Image_Caption
-
Symbal: Detecting Systematic Misalignments in Model-Generated Captions
2026-07-16 17:18:37Maya Varma, Jean-Benoit Delbrouck, Sophie Ostmeier, Akshay Chaudhari, Curtis LanglotzAbstract
Multimodal large language models (MLLMs) often introduce errors when generating image captions, resulting in misaligned image-text pairs. Our work focuses on a class of captioning errors that we refer to as systematic misalignments, where a recurring error in MLLM-generated captions is closely associated with the presence of a specific visual feature in the paired image. Given a vision-language dataset with MLLM-generated captions, our aim in this work is to detect such errors, a task we refer to as systematic misalignment detection. As our first key contribution, we present Symbal, which utilizes a structured, dual-stage setup with off-the-shelf foundation models to identify systematic misalignments and summarize results in natural language. As our second key contribution, we introduce SymbalBench, a benchmark designed to evaluate automated methods on our proposed task. SymbalBench consists of 1.7 million image-text pairs from two domains (natural and medical images), organized into 420 vision-language datasets with annotated systematic misalignments. Symbal exhibits strong performance on this benchmark, correctly identifying systematic misalignments in 63.8% of datasets, a nearly 4x improvement over the closest baseline. We supplement our evaluations on SymbalBench with real-world evaluations, showing that (1) Symbal can accurately surface systematic misalignments in captions generated by four MLLMs and (2) Symbal is a powerful tool for auditing off-the-shelf image-caption datasets. Ultimately, our novel task, method, and benchmark can aid users with auditing MLLM-generated captions and identifying critical errors, without requiring access to the underlying MLLM. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.15216
PDF
-
Towards Enhancing 3D Spatial Reasoning in Medical Multimodal Large Language Models
2026-07-15 14:05:58Zhuoyuan Fu, Zeshang Li, Yiqiong Zhang, Hangui Lin, Yan Shu, Yan Li, Binyang Li, Yaru ZhaoAbstract
While Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in 2D medical image understanding, their extension to 3D volumetric imaging remains hindered by prohibitive annotation costs and dataset opacity. Current data formats, predominantly consisting of rigid Visual Question Answering (VQA) pairs or unstructured final clinical reports, typically fail to capture explicit clinical reasoning. To address this limitation, we introduce a large-scale structured reasoning dataset constructed via a novel slice-wise data synthesis paradigm. Inspired by the genuine diagnostic workflow of radiologists, this paradigm models visual cognition by decomposing the complex 3D reading process, translating global clinical priors into fine-grained, per-slice observations that are subsequently synthesized into an interpretable Chain-of-Thought (CoT). Crucially, this synthesized reasoning framework enforces essential clinical principles: sequential spatial tracking, multi-slice spatial awareness for artifact mitigation, and differential exclusion. To validate this approach, we instruction-tune a standard 2D-pretrained MLLM baseline using the synthesized data to enhance its volumetric comprehension. Comprehensive evaluations across multiple 3D medical benchmarks demonstrate that our method yields significant performance improvements over the 2D baseline. Furthermore, the resulting model exhibits robust spatial reasoning capabilities and rivals resource-intensive native 3D architectures, effectively bridging the performance gap. Ultimately, this data-centric strategy unlocks deep volumetric understanding and highly interpretable clinical logic without requiring computationally expensive 3D-specific pre-training. The complete repository, including datasets and training workflows, is publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.13860
PDF
-
Multimodal Assessment of Pancreatic Cancer Resectability Using Deep Learning
2026-07-15 13:32:44Vincent Ochs, Christoph Kuemmerli, Florentin Bieder, Julia Wolleb, Joel L. Lavanchy, Julia Ruppel, Jan Liechti, Stephanie Taha-Mehlitz, Christian Andreas Nebiker, Beat Mueller, Giuseppe Kito Fusai, Joerg-Matthias Pollok, Anas Taha, Philippe C. Cattin, Sebastian StaubliAbstract
Accurate determination of pancreatic ductal adenocarcinoma (PDAC) resectability relies on evaluating how the tumor interacts with major peripancreatic vessels on CT imaging, yet expert assessment often shows substantial variability. We introduce a fully automated multimodal deep learning framework that jointly analyzes 3D contrast enhanced CT and structured clinical information to classify patients into the three National Comprehensive Cancer Network (NCCN) resectability categories (upfront resectable, borderline resectable, locally advanced). The approach uses a Swin-UNETR backbone to obtain anatomy aware image representations through auxiliary segmentation of pancreas, tumor, and vascular structures. These features are fused with a compact clinical embedding derived from 17 routinely collected variables and processed by a lightweight classification head. Model training is guided by a dynamic multitask objective that adapts the balance between segmentation and classification based on current tumor Dice performance, promoting feature representations that remain both anatomically informed and discriminative.
