# Research Papers — 2026-03 · bundle page 25 of 243

> Full-text markdown of papers #1201–1250 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/25
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/24.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/26.md)

### TrackMAE: Video Representation Learning via Track Mask and Predict

Authors: Renaud Vandeghen, Fida Mohammad Thoker, Marc Van Droogenbroeck, Bernard Ghanem
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27268v1

Masked video modeling (MVM) has emerged as a simple and scalable self-supervised pretraining paradigm, but only encodes motion information implicitly, limiting the encoding of temporal dynamics in the learned representations. As a result, such models struggle on motion-centric tasks that require fine-grained motion awareness. To address this, we propose TrackMAE, a simple masked video modeling paradigm that explicitly uses motion information as a reconstruction signal. In TrackMAE, we use an off-the-shelf point tracker to sparsely track points in the input videos, generating motion trajectories. Furthermore, we exploit the extracted trajectories to improve random tube masking with a motion-aware masking strategy. We enhance video representations learned in both pixel and feature semantic reconstruction spaces by providing a complementary supervision signal in the form of motion targets. We evaluate on six datasets across diverse downstream settings and find that TrackMAE consistently outperforms state-of-the-art video self-supervised learning baselines, learning more discriminative and generalizable representations. Code available at https://github.com/rvandeghen/TrackMAE

---

### TrendGen: An Outfit Recommendation and Display System

Authors: Theodoros Koukopoulos, Dimos Klimenof, Ioannis Xarchakos
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27264v1

Recent advances in Computer Vision have significantly improved image understanding and generation, revolutionizing the fashion industry. However, challenges such as inconsistent lighting, non-ideal garment angles, complex backgrounds, and occlusions in raw images hinder their full potential. Overcoming these obstacles is crucial for developing robust fashion AI systems capable of real-world applications. In this paper, we introduce TrendGen, a Fashion AI system designed to enhance online shopping with intelligent outfit recommendations. Deployed on a major e-commerce platform, TrendGen leverages cloth images and product attributes to generate trend-aligned, cohesive outfit suggestions. Additionally, it employs Generative AI to transform raw images into high-quality lay-down views, offering a clear and structured presentation of garments. Our evaluation on production data demonstrates TrendGen's consistent high-quality outfits and lay-down images, marking a significant advancement in AI-driven solutions for fashion retail.

---

### MD-RWKV-UNet: Scale-Aware Anatomical Encoding with Cross-Stage Fusion for Multi-Organ Segmentation

Authors: Zhuoyi Fang
Published: 2026-03-28
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2603.27261v1

Multi-organ segmentation in medical imaging remains challenging due to large anatomical variability, complex inter-organ dependencies, and diverse organ scales and shapes. Conventional encoder-decoder architectures often struggle to capture both fine-grained local details and long-range context, which are crucial for accurate delineation - especially for small or deformable organs. To address these limitations, we propose MD-RWKV-UNet, a dynamic encoder network that enables scale-aware representation and spatially adaptive context modeling. At its core is the MD-RWKV block, a dual-path module that integrates deformable spatial shifts with the Receptance Weighted Key Value mechanism, allowing the receptive field to adapt dynamically to local structural cues. We further incorporate Selective Kernel Attention to enable adaptive selection of convolutional kernels with varying receptive fields, enhancing multi-scale interaction and improving robustness to organ size and shape variation. In parallel, a cross-stage dual-attention fusion strategy aggregates multi-level features across the encoder, preserving low-level structure while enhancing semantic consistency. Unlike methods that stack static convolutions or rely heavily on global attention, our approach provides a lightweight yet expressive solution for dynamic organ modeling. Experiments on Synapse and ACDC demonstrate state-of-the-art performance, particularly in boundary precision and small-organ segmentation.

---

### Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark

Authors: Seng Nam Chen, Hao Chen, Chenglam Ho, Xinyu Mao, Jinping Wang, Yu Zhang, Chao Li
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27259v3

Long video understanding (LVU) remains a core challenge in multimodal learning. Although recent vision-language models (VLMs) have made notable progress, existing benchmarks mainly focus on either fine-grained perception or coarse summarization, offering limited insight into temporal understanding over long contexts. In this work, we define a scene as a coherent segment of a video in which both visual and semantic contexts remain consistent, aligning with human perception. This leads us to a key question: can current VLMs reason effectively over long, scene-level contexts? To answer this, we introduce a new benchmark, SceneBench, designed to provide scene-level challenges. Our evaluation reveals a sharp drop in accuracy when VLMs attempt to answer scene-level questions, indicating significant forgetting of long-range context. To further validate these findings, we propose Scene Retrieval-Augmented Generation (Scene-RAG), which constructs a dynamic scene memory by retrieving and integrating relevant context across scenes. This Scene-RAG improves VLM performance by +2.50%, confirming that current models still struggle with long-context retention. We hope SceneBench will encourage future research toward VLMs with more robust, human-like video comprehension.

---

### Amalgam: Hybrid LLM-PGM Synthesis Algorithm for Accuracy and Realism

Authors: Antheas Kapenekakis, Bent Thomsen, Katja Hose, Michele Albano
Published: 2026-03-28
Categories: cs.DB, cs.AI
arXiv: https://arxiv.org/abs/2603.27254v1

To generate synthetic datasets, e.g., in domains such as healthcare, the literature proposes approaches of two main types: Probabilistic Graphical Models (PGMs) and Deep Learning models, such as LLMs. While PGMs produce synthetic data that can be used for advanced analytics, they do not support complex schemas and datasets. LLMs on the other hand, support complex schemas but produce skewed dataset distributions, which are less useful for advanced analytics. In this paper, we therefore present Amalgam, a hybrid LLM-PGM data synthesis algorithm supporting both advanced analytics, realism, and tangible privacy properties. We show that Amalgam synthesizes data with an average 91 % $χ^2 P$ value and scores 3.8/5 for realism using our proposed metric, where state-of-the-art is 3.3 and real data is 4.7.

---

### Mitigating Hallucination on Hallucination in RAG via Ensemble Voting

Authors: Zequn Xie, Zhengyang Sun
Published: 2026-03-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.27253v2

Retrieval-Augmented Generation (RAG) aims to reduce hallucinations in Large Language Models (LLMs) by integrating external knowledge. However, RAG introduces a critical challenge: hallucination on hallucination," where flawed retrieval results mislead the generation model, leading to compounded hallucinations. To address this issue, we propose VOTE-RAG, a novel, training-free framework with a two-stage structure and efficient, parallelizable voting mechanisms. VOTE-RAG includes: (1) Retrieval Voting, where multiple agents generate diverse queries in parallel and aggregate all retrieved documents; (2) Response Voting, where multiple agents independently generate answers based on the aggregated documents, with the final output determined by majority vote. We conduct comparative experiments on six benchmark datasets. Our results show that VOTE-RAG achieves performance comparable to or surpassing more complex frameworks. Additionally, VOTE-RAG features a simpler architecture, is fully parallelizable, and avoids the problem drift" risk. Our work demonstrates that simple, reliable ensemble voting is a superior and more efficient method for mitigating RAG hallucinations.

---

### Zero-shot Vision-Language Reranking for Cross-View Geolocalization

Authors: Yunus Talha Erzurumlu, John E. Anderson, William J. Shuart, Charles Toth, Alper Yilmaz
Published: 2026-03-28
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.27251v1

Cross-view geolocalization (CVGL) systems, while effective at retrieving a list of relevant candidates (high Recall@k), often fail to identify the single best match (low Top-1 accuracy). This work investigates the use of zero-shot Vision-Language Models (VLMs) as rerankers to address this gap. We propose a two-stage framework: state-of-the-art (SOTA) retrieval followed by VLM reranking. We systematically compare two strategies: (1) Pointwise (scoring candidates individually) and (2) Pairwise (comparing candidates relatively). Experiments on the VIGOR dataset show a clear divergence: all pointwise methods cause a catastrophic drop in performance or no change at all. In contrast, a pairwise comparison strategy using LLaVA improves Top-1 accuracy over the strong retrieval baseline. Our analysis concludes that, these VLMs are poorly calibrated for absolute relevance scoring but are effective at fine-grained relative visual judgment, making pairwise reranking a promising direction for enhancing CVGL precision.

