VQA
-
MetaDent: Labeling Clinical Images for Vision-Language Models in Dentistry
2026-04-16 10:56:54Meng-Xun Li, Wen-Hui Deng, Zhi-Xing Wu, Chun-Xiao Jin, Jia-Min Wu, Yue Han, James Kit Hon Tsoi, Gui-Song Xia, Cui HuangAbstract
Vision-Language Models (VLMs) have demonstrated significant potential in medical image analysis, yet their application in intraoral photography remains largely underexplored due to the lack of fine-grained, annotated datasets and comprehensive benchmarks. To address this, we present MetaDent, a comprehensive resource that includes (1) a novel and large-scale dentistry image dataset collected from clinical, public, and web sources; (2) a semi-structured annotation framework designed to capture the hierarchical and clinically nuanced nature of dental photography; and (3) comprehensive benchmark suites for evaluating state-of-the-art VLMs on clinical image understanding. Our labeling approach combines a high-level image summary with point-by-point, free-text descriptions of abnormalities. This method enables rich, scalable, and task-agnostic representations. We curated 60,669 dental images from diverse sources and annotated a representative subset of 2,588 images using this meta-labeling scheme. Leveraging Large Language Models (LLMs), we derive standardized benchmarks: approximately 15K Visual Question Answering (VQA) pairs and an 18-class multi-label classification dataset, which we validated with human review and error analysis to justify that the LLM-driven transition reliably preserves fidelity and semantic accuracy. We then evaluate state-of-the-art VLMs across VQA, classification, and image captioning tasks. Quantitative results reveal that even the most advanced models struggle with a fine-grained understanding of intraoral scenes, achieving moderate accuracy and producing inconsistent or incomplete descriptions in image captioning. We publicly release our dataset, annotations, and tools to foster reproducible research and accelerate the development of vision-language systems for dental applications.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14866
PDF
-
AIM: Asymmetric Information Masking for Visual Question Answering Continual Learning
2026-04-16 08:39:02Peifeng Zhang, Zice Qiu, Donghua Yu, Shilei Cao, Juepeng Zheng, Yutong Lu, Haohuan FuAbstract
In continual visual question answering (VQA), existing Continual Learning (CL) methods are mostly built for symmetric, unimodal architectures. However, modern Vision-Language Models (VLMs) violate this assumption, as their trainable components are inherently asymmetric. This structural mismatch renders VLMs highly prone to catastrophic forgetting when learning from continuous data streams. Specifically, the asymmetry causes standard global regularization to favor the massive language decoder during optimization, leaving the smaller but critical visual projection layers highly vulnerable to interference. Consequently, this localized degradation leads to a severe loss of compositional reasoning capabilities. To address this, we propose Asymmetric Information Masking (AIM), which balances stability and plasticity by applying targeted masks based on modality-specific sensitivity. Experiments on VQA v2 and GQA under continual VQA settings show that AIM achieves state-of-the-art performance in both Average Performance (AP) and Average Forgetting (AF), while better preserving generalization to novel skill-concept compositions.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14779
PDF
-
Learning Adaptive Reasoning Paths for Efficient Visual Reasoning
2026-04-16 02:59:30Yixu Huang, Tinghui Zhu, Muhao ChenAbstract
Visual reasoning models (VRMs) have recently shown strong cross-modal reasoning capabilities by integrating visual perception with language reasoning. However, they often suffer from overthinking, producing unnecessarily long reasoning chains for any tasks. We attribute this issue to \textbf{Reasoning Path Redundancy} in visual reasoning: many visual questions do not require the full reasoning process. To address this, we propose \textbf{AVR}, an adaptive visual reasoning framework that decomposes visual reasoning into three cognitive functions: visual perception, logical reasoning, and answer application. It further enables models to dynamically choose among three response formats: Full Format, Perception-Only Format, and Direct Answer. AVR is trained with FS-GRPO, an adaptation of Group Relative Policy Optimization that encourages the model to select the most efficient reasoning format while preserving correctness. Experiments on multiple vision-language benchmarks show that AVR reduces token usage by 50--90\% while maintaining overall accuracy, especially in perception-intensive tasks. These results demonstrate that adaptive visual reasoning can effectively mitigate overthinking in VRMs. Code and data are available at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14568