Abstract (translated)
URL
https://arxiv.org/abs/2607.13826
PDF
-
Towards Spatial Supersensing in the Wild
2026-07-15 10:24:51Tianjun Gu, Tianyu Xin, Kuan Zhang, Bowen Yang, Kok-Chung Chua, Peize Li, Xinran Zhang, Yupeng Chen, Qiyue Zhao, Qinlei Xie, Jianhang Liu, Yucheng Lu, Yinan Han, Marco Pavone, Yiming LiAbstract
Humans can efficiently parse continuous sensory streams, from hours to years, scaffolding an internal world model that grounds spatial reasoning and prediction. To mimic this capacity, spatial supersensing challenges multimodal models to move beyond linguistic understanding toward true world modeling. However, their benchmark relies on synthetic long videos, formed by concatenating random short clips, and is mostly limited to household scenes, leaving real-world continuity and diversity underexplored. To address the gap, we introduce $\textbf{VSI-Super-Wild}$, a large-scale benchmark for evaluating spatial supersensing over long temporal horizons in diverse in-the-wild scenes. Notably, inspired by cognitive studies on how humans structure experience, we systematically probe the full triad of world state: the agent (observer), objects (scene items), and the environment (places and global layout). In total, VSI-Super-Wild contains $\textbf{6,980}$ human-verified question-answer pairs derived from $\textbf{442}$ real-world videos spanning 8 scene categories, including long-form recordings exceeding 4 hours. Results on VSI-Super-Wild expose a fundamental disconnect: despite advances in static image understanding, models consistently fail at tasks that require coherent world-state tracking over time. We characterize how performance degrades with world-state complexity and temporal horizon, and diagnose four failure modes: spatial collapse, semantic shortcuts, insufficient update, and instance confusion. This taxonomy reveals that models lack mechanisms to bind objects, agents, and environments into a unified spatial world model, a fundamental gap that defines the path forward for spatial supersensing.
Abstract (translated)
URL
https://arxiv.org/abs/2607.13681
PDF
-
Learning from Complementary Ultrasound Representations for Liver Disease Classification
2026-07-13 18:30:29Sabahattin Mert Daloglu, Gokce Bekar, Ceren Coskun, Senanur Sahin, Harvey Castro, Soner Hacihaliloglu, Halley P. Letter, Ilker HacihalilogluAbstract
Differentiating non-alcoholic steatohepatitis (NASH) from non-alcoholic fatty liver disease (NAFLD) using ultrasound remains challenging due to subtle tissue alterations and the limited information available in conventional B-mode imaging. In this work, we investigate whether complementary ultrasound representations derived from the same acquisition can improve NASH versus NAFLD classification. Specifically, we combine conventional B-mode ultrasound with physics-guided and local phase-based image representations and evaluate their effectiveness using self-supervised masked autoencoders (MAEs) and graph convolutional networks (GCNs). Experiments were conducted on a multi-site Mayo Clinic cohort consisting of 2,547 liver ultrasound scans from 125 patients. Compared with conventional B-mode ultrasound alone, complementary ultrasound representations consistently improved classification performance, yielding gains of up to 32.4% in accuracy and 91.2% in F1-score. Furthermore, performance improvements were consistently observed across age groups, sex, race, ethnicity,and acquisition sites.