---

### IP-SAM: Rethinking Prompt-Conditioned Segmentation for Prompt-Absent Deployment

Authors: Huiyao Zhang, Jin Bai, Rui Guo, JianWen Tan, HongFei Wang, Ye Li
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27250v2

Prompt-conditioned foundation segmenters have emerged as a dominant paradigm for image segmentation, where explicit spatial prompts(e.g., points, boxes, masks) guide mask decoding. However, many real-world deployments require fully automatic segmentation, creating a structural mismatch: the decoder expects prompts that are unavailable at inference. Existing adaptations typically modify intermediate features, inadvertently bypassing the model's native prompt interface and weakening prompt-conditioned decoding. We propose IP-SAM, which revisits adaptation from a prompt-space perspective through prompt-space conditioning. Specifically, a Self-Prompt Generator (SPG) distills image context into complementary intrinsic prompts that serve as coarse regional anchors. These cues are projected through SAM2's frozen prompt encoder, restoring prompt-guided decoding without external intervention. To suppress background-induced false positives, Prompt-Space Gating (PSG) leverages the intrinsic background prompt as an asymmetric suppressive constraint prior to decoding. Under a deterministic no-external-prompt protocol, IP-SAM achieves state-of-the-art performance across four camouflaged object detection benchmarks with only 21.26M trainable parameters. Furthermore, the proposed conditioning strategy generalizes beyond COD to medical polyp segmentation.

---

### SCOPE: Tree-based Self-Correcting Online Log Parsing via Syntactic-Semantic Collaboration

Authors: Dongyi Fan, Suqiong Zhang, Lili He, Ming Liu, Yifan Huo
Published: 2026-03-28
Categories: cs.CL, cs.SE
arXiv: https://arxiv.org/abs/2603.27247v1

Log parsing is a critical step for automated log analysis in complex systems. Traditional heuristic-based methods offer high efficiency but are limited in accuracy due to overlooking semantic context. In contrast, recent LLM-based parsers improve accuracy via se mantic understanding but incur high latency from frequent model calls. To address this, we propose SCOPE, the first self-correcting online log parsing method that integrates the strengths of both heuristic and LLM-based paradigms. SCOPE introduces a novel bi-directional tree structure that enables efficient template match ing from both forward and reverse directions, resulting in a higher overall matching rate. Additionally, it adopts a two-stage syntactic semantic collaboration framework: a lightweight NLP model first utilizes part-of-speech (POS) information for syntax-based match ing, while the LLM is selectively invoked as a fallback to handle semantically complex cases when uncertainty remains. This design significantly reduces LLM API usage while maintaining high ac curacy, achieving a balance between efficiency and effectiveness. Extensive evaluations on diverse benchmark datasets show that SCOPE outperforms state-of-the-art methods in both accuracy and efficiency. The implementation and datasets are publicly released to facilitate further research.

---

### SaSaSaSa2VA: 2nd Place of the 5th PVUW MeViS-Text Track

Authors: Dengxian Gong, Quanzhu Niu, Shihao Chen, Yuanzheng Wu, Yikang Zhou, Tao Zhang, Haobo Yuan, Lu Qi, Shunping Ji
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27241v1

Referring video object segmentation (RVOS) commonly grounds targets in videos based on static textual cues. MeViS benchmark extends this by incorporating motion-centric expressions (referring & reasoning motion expressions) and introducing no-target queries. Extending SaSaSa2VA, where increased input frames and (SEG) tokens already strengthen the Sa2VA backbone, we adopt a simple yet effective target existence-aware verification mechanism, leading to Still Awesome SaSaSa2VA (SaSaSaSa2VA). Despite its simplicity, the method achieves a final score of 89.19 in the 5th PVUW Challenge (MeViS-Text Track), securing 2nd place. Both quantitative results and ablations suggest that this existence-aware verification strategy is sufficient to unlock strong performance on motion-centric referring tasks.

---

### Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection

Authors: Jinhu Fu, Yihang Lou, Qingyi Si, Shudong Zhang, Yan Bai, Sen Su
Published: 2026-03-28
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.27240v1

Large Vision-Language Models (LVLMs) have achieved impressive performance across multimodal understanding and reasoning tasks, yet their internal safety mechanisms remain opaque and poorly controlled. In this work, we present a comprehensive framework for diagnosing and repairing unsafe channels within LVLMs (CARE). We first perform causal mediation analysis to identify neurons and layers that are causally responsible for unsafe behaviors. Based on these findings, we introduce a dual-modal safety subspace projection method that learns generalized safety subspaces for both visual and textual modalities through generalized eigen-decomposition between benign and malicious activations. During inference, activations are dynamically projected toward these safety subspaces via a hybrid fusion mechanism that adaptively balances visual and textual corrections, effectively suppressing unsafe features while preserving semantic fidelity. Extensive experiments on multiple safety benchmarks demonstrate that our causal-subspace repair framework significantly enhances safety robustness without degrading general multimodal capabilities, outperforming prior activation steering and alignment-based baselines. Additionally, our method exhibits good transferability, defending against unseen attacks.

---

### An Instance-Centric Panoptic Occupancy Prediction Benchmark for Autonomous Driving

Authors: Yi Feng, Junwu E, Zizhan Guo, Yu Ma, Hanli Wang, Rui Fan
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27238v1

Panoptic occupancy prediction aims to jointly infer voxel-wise semantics and instance identities within a unified 3D scene representation. Nevertheless, progress in this field remains constrained by the absence of high-quality 3D mesh resources, instance-level annotations, and physically consistent occupancy datasets. Existing benchmarks typically provide incomplete and low-resolution geometry without instance-level annotations, limiting the development of models capable of achieving precise geometric reconstruction, reliable occlusion reasoning, and holistic 3D understanding. To address these challenges, this paper presents an instance-centric benchmark for the 3D panoptic occupancy prediction task. Specifically, we introduce ADMesh, the first unified 3D mesh library tailored for autonomous driving, which integrates over 15K high-quality 3D models with diverse textures and rich semantic annotations. Building upon ADMesh, we further construct CarlaOcc, a large-scale, physically consistent panoptic occupancy dataset generated using the CARLA simulator. This dataset contains over 100K frames with fine-grained, instance-level occupancy ground truth at voxel resolutions as fine as 0.05 m. Furthermore, standardized evaluation metrics are introduced to quantify the quality of existing occupancy datasets. Finally, a systematic benchmark of representative models is established on the proposed dataset, which provides a unified platform for fair comparison and reproducible research in the field of 3D panoptic perception. Code and dataset are available at https://mias.group/CarlaOcc.

---

### Can pre-trained Deep Learning models predict groove ratings?

Authors: Axel Marmoret, Nicolas Farrugia, Jan Alexander Stupacher
Published: 2026-03-28
Categories: cs.SD, cs.AI, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2603.27237v1

This study explores the extent to which deep learning models can predict groove and its related perceptual dimensions directly from audio signals. We critically examine the effectiveness of seven state-of-the-art deep learning models in predicting groove ratings and responses to groove-related queries through the extraction of audio embeddings. Additionally, we compare these predictions with traditional handcrafted audio features. To better understand the underlying mechanics, we extend this methodology to analyze predictions based on source-separated instruments, thereby isolating the contributions of individual musical elements. Our analysis reveals a clear separation of groove characteristics driven by the underlying musical style of the tracks (funk, pop, and rock). These findings indicate that deep audio representations can successfully encode complex, style-dependent groove components that traditional features often miss. Ultimately, this work highlights the capacity of advanced deep learning models to capture the multifaceted concept of groove, demonstrating the strong potential of representation learning to advance predictive Music Information Retrieval methodologies.

---

### Structural Stress and Learned Helplessness in Afghanistan: A Multi-Layer Analysis of the AFSTRESS Dari Corpus

Authors: Jawid Ahmad Baktash, Mursal Dawodi, Nadira Ahmadi
Published: 2026-03-28
Categories: cs.CL, cs.SI
arXiv: https://arxiv.org/abs/2603.27233v1

We introduce AFSTRESS, the first multi-label corpus of self-reported stress narratives in Dari (Eastern Persian), comprising 737 responses collected from Afghan individuals during an ongoing humanitarian crisis. Participants describe experienced stress and select emotion and stressor labels via Dari checklists. The dataset enables analysis at three levels: computational (multi-label classification), social (structural drivers and gender disparities), and psychological (learned helplessness, chronic stress, and emotional cascade patterns). It includes 12 binary labels (5 emotions, 7 stressors), with high label cardinality (5.54) and density (0.462), reflecting complex, multi-dimensional stress. Structural stressors dominate: uncertain future (62.6 percent) and education closure (60.0 percent) exceed emotional states, indicating stress is primarily structurally driven. The strongest co-occurrence is between hopelessness and uncertain future (J = 0.388). Baseline experiments show that character TF-IDF with Linear SVM achieves Micro-F1 = 0.663 and Macro-F1 = 0.651, outperforming ParsBERT and XLM-RoBERTa, while threshold tuning improves Micro-F1 by 10.3 points. AFSTRESS provides the first Dari resource for computational analysis of stress and well-being in a crisis-affected population.

