiu, Yunlu Shu, Jiamao Wu, Yingzhou Li, Tianyu Wang, Xi Chen Published: 2026-03-15 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2603.14289v1 Wave equations are fundamental to describing a vast array of physical phenomena, yet their simulation in inhomogeneous media poses a computational challenge due to the highly oscillatory nature of the solutions. To overcome the high costs of traditional solvers, we propose the Windowed Fourier Propagator (WFP), a novel neural operator that efficiently learns the solution operator. The WFP's design is rooted in the physical principle of frequency locality, where wave energy scatters primarily to adjacent frequencies. By learning a set of compact, localized propagators, each mapping an input frequency to a small window of outputs, our method avoids the complexity of dense interaction models and achieves computational efficiency. Another key feature is the explicit preservation of superposition, which enables remarkable generalization from simple training data (e.g., plane waves) to arbitrary, complex wave states. We demonstrate that the WFP provides an explainable, efficient and accurate framework for data-driven wave modeling in complex media. --- ### MorphSNN: Adaptive Graph Diffusion and Structural Plasticity for Spiking Neural Networks Authors: Yongsheng Huang, Peibo Duan, Yujie Wu, Kai Sun, Zhipeng Liu, Jiaxiang Liu, Guangyu Li, Changsheng Zhang, Bin Zhang, Mingkun Xu Published: 2026-03-15 Categories: cs.NE arXiv: https://arxiv.org/abs/2603.14285v1 Spiking Neural Networks (SNNs) currently face a critical bottleneck: while individual neurons exhibit dynamic biological properties, their macro-scopic architectures remain confined within conventional connectivity patterns that are static and hierarchical. This discrepancy between neuron-level dynamics and network-level fixed connectivity eliminates critical brain-like lateral interactions, limiting adaptability in changing environments. To address this, we propose MorphSNN, a backbone framework inspired by biological non-synaptic diffusion and structural plasticity. Specifically, we introduce a Graph Diffusion (GD)mechanism to facilitate efficient undirected signal propagation, complementing the feedforward hierarchy. Furthermore, it incorporates a Spatio-Temporal Structural Plasticity (STSP) mechanism, endowing the network with the capability for instance-specific, dynamic topological reorganization, thereby overcoming the limitations of fixed topologies. Experiments demonstrate that MorphSNN achieves state-of-the-art accuracy on static and neuromorphic datasets; for instance, it reaches 83.35% accuracy on N-Caltech101 with only 5 timesteps. More importantly, its self-evolving topology functions as an intrinsic distribution fingerprint, enabling superior Out-of- Distribution (OOD) detection without auxiliary training. The code is available at anonymous.4open.science/r/MorphSNN-B0BC. --- ### High-Fidelity Compression of Seismic Velocity Models via SIREN Auto-Decoders Authors: Caiyun Liu, Xiaoxue Luo, Jie Xiong Published: 2026-03-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.14284v2 Implicit Neural Representations (INRs) have emerged as a powerful paradigm for representing continuous signals independently of grid resolution. In this paper, we propose a high-fidelity neural compression framework based on a SIREN (Sinusoidal Representation Networks) auto-decoder to represent multi-structural seismic velocity models from the OpenFWI benchmark. Our method compresses each 70x70 velocity map (4,900 points) into a compact 256-dimensional latent vector, achieving a compression ratio of 19:1. We evaluate the framework on 1,000 samples across five diverse geological families: FlatVel, CurveVel, FlatFault, CurveFault, and Style. Experimental results demonstrate an average PSNR of 32.47 dB and SSIM of 0.956, indicating high-quality reconstruction. Furthermore, we showcase two key advantages of our implicit representation: (1) smooth latent space interpolation that generates plausible intermediate velocity structures, and (2) zero-shot super-resolution capability that reconstructs velocity fields at arbitrary resolutions up to 280x280 without additional training. The results highlight the potential of INR-based auto-decoders for efficient storage, multi-scale analysis, and downstream geophysical applications such as full waveform inversion. --- ### AEX: Non-Intrusive Multi-Hop Attestation and Provenance for LLM APIs Authors: Yongjie Guan Published: 2026-03-15 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.14283v1 Hosted large language models are increasingly accessed through remote APIs, but the API boundary still offers little direct evidence that a returned output actually corresponds to the client-visible request. Recent audits of shadow APIs show that unofficial or intermediary endpoints can diverge from claimed behavior, while existing approaches such as fingerprinting, model-equality testing, verifiable inference, and TEE attestation either remain inferential or answer different questions. We propose AEX, a non-intrusive attestation extension for existing JSON-based LLM APIs. AEX preserves request, response, tool-calling, streaming, and error semantics, and instead adds a signed top-level attestation object that binds a client-visible request projection to either a complete response object or a committed streaming output. To support realistic deployments, AEX provides explicit request-binding modes, signed request-transform receipts for trusted intermediaries, and source-output / output-transform receipts for trusted output rewriting. For streaming, it separates checkpoint proofs for verified prefixes of an unmodified source stream from complete-output lineage for outputs that have been rewritten, buffered, aggregated, or re-packaged, preventing transformed outputs from being mistaken for source-stream prefixes. AEX therefore makes a deliberately narrow claim: a trusted issuer attests to a specific request-output relation, or to a specific complete-output lineage, at the API boundary. We present the protocol design, threat model, verification state machine, security and privacy analysis, an OpenAI-compatible chat-completions profile, and a reference TypeScript prototype with local conformance tests and microbenchmarks. --- ### Multi-Period Texture Contrast Enhancement for Low-Contrast Wafer Defect Detection and Segmentation Authors: Zihan