A person's demonstration often serves as a key reference for others learning the same task. However, RGB video, the dominant medium for representing these demonstrations, often fails to capture fine-grained contextual cues such as intent, safety-critical environmental factors, and subtle preferences embedded in human behavior. This sensory gap fundamentally limits the ability of Vision Language Models (VLMs) to reason about why actions occur and how they should adapt to individual users. To address this, we introduce MICA (Multimodal Interactive Contextualized Assistance), a framework that improves conversational agents for task assistance by integrating eye gaze and speech cues. MICA segments demonstrations into meaningful sub-tasks and extracts keyframes and captions that capture fine-grained intent and user-specific cues, enabling richer contextual grounding for visual question answering. Evaluations on questions derived from real-time chat-assisted task replication show that multimodal cues significantly improve response quality over frame-based retrieval. Notably, gaze cues alone achieves 93% of speech performance, and their combination yields the highest accuracy. Task type determines the effectiveness of implicit (gaze) vs. explicit (speech) cues, underscoring the need for adaptable multimodal models. These results highlight the limitations of frame-based context and demonstrate the value of multimodal signals for real-world AI task assistance.
Vision-language pretraining on large datasets of images-text pairs is one of the main building blocks of current Vision-Language Models. While with additional training, these models excel in various downstream tasks, including visual question answering, image captioning, and visual commonsense reasoning. However, a notable weakness of pretrained models like CLIP, is their inability to perform entity grounding and compositional image and text matching~\cite{Jiang2024ComCLIP, yang2023amc, Rajabi2023GroundedVSR, learninglocalizeCVPR24}. In this work we propose a novel learning-free zero-shot augmentation of CLIP embeddings that has favorable compositional properties. We compute separate embeddings of sub-images of object entities and relations that are localized by the state of the art open vocabulary detectors and dynamically adjust the baseline global image embedding. % The final embedding is obtained by computing a weighted combination of the sub-image embeddings. The resulting embedding is then utilized for similarity computation with text embedding, resulting in a average 1.5\% improvement in image-text matching accuracy on the Visual Genome and SVO Probes datasets~\cite{krishna2017visualgenome, svo}. Notably, the enhanced embeddings demonstrate superior retrieval performance, thus achieving significant gains on the Flickr30K and MS-COCO retrieval benchmarks~\cite{flickr30ke, mscoco}, improving the state-of-the-art Recall@1 by 12\% and 0.4\%, respectively. Our code is available at https://github.com/madhukarreddyvongala/GroundingCLIP.
The verification of successful grasps is a crucial aspect of robot manipulation, particularly when handling deformable objects. Traditional methods relying on force and tactile sensors often struggle with deformable and non-rigid objects. In this work, we present a vision-based approach for grasp verification to determine whether the robotic gripper has successfully grasped an object. Our method employs a two-stage architecture; first YOLO-based object detection model to detect and locate the robot's gripper and then a ResNet-based classifier determines the presence of an object. To address the limitations of real-world data capture, we introduce HSR-GraspSynth, a synthetic dataset designed to simulate diverse grasping scenarios. Furthermore, we explore the use of Visual Question Answering capabilities as a zero-shot baseline to which we compare our model. Experimental results demonstrate that our approach achieves high accuracy in real-world environments, with potential for integration into grasping pipelines. Code and datasets are publicly available at https://github.com/pauamargant/HSR-GraspSynth .
Medical Visual Question Answering (MedVQA) aims to answer medical questions according to medical images. However, the complexity of medical data leads to confounders that are difficult to observe, so bias between images and questions is inevitable. Such cross-modal bias makes it challenging to infer medically meaningful answers. In this work, we propose a causal inference framework for the MedVQA task, which effectively eliminates the relative confounding effect between the image and the question to ensure the precision of the question-answering (QA) session. We are the first to introduce a novel causal graph structure that represents the interaction between visual and textual elements, explicitly capturing how different questions influence visual features. During optimization, we apply the mutual information to discover spurious correlations and propose a multi-variable resampling front-door adjustment method to eliminate the relative confounding effect, which aims to align features based on their true causal relevance to the question-answering task. In addition, we also introduce a prompt strategy that combines multiple prompt forms to improve the model's ability to understand complex medical data and answer accurately. Extensive experiments on three MedVQA datasets demonstrate that 1) our method significantly improves the accuracy of MedVQA, and 2) our method achieves true causal correlations in the face of complex medical data.