---

### NimbusGS: Unified 3D Scene Reconstruction under Hybrid Weather

Authors: Yanying Li, Jinyang Li, Shengfeng He, Yangyang Xu, Junyu Dong, Yong Du
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27228v1

We present NimbusGS, a unified framework for reconstructing high-quality 3D scenes from degraded multi-view inputs captured under diverse and mixed adverse weather conditions. Unlike existing methods that target specific weather types, NimbusGS addresses the broader challenge of generalization by modeling the dual nature of weather: a continuous, view-consistent medium that attenuates light, and dynamic, view-dependent particles that cause scattering and occlusion. To capture this structure, we decompose degradations into a global transmission field and per-view particulate residuals. The transmission field represents static atmospheric effects shared across views, while the residuals model transient disturbances unique to each input. To enable stable geometry learning under severe visibility degradation, we introduce a geometry-guided gradient scaling mechanism that mitigates gradient imbalance during the self-supervised optimization of 3D Gaussian representations. This physically grounded formulation allows NimbusGS to disentangle complex degradations while preserving scene structure, yielding superior geometry reconstruction and outperforming task-specific methods across diverse and challenging weather conditions. Code is available at https://github.com/lyy-ovo/NimbusGS.

---

### Rethinking Easy-to-Hard: Limits of Curriculum Learning in Post-Training for Deductive Reasoning

Authors: Maximilian Mordig, Andreas Opedal, Weiyang Liu, Bernhard Schölkopf
Published: 2026-03-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.27226v1

Curriculum learning (CL), motivated by the intuition that learning in increasing order of difficulty should ease generalization, is commonly adopted both in pre-training and post-training of large language models (LLMs). The intuition of CL is particularly compelling for compositional reasoning, where complex problems are built from elementary inference rules; however, the actual impact of CL on such tasks remains largely underexplored. We present a systematic empirical study of CL for post-training of LLMs, using synthetic arithmetic and logical benchmarks where difficulty is characterized by reasoning complexity rather than surface-level proxies. Surprisingly, across multiple model families and curriculum schedules, we find no robust advantage in difficulty-based sequencing over standard random sampling in either accuracy or response length. These findings persist across both supervised fine-tuning (SFT) and reinforcement learning (RL) methods. Our study suggests that, in the context of deductive reasoning, the specific ordering of training examples plays a negligible role in achieving compositional generalization, challenging the practical utility of curriculum-based post-training.

---

### EuraGovExam: A Multilingual Multimodal Benchmark from Real-World Civil Service Exams

Authors: Jaeseong Kim, Chaehwan Lim, Sang Hyun Gil, Suan Lee
Published: 2026-03-28
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.27223v2

We present EuraGovExam, a multilingual and multimodal benchmark sourced from real-world civil service examinations across five representative Eurasian regions: South Korea, Japan, Taiwan, India, and the European Union. Designed to reflect the authentic complexity of public-sector assessments, the dataset contains over 8,000 high-resolution scanned multiple-choice questions covering 17 diverse academic and administrative domains. Unlike existing benchmarks, EuraGovExam embeds all question content--including problem statements, answer choices, and visual elements--within a single image, providing only a minimal standardized instruction for answer formatting. This design demands that models perform layout-aware, cross-lingual reasoning directly from visual input. All items are drawn from real exam documents, preserving rich visual structures such as tables, multilingual typography, and form-like layouts. Evaluation results show that even state-of-the-art vision-language models (VLMs) achieve only 86% accuracy, underscoring the benchmark's difficulty and its power to diagnose the limitations of current models. By emphasizing cultural realism, visual complexity, and linguistic diversity, EuraGovExam establishes a new standard for evaluating VLMs in high-stakes, multilingual, image-grounded settings. It also supports practical applications in e-governance, public-sector document analysis, and equitable exam preparation.

---

### HD-VGGT: High-Resolution Visual Geometry Transformer

Authors: Tianrun Chen, Yuanqi Hu, Yidong Han, Hanjie Xu, Deyi Ji, Qi Zhu, Chunan Yu, Xin Zhang, Cheng Chen, Chaotao Ding, Ying Zang, Xuanfu Li et al.
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27222v2

High-resolution imagery is essential for accurate 3D reconstruction, as many geometric details only emerge at fine spatial scales. Recent feed-forward approaches, such as the Visual Geometry Grounded Transformer (VGGT), have demonstrated the ability to infer scene geometry from large collections of images in a single forward pass. However, scaling these models to high-resolution inputs remains challenging: the number of tokens in transformer architectures grows rapidly with both image resolution and the number of views, leading to prohibitive computational and memory costs. Moreover, we observe that visually ambiguous regions, such as repetitive patterns, weak textures, or specular surfaces, often produce unstable feature tokens that degrade geometric inference, especially at higher resolutions. We introduce HD-VGGT, a dual-branch architecture for efficient and robust high-resolution 3D reconstruction. A low-resolution branch predicts a coarse, globally consistent geometry, while a high-resolution branch refines details via a learned feature upsampling module. To handle unstable tokens, we propose Feature Modulation, which suppresses unreliable features early in the transformer. HD-VGGT leverages high-resolution images and supervision without full-resolution transformer costs, achieving state-of-the-art reconstruction quality.

---

### Unsupervised Evaluation of Deep Audio Embeddings for Music Structure Analysis

Authors: Axel Marmoret
Published: 2026-03-28
Categories: cs.SD, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.27218v2

Music Structure Analysis (MSA) aims to uncover the high-level organization of musical pieces. State-of-the-art methods are often based on supervised deep learning, but these methods are bottlenecked by the need for heavily annotated data and inherent structural ambiguities. In this paper, we propose an unsupervised evaluation of nine open-source, generic pre-trained deep audio models, on MSA. For each model, we extract barwise embeddings and segment them using three unsupervised segmentation algorithms (Foote's checkerboard kernels, spectral clustering, and Correlation Block-Matching (CBM)), focusing exclusively on boundary retrieval. Our results demonstrate that modern, generic deep embeddings generally outperform traditional spectrogram-based baselines, but not systematically. Furthermore, our unsupervised boundary estimation methodology generally yields stronger performance than recent linear probing baselines. Among the evaluated techniques, the CBM algorithm consistently emerges as the most effective downstream segmentation method. Finally, we highlight the artificial inflation of standard evaluation metrics and advocate for the systematic adoption of ``trimming'', or even ``double trimming'' annotations to establish more rigorous MSA evaluation standards.

---

### LightMover: Generative Light Movement with Color and Intensity Controls

Authors: Gengze Zhou, Tianyu Wang, Soo Ye Kim, Zhixin Shu, Xin Yu, Yannick Hold-Geoffroy, Sumit Chaturvedi, Qi Wu, Zhe Lin, Scott Cohen
Published: 2026-03-28
Categories: cs.CV, cs.CL, cs.GR, cs.LG
arXiv: https://arxiv.org/abs/2603.27209v1

We present LightMover, a framework for controllable light manipulation in single images that leverages video diffusion priors to produce physically plausible illumination changes without re-rendering the scene. We formulate light editing as a sequence-to-sequence prediction problem in visual token space: given an image and light-control tokens, the model adjusts light position, color, and intensity together with resulting reflections, shadows, and falloff from a single view. This unified treatment of spatial (movement) and appearance (color, intensity) controls improves both manipulation and illumination understanding. We further introduce an adaptive token-pruning mechanism that preserves spatially informative tokens while compactly encoding non-spatial attributes, reducing control sequence length by 41% while maintaining editing fidelity. To train our framework, we construct a scalable rendering pipeline that generates large numbers of image pairs across varied light positions, colors, and intensities while keeping the scene content consistent with the original image. LightMover enables precise, independent control over light position, color, and intensity, and achieves high PSNR and strong semantic consistency (DINO, CLIP) across different tasks.