Abstract (translated)
URL
https://arxiv.org/abs/2607.12062
PDF
-
MonkeyOCRv2: A Visual-Text Foundation Model for Document AI
2026-07-13 13:43:39Yuliang Liu, Zhang Li, Ziyang Zhang, Shuo Zhang, Qiang Liu, Jiajun Song, Zidun Guo, Xinhan Wang, Handong Zheng, Yang Liu, Dongliang Luo, Zhiyin Ma, Jiarui Zhang, Xiang BaiAbstract
Mainstream visual encoders are pretrained on natural images and cannot be effectively applied to document images without document-oriented adaptation, as dense text and fine-grained character strokes demand character-level visual perception. We present MonkeyOCRv2, a visual-text pretrained model for document AI. First, we construct MonkeyDoc v2, to our knowledge the largest document-image pretraining corpus, comprising 113 million images spanning 17 languages. Second, we propose a pretraining strategy that jointly learns image-to-text generation and pixel-level document reconstruction: the former aligns visual representations with textual content, while the latter preserves character strokes and layout details. Extensive experiments are conducted on five representative document analysis tasks, including text recognition, formula recognition, text detection, document tampering detection, and overlapping text segmentation. Replacing the original encoders with MonkeyOCRv2 consistently improves performance across all five tasks. Finally, we validate its effectiveness as the vision encoder of multimodal large language models on the more challenging tasks of document parsing and document understanding. Kept frozen and paired with a lightweight language model, it yields a 0.7B document parsing model that sets a new open-source state-of-the-art on MDPBench, a recent benchmark spanning digital-born and photographed documents across 17 languages, surpassing the previous best 3B this http URL by 2.8% absolute with a vision encoder roughly 11$\times$ smaller. The frozen encoder also powers a document understanding model that outperforms counterparts built on CLIP, DINO, and SAM across eight benchmarks under identical training settings. These results suggest that document-oriented visual pretraining can serve as a foundation for document intelligence in its own right.
Abstract (translated)
URL
https://arxiv.org/abs/2607.11562
PDF
-
UNIBROWSE: A Data-to-Agent Framework for Multimodal BrowseComp
2026-07-12 04:13:27Xiyu Wei, Qingwei Zong, Zhuocheng Yu, Sujian LiAbstract
Multimodal BrowseComp tasks require agents to combine perception, tool use, and long-horizon reasoning over dynamic web content, challenging their ability to handle compositional structure, open-world uncertainty, and multimodal integration across extended interactions. Crucially, real-world multimodal browsing involves three distinct information-flow patterns: text-only, image-to-text, and text-to-image, yet existing data construction methods cover only the text-only and image-to-text patterns, leaving text-to-image largely unaddressed and limiting agent generality and robustness. We introduce UNIBROWSE, a unified data pipeline that for the first time simultaneously generates training data covering all three patterns, augments curated knowledge graphs with live web retrieval for improved fidelity, and introduces a novel metric of exploration degree to filter low-signal instances for efficient reinforcement learning. Through this pipeline, we produce high-quality cold-start tool-use trajectories and exploration-rich QA pairs, and train a 35B-scale agent via supervised fine-tuning and exploration-aware this http URL resulting UNIBROWSE agent achieves state-of-the-art performance on multimodal BrowseComp benchmarks, attaining an average accuracy of 54.4 across five diverse benchmarks -- an improvement of 10.5 points over its base model Qwen3.5-35B-A3B -- and surpassing serveral closed-source agent workflows such as GPT-5 (42.9), Gemini-2.5 Pro (44.8), and Gemini-2.5 Flash (41.3).
