Image_Caption
-
OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR Generation
2026-05-13 17:42:20Youquan Liu, Weidong Yang, Ao Liang, Xiang Xu, Lingdong Kong, Yang Wu, Dekai Zhu, Xin Li, Runnan Chen, Ben Fei, Tongliang Liu, Wanli OuyangAbstract
LiDAR scene generation is increasingly important for scalable simulation and synthetic data creation, especially under diverse sensing conditions that are costly to capture at scale. Typically, diffusion-based LiDAR generators are developed under single-domain settings, requiring separate models for different datasets or sensing conditions and hindering unified, controllable synthesis under heterogeneous distribution shifts. To this end, we present OmniLiDAR, a unified text-conditioned diffusion framework that generates LiDAR scans in a shared range-image representation across eight representative domains spanning three shift types: adverse weather, sensor-configuration changes (e.g., reduced beams), and cross-platform acquisition (vehicle, drone, and quadruped). To enable training a single model over heterogeneous domains without isolating optimization by domain, we introduce a Cross-Domain Training Strategy (CDTS) that mixes domains within each mini-batch and leverages conditioning to steer generation. We further propose Cross-Domain Feature Modeling (CDFM), which captures directional dependencies along azimuth and elevation axes to reflect the anisotropic scanning structure of range images, and Domain-Adaptive Feature Scaling (DAFS) as a lightweight modulation to account for structured domain-dependent feature shifts during denoising. In the absence of a public consolidated benchmark, we construct an 8-domain dataset by combining real-world scans with physically based weather simulation and systematic beam reduction while following official splits. Extensive experiments demonstrate strong generation fidelity and consistent gains in downstream use cases, including generative data augmentation for LiDAR semantic segmentation and 3D object detection, as well as robustness evaluation under corruptions, with consistent benefits in limited-label regimes.
Abstract (translated)
URL
https://arxiv.org/abs/2605.13815
PDF
-
CA-GCL: Cross-Anatomy Global-Local Contrastive Learning for Robust 3D Medical Image Understanding
2026-05-13 13:54:27Hanwen Zhang, Yao Liu, Die Dai, Jiaye Yang, Qiao Liu, Yutong Xie, Peng WangAbstract
Fine-grained Vision-Language Pre-training (FVLP) demonstrates significant potential in 3D medical image understanding by aligning anatomy-level visual representations with corresponding textual descriptions. However, existing FVLP paradigms often suffer from severe representation collapse in the textual embedding space, where text embeddings of distinct anatomical structures become highly clustered and indistinguishable. This distributional degeneracy renders the model hypersensitive to prompt variations, hindering reliable clinical deployment. To address these challenges, we propose a novel Cross-Anatomy Global-Local Contrastive Learning framework (CA-GCL). CA-GCL introduces a global contrastive objective that enforces separation between anatomical categories in the latent space, effectively counteracting the aggregation tendency induced by local alignment. Furthermore, we incorporate a clinical-aware text augmentation strategy based on permutation invariance and partial completeness to enhance robustness against descriptive incompleteness. Extensive evaluations on the CT-RATE and Rad-ChestCT datasets demonstrate that CA-GCL consistently outperforms existing VLP paradigms in zero-shot abnormality detection, achieving superior performance while exhibiting strong cross-dataset generalization. Crucially, CA-GCL reduces performance variance across diverse prompt templates, transforming the collapsed textual similarity distribution into a bell-shaped distribution. These results validate CA-GCL as an effective framework for robust 3D medical image understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2605.13544
PDF
-
CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large VIsion-Language Models
2026-05-13 08:40:40Sangin Lee, Yukyung ChoiAbstract
In large vision-language models, visual tokens typically constitute the majority of input tokens, leading to substantial computational overhead. To address this, recent studies have explored pruning redundant or less informative visual tokens for image understanding tasks. However, these methods struggle with pixel grounding tasks, where token importance is highly contingent on the input text. Through an in-depth analysis of CLIP, we observe that visual tokens located within referent regions often exhibit low similarity to the textual representation. Motivated by this insight, we introduce LiteLVLM, a training-free, text-guided token pruning strategy for efficient pixel grounding inference. By reversing the ranking of CLIP's visual-text similarity, LiteLVLM effectively retains visual tokens covering the referent regions, while recovering context tokens to enable clear foreground-background separation. Extensive experiments demonstrate that LiteLVLM significantly outperforms existing methods by over 5% across diverse token budgets. Without any training or fine-tuning, LiteLVLM maintains 90\% of the original performance with a 22% speedup and a 2.3x memory reduction. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2605.13178