The rapid advancement in generative artificial intelligence have enabled the creation of 3D human faces (HFs) for applications including media production, virtual reality, security, healthcare, and game development, etc. However, assessing the quality and realism of these AI-generated 3D human faces remains a significant challenge due to the subjective nature of human perception and innate perceptual sensitivity to facial features. To this end, we conduct a comprehensive study on the quality assessment of AI-generated 3D human faces. We first introduce Gen3DHF, a large-scale benchmark comprising 2,000 videos of AI-Generated 3D Human Faces along with 4,000 Mean Opinion Scores (MOS) collected across two dimensions, i.e., quality and authenticity, 2,000 distortion-aware saliency maps and distortion descriptions. Based on Gen3DHF, we propose LMME3DHF, a Large Multimodal Model (LMM)-based metric for Evaluating 3DHF capable of quality and authenticity score prediction, distortion-aware visual question answering, and distortion-aware saliency prediction. Experimental results show that LMME3DHF achieves state-of-the-art performance, surpassing existing methods in both accurately predicting quality scores for AI-generated 3D human faces and effectively identifying distortion-aware salient regions and distortion types, while maintaining strong alignment with human perceptual judgments. Both the Gen3DHF database and the LMME3DHF will be released upon the publication.
Task-oriented semantic communication has emerged as a fundamental approach for enhancing performance in various communication scenarios. While recent advances in Generative Artificial Intelligence (GenAI), such as Large Language Models (LLMs), have been applied to semantic communication designs, the potential of Large Multimodal Models (LMMs) remains largely unexplored. In this paper, we investigate an LMM-based vehicle AI assistant using a Large Language and Vision Assistant (LLaVA) and propose a task-oriented semantic communication framework to facilitate efficient interaction between users and cloud servers. To reduce computational demands and shorten response time, we optimize LLaVA's image slicing to selectively focus on areas of utmost interest to users. Additionally, we assess the importance of image patches by combining objective and subjective user attention, adjusting energy usage for transmitting semantic information. This strategy optimizes resource utilization, ensuring precise transmission of critical information. We construct a Visual Question Answering (VQA) dataset for traffic scenarios to evaluate effectiveness. Experimental results show that our semantic communication framework significantly increases accuracy in answering questions under the same channel conditions, performing particularly well in environments with poor Signal-to-Noise Ratios (SNR). Accuracy can be improved by 13.4% at an SNR of 12dB and 33.1% at 10dB, respectively.
Vision Large Language Models (VLLMs) have demonstrated impressive capabilities in general visual tasks such as image captioning and visual question answering. However, their effectiveness in specialized, safety-critical domains like autonomous driving remains largely unexplored. Autonomous driving systems require sophisticated scene understanding in complex environments, yet existing multimodal benchmarks primarily focus on normal driving conditions, failing to adequately assess VLLMs' performance in safety-critical scenarios. To address this, we introduce DVBench, a pioneering benchmark designed to evaluate the performance of VLLMs in understanding safety-critical driving videos. Built around a hierarchical ability taxonomy that aligns with widely adopted frameworks for describing driving scenarios used in assessing highly automated driving systems, DVBench features 10,000 multiple-choice questions with human-annotated ground-truth answers, enabling a comprehensive evaluation of VLLMs' capabilities in perception and reasoning. Experiments on 14 SOTA VLLMs, ranging from 0.5B to 72B parameters, reveal significant performance gaps, with no model achieving over 40% accuracy, highlighting critical limitations in understanding complex driving scenarios. To probe adaptability, we fine-tuned selected models using domain-specific data from DVBench, achieving accuracy gains ranging from 5.24 to 10.94 percentage points, with relative improvements of up to 43.59%. This improvement underscores the necessity of targeted adaptation to bridge the gap between general-purpose VLLMs and mission-critical driving applications. DVBench establishes an essential evaluation framework and research roadmap for developing VLLMs that meet the safety and robustness requirements for real-world autonomous systems. We released the benchmark toolbox and the fine-tuned model at: https://github.com/tong-zeng/DVBench.git.