Abstract (translated)
URL
https://arxiv.org/abs/2607.10557
PDF
-
WeaveEarth: Structured Evidence Construction and Reasoning for Training-Free UHR Remote Sensing Understanding
2026-07-11 04:56:27Xianzhi Ma, Shujun Wang, Xiaohan Li, Hao Liu, Changhua Pei, Jianhui liAbstract
Ultra-High-Resolution (UHR) remote sensing image understanding requires Vision-Language Models (VLMs) to capture both the global scene layout and sparse yet task-critical local details under limited computational budgets. Existing methods mainly follow two paradigms. One is passive perception, which relies on resolution expansion or token compression and may therefore discard fine-grained details. The other is active perception, which depends on multi-round zooming and search, but suffers from high latency, contextual fragmentation, and error accumulation. We argue that a more effective path toward UHR understanding lies not in accessing more, but in organizing better. To this end, we propose WeaveEarth, a training-free framework that reformulates UHR understanding as a problem of structured evidence construction and reasoning under global context constraints. Specifically, WeaveEarth first employs Global-Aware Evidence Construction to select a compact, low-redundancy, and spatially complementary Minimal Support Evidence Set. It then introduces Structured Evidence Reasoning, which weaves local evidence, spatial metadata, and relative topology into a unified reasoning interface, thereby enhancing the VLM's ability to perform global-local joint reasoning. Extensive experiments show that WeaveEarth consistently outperforms strong baselines and existing UHR methods across multiple UHR remote sensing benchmarks and multiple frozen VLM backbones. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.10120
PDF
-
Super-Generalist: Towards Comprehensive and Accurate Medical Image Understanding via Generalist-Specialist Synergy
2026-07-10 06:47:02Shaoteng Zhang, Weiwei Cao, Wanxing Chang, Yutong Xie, Kai Cao, Zaiyi Liu, Yu Shi, Tingbo Liang, Qi Zhang, Ling Zhang, Yong Xia, Jianpeng ZhangAbstract
Medical images require comprehensive and accurate interpretation to support the diagnosis of diverse clincial conditions. Recent vision-language generalist models offer broad task coverage and promising zero-shot capabilities, yet often lack fine-grained anatomical and lesion awareness for reliable diagnosis and spatial interpretability. In contrast, supervised specialist models achieve strong performance on specific tasks but typically lack generalization across diseases and anatomies. In this work, we present SuG, a Super-Generalist framework that unifies generalist vision-language learning with specialist objectives, enabling both broad generalization and specialist-level diagnostic capability. We perform specialist-enhanced vision-language alignment in SuG by incorporating spatial priors from multiple segmentation experts, including anatomy, class-specific lesion and class-agnostic lesion segmentors that captures lesions beyond anatomies annotated during training. To improve lesion grounding capability, we leverage lesion masks as spatial priors to calibrate text-conditioned visual attention, encouraging disease-related semantics to focus on clinically relevant regions. We evaluate SuG on extensive chest and abdominal CT benchmarks, including CT-RATE, Merlin, MedVL-CT69K, and several in-house tumor datasets. SuG achieves state-of-the-art performance across a wide range of disease diagnosis tasks and surpasses specialist models on several critical tumor diagnosis benchmarks. Furthermore, SuG demonstrates strong lesion grounding capability, including robust generalization to lesion types lacking class-specific supervision.