Zhang Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14282v1 Wafer defect segmentation is pivotal for semiconductor yield optimization yet remains challenged by the intrinsic conflict between microscale anomalies and highly periodic, overwhelming background textures. Existing deep learning paradigms often falter due to feature dilution during downsampling and the lack of explicit mechanisms to disentangle low-contrast defects from process-induced noise. To transcend these limitations, we propose TexWDS, a texture-aware framework that harmonizes multi-scale feature retention with frequency-domain perturbation modeling. Our methodology incorporates three strategic innovations: (1) A Multi-scale Receptive Field Reweighting strategy is introduced to mitigate aliasing effects and preserve high-frequency details of micro-defects often lost in standard pyramidal architectures. (2) The Multi-scale Unified Semantic Enhancer (MUSE) integrates local appearance with global context encoding, effectively enhancing feature discriminability in low-visibility regions. (3) Crucially, we design a plug-and-play Multi-Periodic Texture Contrast Enhancement (MPTCE) module. By modeling texture disruptions in the frequency domain, MPTCE explicitly decouples non-periodic anomalies from structured backgrounds, boosting contrast for camouflaged defects. Extensive experiments on real-world industrial datasets demonstrate that TexWDS achieves a new state-of-the-art, surpassing the baseline by 8.3% in mAP50-95 and 7.7% in recall, while reducing the false positive rate by approximately 8.6%. These results underscore the framework's robustness in handling complex periodic patterns and its suitability for high-precision manufacturing inspection. --- ### DC-ViT: Modulating Spatial and Channel Interactions for Multi-Channel Images Authors: Umar Marikkar, Syed Sameed Husain, Muhammad Awais, Sara Atito Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14281v1 Training and evaluation in multi-channel imaging (MCI) remains challenging due to heterogeneous channel configurations arising from varying staining protocols, sensor types, and acquisition settings. This heterogeneity limits the applicability of fixed-channel encoders commonly used in general computer vision. Recent Multi-Channel Vision Transformers (MC-ViTs) address this by enabling flexible channel inputs, typically by jointly encoding patch tokens from all channels within a unified attention space. However, unrestricted token interactions across channels can lead to feature dilution, reducing the ability to preserve channel-specific semantics that are critical in MCI data. To address this, we propose Decoupled Vision Transformer (DC-ViT), which explicitly regulates information sharing using Decoupled Self-Attention (DSA), which decomposes token updates into two complementary pathways: spatial updates that model intra-channel structure, and channel-wise updates that adaptively integrate cross-channel information. This decoupling mitigates informational collapse while allowing selective inter-channel interaction. To further exploit these enhanced channel-specific representations, we introduce Decoupled Aggregation (DAG), which allows the model to learn task-specific channel importances. Extensive experiments across three MCI benchmarks demonstrate consistent improvements over existing MC-ViT approaches. --- ### All-day Multi-scenes Lifelong Vision-and-Language Navigation with Tucker Adaptation Authors: Xudong Wang, Gan Li, Zhiyu Liu, Yao Wang, Lianqing Liu, Zhi Han Published: 2026-03-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.14276v1 Deploying vision-and-language navigation (VLN) agents requires adaptation across diverse scenes and environments, but fine-tuning on a specific scenario often causes catastrophic forgetting in others, which severely limits flexible long-term deployment. We formalize this challenge as the all-day multi-scenes lifelong VLN (AML-VLN) problem. Existing parameter-efficient adapters (e.g., LoRA and its variants) are limited by their two-dimensional matrix form, which fails to capture the multi-hierarchical navigation knowledge spanning multiple scenes and environments. To address this, we propose Tucker Adaptation (TuKA), which represents the multi-hierarchical navigation knowledge as a high-order tensor and leverages Tucker decomposition to decouple the knowledge into shared subspaces and scenario-specific experts. We further introduce a decoupled knowledge incremental learning strategy to consolidate shared subspaces while constraining specific experts for decoupled lifelong learning. Building on TuKA, we also develop a VLN agent named AlldayWalker, which continually learns across multiple navigation scenarios, achieving all-day multi-scenes navigation. Extensive experiments show that AlldayWalker consistently outperforms state-of-the-art baselines. --- ### Controllable Accent Normalization via Discrete Diffusion Authors: Qibing Bai, Yuhan Du, Tom Ko, Shuai Wang, Yannan Wang, Haizhou Li Published: 2026-03-15 Categories: eess.AS, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2603.14275v2 Existing accent normalization methods do not typically offer control over accent strength, yet many applications-such as language learning and dubbing-require tunable accent retention. We propose DLM-AN, a controllable accent normalization system built on masked discrete diffusion over self-supervised speech tokens. A Common Token Predictor identifies source tokens that likely encode native pronunciation; these tokens are selectively reused to initialize the reverse diffusion process. This provides a simple yet effective mechanism for controlling accent strength: reusing more tokens preserves more of the original accent. DLM-AN further incorporates a flow-matching Duration Ratio Predictor that automatically adjusts the total duration to better match the native rhythm. Experiments on multi-accent English data show that DLM-AN achieves the lowest word error rate among all compared systems while delivering competitive accent reduction and smooth, interpretable accent strength control. --- ### Learning in Function Spaces: An Unified Functional Analytic View of Supervised and Unsupervised Learning Authors: K. Lakshmanan Published: 2026-03-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.14272v1 Many machine learning algorithms can be interpreted as procedures for estimating functions defined on the data distribution. In this paper we present a conceptual