PDF
-
Decoding the Delta: Unifying Remote Sensing Change Detection and Understanding with Multimodal Large Language Models
2026-04-15 16:23:05Xiaohe Li, Jiahao Li, Kaixin Zhang, Yuqiang Fang, Leilei Lin, Hong Wang, Haohua Wu, Zide FanAbstract
While Multimodal Large Language Models (MLLMs) excel in general vision-language tasks, their application to remote sensing change understanding is hindered by a fundamental "temporal blindness". Existing architectures lack intrinsic mechanisms for multi-temporal contrastive reasoning and struggle with precise spatial grounding. To address this, we first introduce Delta-QA, a comprehensive benchmark comprising 180k visual question-answering samples. Delta-QA unifies pixel-level segmentation and visual question answering across bi- and tri-temporal scenarios, structuring change interpretation into four progressive cognitive dimensions. Methodologically, we propose Delta-LLaVA, a novel MLLM framework explicitly tailored for multi-temporal remote sensing interpretation. It overcomes the limitations of naive feature concatenation through three core innovations: a Change-Enhanced Attention module that systematically isolates and amplifies visual differences, a Change-SEG module utilizing Change Prior Embedding to extract differentiable difference features as input for the LLM, and Local Causal Attention to prevent cross-temporal contextual leakage. Extensive experiments demonstrate that Delta-LLaVA decisively outperforms leading generalist MLLMs and specialized segmentation models in complex change deduction and high-precision boundary localization, establishing a unified framework for earth observation intelligence.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14044
PDF
-
Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA
2026-04-15 11:12:27Yuanlei Zheng, Pei Fu, Hang Li, Ziyang Wang, Yuyi Zhang, Wenyu Ruan, Xiaojin Zhang, Zhongyu Wei, Zhenbo Luo, Jian Luan, Wei Chen, Xiang BaiAbstract
Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents. Existing OCR-free methods face a trade-off between capacity and precision: end-to-end models scale poorly with document length, while visual retrieval-based pipelines are brittle and passive. We propose Doc-$V^*$, an \textbf{OCR-free agentic} framework that casts multi-page DocVQA as sequential evidence aggregation. Doc-$V^*$ begins with a thumbnail overview, then actively navigates via semantic retrieval and targeted page fetching, and aggregates evidence in a structured working memory for grounded reasoning. Trained by imitation learning from expert trajectories and further optimized with Group Relative Policy Optimization, Doc-$V^*$ balances answer accuracy with evidence-seeking efficiency. Across five benchmarks, Doc-$V^*$ outperforms open-source baselines and approaches proprietary models, improving out-of-domain performance by up to \textbf{47.9\%} over RAG baseline. Other results reveal effective evidence aggregation with selective attention, not increased input pages.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13731
PDF
-
MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning
2026-04-15 07:39:08Jiahang Lin, Kai Hu, Binghai Wang, Yuhao Zhou, Zhiheng Xi, Honglin Guo, Shichun Liu, Junzhe Wang, Shihan Dou, Enyu Zhou, Hang Yan, Zhenhua Han, Tao Gui, Qi Zhang, Xuanjing HuangAbstract
Conventional Retrieval-Augmented Generation (RAG) systems often struggle with complex multi-hop queries over long documents due to their single-pass retrieval. We introduce MM-Doc-R1, a novel framework that employs an agentic, vision-aware workflow to address long document visual question answering through iterative information discovery and synthesis. To incentivize the information seeking capabilities of our agents, we propose Similarity-based Policy Optimization (SPO), addressing baseline estimation bias in existing multi-turn reinforcement learning (RL) algorithms like GRPO. Our core insight is that in multi-turn RL, the more semantically similar two trajectories are, the more accurate their shared baseline estimation becomes. Leveraging this, SPO calculates a more precise baseline by similarity-weighted averaging of rewards across multiple trajectories, unlike GRPO which inappropriately applies the initial state's baseline to all intermediate states. This provides a more stable and accurate learning signal for our agents, leading to superior training performance that surpasses GRPO. Our experiments on the MMLongbench-Doc benchmark show that MM-Doc-R1 outperforms previous baselines by 10.4%. Furthermore, SPO demonstrates superior performance over GRPO, boosting results by 5.0% with Qwen3-8B and 6.1% with Qwen3-4B. These results highlight the effectiveness of our integrated framework and novel training algorithm in advancing the state-of-the-art for complex, long-document visual question answering.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13579