Abstract (translated)
URL
https://arxiv.org/abs/2607.09135
PDF
-
Integrating Large Language Models and Graph Convolutional Networks for Semi-Supervised Image Classification
2026-07-10 05:39:41Camila Piscioneri Magalh\~aes, Lucas Pascotti ValemAbstract
While the growing availability of image data has driven significant advances, labeling datasets remains costly and time-consuming. Therefore, semi-supervised approaches such as Graph Convolutional Networks (GCNs), which learn from both labeled and unlabeled data, have emerged as a promising solution. One of the primary challenges in applying GCNs to image classification is graph construction, since, unlike in citation networks or similar domains, images typically do not come with a predefined structural representation. For visual data, most studies construct graphs based on the similarity between feature vectors from pretrained deep learning backbones, typically by employing kNN or reciprocal kNN algorithms. Although Large Language Models (LLMs) have shown remarkable capability in capturing high-level semantics, their integration with GCNs for image classification remains underexplored. Aiming to fill this gap, our approach uses a Vision Language Model (VLM) to generate textual image descriptions, which are then processed by an LLM to estimate semantic similarity scores between connected images. These scores guide the pruning of edges in kNN and reciprocal kNN graphs, filtering out semantically irrelevant neighbors. Experimental results reveal that leveraging LLMs for graph refinement can improve classification accuracy, particularly for kNN graphs and some backbones. The source code is publicly available at this http URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.09104
PDF
-
Unpaired Joint Distribution Modeling via Multi-Scale Image Representations
2026-07-09 07:54:45Yihang Zou, Hui Zhang, Zuowei Shen, Chenglong BaoAbstract
This paper studies the problem of learning a joint distribution from marginal observations, which is inherently ill-posed due to the ambiguity of feasible couplings. We propose LUD-MSR, a latent-variable probabilistic framework that models the joint distribution via auxiliary representations and optimizes evidence lower bounds using only marginal data. Under mild assumptions, we establish an upper bound on the distribution approximation error. This analysis reveals a trade-off in representation learning between domain consistency and information preservation. To address this trade-off, we introduce a Multi-Scale image Representation (MSR) mapping that exploits structural similarity at coarse scales while suppressing domain-specific variations. We show that MSR achieves a more favorable balance of this trade-off compared to existing approaches. Experiments on real-world denoising benchmarks, including cryo-electron microscopy (cryo-EM), demonstrate the effectiveness of the proposed framework.
Abstract (translated)
URL
https://arxiv.org/abs/2607.08198
PDF
-
LEMUR 2: Unlocking Neural Network Diversity for AI
2026-07-07 22:21:53Tolgay Atinc Uzun, Waleed Khalid, Saif U Din, Sai Revanth Mulukuledu, Akashdeep Singh, Chandini Vysyaraju, Raghuvir Duvvuri, Avi Goyal, Yashkumar Rajeshbhai Lukhi, Muhammad A. Hussain, Krunal Jesani, Usha Shrestha, Yash Mittal, Roman Kochnev, Pritam Kadam, Mohsin Ikram, Harsh R. Moradiya, Alice Arslanian, Dmitry Ignatov, Radu TimofteAbstract
Existing NAS benchmarks (e.g., NAS-Bench, NATS-Bench) cover only narrow, task-specific regions of the architectural design space and lack cross-domain or deployment-aware evaluation. LEMUR 2 introduces a large-scale, extensible framework unifying generative, evaluative, and deployment pipelines to unlock neural-network diversity. It comprises over 14,000 distinct architectures and more than 750,000 structured training records documenting model performance, hyperparameters, and task outcomes. These models were produced through AST-based code mutation, genetic and reinforcement-learning evolution, generation of fractal architectures, and synthesis guided by a Large Language Model (LLM). This includes deep models generated with the retrieval-augmented system NN-RAG, which derived and used architectural motifs from over 900 PyTorch modules extracted from public repositories. LEMUR 2 further employs NN-VR and NN-Lite pipelines for automated deployment and latency benchmarking on heterogeneous mobile and Unity-based VR platforms, providing real-device performance metadata. It spans multimodal tasks, image captioning, text-to-image synthesis, and language modeling, supporting cross-domain analysis of architectural transferability. By linking diverse architectures, tasks, and deployment data, LEMUR 2 provides the data foundation for LLM fine-tuning and coupling diverse architectural origins with large-scale, cross-platform empirical validation. This dataset defines a new basis for reproducible and data-driven AI design, advancing the emerging paradigm of LLM-driven AutoML and architectural generalization across modalities and hardware.