PDF
-
Lifelong Learning in Vision-Language Models: Enhanced EWC with Cross-Modal Knowledge Retention
2026-05-12 22:05:30Hamza Ahmed Durrani, Rafay Suleman DurraniAbstract
Large language-vision models (LVLMs) such as CLIP, Flamingo, and BLIP have revolutionized AI by enabling understanding across textual and visual modalities. These models excel at tasks like image captioning, visual question answering, and cross-modal retrieval. However, they face catastrophic forgetting when learning new tasks sequentially, particularly challenging in multi-modal settings where preserving cross-modal alignments adds complexity to the learning process. This paper presents a comprehensive continual learning framework for LVLMs that combines enhanced Elastic Weight Consolidation (EWC) with parameter-efficient fine-tuning techniques. We integrate multi-modal Fisher Information Matrix calculation, consistency preservation across modalities, and adaptive regularization that considers dependencies across visual and textual encoders. The framework achieves a 78% reduction in forgetting rates relative to naive sequential training approaches through extensive evaluation testing. The framework also preserves alignment between modalities during sequential learning with only 15% additional computational cost. This work advances the state of the art in lifelong learning for multi-modal AI systems, with direct applications to autonomous driving, intelligent robotic assistants, and adaptive robotic systems that must continuously learn in dynamic real-world environments.
Abstract (translated)
URL
https://arxiv.org/abs/2605.12789
PDF
-
G$^2$TR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models
2026-05-12 15:56:22Junxian Li, Kai Liu, Zizhong Ding, Zhixin Wang, Zhikai Chen, Renjing Pei, Yulun ZhangAbstract
The development of separate-encoder Unified multimodal models (UMMs) comes with a rapidly growing inference cost due to dense visual token processing. In this paper, we focus on understanding-side visual token reduction for improving the efficiency of separate-encoder UMMs. While this topic has been widely studied for MLLMs, existing methods typically rely on attention scores, text-image similarity and so on, implicitly assuming that the final objective is discriminative reasoning. This assumption does not hold for UMMs, where understanding-side visual tokens must also preserve the model's capabilities for editing images. We propose G$^2$TR, a generation-guided visual token reduction framework for separate-encoder UMMs. Our key insight is that the generation branch provides a task-agnostic signal for identifying understanding-side visual tokens that are not only semantically relevant but also important for latent-space image reconstruction and generation. G$^2$TR estimates token importance from consistency with VAE latent, performs balanced token selection, and merges redundant tokens into retained representatives to reduce information loss. The method is training-free, plug-and-play, and applied only after the understanding encoding stage, making it compatible with existing UMM inference pipelines. Experiments on image understanding and editing benchmarks show that G$^2$TR substantially reduces visual tokens and prefill computation by 1.94x while maintaining both reasoning accuracy and editing quality, outperforming baselines on almost all benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2605.12309
PDF
-
What-Where Transformer: A Slot-Centric Visual Backbone for Concurrent Representation and Localization
2026-05-12 12:08:46Ryota Yoshihashi, Masahiro Kada, Satoshi Ikehata, Rei Kawakami, Ikuro SatoAbstract
Many image understanding tasks involve identifying what is present and where it appears. However, tasks that address where, such as object discovery, detection, and segmentation, are often considerably more complex than image classification, which primarily focuses on what. One possible reason is that classification-oriented backbones tend to emphasize semantic information about what, while implicitly entangling or suppressing information about where. In this work, we focus on an inductive bias termed what-where separation, which encourages models to represent object appearance and spatial location in a decomposed manner. To incorporate this bias throughout an attentive backbone in the style of Vision Transformer (ViT), we propose the What-Where Transformer (WWT). Our method introduces two key novel designs: (1) it treats tokens as representations of what and attention maps as representations of where, and processes them in concurrent feed-forward modules via a multi-stream, slot-based architecture; (2) it reuses both the final-layer tokens and attention maps for downstream tasks, and directly exposes them to gradients derived from task losses, thereby facilitating more effective and explicit learning of localization. We demonstrate that even under standard single-label classification-based supervision on ImageNet, WWT exhibits emergent multiple object discovery directly from raw attention maps, rather than via additional postprocessing such as token clustering. Furthermore, WWT achieves superior performance compared to ViT-based methods on zero-shot object discovery and weakly supervised semantic segmentation, and it is transferable to various localization setups with minimal modifications. Code will be published after acceptance.