framework that formulates a wide range of learning problems as variational optimization over function spaces induced by the data distribution. Within this framework the data distribution defines operators that capture structural properties of the data, such as similarity relations or statistical dependencies. Learning algorithms can then be viewed as estimating functions expressed in bases determined by these operators. This perspective provides a unified way to interpret several learning paradigms. In supervised learning the objective functional is defined using labeled data and typically corresponds to minimizing prediction risk, whereas unsupervised learning relies on structural properties of the input distribution and leads to objectives based on similarity or smoothness constraints. From this viewpoint, the distinction between learning paradigms arises primarily from the choice of the functional being optimized rather than from the underlying function space. We illustrate this framework by discussing connections with kernel methods, spectral clustering, and manifold learning, highlighting how operators induced by data distributions naturally define function representations used by learning algorithms. The goal of this work is not to introduce a new algorithm but to provide a conceptual framework that clarifies the role of function spaces and operators in modern machine learning. --- ### Toward Clinically Ready Foundation Models in Medical Image Analysis: Adaptation Mechanisms and Deployment Trade-offs Authors: Karma Phuntsho, Abdullah, Kyungmi Lee, Ickjai Lee, Euijoon Ahn Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14271v1 Foundation models (FMs) have demonstrated strong transferability across medical imaging tasks, yet their clinical utility depends critically on how pretrained representations are adapted to domain-specific data, supervision regimes, and deployment constraints. Prior surveys primarily emphasize architectural advances and application coverage, while the mechanisms of adaptation and their implications for robustness, calibration, and regulatory feasibility remain insufficiently structured. This review introduces a strategy-centric framework for FM adaptation in medical image analysis (MIA). We conceptualize adaptation as a post-pretraining intervention and organize existing approaches into five mechanisms: parameter-, representation-, objective-, data-centric, and architectural/sequence-level adaptation. For each mechanism, we analyze trade-offs in adaptation depth, label efficiency, domain robustness, computational cost, auditability, and regulatory burden. We synthesize evidence across classification, segmentation, and detection tasks, highlighting how adaptation strategies influence clinically relevant failure modes rather than only aggregate benchmark performance. Finally, we examine how adaptation choices interact with validation protocols, calibration stability, multi-institutional deployment, and regulatory oversight. By reframing adaptation as a process of controlled representational change under clinical constraints, this review provides practical guidance for designing FM-based systems that are robust, auditable, and compatible with clinical deployment. --- ### DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization Authors: Ngoc-Son Nguyen, Thanh V. T. Tran, Jeongsoo Choi, Hieu-Nghia Huynh-Nguyen, Truong-Son Hy, Van Nguyen Published: 2026-03-15 Categories: cs.CV, cs.AI, cs.MM, cs.SD arXiv: https://arxiv.org/abs/2603.14267v4 Video dubbing requires content accuracy, expressive prosody, high-quality acoustics, and precise lip synchronization, yet existing approaches struggle on all four fronts. To address these issues, we propose DiFlowDubber, the first video dubbing framework built upon a discrete flow matching backbone with a novel two-stage training strategy. In the first stage, a zero-shot text-to-speech (TTS) system is pre-trained on large-scale corpora, where a deterministic architecture captures linguistic structures, and the Discrete Flow-based Prosody-Acoustic (DFPA) module models expressive prosody and realistic acoustic characteristics. In the second stage, we propose the Content-Consistent Temporal Adaptation (CCTA) to transfer TTS knowledge to the dubbing domain: its Synchronizer enforces cross-modal alignment for lip-synchronized speech. Complementarily, the Face-to-Prosody Mapper (FaPro) conditions prosody on facial expressions, whose outputs are then fused with those of the Synchronizer to construct rich, fine-grained multimodal embeddings that capture prosody-content correlations, guiding the DFPA to generate expressive prosody and acoustic tokens for content-consistent speech. Experiments on two benchmark datasets demonstrate that DiFlowDubber outperforms prior methods across multiple evaluation metrics. --- ### MedPriv-Bench: Benchmarking the Privacy-Utility Trade-off of Large Language Models in Medical Open-Ended Question Answering Authors: Shaowei Guan, Yu Zhai, Hin Chi Kwok, Jiawei Du, Xinyu Feng, Jing Li, Harry Qin, Vivian Hui Published: 2026-03-15 Categories: cs.CL, cs.MA arXiv: https://arxiv.org/abs/2603.14265v2 Recent advances in Retrieval-Augmented Generation enable LLMs to ground outputs in clinical evidence, but connections to external databases create the risk of contextual leakage, where unique combinations of medical details enable patient re-identification without explicit identifiers. Existing healthcare benchmarks emphasize accuracy while overlooking this risk. To fill this gap, we present MedPriv-Bench, the first benchmark for jointly evaluating privacy preservation and clinical utility in medical open-ended question answering. Our framework utilizes a multi-agent, human-in-the-loop pipeline to synthesize sensitive medical contexts and clinically relevant queries that create realistic privacy pressure. We also establish an automated evaluation protocol using a fine-tuned RoBERTa-NLI model, which achieved an instance-level F1 score of 75.3%, sensitivity of 90.7%, and an average inference time of 0.056 s per sample against human annotations. Across nine LLMs and three privacy-preserving methods, we observed a pervasive privacy-utility trade-off. Relative to unprotected Med42-v2-8B (utility 3.87/5; leakage 72.8%), supervised fine-tuning improved utility to 4.25 and reduced leakage to 38.9%, whereas local differential privacy reduced leakage to 20.5% but lowered utility to 3.03. These results