---

### Make It Up: Fake Images, Real Gains in Generalized Few-shot Semantic Segmentation

Authors: Guohuan Xie, Xin He, Dingying Fan, Le Zhang, Ming-Ming Cheng, Yun Liu
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27206v1

Generalized few-shot semantic segmentation (GFSS) is fundamentally limited by the coverage of novel-class appearances under scarce annotations. While diffusion models can synthesize novel-class images at scale, practical gains are often hindered by insufficient coverage and noisy supervision when masks are unavailable or unreliable. We propose Syn4Seg, a generation-enhanced GFSS framework designed to expand novel-class coverage while improving pseudo-label quality. Syn4Seg first maximizes prompt-space coverage by constructing an embedding-deduplicated prompt bank for each novel class, yielding diverse yet class-consistent synthetic images. It then performs support-guided pseudo-label estimation via a two-stage refinement that i) filters low-consistency regions to obtain high-precision seeds and ii) relabels uncertain pixels with image-adaptive prototypes that combine global (support) and local (image) statistics. Finally, we refine only boundary-band and unlabeled pixels using a constrained SAM-based update to improve contour fidelity without overwriting high-confidence interiors. Extensive experiments on PASCAL-$5^i$ and COCO-$20^i$ demonstrate consistent improvements in both 1-shot and 5-shot settings, highlighting synthetic data as a scalable path for GFSS with reliable masks and precise boundaries.

---

### Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought Models

Authors: Ji Ma, Wei Suo, Peng Wang, Yanning Zhang
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27201v1

Multimodal Chain-of-Thought (MCoT) models have demonstrated impressive capability in complex visual reasoning tasks. Unfortunately, recent studies reveal that they suffer from severe hallucination problems due to diminished visual attention during the generation process. However, visual attention decay is a well-studied problem in Large Vision-Language Models (LVLMs). Considering the fundamental differences in reasoning processes between MCoT models and traditional LVLMs, we raise a basic question: Whether MCoT models have unique causes of hallucinations? To answer this question, we systematically investigate the hallucination patterns of MCoT models and find that fabricated texts are primarily generated in associative reasoning steps, which we term divergent thinking. Leveraging these insights, we introduce a simple yet effective strategy that can effectively localize divergent thinking steps and intervene in the decoding process to mitigate hallucinations. Extensive experiments show that our method outperforms existing methods by a large margin. More importantly, our proposed method can be conveniently integrated with other hallucination mitigation methods and further boost their performance. The code is publicly available at https://github.com/ASGO-MM/MCoT-hallucination.

---

### Let Triggers Control: Frequency-Aware Dropout for Effective Token Control

Authors: Junyoung Koh, Hoyeon Moon, Dongha Kim, Seungmin Lee, Sanghyun Park, Min Song
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27199v1

Text-to-image models such as Stable Diffusion have achieved unprecedented levels of high-fidelity visual synthesis. As these models advance, personalization of generative models -- commonly facilitated through Low-Rank Adaptation (LoRA) with a dedicated trigger token -- has become a significant area of research. Previous works have naively assumed that fine-tuning with a single trigger token to represent new concepts. However, this often results in poor controllability, where the trigger token alone fails to reliably evoke the intended concept. We attribute this issue to the frequent co-occurrence of the trigger token with the surrounding context during fine-tuning, which entangles their representations and compromises the token's semantic distinctiveness. To disentangle this, we propose Frequency-Aware Dropout (FAD) -- a novel regularization technique that improves prompt controllability without adding new parameters. FAD consists of two key components: co-occurrence analysis and curriculum-inspired scheduling. Qualitative and quantitative analyses across token-based diffusion models (SD~1.5 and SDXL) and natural language--driven backbones (FLUX and Qwen-Image) demonstrate consistent gains in prompt fidelity, stylistic precision, and user-perceived quality. Our method provides a simple yet effective dropout strategy that enhances controllability and personalization in text-to-image generation. Notably, it achieves these improvements without introducing additional parameters or architectural modifications, making it readily applicable to existing models with minimal computational overhead.

---

### K$α$LOS finds Consensus: A Meta-Algorithm for Evaluating Inter-Annotator Agreement in Complex Vision Tasks

Authors: David Tschirschwitz, Volker Rodehorst
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27197v1

Progress in object detection benchmarks is stagnating. It is limited not by architectures but by the inability to distinguish model improvements from label noise. To restore trust in benchmarking the field requires rigorous quantification of annotation consistency to ensure the reliability of evaluation data. However, standard statistical metrics fail to handle the instance correspondence problem inherent to vision tasks. Furthermore, validating new agreement metrics remains circular because no objective ground truth for agreement exists. This forces reliance on unverifiable heuristics. We propose K$α$LOS (KALOS), a unified meta-algorithm that generalizes the "Localization First" principle to standardize dataset quality evaluation. By resolving spatial correspondence before assessing agreement, our framework transforms complex spatio-categorical problems into nominal reliability matrices. Unlike prior heuristic implementations, K$α$LOS employs a principled, data-driven configuration; by statistically calibrating the localization parameters to the inherent agreement distribution, it generalizes to diverse tasks ranging from bounding boxes to volumetric segmentation or pose estimation. This standardization enables granular diagnostics beyond a single score. These include annotator vitality, collaboration clustering, and localization sensitivity. To validate this approach, we introduce a novel and empirically derived noise generator. Where prior validations relied on uniform error assumptions, our controllable testbed models complex and non-isotropic human variability. This provides evidence of the metric's properties and establishes K$α$LOS as a robust standard for distinguishing signal from noise in modern computer vision benchmarks.

---

### AutoMS: Multi-Agent Evolutionary Search for Cross-Physics Inverse Microstructure Design

Authors: Zhenyuan Zhao, Yu Xing, Tianyang Xue, Lingxin Cao, Xin Yan, Lin Lu
Published: 2026-03-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.27195v2

Designing microstructures with coupled cross-physics objectives is a fundamental challenge where traditional topology optimization is often computationally prohibitive and deep generative models frequently suffer from physical hallucinations. We introduce AutoMS, a multi-agent neuro-symbolic framework that reformulates inverse design as an LLM-driven evolutionary search. AutoMS leverages LLMs as semantic navigators to decompose complex requirements and coordinate agent workflows, while a novel Simulation-Aware Evolutionary Search (SAES) mechanism handles low-level numerical optimization via local gradient approximation and directed parameter updates. This architecture achieves a state-of-the-art 83.8% success rate on 17 diverse cross-physics tasks, significantly outperforming both traditional evolutionary algorithms and existing agentic baselines. By decoupling open-ended semantic orchestration from simulation-grounded numerical search, AutoMS provides a robust pathway for navigating complex physical landscapes that remain intractable for standard generative or purely linguistic approaches.

---

### Multi-AUV Ad-hoc Networks-Based Multi-Target Tracking Based on Scene-Adaptive Embodied Intelligence

Authors: Kai Tian, Jialun Wang, Chuan Lin, Guangjie Han, Shengchao Zhu, Ying Liu, Qian Zhu
Published: 2026-03-28
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2603.27194v1

With the rapid advancement of underwater net-working and multi-agent coordination technologies, autonomous underwater vehicle (AUV) ad-hoc networks have emerged as a pivotal framework for executing complex maritime missions, such as multi-target tracking. However, traditional data-centricarchitectures struggle to maintain operational consistency under highly dynamic topological fluctuations and severely constrained acoustic communication bandwidth. This article proposes a scene-adaptive embodied intelligence (EI) architecture for multi-AUV ad-hoc networks, which re-envisions AUVs as embodied entities by integrating perception, decision-making, and physical execution into a unified cognitive loop. To materialize the functional interaction between these layers, we define a beacon-based communication and control model that treats the communication link as a dynamic constraint-aware channel, effectively bridging the gap between high-level policy inference and decentralized physical actuation. Specifically, the proposed architecture employs a three-layer functional framework and introduces a Scene-Adaptive MARL (SA-MARL) algorithm featuring a dual-path critic mechanism. By integrating a scene critic network and a general critic network through a weight-based dynamic fusion process, SA-MARL effectively decouples specialized tracking tasks from global safety constraints, facilitating autonomous policy evolution. Evaluation results demonstrate that the proposedscheme significantly accelerates policy convergence and achieves superior tracking accuracy compared to mainstream MARL approaches, maintaining robust performance even under intense environmental interference and fluid topological shifts.