Abstract (translated)
URL
https://arxiv.org/abs/2605.12021
PDF
-
Revisiting Shadow Detection from a Vision-Language Perspective
2026-05-12 08:42:30Yonghui Wang, Wengang Zhou, Hao Feng, Houqiang LiAbstract
Shadow detection is commonly formulated as a vision-driven dense prediction problem, where models rely primarily on pixel-wise visual supervision to distinguish shadows from non-shadow regions. However, this formulation can become unreliable in visually ambiguous cases, where similar dark regions may correspond either to cast shadows or to intrinsically dark surfaces, making visual evidence alone insufficient for establishing a stable decision rule. In this work, we revisit shadow detection from a vision--language perspective and argue that robust prediction benefits from an explicit semantic reference beyond visual cues alone. We propose SVL, a Shadow Vision--Language framework that uses language as an explicit semantic reference to disambiguate shadows from visually similar dark regions. SVL aligns the global image representation with shadow-related text embeddings through a scene-level shadow ratio regression objective, thereby providing image-level guidance on the overall extent of shadows. To transfer this global guidance to dense inference, SVL introduces a global-to-local coupling mechanism that enforces consistency between image-level guidance and patch-level predictions. In parallel, SVL applies local patch-level constraints with text embeddings to improve fine-grained discrimination under challenging appearance conditions. Built on a frozen DINOv3 image encoder, the framework learns only lightweight projection and decoding modules, yielding a parameter-efficient design with less than $1\%$ trainable parameters. Extensive experiments on multiple shadow detection benchmarks, including dedicated hard-case evaluations, suggest strong overall performance and improved robustness under visually ambiguous conditions.
Abstract (translated)
URL
https://arxiv.org/abs/2605.11771
PDF
-
Towards a Large Language-Vision Question Answering Model for MSTAR Automatic Target Recognition
2026-05-11 16:05:58David F. Ramirez, Tim L. Overman, Kristen Jaskie, Marv Kleine, Andreas SpaniasAbstract
Large language-vision models (LLVM), such as OpenAI's ChatGPT and GPT-4, have gained prominence as powerful tools for analyzing text and imagery. The merging of these data domains represents a significant paradigm shift with far-reaching implications for automatic target recognition (ATR). Recent transformer-based LLVM research has shown substantial improvements for geospatial perception tasks. Our study examines the application of LLVM to remote sensing image captioning and visual question-answering (VQA), with a specific focus on synthetic aperture radar (SAR) imagery. We examine newly published LLVM methods, including CLIP and LLaVA neural network transformer architectures. We have developed a work-in-progress SAR training and evaluation benchmark derived from the MSTAR Public Dataset. This has been extended to include descriptive text captions and question-answer pairs for VQA tasks. This challenge dataset is designed to push the boundaries of an LLVM in identifying nuanced ATR details in SAR imagery. Utilizing parameter-efficient fine-tuning, we train an LLVM method to identify fine-grained target qualities at 98% accuracy. We detail our data setup and experiments, addressing potential pitfalls that could lead to misleading conclusions. Accurately identifying and differentiating military vehicle types in SAR data poses a critical challenge, especially under complex environmental conditions. Mastering this target recognition skill may require a human analyst months of training and years of practice. This research represents a unique effort to apply LLVM to SAR applications, advancing machine-assisted remote sensing ATR for military and intelligence contexts.