demonstrate the need for domain-specific benchmarks to validate medical AI systems in privacy-sensitive settings. --- ### MedPriv-Bench: Benchmarking the Privacy-Utility Trade-off of Large Language Models in Medical Open-End Question Answering Authors: Shaowei Guan, Yu Zhai, Hin Chi Kwok, Jiawei Du, Xinyu Feng, Jing Li, Harry Qin, Vivian Hui Published: 2026-03-15 Categories: cs.CL, cs.MA arXiv: https://arxiv.org/abs/2603.14265v1 Recent advances in Retrieval-Augmented Generation (RAG) have enabled large language models (LLMs) to ground outputs in clinical evidence. However, connecting LLMs with external databases introduces the risk of contextual leakage: a subtle privacy threat where unique combinations of medical details enable patient re-identification even without explicit identifiers. Current benchmarks in healthcare heavily focus on accuracy, ignoring such privacy issues, despite strict regulations like Health Insurance Portability and Accountability Act (HIPAA) and General Data Protection Regulation (GDPR). To fill this gap, we present MedPriv-Bench, the first benchmark specifically designed to jointly evaluate privacy preservation and clinical utility in medical open-ended question answering. Our framework utilizes a multi-agent, human-in-the-loop pipeline to synthesize sensitive medical contexts and clinically relevant queries that create realistic privacy pressure. We establish a standardized evaluation protocol leveraging a pre-trained RoBERTa-Natural Language Inference (NLI) model as an automated judge to quantify data leakage, achieving an average of 85.9% alignment with human experts. Through an extensive evaluation of 9 representative LLMs, we demonstrate a pervasive privacy-utility trade-off. Our findings underscore the necessity of domain-specific benchmarks to validate the safety and efficacy of medical AI systems in privacy-sensitive environments. --- ### GenRecEdit: Adapting Model Editing for Generative Recommendation with Cold-Start Items Authors: Chenglei Shen, Teng Shi, Weijie Yu, Xiao Zhang, Jun Xu Published: 2026-03-15 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2603.14259v2 Generative recommendation (GR) has shown strong potential for sequential recommendation in an end-to-end generation paradigm. However, existing GR models suffer from severe cold-start collapse: their recommendation accuracy on cold-start items can drop to near zero. Current solutions typically rely on retraining with cold-start interactions, which is hindered by sparse feedback, high computational cost, and delayed updates, limiting practical utility in rapidly evolving recommendation catalogs. Inspired by model editing in NLP, which enables training-free knowledge injection into large language models, we explore how to bring this paradigm to generative recommendation. This, however, faces two key challenges: GR lacks the explicit subject-object binding common in natural language, making targeted edits difficult; and GR does not exhibit stable token co-occurrence patterns, making the injection of multi-token item representations unreliable. To address these challenges, we propose GenRecEdit, a model editing framework tailored for generative recommendation. GenRecEdit explicitly models the relationship between the full sequence context and next-token generation, adopts iterative token-level editing to inject multi-token item representations, and introduces a one-to-one trigger mechanism to reduce interference among multiple edits during inference. Extensive experiments on multiple datasets show that GenRecEdit substantially improves recommendation performance on cold-start items while preserving the model's original recommendation quality. Moreover, it achieves these gains using only about 9.5% of the training time required for retraining, enabling more efficient and frequent model updates. --- ### Sampling Boltzmann distributions via normalizing flow approximation of transport maps Authors: Zia Ur Rehman, Gero Friesecke Published: 2026-03-15 Categories: cs.LG, math.NA, math.PR arXiv: https://arxiv.org/abs/2603.14258v1 In a celebrated paper \cite{noe2019boltzmann}, Noé, Olsson, Köhler and Wu introduced an efficient method for sampling high-dimensional Boltzmann distributions arising in molecular dynamics via normalizing flow approximation of transport maps. Here, we place this approach on a firm mathematical foundation. We prove the existence of a normalizing flow between the reference measure and the true Boltzmann distribution up to an arbitrarily small error in the Wasserstein distance. This result covers general Boltzmann distributions from molecular dynamics, which have low regularity due to the presence of interatomic Coulomb and Lennard-Jones interactions. The proof is based on a rigorous construction of the Moser transport map for low-regularity endpoint densities and approximation theorems for neural networks in Sobolev spaces. Numerical simulations for a simple model system and for the alanine dipeptide molecule confirm that the true and generated distributions are close in the Wasserstein distance. Moreover we observe that the RealNVP architecture does not just successfully capture the equilibrium Boltzmann distribution but also the metastable dynamics. --- ### Automatic Inter-document Multi-hop Scientific QA Generation Authors: Seungmin Lee, Dongha Kim, Yuni Jeon, Junyoung Koh, Min Song Published: 2026-03-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.14257v1 Existing automatic scientific question generation studies mainly focus on single-document factoid QA, overlooking the inter-document reasoning crucial for scientific understanding. We present AIM-SciQA, an automated framework for generating multi-document, multi-hop scientific QA datasets. AIM-SciQA extracts single-hop QAs using large language models (LLMs) with machine reading comprehension and constructs cross-document relations based on embedding-based semantic alignment while selectively leveraging citation information. Applied to 8,211 PubMed Central papers, it produced 411,409 single-hop and 13,672 multi-hop QAs, forming the IM-SciQA dataset. Human and automatic validation confirmed high factual consistency, and experimental results demonstrate that IM-SciQA effectively differentiates reasoning capabilities across retrieval and QA stages, providing a realistic and interpretable benchmark for retrieval-augmented scientific reasoning. We further extend this framework to construct CIM-SciQA, a