Abstract (translated)
URL
https://arxiv.org/abs/2607.06839
PDF
-
KOAL: Knowledge-Driven Prostate Cancer Grading with Ordinal-Aware Learning
2026-07-07 09:01:40Zheng Guo, Jiaqi Cui, Haocheng Xiong, Jize Han, Bo Liu, Qianwen Zhang, Rui Chen, Yan WangAbstract
Non-invasive prediction of Gleason Grade Group (GGG) in prostate cancer using multiparametric MRI (mpMRI) is clinically vital for reducing unnecessary biopsies. Existing GGG prediction methods face two major limitations. First, they often overlook non-image information critical for GGG prediction, including age, prostate-specific antigen (PSA), and expert priors embedded in radiology reports. Second, they tend to oversimplify GGG as flat categorical labels, failing to account for its intrinsic hierarchy of primary and secondary Gleason patterns. To this end, we propose a novel Knowledge-Driven Ordinal-Aware Learning (KOAL) framework with three synergistic modules. Specifically, the Clinical-Context Modulation (CCM) module uses clinical variables (e.g., age and PSA) to dynamically modulate discriminative image representations. The Knowledge-Guided Prototype Alignment (KGPA) module leverages an LLM to extract group-specific expert knowledge from training radiology reports and clinical guidelines, producing offline semantic anchors describing grade-specific radiological findings without requiring patient-specific reports at inference. Through prototype contrastive alignment, patient-specific mpMRI representations are matched with these anchors to promote pathology-aligned representation learning. The Hierarchical Ordinal-aware Constraints (HOC) module decouples primary and secondary Gleason pattern prediction and maps their probabilistic outputs to GGG via a Differentiable Bio-logic Mapping Layer (DBML), ensuring pathological grading consistency. Experiments on public PI-CAI and in-house datasets demonstrate that KOAL outperforms state-of-the-art methods. Code is available at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.06019
PDF
-
Clustered Codebook Quantization for 2D Gaussian-based Image Compression
2026-07-06 22:16:37Runze Cheng, Yicheng Zhan, Josef Spjut, Kaan Ak\c{s}itAbstract
Gaussian-based image representations effectively model image content using compact parametric primitives while preserving high visual fidelity, yet storing a large number of floating-point parameters per primitive degrades rate-distortion efficiency at higher fidelity targets. To improve the rate-distortion performance in Gaussian representation, we present our Cluster-Guided Vector Quantization (CGVQ), a Gaussian primitive based image compression method. Our key idea is to partition Gaussian parameters further into homogeneous groups prior to quantization, enabling higher compression efficiency and accurate parameter reconstruction. In practice, our extensive experiments show that CGVQ decreases the bpp by 20% with respect to our baseline, while maintaining on-par visual quality
Abstract (translated)
URL
https://arxiv.org/abs/2607.05667
PDF
-
DiCE-CIR: Direct Composition Learning for Efficient Zero-Shot Composed Image Retrieval
2026-07-06 04:37:30Gwang-Ho Na, Ho-Joong Kim, Seong-Whan LeeAbstract
Zero-shot composed image retrieval (ZS-CIR) aims to retrieve a target image from a multimodal query consisting of a reference image and an edit text describing the desired modification. Recent ZS-CIR studies have relied on projection-based methods that map a reference image into pseudo-word tokens in the text embedding space. However, such methods require additional projection and re-encoding steps, increasing training complexity, reducing efficiency, and introducing a discrepancy between training and inference. In this paper, we propose DiCE-CIR, a direct composition learning method that predicts composed query representations by directly composing a reference image and an edit text. To enable scalable training without manually annotated triplets, we automatically construct compositional training samples from large-scale image-caption pairs using a large language model. Based on these samples, we train a lightweight composition module with objectives that promote alignment with the target, edit-consistent semantic transformation, and retrieval discriminability. We conduct extensive experiments on ZS-CIR benchmarks and show that DiCE-CIR achieves state-of-the-art performance on CIRCO and competitive performance on CIRR while maintaining high computational efficiency.