Abstract (translated)
URL
https://arxiv.org/abs/2605.10772
PDF
-
TINS: Test-time ID-prototype-separated Negative Semantics Learning for OOD Detection
2026-05-11 15:54:34Yifeng Yang, Jubo Feng, Jing Xu, Xinbing Wang, Qinying Gu, Nanyang YeAbstract
Vision-language models enable OOD detection by comparing image alignment with ID labels and negative semantics. Existing negative-label-based methods mainly rely on static negative labels constructed before inference, limiting their ability to cover diverse and evolving OOD concepts. Although test-time expansion provides a natural solution, naively learning negative semantics from potential OOD samples may introduce hard ID contamination. To address this issue, we propose a \textbf{T}est-time \textbf{I}D-prototype-separated \textbf{N}egative \textbf{S}emantics learning method, termed \textbf{TINS}. TINS learns sample-specific negative text embeddings via image-to-text modality inversion and introduces ID-prototype-separated regularization to keep them separated from ID semantics. To further stabilize negative semantics expansion, TINS employs group-wise aggregation scoring and a buffer update strategy. Extensive experiments across Four-OOD, OpenOOD, Temporal-shift, and Various ID settings show consistent improvements over strong baselines. Notably, on the Four-OOD benchmark with ImageNet-1K as ID, TINS reduces the average FPR95 from 14.04\% to 6.72\%. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2605.10756
PDF
-
Med-StepBench: A Hierarchical Reasoning Framework for Evaluating Hallucinations in Medical Vision-Language Models
2026-05-11 05:26:59Minh Khoi Nguyen, Dai Lam Le, Amir Reza Jafari, Tuan Dung Nguyen, Mai Hong Son, Mai Huy Thong, Quang Huy Nguyen, Thanh Trung Nguyen, Reza Farahbakhsh, Noel Crespi, Phi Le NguyenAbstract
Large vision-language models (VLMs) demonstrate strong performance in medical image understanding, but frequently generate clinically plausible yet incorrect statements, raising significant safety concerns. Existing medical hallucination benchmarks primarily focus on 2D imaging with one-shot diagnostic questions, offering limited insight into whether predictions are grounded in correct localization and abnormality identification, allowing critical reasoning errors to remain hidden behind seemingly correct diagnoses. We introduce Med-StepBench, the first large-scale benchmark for step-wise hallucination detection in 3D oncological PET/CT, comprising over 12,000 images and more than 1,000,000 image-statement pairs across volumetric and multi-view 2D data, which decomposes clinical reasoning into four expert-designed diagnostic stages. Using clinician-verified annotations, we perform the first step-level evaluation of general-purpose and medical VLMs, revealing systematic failure modes obscured by aggregate accuracy metrics. Furthermore, we show that current VLMs are highly susceptible to adversarial yet clinically plausible intermediate explanations, which significantly amplify hallucinations despite contradictory visual evidence. Together, our findings highlight fundamental limitations in grounding multi-step clinical reasoning and establish Med-StepBench as a rigorous benchmark for developing safer and more reliable medical VLMs.
Abstract (translated)
URL
https://arxiv.org/abs/2605.10002
PDF
-
LiteMedCoT-VL: Parameter-Efficient Adaptation for Medical Visual Question Answering
2026-05-10 07:21:33Runze Ma, Shunbo Jia, Haonan Lyu, Guo Liu, Caizhi LiaoAbstract
The reasoning gap between large and compact vision-language models (VLMs) limits the deployment of medical AI on portable clinical devices. Compact VLMs of 2--4B parameters can run on resource-constrained hardware but lack the multi-step reasoning capacity needed for interpretable clinical decision support. Existing knowledge distillation methods transfer answers without the reasoning process behind them. Medical visual question answering (VQA) serves as a testbed for this problem, as it requires models to integrate visual evidence with clinical knowledge through structured reasoning chains. We introduce LiteMedCoT-VL, a pipeline that transfers chain-of-thought reasoning from a 235B teacher model to 2B student models through LoRA-based fine-tuning on explanation-enriched training data. All inference is conducted without image captions by default, simulating the clinical scenario in which a physician interprets a medical image directly without an accompanying radiology report. On the PMC-VQA benchmark, LiteMedCoT-VL achieves 64.9% accuracy, exceeding the zero-shot Qwen3-VL-4B baseline of 53.9% by 11.0 percentage points and outperforming all published baselines. This result indicates that a 2B model with reasoning distillation can match or exceed models with twice the parameters. Visual grounding analysis shows that the model relies on image content rather than exploiting textual priors. Our code is publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2605.09384
PDF
-
ZAYA1-VL-8B Technical Report
2026-05-08 23:41:13Hassan Shapourian, Kasra Hejazi, Olabode M. Sule, Beren MillidgeAbstract