citation-guided variant achieving comparable performance to the Oracle setting, reinforcing the dataset's validity and generality. --- ### ITKIT: Feasible CT Image Analysis based on SimpleITK and MMEngine Authors: Yiqin Zhang, Meiling Chen Published: 2026-03-15 Categories: cs.SE, cs.CV arXiv: https://arxiv.org/abs/2603.14255v2 CT images are widely used in clinical diagnosis and treatment, and their data have formed a de facto standard - DICOM. It is clear and easy to use, and can be efficiently utilized by data-driven analysis methods such as deep learning. In the past decade, many program frameworks for medical image analysis have emerged in the open-source community. ITKIT analyzed the characteristics of these frameworks and hopes to provide a better choice in terms of ease of use and configurability. ITKIT offers a complete pipeline from DICOM to 3D segmentation inference. Its basic practice only includes some essential steps, enabling users with relatively weak computing capabilities to quickly get started using the CLI according to the documentation. For advanced users, the OneDL-MMEngine framework provides a flexible model configuration and deployment entry. This paper conducted 12 typical experiments to verify that ITKIT can meet the needs of most basic scenarios. --- ### ZOTTA: Test-Time Adaptation with Gradient-Free Zeroth-Order Optimization Authors: Ronghao Zhang, Shuaicheng Niu, Qi Deng, Yanjie Dong, Jian Chen, Runhao Zeng Published: 2026-03-15 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.14254v2 Test-time adaptation (TTA) aims to improve model robustness under distribution shifts by adapting to unlabeled test data, but most existing methods rely on backpropagation (BP), which is computationally costly and incompatible with non-differentiable models such as quantized models, limiting practical deployment on numerous edge devices. Recent BP-free approaches alleviate overhead but remain either architecture-specific or limited in optimization capacity to handle high-dimensional models. We propose ZOTTA, a fully BP-free TTA framework that performs efficient adaptation using only forward passes via Zeroth-Order Optimization (ZOO). While ZOO is theoretically appealing, naive application leads to slow convergence under high-dimensional parameter spaces and unstable optimization due to the lack of labels. ZOTTA overcomes these challenges through 1) Distribution-Robust Layer Selection, which automatically identifies and freezes layers that already extract distribution-invariant features, updating only domain-sensitive layers to reduce the optimization dimensionality and accelerate convergence; 2) Spatial Feature Aggregation Alignment, which stabilizes ZOO by aligning globally aggregated spatial features between source and target to reduce gradient variance. Together, these components enable architecture-agnostic and stable BP-free adaptation. Extensive experiments on ImageNet-C/R/Sketch/A show that ZOTTA outperforms or matches BP-based methods, e.g., it reduces memory usage by 84% and improves accuracy by 3.9% over SAR on ImageNet-C. Code:https://github.com/Zhang-Ronghao/zotta. --- ### ZOTTA: Test-Time Adaptation with Gradient-Free Zeroth-Order Optimization Authors: Ronghao Zhang, Shuaicheng Niu, Qi Deng, Yanjie Dong, Jian Chen, Runhao Zeng Published: 2026-03-15 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.14254v1 Test-time adaptation (TTA) aims to improve model robustness under distribution shifts by adapting to unlabeled test data, but most existing methods rely on backpropagation (BP), which is computationally costly and incompatible with non-differentiable models such as quantized models, limiting practical deployment on numerous edge devices. Recent BP-free approaches alleviate overhead but remain either architecture-specific or limited in optimization capacity to handle high-dimensional models. We propose ZOTTA, a fully BP-free TTA framework that performs efficient adaptation using only forward passes via Zeroth-Order Optimization (ZOO). While ZOO is theoretically appealing, naive application leads to slow convergence under high-dimensional parameter spaces and unstable optimization due to the lack of labels. ZOTTA overcomes these challenges through 1) Distribution-Robust Layer Selection, which automatically identifies and freezes layers that already extract distribution-invariant features, updating only domain-sensitive layers to reduce the optimization dimensionality and accelerate convergence; 2) Spatial Feature Aggregation Alignment, which stabilizes ZOO by aligning globally aggregated spatial features between source and target to reduce gradient variance. Together, these components enable architecture-agnostic and stable BP-free adaptation. Extensive experiments on ImageNet-C/R/Sketch/A show that ZOTTA outperforms or matches BP-based methods, e.g., it reduces memory usage by 84% and improves accuracy by 3.9% over SAR on ImageNet-C. --- ### MistExit: Learning to Exit for Early Mistake Detection in Procedural Videos Authors: Sagnik Majumder, Anish Nethi, Ziad Al-Halah, Kristen Grauman Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14252v1 We introduce the task of early mistake detection in video, where the goal is to determine whether a keystep in a procedural activity is performed correctly while observing as little of the streaming video as possible. To tackle this problem, we propose a method comprising a mistake detector and a reinforcement learning policy. At each timestep, the detector processes recently observed frames to estimate the keystep's correctness while anticipating future visual features, enabling reliable early mistake estimates. Meanwhile, the policy aggregates the detector outputs and visual observations over time and adaptively decides when to exit (i.e., stop processing incoming frames) while producing the final prediction. Using diverse real-world procedural video datasets, we demonstrate that our MistExit model achieves superior mistake detection accuracy while reducing the fraction of video observed compared to state-of-the-art models. Project: https://vision.cs.utexas.edu/projects/mist_exit. --- ### Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring Authors: Weixin Guan, Liang Li, Jiapeng Liu, Bing Li, Peng Fu, Chengyang Fang, Xiaoshuai Hao, Can Ma, Weiping Wang Published: 2026-03-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.14251v1 Large Reasoning Language Models (LRLMs) demonstrate impressive