Abstract (translated)
URL
https://arxiv.org/abs/2607.04665
PDF
-
Transferability Between Understanding and Generation in Unified Multimodal Models
2026-07-05 17:33:59Jiwon Kang, Heeji Yoon, Jaewoo Jung, Jaewon Min, Minkyeong Jeon, Biyeon Hwang, Sangwon Jung, Seungryong KimAbstract
Unified Multimodal Models (UMMs) integrate image understanding and generation within a single architecture, yet how the two tasks interact remains understudied. We investigate $\boldsymbol{\mathsf{transferability}}$ in UMMs: whether training a capability on one task improves the same capability on the other without explicit supervision. Through controlled experiments, we empirically find that transferability depends on architecture-models with fully shared transformer backbone and a unified visual encoder exhibit consistent cross-task transfer, while loosely coupled designs show little or none. Leveraging this transferability, we propose a practical training strategy. The most straightforward way to improve a target generative capability (e.g., counting) is to fine-tune generation directly, but this can degrade visual quality due to distribution shift. Instead, we train the corresponding understanding task and let it transfer into generation, which improves capability-specific generative performance while minimizing distribution shift. We validate this across three capabilities-counting, spatial relation, and text recognition/generation-showing that cross-task transferability can be systematically exploited in UMMs.
Abstract (translated)
URL
https://arxiv.org/abs/2607.04423
PDF
-
IRIS: An Intelligent Vision-Language System for Ocular Surface Diseases via Topic Tree and Scene-Driven VQA Generation
2026-07-05 14:59:32Hao Wei, Wenjin Qi, Dasen Dai, Minqing Zhang, Wu YuanAbstract
While Large Vision-Language Models (VLMs) demonstrate remarkable generic capabilities, their clinical reasoning in specialized domains like ocular surface diseases (OSDs) is severely hindered by a paucity of high-fidelity, multimodal instruction-tuning data. To dismantle this data bottleneck, we introduce IRIS, an Intelligent Recognition and Interaction System tailored for fine-grained OSD understanding via external eye photography. First, we curate IRIS-120K, the largest and most comprehensive OSD visual question-answering (VQA) dataset to date. Crucially, to overcome the semantic shallowness of conventional image-caption pairs, we propose a synergistic data generation paradigm to explicitly inject clinical priors. Our data engine operates via a dual-branch framework: 1) a Topic Finding Tree (TFT) that hierarchically anchors visual features to precise anatomical and pathological concepts, enforcing rigorous medical deduction logic; and 2) a Scene-driven strategy that synthesizes role-adaptive clinical dialogues to ensure pragmatic generalization. By explicitly aligning a compact 4B-parameter VLM on this structurally enriched corpus, IRIS achieves state-of-the-art performance, comprehensively outperforming both generalist and specialized medical VLMs with up to 34B parameters. Our findings underscore that structured knowledge injection profoundly prevails over sheer parameter scaling, unlocking the potential for resource-efficient, expert-level AI deployment on mobile edge devices for scalable OSD screening. Code, datasets, and model weights will be publicly released by this repo.
Abstract (translated)
URL
https://arxiv.org/abs/2607.04344
PDF
-
One Framework for All: Cross-Modal Membership Inference for Generative Models
2026-07-05 14:45:29Dayong Ye, Tainqing Zhu, Kun Gao, Junhao Liu, Yichuan Chen, Shuai Zhou, Hengzhu Liu, Bo Liu, Wanlei ZhouAbstract
Large generative models across text-to-text, text-to-image, and image-to-text modalities have been shown to pose significant privacy risks. One fundamental threat is membership inference attacks (MIA), which aim to determine whether a given data point was used in a model's training set. Although prior work has investigated MIAs against these three classes of generative models, existing approaches treat them in isolation and are not cross-applicable, thereby limiting their real-world utility. To address this limitation, we present the first comprehensive study of a unified membership inference framework that applies across text-to-text, text-to-image, and image-to-text modalities. Our approach is grounded in a key modality-agnostic observation: the output distribution of a generative model can approximate its training data distribution. Leveraging this property, we model the distributions of model-generated outputs and auxiliary non-member samples in a shared embedding space, and perform membership inference via likelihood ratio testing. We conduct extensive experiments in a strict black-box setting under both partial-knowledge and zero-knowledge threat models, and evaluate membership inference against both fine-tuning and pre-training data. Experimental results demonstrate our approach's superior performance in comparison to existing state-of-the-art methods, which are typically optimized for a single model class.