---

### Conformal Prediction Assessment: A Framework for Conditional Coverage Evaluation and Selection

Authors: Zheng Zhou, Xiangfei Zhang, Chongguang Tao, Yuhong Yang
Published: 2026-03-28
Categories: stat.ME, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2603.27189v2

Conformal prediction provides rigorous distribution-free finite-sample guarantees for marginal coverage under the assumption of exchangeability, but may exhibit systematic undercoverage or overcoverage for specific subpopulations. Assessing conditional validity is challenging, as standard stratification methods suffer from the curse of dimensionality. We propose Conformal Prediction Assessment (CPA), a framework that reframes the evaluation of conditional coverage as a supervised learning task by training a reliability estimator that predicts instance-level coverage probabilities. Building on this estimator, we introduce the Conditional Validity Index (CVI), which decomposes reliability into safety (undercoverage risk) and efficiency (overcoverage cost). We establish convergence rates for the reliability estimator and prove the consistency of CVI-based model selection. Extensive experiments on synthetic and real-world datasets demonstrate that CPA effectively diagnoses local failure modes and that CC-Select, our CVI-based model selection algorithm, consistently identifies predictors with superior conditional coverage performance.

---

### Persistent Memory Through Triple-Loop Consolidation Under Stochastic Unit Turnover

Authors: Jianwei Lou
Published: 2026-03-28
Categories: cs.NE, q-bio.NC
arXiv: https://arxiv.org/abs/2603.27188v3

Dissipative cognitive architectures maintain computation through continuous energy expenditure, where units that exhaust their energy are stochastically replaced with fresh random state. This creates a fundamental challenge: how can persistent, context-specific memory survive when all learnable state is periodically destroyed? Existing memory mechanisms -- including elastic weight consolidation, synaptic intelligence, and surprise-driven gating -- rely on gradient computation and are inapplicable to systems that do not perform it. We introduce Deep Memory (DM), a backpropagation-free persistent memory mechanism operating through a triple-loop consolidation cycle: (1) recording of expert-specific content centroids, (2) seeding of replaced units with stored representations, and (3) stabilization through continuous re-entry. Discrete expert routing via Mixture-of-Experts (MoE) gating is required, in the regimes tested, to prevent the centroid convergence that would render stored memories identical. We derive a Foster-Lyapunov drift bound for the full triple loop, showing that seeding rescales the turnover noise floor. Across $1{,}007$ simulation runs over thirteen blocks: (i) removing stable context-expert binding removes specialization ($\mathrm{MI}=1.10$ vs. $0.001$; $n=91$); (ii) DM achieves $R=0.984$ vs. $0.385$ without memory ($n=16$); (iii) continuous seeding reconstructs representations after interference ($R_\mathrm{recon}=0.978$; one-shot fails; $n=30$); (iv) the mechanism operates within a characterized $(K,p)$ envelope ($n=350$); (v) recording $\times$ seeding is the minimal critical dyad ($n=40$); (vi) associative and reservoir baselines (Hopfield, ESN) are compared under matched turnover ($n=370$). DM is thus a falsifiable, bounded mechanism for persistent memory in backpropagation-free cognitive systems, with functional parallels to hippocampal consolidation.

---

### Persistent Memory Through Triple-Loop Consolidation in a Non-Gradient Dissipative Cognitive Architecture

Authors: Jianwei Lou
Published: 2026-03-28
Categories: cs.NE, q-bio.NC
arXiv: https://arxiv.org/abs/2603.27188v1

Dissipative cognitive architectures maintain computation through continuous energy expenditure, where units that exhaust their energy are stochastically replaced with fresh random state. This creates a fundamental challenge: how can persistent, context-specific memory survive when all learnable state is periodically destroyed? Existing memory mechanisms -- including elastic weight consolidation, synaptic intelligence, and surprise-driven gating -- rely on gradient computation and are inapplicable to non-gradient dissipative systems. We introduce Deep Memory (DM), a non-gradient persistent memory mechanism operating through a triple-loop consolidation cycle: (1) recording of expert-specific content centroids, (2) seeding of replaced units with stored representations, and (3) stabilization through continuous re-entry. We demonstrate that discrete expert routing via Mixture-of-Experts (MoE) gating is a causal prerequisite for DM, preventing centroid convergence that would render stored memories identical. Across ${\sim}970$ simulation runs spanning thirteen experimental blocks: (i) discrete routing is causally necessary for specialization ($\text{MI}=1.10$ vs. $0.001$; $n=91$); (ii) DM achieves $R=0.984$ vs. $0.385$ without memory ($n=16$); (iii) continuous seeding reconstructs representations after interference ($R_\mathrm{recon}=0.978$; one-shot fails; $n=30$); (iv) the mechanism operates within a characterized $(K,p)$ envelope ($n=350$); (v) recording $\times$ seeding is the minimal critical dyad ($n=40$); (vi) DM outperforms non-gradient baselines (Hopfield, ESN) under matched turnover ($n=370$). These results establish DM as a falsifiable mechanism for persistent memory in non-gradient cognitive systems, with functional parallels to hippocampal consolidation.

---

### Omni-Modal Dissonance Benchmark: Systematically Breaking Modality Consensus to Probe Robustness and Calibrated Abstention

Authors: Zabir Al Nazi, Shubhashis Roy Dipta, Md Rizwan Parvez
Published: 2026-03-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.27187v1

Existing omni-modal benchmarks attempt to measure modality-specific contributions, but their measurements are confounded: naturally co-occurring modalities carry correlated yet unequal information, making it unclear whether results reflect true modality reliance or information asymmetry. We introduce OMD-Bench, where all modalities are initially congruent - each presenting the same anchor, an object or event independently perceivable through video, audio, and text - which we then systematically corrupt to isolate each modality's contribution. We also evaluate calibrated abstention: whether models appropriately refrain from answering when evidence is conflicting. The benchmark comprises 4,080 instances spanning 27 anchors across eight corruption conditions. Evaluating ten omni-modal models under zero-shot and chain-of-thought prompting, we find that models over-abstain when two modalities are corrupted yet under-abstain severely when all three are, while maintaining high confidence (~60-100%) even under full corruption. Chain-of-thought prompting improves abstention alignment with human judgment but amplifies overconfidence rather than mitigating it. OMD-Bench provides a diagnostic benchmark for diagnosing modality reliance, robustness to cross-modal inconsistency, and uncertainty calibration in omni-modal systems.

---

### Hybrid Deep Learning with Temporal Data Augmentation for Accurate Remaining Useful Life Prediction of Lithium-Ion Batteries

Authors: Yun Tian, Guili Wang, Jian Bi, Kaixin Han, Chenglu Wu, Zhiyi Lu, Chenhao Li, Liangwang Sun, Minyu Zhou, Chenchen Xu
Published: 2026-03-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.27186v1

Accurate prediction of lithium-ion battery remaining useful life (RUL) is essential for reliable health monitoring and data-driven analysis of battery degradation. However, the robustness and generalization capabilities of existing RUL prediction models are significantly challenged by complex operating conditions and limited data availability. To address these limitations, this study proposes a hybrid deep learning model, CDFormer, which integrates convolutional neural networks, deep residual shrinkage networks, and Transformer encoders extract multiscale temporal features from battery measurement signals, including voltage, current, and capacity. This architecture enables the joint modeling of local and global degradation dynamics, effectively improving the accuracy of RUL prediction.To enhance predictive reliability, a composite temporal data augmentation strategy is proposed, incorporating Gaussian noise, time warping, and time resampling, explicitly accounting for measurement noise and variability. CDFormer is evaluated on two real-world datasets, with experimental results demonstrating its consistent superiority over conventional recurrent neural network-based and Transformer-based baselines across key metrics. By improving the reliability and predictive performance of RUL prediction from measurement data, CDFormer provides accurate and reliable forecasts, supporting effective battery health monitoring and data-driven maintenance strategies.