capabilities on complex tasks by utilizing long Chain-of-Thought reasoning. However, they are prone to overthinking, which generates redundant reasoning steps that degrade both performance and efficiency. Recently, early-exit strategies are proposed to mitigate overthinking by dynamically and adaptively terminating redundant reasoning. However, current early-exit methods either introduce extra training overhead by relying on proxy models or limit inference throughput due to the frequent content switching between reasoning and generating probing answers. Moreover, most early-exit methods harm LRLMs performance due to over-truncation. Our insight stems from an observation: overthinking often causes LRLMs to deviate from the correct reasoning path, which is frequently accompanied by high-entropy transition tokens. Given this, we propose an early-exit method deeply coupled with the native reasoning process, which leverages the path deviation index as a dedicated monitoring metric for the frequent occurrence of high-entropy transition tokens to dynamically detect and terminate overthinking trajectories. We conduct experiments across multiple benchmarks using LRLMs of different types and scales, and the results indicate that our method delivers the largest performance improvement over vanilla CoT compared to existing early-exit methods. --- ### OAHuman: Occlusion-Aware 3D Human Reconstruction from Monocular Images Authors: Yuanwang Yang, Hongliang Liu, Muxin Zhang, Nan Ma, Jingyu Yang, Yu-Kun Lai, Kun Li Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14249v1 Monocular 3D human reconstruction in real-world scenarios remains highly challenging due to frequent occlusions from surrounding objects, people, or image truncation. Such occlusions lead to missing geometry and unreliable appearance cues, severely degrading the completeness and realism of reconstructed human models. Although recent neural implicit methods achieve impressive results on clean inputs, they struggle under occlusion due to entangled modeling of shape and texture. In this paper, we propose OAHuman, an occlusion-aware framework that explicitly decouples geometry reconstruction and texture synthesis for robust 3D human modeling from a single RGB image. The core innovation lies in the decoupling-perception paradigm, which addresses the fundamental issue of geometry-texture cross-contamination in occluded regions. Our framework ensures that geometry reconstruction is perceptually reinforced even in occluded areas, isolating it from texture interference. In parallel, texture synthesis is learned exclusively from visible regions, preventing texture errors from being transferred to the occluded areas. This decoupling approach enables OAHuman to achieve robust and high-fidelity reconstruction under occlusion, which has been a long-standing challenge in the field. Extensive experiments on occlusion-rich benchmarks demonstrate that OAHuman achieves superior performance in terms of structural completeness, surface detail, and texture realism, significantly improving monocular 3D human reconstruction under occlusion conditions. --- ### Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspective Authors: Mohamed Aghzal, Gregory J. Stein, Ziyu Yao Published: 2026-03-15 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.14248v2 Large language model (LLM) web agents are increasingly used for web navigation but remain far from human reliability on realistic, long-horizon tasks. Existing evaluations focus primarily on end-to-end success, offering limited insight into where failures arise. We propose a hierarchical planning framework to analyze web agents across three layers (i.e., high-level planning, low-level execution, and replanning), enabling process-based evaluation of reasoning, grounding, and recovery. Our experiments show that structured Planning Domain Definition Language (PDDL) plans produce more concise and goal-directed strategies than natural language (NL) plans, but low-level execution remains the dominant bottleneck. These results indicate that improving perceptual grounding and adaptive control, not only high-level reasoning, is critical for achieving human-level reliability. This hierarchical perspective provides a principled foundation for diagnosing and advancing LLM web agents. --- ### GoldenStart: Q-Guided Priors and Entropy Control for Distilling Flow Policies Authors: He Zhang, Ying Sun, Hui Xiong Published: 2026-03-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.14245v1 Flow-matching policies hold great promise for reinforcement learning (RL) by capturing complex, multi-modal action distributions. However, their practical application is often hindered by prohibitive inference latency and ineffective online exploration. Although recent works have employed one-step distillation for fast inference, the structure of the initial noise distribution remains an overlooked factor that presents significant untapped potential. This overlooked factor, along with the challenge of controlling policy stochasticity, constitutes two critical areas for advancing distilled flow-matching policies. To overcome these limitations, we propose GoldenStart (GSFlow), a policy distillation method with Q-guided priors and explicit entropy control. Instead of initializing generation from uninformed noise, we introduce a Q-guided prior modeled by a conditional VAE. This state-conditioned prior repositions the starting points of the one-step generation process into high-Q regions, effectively providing a "golden start" that shortcuts the policy to promising actions. Furthermore, for effective online exploration, we enable our distilled actor to output a stochastic distribution instead of a deterministic point. This is governed by entropy regularization, allowing the policy to shift from pure exploitation to principled exploration. Our integrated framework demonstrates that by designing the generative startpoint and explicitly controlling policy entropy, it is possible to achieve efficient and exploratory policies, bridging the generative models and the practical actor-critic methods. We conduct extensive experiments on offline and online continuous control benchmarks, where our method significantly outperforms prior state-of-the-art approaches. Code will be available at https://github.com/ZhHe11/GSFlow-RL. --- ### BIT: Matching-based Bi-directional Interaction Transformation Network for Visible-Infrared Person Re-Identification