Including children's images in datasets has raised ethical concerns, particularly regarding privacy, consent, data protection, and accountability. These datasets, often built by scraping publicly available images from the Internet, can expose children to risks such as exploitation, profiling, and tracking. Despite the growing recognition of these issues, approaches for addressing them remain limited. We explore the ethical implications of using children's images in AI datasets and propose a pipeline to detect and remove such images. As a use case, we built the pipeline on a Vision-Language Model under the Visual Question Answering task and tested it on the #PraCegoVer dataset. We also evaluate the pipeline on a subset of 100,000 images from the Open Images V7 dataset to assess its effectiveness in detecting and removing images of children. The pipeline serves as a baseline for future research, providing a starting point for more comprehensive tools and methodologies. While we leverage existing models trained on potentially problematic data, our goal is to expose and address this issue. We do not advocate for training or deploying such models, but instead call for urgent community reflection and action to protect children's rights. Ultimately, we aim to encourage the research community to exercise - more than an additional - care in creating new datasets and to inspire the development of tools to protect the fundamental rights of vulnerable groups, particularly children.
Medical image analysis is essential in modern healthcare. Deep learning has redirected research focus toward complex medical multimodal tasks, including report generation and visual question answering. Traditional task-specific models often fall short in handling these challenges. Large vision-language models (LVLMs) offer new solutions for solving such tasks. In this study, we build on the popular LLaVA framework to systematically explore model architectures and training strategies for both 2D and 3D medical LVLMs. We present extensive empirical findings and practical guidance. To support reproducibility and future research, we release a modular codebase, MedM-VL, and two pre-trained models: MedM-VL-2D for 2D medical image analysis and MedM-VL-CT-Chest for 3D CT-based applications. The code and models are available at: https://github.com/MSIIP/MedM-VL
We aim to develop a retrieval-augmented generation (RAG) framework that answers questions over a corpus of visually-rich documents presented in mixed modalities (e.g., charts, tables) and diverse formats (e.g., PDF, PPTX). In this paper, we introduce a new RAG framework, VDocRAG, which can directly understand varied documents and modalities in a unified image format to prevent missing information that occurs by parsing documents to obtain text. To improve the performance, we propose novel self-supervised pre-training tasks that adapt large vision-language models for retrieval by compressing visual information into dense token representations while aligning them with textual content in documents. Furthermore, we introduce OpenDocVQA, the first unified collection of open-domain document visual question answering datasets, encompassing diverse document types and formats. OpenDocVQA provides a comprehensive resource for training and evaluating retrieval and question answering models on visually-rich documents in an open-domain setting. Experiments show that VDocRAG substantially outperforms conventional text-based RAG and has strong generalization capability, highlighting the potential of an effective RAG paradigm for real-world documents.
Medical Visual Question Answering (MVQA) systems can interpret medical images in response to natural language queries. However, linguistic variability in question phrasing often undermines the consistency of these systems. To address this challenge, we propose a Semantically Equivalent Question Augmentation (SEQA) framework, which leverages large language models (LLMs) to generate diverse yet semantically equivalent rephrasings of questions. Specifically, this approach enriches linguistic diversity while preserving semantic meaning. We further introduce an evaluation metric, Total Agreement Rate with Semantically Equivalent Input and Correct Answer (TAR-SC), which assesses a model's capability to generate consistent and correct responses to semantically equivalent linguistic variations. In addition, we also propose three other diversity metrics - average number of QA items per image (ANQI), average number of questions per image with the same answer (ANQA), and average number of open-ended questions per image with the same semantics (ANQS). Using the SEQA framework, we augmented the benchmarked MVQA public datasets of SLAKE, VQA-RAD, and PathVQA. As a result, all three datasets achieved significant improvements by incorporating more semantically equivalent questions: ANQI increased by an average of 86.1, ANQA by 85.1, and ANQS by 46. Subsequent experiments evaluate three MVQA models (M2I2, MUMC, and BiomedGPT) under both zero-shot and fine-tuning settings on the enhanced datasets. Experimental results in MVQA datasets show that fine-tuned models achieve an average accuracy improvement of 19.35%, while our proposed TAR-SC metric shows an average improvement of 11. 61%, indicating a substantial enhancement in model consistency.