---

### MotionRFT: Unified Reinforcement Fine-Tuning for Text-to-Motion Generation

Authors: Xiaofeng Tan, Wanjiang Weng, Hongsong Wang, Fang Zhao, Xin Geng, Liang Wang
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27185v1

Text-to-motion generation has advanced with diffusion- and flow-based generative models, yet supervised pretraining remains insufficient to align models with high-level objectives such as semantic consistency, realism, and human preference. Existing post-training methods have key limitations: they (1) target a specific motion representation, such as joints, (2) optimize a particular aspect, such as text-motion alignment, and may compromise other factors; and (3) incur substantial computational overhead, data dependence, and coarse-grained optimization. We present a reinforcement fine-tuning framework that comprises a heterogeneous-representation, multi-dimensional reward model, MotionReward, and an efficient, fine-grained fine-tuning method, EasyTune. To obtain a unified semantics representation, MotionReward maps heterogeneous motions into a shared semantic space anchored by text, enabling multidimensional reward learning; Self-refinement Preference Learning further enhances semantics without additional annotations. For efficient and effective fine-tuning, we identify the recursive gradient dependence across denoising steps as the key bottleneck, and propose EasyTune, which optimizes step-wise rather than over the full trajectory, yielding dense, fine-grained, and memory-efficient updates. Extensive experiments validate the effectiveness of our framework, achieving FID 0.132 at 22.10 GB peak memory for MLD model and saving up to 15.22 GB over DRaFT. It reduces FID by 22.9% on joint-based ACMDM, and achieves a 12.6% R-Precision gain and 23.3% FID improvement on rotation-based HY Motion. Our project page with code is publicly available.

---

### Incentivizing Temporal-Awareness in Egocentric Video Understanding Models

Authors: Zhiyang Xu, Tian Qin, Bowen Jin, Zhengfeng Lai, Meng Cao, Lifu Huang, Peng Zhang
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27184v1

Multimodal large language models (MLLMs) have recently shown strong performance in visual understanding, yet they often lack temporal awareness, particularly in egocentric settings where reasoning depends on the correct ordering and evolution of events. This deficiency stems in part from training objectives that fail to explicitly reward temporal reasoning and instead rely on frame-level spatial shortcuts. To address this limitation, we propose Temporal Global Policy Optimization (TGPO), a reinforcement learning with verifiable rewards (RLVR) algorithm designed to incentivize temporal awareness in MLLMs. TGPO contrasts model outputs generated from temporally ordered versus shuffled video frames to derive calibrated, globally normalized reward signals that explicitly favor temporally coherent reasoning. Integrated with GRPO and GSPO, TGPO supports cold-start RL training and effectively suppresses spatial shortcut behaviors learned by existing MLLMs. Experiments across five egocentric video benchmarks demonstrate that TGPO consistently improves temporal grounding and causal coherence, outperforming prior RL-based video reasoning approaches. Our results suggest that TGPO offers a simple and scalable pathway toward temporally robust MLLMs for egocentric video understanding.

---

### Communicating about Space: Language-Mediated Spatial Integration Across Partial Views

Authors: Ankur Sikarwar, Debangan Mishra, Sudarshan Nikhil, Ponnurangam Kumaraguru, Aishwarya Agrawal
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27183v2

Humans build shared spatial understanding by communicating partial, viewpoint-dependent observations. We ask whether Multimodal Large Language Models (MLLMs) can do the same, aligning distinct egocentric views through dialogue to form a coherent, allocentric mental model of a shared environment. To study this systematically, we introduce COSMIC, a benchmark for Collaborative Spatial Communication. In this setting, two static MLLM agents observe a 3D indoor environment from different viewpoints and exchange natural-language messages to solve spatial queries. COSMIC contains 899 diverse scenes and 1250 question-answer pairs spanning five tasks. We find a capability hierarchy, MLLMs are most reliable at identifying shared anchor objects across views, perform worse on relational reasoning, and largely fail at building globally consistent maps, performing near chance, even for frontier models. Moreover, we find thinking capability yields gains in anchor grounding, but is insufficient for higher-level spatial communication. To contextualize model behavior, we collect 250 human-human dialogues. Humans achieve 95% aggregate accuracy, while the best model, Gemini-3-Pro-Thinking, reaches 72%, leaving substantial room for improvement. Moreover, human conversations grow more precise as partners align on a shared spatial understanding, whereas MLLMs keep exploring without converging, suggesting limited capacity to form and sustain a robust shared mental model throughout the dialogue. Our code and data is available at https://github.com/ankursikarwar/Cosmic.

---

### An End-to-end Flight Control Network for High-speed UAV Obstacle Avoidance based on Event-Depth Fusion

Authors: Dikai Shang, Jingyue Zhao, Shi Xu, Nanyang Ye, Lei Wang
Published: 2026-03-28
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2603.27181v1

Achieving safe, high-speed autonomous flight in complex environments with static, dynamic, or mixed obstacles remains challenging, as a single perception modality is incomplete. Depth cameras are effective for static objects but suffer from motion blur at high speeds. Conversely, event cameras excel at capturing rapid motion but struggle to perceive static scenes. To exploit the complementary strengths of both sensors, we propose an end-to-end flight control network that achieves feature-level fusion of depth images and event data through a bidirectional crossattention module. The end-to-end network is trained via imitation learning, which relies on high-quality supervision. Building on this insight, we design an efficient expert planner using Spherical Principal Search (SPS). This planner reduces computational complexity from $O(n^2)$ to $O(n)$ while generating smoother trajectories, achieving over 80% success rate at 17m/s--nearly 20% higher than traditional planners. Simulation experiments show that our method attains a 70-80% success rate at 17 m/s across varied scenes, surpassing single-modality and unidirectional fusion models by 10-20%. These results demonstrate that bidirectional fusion effectively integrates event and depth information, enabling more reliable obstacle avoidance in complex environments with both static and dynamic objects.

---

### Reasoning-Driven Anomaly Detection and Localization with Image-Level Supervision

Authors: Yizhou Jin, Yuezhu Feng, Jinjin Zhang, Peng Wang, Qingjie Liu, Yunhong Wang
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27179v1

Multimodal large language models (MLLMs) have recently demonstrated remarkable reasoning and perceptual abilities for anomaly detection. However, most approaches remain confined to image-level anomaly detection and textual reasoning, while pixel-level localization still relies on external vision modules and dense annotations. In this work, we activate the intrinsic reasoning potential of MLLMs to perform anomaly detection, pixel-level localization, and interpretable reasoning solely from image-level supervision, without any auxiliary components or pixel-wise labels. Specifically, we propose Reasoning-Driven Anomaly Localization (ReAL), which extracts anomaly-related tokens from the autoregressive reasoning process and aggregates their attention responses to produce pixel-level anomaly maps. We further introduce a Consistency-Guided Reasoning Optimization (CGRO) module that leverages reinforcement learning to align reasoning tokens with visual attentions, resulting in more coherent reasoning and accurate anomaly localization. Extensive experiments on four public benchmarks demonstrate that our method significantly improves anomaly detection, localization, and interpretability. Remarkably, despite relying solely on image-level supervision, our approach achieves performance competitive with MLLM-based methods trained under dense pixel-level supervision. Code is available at https://github.com/YizhouJin313/ReADL.

---

### MEDIC-AD: Towards Medical Vision-Language Model's Clinical Intelligence

Authors: Woohyeon Park, Jaeik Kim, Sunghwan Steve Cho, Pa Hong, Wookyoung Jeong, Yoojin Nam, Namjoon Kim, Ginny Y. Wong, Ka Chun Cheung, Jaeyoung Do
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27176v2

Lesion detection, symptom tracking, and visual explainability are central to real-world medical image analysis, yet current medical Vision-Language Models (VLMs) still lack mechanisms that translate their broad knowledge into clinically actionable outputs. To bridge this gap, we present MEDIC-AD, a clinically oriented VLM that strengthens these three capabilities through a stage-wise framework. First, learnable anomaly-aware tokens (<Ano>) encourage the model to focus on abnormal regions and build more discriminative lesion centered representations. Second, inter image difference tokens (<Diff>) explicitly encode temporal changes between studies, allowing the model to distinguish worsening, improvement, and stability in disease burden. Finally, a dedicated explainability stage trains the model to generate heatmaps that highlight lesion-related regions, offering clear visual evidence that is consistent with the model's reasoning. Through our staged design, MEDIC-AD steadily boosts performance across anomaly detection, symptom tracking, and anomaly segmentation, achieving state-of-the-art results compared with both closed source and medical-specialized baselines. Evaluations on real longitudinal clinical data collected from real hospital workflows further show that MEDIC-AD delivers stable predictions and clinically faithful explanations in practical patient-monitoring and decision-support workflows

---

### MultiLoc: Multi-view Guided Relative Pose Regression for Fast and Robust Visual Re-Localization

Authors: Nobel Dang, Bing Li
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27170v1

Relative Pose Regression (RPR) generalizes well to unseen environments, but its performance is often limited due to pairwise and local spatial views. To this end, we propose MultiLoc, a novel multi-view guided RPR model trained at scale, equipping relative pose regression with globally consistent spatial and geometric understanding. Specifically, our method jointly fuses multiple reference views and their associated camera poses in a single forward pass, enabling accurate zero-shot pose estimation with real-time efficiency. To reliably supply informative context, we further propose a co-visibility-driven retrieval strategy for geometrically relevant reference view selection. MultiLoc establishes a new benchmark in visual re-localization, consistently outperforming existing state-of-the-art (SOTA) relative pose regression (RPR) methods across diverse datasets, including WaySpots, Cambridge Landmarks, and Indoor6. Furthermore, MultiLoc's pose regressor exhibits SOTA performance in relative pose estimation, surpassing RPR, feature matching and non-regression-based techniques on the MegaDepth-1500, ScanNet-1500, and ACID benchmarks. These results demonstrate robust domain generalization of MultiLoc across indoor, outdoor and natural environments. Code will be made publicly available.