PDF
-
Enhanced Text-to-Image Generation by Fine-grained Multimodal Reasoning
2026-04-15 05:24:29Yongjin Kim, Yoonjin Oh, Yerin Kim, Hyomin Kim, Jeeyoung Yun, Yujung Heo, Minjun Kim, Sungwoong KimAbstract
With the rapid progress of Multimodal Large Language Models (MLLMs), unified MLLMs that jointly perform image understanding and generation have advanced significantly. However, despite the inherent reasoning capabilities of unified MLLMs for self-reflection and self-refinement, their use in text-to-image generation remains largely underexplored. Meanwhile, existing multimodal reasoning-based image generation methods mostly rely on holistic image-text alignment judgments, without fine-grained reflection and refinement of detailed prompt attributes, leading to limited fine-grained control. Therefore, we propose Fine-grained Multimodal Reasoning (FiMR), a framework that leverages decomposed visual question answering (VQA) to break down an input prompt into minimal semantic units-such as entities and attributes-and verify each unit via VQA to generate explicit, fine-grained feedback. Based on this feedback, FiMR then applies targeted, localized refinements. This fine-grained self-reasoning and self-refinement enable MLLMs to achieve more precise improvements in image-prompt alignment and overall generation quality at test time. Extensive experiments demonstrate that FiMR consistently outperforms image generation baselines, including reasoning-based methods, particularly on compositional text-to-image benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13491
PDF
-
Challenging Vision-Language Models with Physically Deployable Multimodal Semantic Lighting Attacks
2026-04-14 14:52:15Yingying Zhao, Chengyin Hu, Qike Zhang, Xin Li, Xin Wang, Yiwei Wei, Jiujiang Guo, Jiahuan Long, Tingsong Jiang, Wen YaoAbstract
Vision-Language Models (VLMs) have shown remarkable performance, yet their security remains insufficiently understood. Existing adversarial studies focus almost exclusively on the digital setting, leaving physical-world threats largely unexplored. As VLMs are increasingly deployed in real environments, this gap becomes critical, since adversarial perturbations must be physically realizable. Despite this practical relevance, physical attacks against VLMs have not been systematically studied. Such attacks may induce recognition failures and further disrupt multimodal reasoning, leading to severe semantic misinterpretation in downstream tasks. Therefore, investigating physical attacks on VLMs is essential for assessing their real-world security risks. To address this gap, we propose Multimodal Semantic Lighting Attacks (MSLA), the first physically deployable adversarial attack framework against VLMs. MSLA uses controllable adversarial lighting to disrupt multimodal semantic understanding in real scenes, attacking semantic alignment rather than only task-specific outputs. Consequently, it degrades zero-shot classification performance of mainstream CLIP variants while inducing severe semantic hallucinations in advanced VLMs such as LLaVA and BLIP across image captioning and visual question answering (VQA). Extensive experiments in both digital and physical domains demonstrate that MSLA is effective, transferable, and practically realizable. Our findings provide the first evidence that VLMs are highly vulnerable to physically deployable semantic attacks, exposing a previously overlooked robustness gap and underscoring the urgent need for physical-world robustness evaluation of VLMs.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12833
PDF
-
DPC-VQA: Decoupling Quality Perception and Residual Calibration for Video Quality Assessment
2026-04-14 14:40:23Xinyue Li, Shubo Xu, Zhichao Zhang, Zhaolin Cai, Yitong Chen, Guangtao ZhaiAbstract