Abstract (translated)
URL
https://arxiv.org/abs/2607.04339
PDF
-
SeeMe: Mitigating Hallucinations in Large Vision-Language Models through Effective Visual Token Engineering
2026-07-05 08:07:51Kai Tang, Jinhao You, Bohua Zhang, Yichen Guo, Yiding Sun, Dongxu Zhang, Chenxi Li, Xiande Huang, Shanghang ZhangAbstract
Large Vision-Language Models (LVLMs) have achieved remarkable progress in visual understanding tasks such as image captioning and visual question answering. However, they remain susceptible to hallucinations, generating content that is inconsistent with the actual visual input. Existing methods primarily intervene at the decoding stage, while overlooking a critical source of hallucinations: irrelevant or noisy visual tokens that mislead the decoding process. To address this issue, we propose SeeMe, a training-free framework that introduces the concept of feature engineering from traditional machine learning into LVLMs. SeeMe restructures visual tokens through a three-stage token engineering process to suppress hallucination sources while preserving informative visual evidence. Experiments on MME, POPE, and AMBER benchmarks across four LVLMs demonstrate that SeeMe consistently reduces hallucinations and improves output consistency, providing a novel perspective for mitigating hallucinations in LVLMs.
Abstract (translated)
URL
https://arxiv.org/abs/2607.04163
PDF
-
Evaluation of Medical Vision Language Models HuluMed and MedGemma, and general purpose chatbots Gemma 3, ChatGPT Plus, and Claude Pro on real previously unseen wound images
2026-07-05 00:08:36Yunzhe Xue, Mohammed Saim Ahmed Quadri, Neal Panse, Justin W. Ady, Usman RoshanAbstract
Chronic wound assessment remains a clinically challenging task that requires accurate interpretation of wound morphology, tissue composition, vascular characteristics, and infection risk. Recent advances in Vision-Language Models (VLMs) have introduced the possibility of automated multimodal wound analysis through image understanding combined with clinical reasoning. This study evaluates the performance of several general-purpose and medically specialized open-source and proprietary VLMs for clinical wound assessment using an expanded, curated dataset of 20 clinically diverse wounds spanning vascular, surgical, ischemic, venous, lymphedema, and amputation-related etiologies. Six VLMs were evaluated using a structured twelve-question clinical framework covering wound classification, infection risk, vascular intervention recommendations, debridement urgency, wound therapy selection, and advanced management planning. Across 20 wound cases and 240 clinician-graded wound-analysis decisions, ChatGPT achieved the highest overall performance with 174/240 correct responses (72.50%), followed by Claude with 149/240 (62.08%). Among the open-source and medically specialized models, HuluMed achieved the strongest performance with 96/240 correct responses (40.00%), followed by Gemma 3 (81/240, 33.75%), MedGemma 4B (62/240, 25.83%), and MedGemma 27B (42/240, 17.50%). The findings suggest that frontier general-purpose multimodal systems currently demonstrate substantially stronger wound-analysis performance than medically specialized alternatives, highlighting the continued importance of broad multimodal reasoning capabilities alongside domain-specific medical knowledge. Although current VLMs demonstrate promising potential for clinical decision support, substantial limitations remain in advanced wound-management reasoning, procedural planning, and autonomous clinical reliability.
Abstract (translated)
URL
https://arxiv.org/abs/2606.20723
PDF