We present ZAYA1-VL-8B, a compact mixture-of-experts vision-language model built upon our in-house language model, ZAYA1-8B. Despite its compact size, ZAYA1-VL achieves performance competitive with leading base models such as Molmo2-4B and InternVL3.5-4B, while surpassing models including Qwen2.5-VL-3B, PLM-3B, and MolmoE-1B across a range of image understanding, reasoning, and counting benchmarks. The architecture incorporates two key innovations: (1) vision-specific LoRA adapters integrated into the LLM to increase modality-specific capacity without increasing the number of experts, and (2) bidirectional attention over image tokens within the LLM to enhance visual understanding. We detail the full training pipeline including data composition at each stage, sequence packing, and the attention masking scheme. The model comprises 9.2B total parameters, with 1.4B active parameters including the vision encoder, and is publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2605.08560
PDF
-
Decoupling Endpoint and Semantic Transition Learning for Zero-Shot Composed Image Retrieval
2026-05-08 18:55:41Mingyu Liu, Sihan Huang, Yijia Fan, Yinlin Yan, Quan Zhang, Jian-Fang Hu, Jianhuang LaiAbstract
Zero-shot composed image retrieval (ZS-CIR) retrieves a target image from a reference image and a text modification without human-annotated CIR triplets. Projection-based ZS-CIR methods are attractive because they do not rely on LLMs at inference and remain lightweight, but they often underperform LLM-based approaches on complex semantic modifications. This gap reflects a semantic transition bottleneck in projection-based ZS-CIR: endpoint-level matching can let the edit text act as a target-side attribute cue rather than grounding it as a source-conditioned semantic transition. We further show that adding semantic transition supervision to the same text adapter creates an endpoint--transition conflict between endpoint alignment and semantic transition alignment. To address this conflict, DeCIR decouples endpoint and transition learning. It constructs paired forward/reverse edit tuples from image-caption pairs, trains separate low-rank text adapter branches for endpoint alignment and semantic transition alignment, and merges them with Low-Rank Directional Merge (LRDM) into one deployable adapter. Extensive experiments on CIRR, CIRCO, FashionIQ, and GeneCIS demonstrate that DeCIR consistently improves projection-based ZS-CIR without increasing inference complexity.
Abstract (translated)
URL
https://arxiv.org/abs/2605.08389
PDF
-
LithoBench: Benchmarking Large Multimodal Models for Remote-Sensing Lithology Interpretation
2026-05-08 12:07:26Jun Wang, Fengpeng Li, Hang Dong, Tianjin Huang, Wei HanAbstract
Remote sensing lithology interpretation is fundamental to geological surveys, mineral exploration, and regional geological mapping. Unlike general land-cover recognition, lithology interpretation is a knowledge-intensive task that requires experts to infer rock types from various features, e.g., subtle visual, spectral, textural, geomorphological, and contextual cues, making reliable automated interpretation highly challenging. Geological knowledge-guided large multimodal models offer new opportunities, yet their evaluation remains constrained by the lack of benchmarks that capture lithological annotations, multi-level geological semantics, and expert-informed assessment. Here, we propose LithoBench, a multi-level benchmark for evaluating geological semantic understanding in remote sensing lithology interpretation. LithoBench contains 10,000 expert-annotated interpretation instances across 12 representative lithological categories, including 4,000 multiple-choice and 6,000 open-ended tasks organized into five cognitive levels: Identification and Description, Comparative Analysis, Mechanism Explanation, Practical Application, and Comprehensive Reasoning. We further develop an expert-in-the-loop, knowledge-grounded semi-automated construction pipeline, coupling multi sub-processes, e.g., structured geological image descriptions, to enhance geological validity and evaluation reliability. Experiments with multiple large vision-language models eveal substantial limitations in geological semantic understanding, particularly on higher-order explanation, application, and reasoning tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2605.07640
PDF
-
BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning
2026-05-08 07:48:36Shaokai Ye, Vasileios Saveris, Yihao Qian, Jiaming Hu, Elmira Amirloo, Peter GraschAbstract
Image captioning is one of the most fundamental tasks in computer vision. Owing to its open-ended nature, it has received significant attention in the era of multimodal large language models (MLLMs). In pursuit of ever more detailed and accurate captions, recent work has increasingly turned to reinforcement learning (RL). However, existing captioning-RL methods and evaluation metrics often emphasize a narrow notion of caption quality, inducing trade-offs across core dimensions of captioning. For example, utility-oriented objectives can encourage noisy, hallucinated, or overlong captions that improve downstream question answering while harming fluency, whereas arena-style objectives can favor fluent but generic descriptions with limited usefulness. To address this, we propose a more balanced RL framework that jointly optimizes utility-aware correctness, reference coverage, and linguistic quality. In order to effectively optimize the resulting continuous multi-objective reward formulation, we apply GDPO-style reward-decoupled normalization to continuous-valued captioning rewards and show that it improves performance over vanilla GRPO. Additionally, we introduce length-conditional reward masking, yielding a more suitable length penalty for captioning. Across LLaVA-1.5-7B and Qwen2.5-VL 3B and 7B base models, our method consistently improves caption quality, with peak gains of +13.6 DCScore, +9.0 CaptionQA, and +29.0 CapArena across different models.