With the rapid advancement of text-to-image (T2I) generation models, assessing the semantic alignment between generated images and text descriptions has become a significant research challenge. Current methods, including those based on Visual Question Answering (VQA), still struggle with fine-grained assessments and precise quantification of image-text alignment. This paper presents an improved evaluation method named Instruction-augmented Multimodal Alignment for Image-Text and Element Matching (iMatch), which evaluates image-text semantic alignment by fine-tuning multimodal large language models. We introduce four innovative augmentation strategies: First, the QAlign strategy creates a precise probabilistic mapping to convert discrete scores from multimodal large language models into continuous matching scores. Second, a validation set augmentation strategy uses pseudo-labels from model predictions to expand training data, boosting the model's generalization performance. Third, an element augmentation strategy integrates element category labels to refine the model's understanding of image-text matching. Fourth, an image augmentation strategy employs techniques like random lighting to increase the model's robustness. Additionally, we propose prompt type augmentation and score perturbation strategies to further enhance the accuracy of element assessments. Our experimental results show that the iMatch method significantly surpasses existing methods, confirming its effectiveness and practical value. Furthermore, our iMatch won first place in the CVPR NTIRE 2025 Text to Image Generation Model Quality Assessment - Track 1 Image-Text Alignment.
Objective: This review explores the trustworthiness of multimodal artificial intelligence (AI) systems, specifically focusing on vision-language tasks. It addresses critical challenges related to fairness, transparency, and ethical implications in these systems, providing a comparative analysis of key tasks such as Visual Question Answering (VQA), image captioning, and visual dialogue. Background: Multimodal models, particularly vision-language models, enhance artificial intelligence (AI) capabilities by integrating visual and textual data, mimicking human learning processes. Despite significant advancements, the trustworthiness of these models remains a crucial concern, particularly as AI systems increasingly confront issues regarding fairness, transparency, and ethics. Methods: This review examines research conducted from 2017 to 2024 focusing on forenamed core vision-language tasks. It employs a comparative approach to analyze these tasks through the lens of trustworthiness, underlining fairness, explainability, and ethics. This study synthesizes findings from recent literature to identify trends, challenges, and state-of-the-art solutions. Results: Several key findings were highlighted. Transparency: Explainability of vision language tasks is important for user trust. Techniques, such as attention maps and gradient-based methods, have successfully addressed this issue. Fairness: Bias mitigation in VQA and visual dialogue systems is essential for ensuring unbiased outcomes across diverse demographic groups. Ethical Implications: Addressing biases in multilingual models and ensuring ethical data handling is critical for the responsible deployment of vision-language systems. Conclusion: This study underscores the importance of integrating fairness, transparency, and ethical considerations in developing vision-language models within a unified framework.
While convolution and self-attention mechanisms have dominated architectural design in deep learning, this survey examines a fundamental yet understudied primitive: the Hadamard product. Despite its widespread implementation across various applications, the Hadamard product has not been systematically analyzed as a core architectural primitive. We present the first comprehensive taxonomy of its applications in deep learning, identifying four principal domains: higher-order correlation, multimodal data fusion, dynamic representation modulation, and efficient pairwise operations. The Hadamard product's ability to model nonlinear interactions with linear computational complexity makes it particularly valuable for resource-constrained deployments and edge computing scenarios. We demonstrate its natural applicability in multimodal fusion tasks, such as visual question answering, and its effectiveness in representation masking for applications including image inpainting and pruning. This systematic review not only consolidates existing knowledge about the Hadamard product's role in deep learning architectures but also establishes a foundation for future architectural innovations. Our analysis reveals the Hadamard product as a versatile primitive that offers compelling trade-offs between computational efficiency and representational power, positioning it as a crucial component in the deep learning toolkit.