Authors: Haoxuan Xu, Guanglin Niu Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14243v1 Visible-Infrared Person Re-Identification (VI-ReID) is a challenging retrieval task due to the substantial modality gap between visible and infrared images. While existing methods attempt to bridge this gap by learning modality-invariant features within a shared embedding space, they often overlook the complex and implicit correlations between modalities. This limitation becomes more severe under distribution shifts, where infrared samples are often far fewer than visible ones. To address these challenges, we propose a novel network termed Bi-directional Interaction Transformation (BIT). Instead of relying on rigid feature alignment, BIT adopts a matching-based strategy that explicitly models the interaction between visible and infrared image pairs. Specifically, BIT employs an encoder-decoder architecture where the encoder extracts preliminary feature representations, and the decoder performs bi-directional feature integration and query aware scoring to enhance cross-modality correspondence. To our best knowledge, BIT is the first to introduce such pairwise matching-driven interaction in VI-ReID. Extensive experiments on several benchmarks demonstrate that our BIT achieves state-of-the-art performance, highlighting its effectiveness in the VI-ReID task. --- ### CamLit: Unified Video Diffusion with Explicit Camera and Lighting Control Authors: Zhiyi Kuang, Chengan He, Egor Zakharov, Yuxuan Xue, Shunsuke Saito, Olivier Maury, Timur Bagautdinov, Youyi Zheng, Giljoo Nam Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14241v1 We present CamLit, the first unified video diffusion model that jointly performs novel view synthesis (NVS) and relighting from a single input image. Given one reference image, a user-defined camera trajectory, and an environment map, CamLit synthesizes a video of the scene from new viewpoints under the specified illumination. Within a single generative process, our model produces temporally coherent and spatially aligned outputs, including relit novel-view frames and corresponding albedo frames, enabling high-quality control of both camera pose and lighting. Qualitative and quantitative experiments demonstrate that CamLit achieves high-fidelity outputs on par with state-of-the-art methods in both novel view synthesis and relighting, without sacrificing visual quality in either task. We show that a single generative model can effectively integrate camera and lighting control, simplifying the video generation pipeline while maintaining competitive performance and consistent realism. --- ### FOCUS: Bridging Fine-Grained Recognition and Open-World Discovery across Domains Authors: Vaibhav Rathore, Divyam Gupta, Moloud Abdar, Subhasis Chaudhuri, Biplab Banerjee Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14240v1 We introduce the first unified framework for *Fine-Grained Domain-Generalized Generalized Category Discovery* (FG-DG-GCD), bringing open-world recognition closer to real-world deployment under domain shift. Unlike conventional GCD, which assumes labeled and unlabeled data come from the same distribution, DG-GCD learns only from labeled source data and must both recognize known classes and discover novel ones in unseen, unlabeled target domains. This problem is especially challenging in fine-grained settings, where subtle inter-class differences and large intra-class variation make domain generalization significantly harder. To support systematic evaluation, we establish the first *FG-DG-GCD benchmarks* by creating identity-preserving *painting* and *sketch* domains for CUB-200-2011, Stanford Cars, and FGVC-Aircraft using controlled diffusion-adapter stylization. On top of this ,we propose FoCUS, a single-stage framework that combines *Domain-Consistent Parts Discovery* (DCPD) for geometry-stable part reasoning with *Uncertainty-Aware Feature Augmentation* (UFA) for confidence-calibrated feature regularization through uncertainty-guided perturbations. Extensive experiments show that FoCUS outperforms strong GCD, FG-GCD, and DG-GCD baselines by **3.28%**, **9.68%**, and **2.07%**, respectively, in clustering accuracy on the proposed benchmarks. It also remains competitive on coarse-grained DG-GCD tasks while achieving nearly **3x** higher computational efficiency than the current state of the art. ^(Code and datasets will be released upon acceptance.) --- ### QiMeng-CodeV-SVA: Training Specialized LLMs for Hardware Assertion Generation via RTL-Grounded Bidirectional Data Synthesis Authors: Yutong Wu, Chenrui Cao, Pengwei Jin, Di Huang, Rui Zhang, Xishan Zhang, Zidong Du, Qi Guo, Xing Hu Published: 2026-03-15 Categories: cs.CL, cs.AI, cs.AR, cs.LG arXiv: https://arxiv.org/abs/2603.14239v1 SystemVerilog Assertions (SVAs) are crucial for hardware verification. Recent studies leverage general-purpose LLMs to translate natural language properties to SVAs (NL2SVA), but they perform poorly due to limited data. We propose a data synthesis framework to tackle two challenges: the scarcity of high-quality real-world SVA corpora and the lack of reliable methods to determine NL-SVA semantic equivalence. For the former, large-scale open-source RTLs are used to guide LLMs to generate real-world SVAs; for the latter, bidirectional translation serves as a data selection method. With the synthesized data, we train CodeV-SVA, a series of SVA generation models. Notably, CodeV-SVA-14B achieves 75.8% on NL2SVA-Human and 84.0% on NL2SVA-Machine in Func.