Abstract (translated)
URL
https://arxiv.org/abs/2605.07394
PDF
-
ShellfishNet: A Domain-Specific Benchmark for Visual Recognition of Marine Molluscs
2026-05-08 06:42:55Ziheng Zhou, Yang Wang, Nan Wang, Chengliang Wu, Jun YanAbstract
The decline of global shellfish biodiversity poses a severe threat to coastal ecosystems. Although artificial intelligence (AI) technologies show potential for automated ecological monitoring, existing marine benthic datasets often lack adaptation to the complexities of real underwater environments (e.g., variable lighting conditions and diverse species postures), posing challenges for the robust generalization of vision models in practical ecological monitoring. To address this problem, we construct ShellfishNet, a comprehensive image benchmark dataset designed specifically for real-world ecological monitoring constraints. Comprising 8,691 images across 32 taxa, this dataset includes a curated subset annotated with descriptive captions. It is constructed through field photography and web scraping, encompassing samples from complex real-world environments. Based on this benchmark, we systematically evaluate 80 representative neural network models, including Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), State Space Models (SSMs), and Self-Supervised Learning (SSL) methods. Furthermore, we evaluate the performance of fine-grained visual categorization (FGVC) models and investigate the image captioning capabilities of several mainstream multimodal large language models (MLLMs). Meanwhile, we introduce image corruption benchmark tests to simulate common underwater degradation scenarios (turbidity, severe weather) and assess the robustness of vision models, enabling trustworthy decisions on ecological protection in the wild. ShellfishNet is dedicated to providing a data foundation and a model-evaluation benchmark for the intelligent monitoring of benthic organisms.
Abstract (translated)
URL
https://arxiv.org/abs/2605.07338
PDF
-
Fine-tuning a vision-language model for fracture-surface morphology recognition
2026-05-08 02:26:36Quanliang Liu, Jungtaek Kim, Kangwook Lee, Hyunseok OhAbstract
Vision-language models (VLMs) have shown strong potential for scientific image understanding, but general-purpose models often lack the domain-specific visual knowledge required for reliable materials characterization. In this work, we fine-tuned an open-source VLM (Qwen3-VL-32B-Instruct) for fracture-surface image analysis using a curated dataset of 13,168 open-source, literature-mined fracture-surface images. Morphology annotations were generated by GPT-5.2-Reasoning (high) from both the images and relevant excerpts of their source papers, and the dataset was further enriched with targeted manual collection and rotation-based augmentation. The resulting specialist model outperforms flagship proprietary multimodal models on a benchmark of 100 manually annotated images. It achieves a precision of 0.92, compared to 0.35 for the base Qwen3-VL-32B-Instruct, 0.58 for GPT-5.5-Reasoning (high), and 0.78 for Gemini 3.1 Pro-Reasoning (high). Dataset ablations show that manual collection of rare-feature images and augmentation via image rotation are both beneficial to improve recognition of less common fracture morphology features. We further discuss integrated use of the fine-tuned model with proprietary models to combine fracture-specific visual accuracy with broader multimodal reasoning for autonomous fractography. Although focused on fracture-surface images, this work demonstrates how VLMs can be adapted through targeted collection and fine-tuning on novel feature images to recognize those features and support downstream decision-making in autonomous microscopy workflows.