---

### Aligning LLMs with Graph Neural Solvers for Combinatorial Optimization

Authors: Shaodi Feng, Zhuoyi Lin, Yaoxin Wu, Haiyan Yin, Yan Jin, Senthilnath Jayavelu, Xun Xu
Published: 2026-03-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.27169v1

Recent research has demonstrated the effectiveness of large language models (LLMs) in solving combinatorial optimization problems (COPs) by representing tasks and instances in natural language. However, purely language-based approaches struggle to accurately capture complex relational structures inherent in many COPs, rendering them less effective at addressing medium-sized or larger instances. To address these limitations, we propose AlignOPT, a novel approach that aligns LLMs with graph neural solvers to learn a more generalizable neural COP heuristic. Specifically, AlignOPT leverages the semantic understanding capabilities of LLMs to encode textual descriptions of COPs and their instances, while concurrently exploiting graph neural solvers to explicitly model the underlying graph structures of COP instances. Our approach facilitates a robust integration and alignment between linguistic semantics and structural representations, enabling more accurate and scalable COP solutions. Experimental results demonstrate that AlignOPT achieves state-of-the-art results across diverse COPs, underscoring its effectiveness in aligning semantic and structural representations. In particular, AlignOPT demonstrates strong generalization, effectively extending to previously unseen COP instances.

---

### RiskProp: Collision-Anchored Self-Supervised Risk Propagation for Early Accident Anticipation

Authors: Yiyang Zou, Tianhao Zhao, Peilun Xiao, Hongyu Jin, Longyu Qi, Yuxuan Li, Liyin Liang, Yifeng Qian, Chunbo Lai, Yutian Lin, Zhihui Li, Yu Wu
Published: 2026-03-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27165v1

Accident anticipation aims to predict impending collisions from dashcam videos and trigger early alerts. Existing methods rely on binary supervision with manually annotated "anomaly onset" frames, which are subjective and inconsistent, leading to inaccurate risk estimation. In contrast, we propose RiskProp, a novel collision-anchored self-supervised risk propagation paradigm for early accident anticipation, which removes the need for anomaly onset annotations and leverages only the reliably annotated collision frame. RiskProp models temporal risk evolution through two observation-driven losses: first, since future frames contain more definitive evidence of an impending accident, we introduce a future-frame regularization loss that uses the model's next-frame prediction as a soft target to supervise the current frame, enabling backward propagation of risk signals; second, inspired by the empirical trend of rising risk before accidents, we design an adaptive monotonic constraint to encourage a non-decreasing progression over time. Experiments on CAP and Nexar demonstrate that RiskProp achieves state-of-the-art performance and produces smoother, more discriminative risk curves, improving both early anticipation and interpretability.

---

### daVinci-LLM:Towards the Science of Pretraining

Authors: Yiwei Qin, Yixiu Liu, Tiantian Mi, Muhang Xie, Zhen Huang, Weiye Si, Pengrui Lu, Siyuan Feng, Xia Wu, Liming Liu, Ye Luo, Jinlong Hou et al.
Published: 2026-03-28
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.27164v1

The foundational pretraining phase determines a model's capability ceiling, as post-training struggles to overcome capability foundations established during pretraining, yet it remains critically under-explored. This stems from a structural paradox: organizations with computational resources operate under commercial pressures that inhibit transparent disclosure, while academic institutions possess research freedom but lack pretraining-scale computational resources. daVinci-LLM occupies this unexplored intersection, combining industrial-scale resources with full research freedom to advance the science of pretraining. We adopt a fully-open paradigm that treats openness as scientific methodology, releasing complete data processing pipelines, full training processes, and systematic exploration results. Recognizing that the field lacks systematic methodology for data processing, we employ the Data Darwinism framework, a principled L0-L9 taxonomy from filtering to synthesis. We train a 3B-parameter model from random initialization across 8T tokens using a two-stage adaptive curriculum that progressively shifts from foundational capabilities to reasoning-intensive enhancement. Through 200+ controlled ablations, we establish that: processing depth systematically enhances capabilities, establishing it as a critical dimension alongside volume scaling; different domains exhibit distinct saturation dynamics, necessitating adaptive strategies from proportion adjustments to format shifts; compositional balance enables targeted intensification while preventing performance collapse; how evaluation protocol choices shape our understanding of pretraining progress. By releasing the complete exploration process, we enable the community to build upon our findings and systematic methodologies to form accumulative scientific knowledge in pretraining.

---

### Online Learning of Kalman Filtering: From Output to State Estimation

Authors: Lintao Ye, Ankang Zhang, Ming Chi, Bin Du, Jianghai Hu
Published: 2026-03-28
Categories: cs.LG, eess.SY, math.OC
arXiv: https://arxiv.org/abs/2603.27159v1

In this paper, we study the problem of learning Kalman filtering with unknown system model in partially observed linear dynamical systems. We propose a unified algorithmic framework based on online optimization that can be used to solve both the output estimation and state estimation scenarios. By exploring the properties of the estimation error cost functions, such as conditionally strong convexity, we show that our algorithm achieves a $\log T$-regret in the horizon length $T$ for the output estimation scenario. More importantly, we tackle the more challenging scenario of learning Kalman filtering for state estimation, which is an open problem in the literature. We first characterize a fundamental limitation of the problem, demonstrating the impossibility of any algorithm to achieve sublinear regret in $T$. By further introducing a random query scheme into our algorithm, we show that a $\sqrt{T}$-regret is achievable when rendering the algorithm limited query access to more informative measurements of the system state in practice. Our algorithm and regret readily capture the trade-off between the number of queries and the achieved regret, and shed light on online learning problems with limited observations. We validate the performance of our algorithms using numerical examples.

---

### Weakly Convex Ridge Regularization for 3D Non-Cartesian MRI Reconstruction

Authors: German Shâma Wache, Chaithya G R, Asma Tanabene, Sebastian Neumayer
Published: 2026-03-28
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.27158v2

While highly accelerated non-Cartesian acquisition protocols significantly reduce scan time, they often entail long reconstruction delays. Deep learning based reconstruction methods can alleviate this, but often lack stability and robustness to distribution shifts. As an alternative, we train a rotation invariant weakly convex ridge regularizer (WCRR). The resulting variational reconstruction approach is benchmarked against state of the art methods on retrospectively simulated data and (out of distribution) on prospective GoLF SPARKLING and CAIPIRINHA acquisitions. Our approach consistently outperforms widely used baselines and achieves performance comparable to Plug and Play reconstruction with a state of the art 3D DRUNet denoiser, while offering substantially improved computational efficiency and robustness to acquisition changes. In summary, WCRR unifies the strengths of principled variational methods and modern deep learning based approaches.