Recent multimodal large language models (MLLMs) have shown promising performance on video quality assessment (VQA) tasks. However, adapting them to new scenarios remains expensive due to large-scale retraining and costly mean opinion score (MOS) annotations. In this paper, we argue that a pretrained MLLM already provides a useful perceptual prior for VQA, and that the main challenge is to efficiently calibrate this prior to the target MOS space. Based on this insight, we propose DPC-VQA, a decoupling perception and calibration framework for video quality assessment. Specifically, DPC-VQA uses a frozen MLLM to provide a base quality estimate and perceptual prior, and employs a lightweight calibration branch to predict a residual correction for target-scenario adaptation. This design avoids costly end-to-end retraining while maintaining reliable performance with lower training and data costs. Extensive experiments on both user-generated content (UGC) and AI-generated content (AIGC) benchmarks show that DPC-VQA achieves competitive performance against representative baselines, while using less than 2% of the trainable parameters of conventional MLLM-based VQA methods and remaining effective with only 20\% of MOS labels. The code will be released upon publication.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12813
PDF
-
From Attenuation to Attention: Variational Information Flow Manipulation for Fine-Grained Visual Perception
2026-04-14 09:32:13Jilong Zhu, Yang FengAbstract
While Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in general visual understanding, they frequently falter in fine-grained perception tasks that require identifying tiny objects or discerning subtle visual relationships. We attribute this limitation to Visual Attenuation: a phenomenon where sparse fine-grained visual signals are prematurely suppressed or diluted by dominant textual tokens during network propagation, resulting in a "loss of focus" during the deep-level decision-making process. Existing input-centric solutions fail to fundamentally reverse this intrinsic mechanism of information loss. To address this challenge, we propose the Variational Information Flow (VIF) framework. Adopting a probabilistic perspective, VIF leverages a Conditional Variational Autoencoder (CVAE) to model the visual saliency relevant to the question-answer pair as a latent distribution. As a plug-and-play module, VIF can be integrated into existing architectures. Extensive evaluations across diverse benchmarks, covering General VQA, fine-grained perception, and visual grounding, demonstrate that VIF yields competitive improvements over previous methods, validating its effectiveness in enhancing the fine-grained perception of MLLMs.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12508
PDF
-
All in One: A Unified Synthetic Data Pipeline for Multimodal Video Understanding
2026-04-14 06:17:35Tanzila Rahman, Renjie Liao, Leonid SigalAbstract
Training multimodal large language models (MLLMs) for video understanding requires large-scale annotated data spanning diverse tasks such as object counting, question answering, and segmentation. However, collecting and annotating multimodal video data in real-world is costly, slow, and inherently limited in diversity and coverage. To address this challenge, we propose a unified synthetic data generation pipeline capable of automatically producing unlimited multimodal video data with rich and diverse supervision. Our framework supports multiple task formats within a single pipeline, enabling scalable and consistent data creation across tasks. To further enhance reasoning ability, we introduce a VQA-based fine-tuning strategy that trains models to answer structured questions about visual content rather than relying solely on captions or simple instructions. This formulation encourages deeper visual grounding and reasoning. We evaluate our approach in three challenging tasks: video object counting, video-based visual question answering, and video object segmentation. Experimental results demonstrate that models trained predominantly on synthetic data generalize effectively to real-world datasets, often outperforming traditionally trained counterparts. Our findings highlight the potential of unified synthetic data pipelines as a scalable alternative to expensive real-world annotation for multimodal video understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12335
PDF
-
Unveiling the Surprising Efficacy of Navigation Understanding in End-to-End Autonomous Driving
2026-04-14 02:34:44Zhihua Hua, Junli Wang, Pengfei LI, Qihao Jin, Bo Zhang, Kehua Sheng, Yilun Chen, Zhongxue Gan, Wenchao DingAbstract