Abstract (translated)
URL
https://arxiv.org/abs/2605.07145
PDF
-
MedHorizon: Towards Long-context Medical Video Understanding in the Wild
2026-05-07 16:37:10Bodong Du, Bowen Liu, Yang Yu, Xinpeng Ding, Zhiheng Wu, Shuning Wang, Shuo Nie, Naiming Liu, Qifeng Chen, Yangqiu Song, Xiaomeng LiAbstract
Medical multimodal large language models (MLLMs) have advanced image understanding and short-video analysis, but real clinical review often requires full-procedure video understanding. Unlike general long videos, medical procedures contain highly redundant anatomical views, while decisive evidence is temporally sparse, spatially subtle, and context dependent. Existing benchmarks often assume this evidence has already been localized through images, short clips, or pre-segmented videos, leaving the retrieval-before-reasoning problem under-tested. We introduce MedHorizon, an in-the-wild benchmark for long-context medical video understanding. MedHorizon preserves 759 hours of full-length clinical procedures and provides 1,253 evidence-grounded multiple-choice questionsthat jointly evaluate sparse evidence understanding and multi-hop clinical reasoning. Its evidence is extremely sparse, with only 0.166% evidence frames on average, requiring models to search noisy procedural streams before interpreting and aggregating findings. We evaluate representative general-domain, medical-domain, and long-video MLLMs. The best model reaches only 41.1% accuracy, showing that current systems remain far from robust full-procedure understanding. Further analysis yields four key findings: performance does not scale reliably with more frames, evidence retrieval and clinical interpretation remain primary bottlenecks; these bottlenecks are rooted in weak procedural reasoning and attention drift under redundancy, and generic sampling methods only partially balances local detail with global coverage. MedHorizon provides a rigorous testbed for MLLMs that retrieve sparse evidence and reason over complete clinical workflows.
Abstract (translated)
URL
https://arxiv.org/abs/2605.06537
PDF
-
Metonymy in vision models undermines attention-based interpretability
2026-05-07 12:14:46Ananthu Aniraj, Cassio F. Dantas, Dino Ienco, Massimiliano Mancini, Diego MarcosAbstract
Part-based reasoning is a classical strategy to make a computer vision model directly focus on the object parts that are relevant to the downstream task. In the context of deep learning, this also serves to improve by-design interpretability, often by using part-centric attention mechanisms on top of a latent image representation provided by a standard, black-box model. This approach is based on a locality assumption: that the latent representation of an object part encodes primarily information about the corresponding image region. In this work, we test this basic assumption, measuring intra-object leakage in vision models using part-based attribute annotations. Through a comprehensive experimental evaluation, we show that modern pretrained vision transformers violate the locality assumption and exhibit a strong intra-object leakage, in which each part encodes information from the whole object, a visual metonymy that compromises the faithfulness of attention-based interpretable-by-design methods for part-based reasoning, ultimately rendering them uninterpretable. In addition, we establish an upper bound using a two-stage approach that prevents leakage by design. We then show that this inherently disentangled feature extraction improves attribute-driven part discovery on a variety of tasks, confirming the practical impact of intra-object leakage. Our results uncover a neglected issue affecting the interpretability of part-based representations, such as those in CBMs relying on part-centric concepts, highlighting that two-stage approaches offer a promising way to mitigate it.
Abstract (translated)
URL
https://arxiv.org/abs/2605.06095
PDF
-
MSD-Score: Multi-Scale Distributional Scoring for Reference-Free Image Caption Evaluation
2026-05-07 12:02:23Shichao Kan, Xuyang Zhang, Haojie Zhang, Zhe Zhu, Yigang Cen, Yixiong Liang, Lianlei Shan, Linna Zhang, Zhe Qu, Jiazhi XiaAbstract
Evaluating image captions without references remains challenging because global embedding similarity often misses fine-grained mismatches such as hallucinated objects, missing attributes, or incorrect relations. We propose MSD-Score, a reference-free metric that models image patch and text token embeddings as von Mises-Fisher mixtures on the unit hypersphere. Instead of treating each modality as a single point, MSD-Score formulates image-text matching as a multi-scale distributional scoring problem. Semantic discrepancies are quantified via a weighted bi-directional KL divergence and combined with global similarity in a multi-scale framework for both single- and multi-candidate evaluations. Extensive experiments show that MSD-Score achieves state-of-the-art correlation with human judgments among reference-free metrics. Beyond accuracy, its probabilistic formulation yields transparent and decomposable diagnostics of local grounding errors, providing a deterministic complementary signal to holistic similarity metrics and judge-based evaluators.
Abstract (translated)
URL
https://arxiv.org/abs/2605.06080
PDF