@1, matching or exceeding advanced LLMs like GPT-5 and DeepSeek-R1. --- ### Domain-Skewed Federated Learning with Feature Decoupling and Calibration Authors: Huan Wang, Jun Shen, Jun Yan, Guansong Pang Published: 2026-03-15 Categories: cs.LG, cs.MM arXiv: https://arxiv.org/abs/2603.14238v1 Federated learning (FL) allows distributed clients to collaboratively train a global model in a privacy-preserving manner. However, one major challenge is domain skew, where clients' data originating from diverse domains may hinder the aggregated global model from learning a consistent representation space, resulting in poor generalizable ability in multiple domains. In this paper, we argue that the domain skew is reflected in the domain-specific biased features of each client, causing the local model's representations to collapse into a narrow low-dimensional subspace. We then propose Federated Feature Decoupling and Calibration ($F^2$DC), which liberates valuable class-relevant information by calibrating the domain-specific biased features, enabling more consistent representations across domains. A novel component, Domain Feature Decoupler (DFD), is first introduced in $F^2$DC to determine the robustness of each feature unit, thereby separating the local features into domain-robust features and domain-related features. A Domain Feature Corrector (DFC) is further proposed to calibrate these domain-related features by explicitly linking discriminative signals, capturing additional class-relevant clues that complement the domain-robust features. Finally, a domain-aware aggregation of the local models is performed to promote consensus among clients. Empirical results on three popular multi-domain datasets demonstrate the effectiveness of the proposed $F^2$DC and the contributions of its two modules. Code is available at https://github.com/mala-lab/F2DC. --- ### S2GS: Streaming Semantic Gaussian Splatting for Online Scene Understanding and Reconstruction Authors: Renhe Zhang, Yuyang Tan, Jingyu Gong, Zhizhong Zhang, Lizhuang Ma, Yuan Xie, Xin Tan Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14232v1 Existing offline feed-forward methods for joint scene understanding and reconstruction on long image streams often repeatedly perform global computation over an ever-growing set of past observations, causing runtime and GPU memory to increase rapidly with sequence length and limiting scalability. We propose Streaming Semantic Gaussian Splatting (S2GS), a strictly causal, incremental 3D Gaussian semantic field framework: it does not leverage future frames and continuously updates scene geometry, appearance, and instance-level semantics without reprocessing historical frames, enabling scalable online joint reconstruction and understanding. S2GS adopts a geometry-semantic decoupled dual-backbone design: the geometry branch performs causal modeling to drive incremental Gaussian updates, while the semantic branch leverages a 2D foundation vision model and a query-driven decoder to predict segmentation masks and identity embeddings, further stabilized by query-level contrastive alignment and lightweight online association with an instance memory. Experiments show that S2GS matches or outperforms strong offline baselines on joint reconstruction-and-understanding benchmarks, while significantly improving long-horizon scalability: it processes 1,000+ frames with much slower growth in runtime and GPU memory, whereas offline global-processing baselines typically run out of memory at around 80 frames under the same setting. --- ### Agentic DAG-Orchestrated Planner Framework for Multi-Modal, Multi-Hop Question Answering in Hybrid Data Lakes Authors: Kirushikesh D B, Manish Kesarwani, Nishtha Madaan, Sameep Mehta, Aldrin Dennis, Siddarth Ajay, Rakesh B R, Renu Rajagopal, Sudheesh Kairali Published: 2026-03-15 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2603.14229v1 Enterprises increasingly need natural language (NL) question answering over hybrid data lakes that combine structured tables and unstructured documents. Current deployed solutions, including RAG-based systems, typically rely on brute-force retrieval from each store and post-hoc merging. Such approaches are inefficient and leaky, and more critically, they lack explicit support for multi-hop reasoning, where a query is decomposed into successive steps (hops) that may traverse back and forth between structured and unstructured sources. We present Agentic DAG-Orchestrated Transformer (A.DOT) Planner, a framework for multi-modal, multi-hop question answering, that compiles user NL queries into directed acyclic graph (DAG) execution plans spanning both structured and unstructured stores. The system decomposes queries into parallelizable sub-queries, incorporates schema-aware reasoning, and applies both structural and semantic validation before execution. The execution engine adheres to the generated DAG plan to coordinate concurrent retrieval across heterogeneous sources, route intermediate outputs to dependent sub-queries, and merge final results in strict accordance with the plan's logical dependencies. Advanced caching mechanisms, incorporating paraphrase-aware template matching, enable the system to detect equivalent queries and reuse prior DAG execution plans for rapid re-execution, while the DataOps System addresses validation feedback or execution errors. The proposed framework not only improves accuracy and latency, but also produces explicit evidence trails, enabling verification of retrieved content, tracing of data lineage, and fostering user trust in the system's outputs. On benchmark dataset, A.DOT achieves 14.8% absolute gain in correctness and 10.7% in completeness over baselines. --- ### Not All Directions Matter: Towards Structured and Task-Aware Low-Rank Model Adaptation Authors: Xi Xiao, Chenrui Ma, Yunbei Zhang, Chen Liu, Zhuxuanzi Wang, Yanshu Li, Lin Zhao, Guosheng Hu, Tianyang Wang, Hao Xu Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14228v2 Low-Rank Adaptation (LoRA) has become a cornerstone of parameter-efficient fine-tuning (PEFT). Yet, its efficacy is hampered by two fundamental limitations: semantic drift, by treating all update directions with equal importance, and structural incoherence, from adapting layers independently, resulting in suboptimal, uncoordinated updates. To remedy these, we propose StructLoRA, a framework that addresses both limitations through a principled, dual-component design: (1) an Information Bottleneck-guided filter that prunes task-irrelevant directions to mitigate semantic drift, and (2) a lightweight, training-only graph-based coordinator that enforces inter-layer consistency to resolve structural incoherence. Extensive experiments across large language model , vision language model, and vision model (including LLaMA, LLaVA, and ViT) demonstrate that StructLoRA consistently establishes a new state-of-the-art, outperforming not only vanilla LoRA but also advanced dynamic rank allocation and sparsity-based methods. Notably, the benefits are particularly pronounced in challenging low-rank and low-data regimes. Crucially, since our proposed modules operate only during training, StructLoRA enhances performance with zero additional inference cost, advancing the focus of PEFT -- from mere parameter compression to a more holistic optimization of information quality and structural integrity. ---