---

### GSR-GNN: Training Acceleration and Memory-Saving Framework of Deep GNNs on Circuit Graph

Authors: Yuebo Luo, Shiyang Li, Yifei Feng, Vishal Kancharla, Shaoyi Huang, Caiwen Ding
Published: 2026-03-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.27156v1

Graph Neural Networks (GNNs) show strong promise for circuit analysis, but scaling to modern large-scale circuit graphs is limited by GPU memory and training cost, especially for deep models. We revisit deep GNNs for circuit graphs and show that, when trainable, they significantly outperform shallow architectures, motivating an efficient, domain-specific training framework. We propose Grouped-Sparse-Reversible GNN (GSR-GNN), which enables training GNNs with up to hundreds of layers while reducing both compute and memory overhead. GSR-GNN integrates reversible residual modules with a group-wise sparse nonlinear operator that compresses node embeddings without sacrificing task-relevant information, and employs an optimized execution pipeline to eliminate fragmented activation storage and reduce data movement. On sampled circuit graphs, GSR-GNN achieves up to 87.2\% peak memory reduction and over 30$\times$ training speedup with negligible degradation in correlation-based quality metrics, making deep GNNs practical for large-scale EDA workloads.

---

### A Tight Expressivity Hierarchy for GNN-Based Entity Resolution in Master Data Management

Authors: Ashwin Ganesan
Published: 2026-03-28
Categories: cs.LG, cs.AI, cs.DS
arXiv: https://arxiv.org/abs/2603.27154v1

Entity resolution -- identifying database records that refer to the same real-world entity -- is naturally modelled on bipartite graphs connecting entity nodes to their attribute values. Applying a message-passing neural network (MPNN) with all available extensions (reverse message passing, port numbering, ego IDs) incurs unnecessary overhead, since different entity resolution tasks have fundamentally different complexity. For a given matching criterion, what is the cheapest MPNN architecture that provably works? We answer this with a four-theorem separation theory on typed entity-attribute graphs. We introduce co-reference predicates $\mathrm{Dup}_r$ (two same-type entities share at least $r$ attribute values) and the $\ell$-cycle predicate $\mathrm{Cyc}_\ell$ for settings with entity-entity edges. For each predicate we prove tight bounds -- constructing graph pairs provably indistinguishable by every MPNN lacking the required adaptation, and exhibiting explicit minimal-depth MPNNs that compute the predicate on all inputs. The central finding is a sharp complexity gap between detecting any shared attribute and detecting multiple shared attributes. The former is purely local, requiring only reverse message passing in two layers. The latter demands cross-attribute identity correlation -- verifying that the same entity appears at several attributes of the target -- a fundamentally non-local requirement needing ego IDs and four layers, even on acyclic bipartite graphs. A similar necessity holds for cycle detection. Together, these results yield a minimal-architecture principle: practitioners can select the cheapest sufficient adaptation set, with a guarantee that no simpler architecture works. Computational validation confirms every prediction.

---

### Preconditioned Attention: Enhancing Efficiency in Transformers

Authors: Hemanth Saratchandran
Published: 2026-03-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.27153v1

Central to the success of Transformers is the attention block, which effectively models global dependencies among input tokens associated to a dataset. However, we theoretically demonstrate that standard attention mechanisms in transformers often produce ill-conditioned matrices with large condition numbers. This ill-conditioning is a well-known obstacle for gradient-based optimizers, leading to inefficient training. To address this issue, we introduce preconditioned attention, a novel approach that incorporates a conditioning matrix into each attention head. Our theoretical analysis shows that this method significantly reduces the condition number of attention matrices, resulting in better-conditioned matrices that improve optimization. Conditioned attention serves as a simple drop-in replacement for a wide variety of attention mechanisms in the literature. We validate the effectiveness of preconditioned attention across a diverse set of transformer applications, including image classification, object detection, instance segmentation, long sequence modeling and language modeling.

---

### DiffSoup: Direct Differentiable Rasterization of Triangle Soup for Extreme Radiance Field Simplification

Authors: Kenji Tojo, Bernd Bickel, Nobuyuki Umetani
Published: 2026-03-28
Categories: cs.GR, cs.CV
arXiv: https://arxiv.org/abs/2603.27151v2

Radiance field reconstruction aims to recover high-quality 3D representations from multi-view RGB images. Recent advances, such as 3D Gaussian splatting, enable real-time rendering with high visual fidelity on sufficiently powerful graphics hardware. However, efficient online transmission and rendering across diverse platforms requires drastic model simplification, reducing the number of primitives by several orders of magnitude. We introduce DiffSoup, a radiance field representation that employs a soup (i.e., a highly unstructured set) of a small number of triangles with neural textures and binary opacity. We show that this binary opacity representation is directly differentiable via stochastic opacity masking, enabling stable training without a mollifier (i.e., smooth rasterization). DiffSoup can be rasterized using standard depth testing, enabling seamless integration into traditional graphics pipelines and interactive rendering on consumer-grade laptops and mobile devices. Code is available at https://github.com/kenji-tojo/diffsoup.

---

### DiffSoup: Direct Differentiable Rasterization of Triangle Soup for Extreme Radiance Field Simplification

Authors: Kenji Tojo, Bernd Bickel, Nobuyuki Umetani
Published: 2026-03-28
Categories: cs.GR, cs.CV
arXiv: https://arxiv.org/abs/2603.27151v1

Radiance field reconstruction aims to recover high-quality 3D representations from multi-view RGB images. Recent advances, such as 3D Gaussian splatting, enable real-time rendering with high visual fidelity on sufficiently powerful graphics hardware. However, efficient online transmission and rendering across diverse platforms requires drastic model simplification, reducing the number of primitives by several orders of magnitude. We introduce DiffSoup, a radiance field representation that employs a soup (i.e., a highly unstructured set) of a small number of triangles with neural textures and binary opacity. We show that this binary opacity representation is directly differentiable via stochastic opacity masking, enabling stable training without a mollifier (i.e., smooth rasterization). DiffSoup can be rasterized using standard depth testing, enabling seamless integration into traditional graphics pipelines and interactive rendering on consumer-grade laptops and mobile devices. Code is available at https://github.com/kenji-tojo/diffsoup.

---

### MediHive: A Decentralized Agent Collective for Medical Reasoning

Authors: Xiaoyang Wang, Christopher C. Yang
Published: 2026-03-28
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2603.27150v2

Large language models (LLMs) have revolutionized medical reasoning tasks, yet single-agent systems often falter on complex, interdisciplinary problems requiring robust handling of uncertainty and conflicting evidence. Multi-agent systems (MAS) leveraging LLMs enable collaborative intelligence, but prevailing centralized architectures suffer from scalability bottlenecks, single points of failure, and role confusion in resource-constrained environments. Decentralized MAS (D-MAS) promise enhanced autonomy and resilience via peer-to-peer interactions, but their application to high-stakes healthcare domains remains underexplored. We introduce MediHive, a novel decentralized multi-agent framework for medical question answering that integrates a shared memory pool with iterative fusion mechanisms. MediHive deploys LLM-based agents that autonomously self-assign specialized roles, conduct initial analyses, detect divergences through conditional evidence-based debates, and locally fuse peer insights over multiple rounds to achieve consensus. Empirically, MediHive outperforms single-LLM and centralized baselines on MedQA and PubMedQA datasets, attaining accuracies of 84.3% and 78.4%, respectively. Our work advances scalable, fault-tolerant D-MAS for medical AI, addressing key limitations of centralized designs while demonstrating superior performance in reasoning-intensive tasks.

---

### SafetyDrift: Predicting When AI Agents Cross the Line Before They Actually Do

Authors: Aditya Dhodapkar, Farhaan Pishori
Published: 2026-03-28
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2603.27148v1

When an LLM agent reads a confidential file, then writes a summary, then emails it externally, no single step is unsafe, but the sequence is a data leak. We call this safety drift: individually safe actions compounding into violations. Prior work has measured this problem; we predict it. SafetyDrift models agent safety trajectories as absorbing Markov chains, computing the probability that a trajectory will reach a violation within a given number of steps via closed form absorption analysis. A consequence of the monotonic state design is that every agent will eventually violate safety if left unsupervised (absorption probability 1.0 from all states), making the practical question not if but when, and motivating our focus on finite horizon prediction. Across 357 traces spanning 40 realistic tasks in four categories, we discover that "points of no return" are sharply task dependent: in communication tasks, agents that reach even a mild risk state have an 85% chance of violating safety within five steps, while in technical tasks the probability stays below 5% from any state. A lightweight monitor built on these models detects 94.7% of violations with 3.7 steps of advance warning at negligible computational cost, outperforming both keyword matching (44.7% detection, 55.9% false positive rate) and per step LLM judges (52.6% detection, 38.2% false positive rate) while running over 60,000x faster.

---