Global navigation information and local scene understanding are two crucial components of autonomous driving systems. However, our experimental results indicate that many end-to-end autonomous driving systems tend to over-rely on local scene understanding while failing to utilize global navigation information. These systems exhibit weak correlation between their planning capabilities and navigation input, and struggle to perform navigation-following in complex scenarios. To overcome this limitation, we propose the Sequential Navigation Guidance (SNG) framework, an efficient representation of global navigation information based on real-world navigation patterns. The SNG encompasses both navigation paths for constraining long-term trajectories and turn-by-turn (TBT) information for real-time decision-making logic. We constructed the SNG-QA dataset, a visual question answering (VQA) dataset based on SNG that aligns global and local planning. Additionally, we introduce an efficient model SNG-VLA that fuses local planning with global planning. The SNG-VLA achieves state-of-the-art performance through precise navigation information modeling without requiring auxiliary loss functions from perception tasks. Project page: SNG-VLA
Abstract (translated)
URL
https://arxiv.org/abs/2604.12208
PDF
-
Benchmarking Deflection and Hallucination in Large Vision-Language Models
2026-04-13 20:22:22Nicholas Moratelli, Christopher Davis, Leonardo F. R. Ribeiro, Bill Byrne, Gonzalo IglesiasAbstract
Large Vision-Language Models (LVLMs) increasingly rely on retrieval to answer knowledge-intensive multimodal questions. Existing benchmarks overlook conflicts between visual and textual evidence and the importance of generating deflections (e.g., Sorry, I cannot answer...) when retrieved knowledge is incomplete. These benchmarks also suffer from rapid obsolescence, as growing LVLM training sets allow models to answer many questions without retrieval. We address these gaps with three contributions. First, we propose a dynamic data curation pipeline that preserves benchmark difficulty over time by filtering for genuinely retrieval-dependent samples. Second, we introduce VLM-DeflectionBench, a benchmark of 2,775 samples spanning diverse multimodal retrieval settings, designed to probe model behaviour under conflicting or insufficient evidence. Third, we define a fine-grained evaluation protocol with four scenarios that disentangle parametric memorization from retrieval robustness. Experiments across 20 state-of-the-art LVLMs indicate that models usually fail to deflect in the presence of noisy or misleading evidence. Our results highlight the need to evaluate not only what models know, but how they behave when they do not, and serve as a reusable and extensible benchmark for reliable KB-VQA evaluation. All resources will be publicly available upon publication.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12033
PDF
-
INDOTABVQA: A Benchmark for Cross-Lingual Table Understanding in Bahasa Indonesia Documents
2026-04-13 19:03:10Somraj Gautam, Anathapindika Dravichi, Gaurav HaritAbstract
We introduce INDOTABVQA, a benchmark for evaluating cross-lingual Table Visual Question Answering (VQA) on real-world document images in Bahasa Indonesia. The dataset comprises 1,593 document images across three visual styles (bordered, borderless, and colorful) with one or more than one tables, and 1,593 question-answer sets in four languages: Bahasa Indonesia, English, Hindi, and Arabic. This enables evaluation of Vision-Language Models (VLMs) in both monolingual (Bahasa documents with Bahasa questions) and cross-lingual settings (Bahasa documents with questions in other languages). We benchmark leading open-source VLMs (Qwen2.5-VL, Gemma-3, LLaMA-3.2) and GPT-4o and reveal substantial performance gaps, particularly on structurally complex tables and in low-resource languages. Fine-tuning a compact 3B and LoRA-finetuned 7B model on our dataset yields 11.6% and 17.8% improvements in accuracy. Providing explicit table region coordinates as additional input further improves performance by 4-7%, demonstrating the value of Spatial priors for table-based reasoning. Our findings underscore the importance of language-diverse, domain-specific datasets and demonstrate that targeted fine-tuning can significantly enhance VLM performance on specialized document understanding tasks. INDOTABVQA provides a valuable resource for advancing research in cross-lingual, structure-aware document understanding, especially in underrepresented regions of the world. Full dataset can be accessed in huggingface at: this https URL}
Abstract (translated)
URL
https://arxiv.org/abs/2604.11970
PDF
-
FPBench: A Comprehensive Benchmark of Multimodal Large Language Models for Fingerprint Analysis
2026-04-13 16:17:11Ekta Gavas, Sudipta Banerjee, Chinmay Hegde, Nasir MemonAbstract
Multimodal LLMs (MLLMs) are capable of performing complex data analysis, visual question answering, generation, and reasoning tasks. However, their ability to analyze biometric data is relatively underexplored. In this work, we investigate the effectiveness of MLLMs in understanding fine structural and textural details present in fingerprint images. To this end, we design a comprehensive benchmark, FPBench, to evaluate 20 MLLMs (open-source and proprietary models) across 7 real and synthetic datasets on a suite of 8 biometric and forensic tasks (e.g., pattern analysis, fingerprint verification, real versus synthetic classification, etc.) using zero-shot and chain-of-thought prompting strategies. We further fine-tune vision and language encoders on a subset of open-source MLLMs to demonstrate domain adaptation. FPBench is a novel benchmark designed as a first step towards developing foundation models in fingerprints. Our findings indicate fine-tuning of vision and language encoders improves the performance by 7%-39%. Our codes are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2512.18073
PDF
-
GazeVaLM: A Multi-Observer Eye-Tracking Benchmark for Evaluating Clinical Realism in AI-Generated X-Rays
2026-04-13 16:05:45David Wong, Zeynep Isik, Bin Wang, Marouane Tliba, Gorkem Durak, Elif Keles, Halil Ertugrul Aktas, Aladine Chetouani, Cagdas Topel, Nicolo Gennaro, Camila Lopes Vendrami, Tugce Agirlar Trabzonlu, Amir Ali Rahsepar, Laetitia Perronne, Matthew Antalek, Onural Ozturk, Gokcan Okur, Andrew C. Gordon, Ayis Pyrros, Frank H. Miller, Amir Borhani, Hatice Savas, Eric Hart, Elizabeth Krupinski, Ulas BagciAbstract
We introduce GazeVaLM, a public eye-tracking dataset for studying clinical perception during chest radiograph authenticity assessment. The dataset comprises 960 gaze recordings from 16 expert radiologists interpreting 30 real and 30 synthetic chest X-rays (generated by diffusion based generative AI) under two conditions: diagnostic assessment and real-fake classification (Visual Turing test). For each image-observer pair, we provide raw gaze samples, fixation maps, scanpaths, saliency density maps, structured diagnostic labels, and authenticity judgments. We extend the protocol to 6 state-of-the-art multimodal LLMs, releasing their predicted diagnoses, authenticity labels, and confidence scores under matched conditions - enabling direct human-AI comparison at both decision and uncertainty levels. We further provide analyses of gaze agreement, inter-observer consistency, and benchmarking of radiologists versus LLMs in diagnostic accuracy and authenticity detection. GazeVaLM supports research in gaze modeling, clinical decision-making, human-AI comparison, generative image realism assessment, and uncertainty quantification. By jointly releasing visual attention data, clinical labels, and model predictions, we aim to facilitate reproducible research on how experts and AI systems perceive, interpret, and evaluate medical images. The dataset is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.11653
PDF
-
Dialectic-Med: Mitigating Diagnostic Hallucinations via Counterfactual Adversarial Multi-Agent Debate
2026-04-13 10:09:36Zhixiang Lu, Jionglong SuAbstract
Multimodal Large Language Models (MLLMs) in healthcare suffer from severe confirmation bias, often hallucinating visual details to support initial, potentially erroneous diagnostic hypotheses. Existing Chain-of-Thought (CoT) approaches lack intrinsic correction mechanisms, rendering them vulnerable to error propagation. To bridge this gap, we propose Dialectic-Med, a multi-agent framework that enforces diagnostic rigor through adversarial dialectics. Unlike static consensus models, Dialectic-Med orchestrates a dynamic interplay between three role-specialized agents: a proponent that formulates diagnostic hypotheses; an opponent equipped with a novel visual falsification module that actively retrieves contradictory visual evidence to challenge the Proponent; and a mediator that resolves conflicts via a weighted consensus graph. By explicitly modeling the cognitive process of falsification, our framework guarantees that diagnostic reasoning is tightly grounded in verified visual regions. Empirical evaluations on MIMIC-CXR-VQA, VQA-RAD, and PathVQA demonstrate that Dialectic-Med not only achieves state-of-the-art performance but also fundamentally enhances the trustworthiness of the reasoning process. Beyond accuracy, our approach significantly enhances explanation faithfulness and decisively mitigates hallucinations, establishing a new standard over single-agent baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2604.11258
PDF
-
rPPG-VQA: A Video Quality Assessment Framework for Unsupervised rPPG Training
2026-04-13 08:17:56Tianyang Dai, Ming Chang, Yan Chen, Yang HuAbstract
Unsupervised remote photoplethysmography (rPPG) promises to leverage unlabeled video data, but its potential is hindered by a critical challenge: training on low-quality "in-the-wild" videos severely degrades model performance. An essential step missing here is to assess the suitability of the videos for rPPG model learning before using them for the task. Existing video quality assessment (VQA) methods are mainly designed for human perception and not directly applicable to the above purpose. In this work, we propose rPPG-VQA, a novel framework for assessing video suitability for rPPG. We integrate signal-level and scene-level analyses and design a dual-branch assessment architecture. The signal-level branch evaluates the physiological signal quality of the videos via robust signal-to-noise ratio (SNR) estimation with a multi-method consensus mechanism, and the scene-level branch uses a multimodal large language model (MLLM) to identify interferences like motion and unstable lighting. Furthermore, we propose a two-stage adaptive sampling (TAS) strategy that utilizes the quality score to curate optimal training datasets. Experiments show that by training on large-scale, "in-the-wild" videos filtered by our framework, we can develop unsupervised rPPG models that achieve a substantial improvement in accuracy on standard benchmarks. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.11156
PDF
-
Back to the Barn with LLAMAs: Evolving Pretrained LLM Backbones in Finetuning Vision Language Models
2026-04-13 04:44:42Sameera Horawalavithana, Lauren Phillips, Ian Stewart, Sai Munikoti, Karl PazdernikAbstract
Vision-Language Models (VLMs) have rapidly advanced by leveraging powerful pre-trained Large Language Models (LLMs) as core reasoning backbones. As new and more capable LLMs emerge with improved reasoning, instruction-following, and generalization, there is a pressing need to efficiently update existing VLMs to incorporate these advancements. However, the integration of new LLMs into VLMs, particularly how the evolving LLMs contribute to multimodal reasoning, alignment, and task-specific performance remains underexplored. Addressing this gap is important for VLM development, given the rapid evolution of pretrained LLM backbones. This study presents a controlled and systematic investigation of how changes in the pretrained LLM backbone affect downstream VLM task performance. By having the vision encoder, training data, and post-training algorithm remain same across LLAMA-1, LLAMA-2, and LLAMA-3 based VLMs, we find that newer LLM backbones do not always lead to better VLMs, but the performance depends on the downstream VLM task. For example, in visual question and answering tasks, newer LLM backbones tend to solve different questions rather than just more questions, and our analysis shows this is driven by differences in how the models process information, including better calibrated confidence and more stable internal representations. We also find that some VLM capabilities appear only in the newest LLM generation, while tasks that depend mainly on visual understanding see little benefit from a newer LLM backbone.
Abstract (translated)
URL
https://arxiv.org/abs/2604.10985
PDF
-
ReXSonoVQA: A Video QA Benchmark for Procedure-Centric Ultrasound Understanding
2026-04-13 02:32:51Xucheng Wang, Xiaoman Zhang, Sung Eun Kim, Ankit Pal, Pranav RajpurkarAbstract
Ultrasound acquisition requires skilled probe manipulation and real-time adjustments. Vision-language models (VLMs) could enable autonomous ultrasound systems, but existing benchmarks evaluate only static images, not dynamic procedural understanding. We introduce ReXSonoVQA, a video QA benchmark with 514 video clips and 514 questions (249 MCQ, 265 free-response) targeting three competencies: Action-Goal Reasoning, Artifact Resolution & Optimization, and Procedure Context & Planning. Zero-shot evaluation of Gemini 3 Pro, Qwen3.5-397B, LLaVA-Video-72B, and Seed 2.0 Pro shows VLMs can extract some procedural information, but troubleshooting questions remain challenging with minimal gains over text-only baselines, exposing limitations in causal reasoning. ReXSonoVQA enables developing perception systems for ultrasound training, guidance, and robotic automation.
Abstract (translated)
URL
https://arxiv.org/abs/2604.10916
PDF