Data curation plays a crucial role in training powerful Visual Language Models (VLMs). In this work, we introduce the concept of Data Metabolism and present our data-centric framework to build VLMs throughout the development lifecycle. Starting from a standard model architecture, we discuss and provide insights into two crucial development steps: data curation and iteration, forming a closed-loop system that continuously improves model performance. We show a detailed codebook on how to process existing massive datasets and build user-specific data flywheel. As a demonstration, we release a VLM, named Capybara-VL, which excels in typical multimodal tasks (e.g. , visual question answering, scientific reasoning, and text-rich tasks). Despite its relatively compact size, Capybara-VL surpasses several open-source models that are up to 10 times larger in size. Moreover, it achieves results that are on par with those of several leading proprietary models, demonstrating its remarkable competitiveness. These results highlight the power of our data-centric framework and the potential of training smaller and more efficient VLMs.
Vision-language models (VLMs) integrate visual and textual information, enabling a wide range of applications such as image captioning and visual question answering, making them crucial for modern AI systems. However, their high computational demands pose challenges for real-time applications. This has led to a growing focus on developing efficient vision language models. In this survey, we review key techniques for optimizing VLMs on edge and resource-constrained devices. We also explore compact VLM architectures, frameworks and provide detailed insights into the performance-memory trade-offs of efficient VLMs. Furthermore, we establish a GitHub repository at https://github.com/MPSCUMBC/Efficient-Vision-Language-Models-A-Survey to compile all surveyed papers, which we will actively update. Our objective is to foster deeper research in this area.
In typical multimodal tasks, such as Visual Question Answering (VQA), adversarial attacks targeting a specific image and question can lead large vision-language models (LVLMs) to provide incorrect answers. However, it is common for a single image to be associated with multiple questions, and LVLMs may still answer other questions correctly even for an adversarial image attacked by a specific question. To address this, we introduce the query-agnostic visual attack (QAVA), which aims to create robust adversarial examples that generate incorrect responses to unspecified and unknown questions. Compared to traditional adversarial attacks focused on specific images and questions, QAVA significantly enhances the effectiveness and efficiency of attacks on images when the question is unknown, achieving performance comparable to attacks on known target questions. Our research broadens the scope of visual adversarial attacks on LVLMs in practical settings, uncovering previously overlooked vulnerabilities, particularly in the context of visual adversarial threats. The code is available at https://github.com/btzyd/qava.
Large Vision Language Models (LVLMs) have been widely adopted to guide vision foundation models in performing reasoning segmentation tasks, achieving impressive performance. However, the substantial computational overhead associated with LVLMs presents a new challenge. The primary source of this computational cost arises from processing hundreds of image tokens. Therefore, an effective strategy to mitigate such overhead is to reduce the number of image tokens, a process known as image token pruning. Previous studies on image token pruning for LVLMs have primarily focused on high level visual understanding tasks, such as visual question answering and image captioning. In contrast, guiding vision foundation models to generate accurate visual masks based on textual queries demands precise semantic and spatial reasoning capabilities. Consequently, pruning methods must carefully control individual image tokens throughout the LVLM reasoning process. Our empirical analysis reveals that existing methods struggle to adequately balance reductions in computational overhead with the necessity to maintain high segmentation accuracy. In this work, we propose LVLM_CSP, a novel training free visual token pruning method specifically designed for LVLM based reasoning segmentation tasks. LVLM_CSP consists of three stages: clustering, scattering, and pruning. Initially, the LVLM performs coarse-grained visual reasoning using a subset of selected image tokens. Next, fine grained reasoning is conducted, and finally, most visual tokens are pruned in the last stage. Extensive experiments demonstrate that LVLM_CSP achieves a 65% reduction in image token inference FLOPs with virtually no accuracy degradation, and a 70% reduction with only a minor 1% drop in accuracy on the 7B LVLM.
Recent advancements in large language models (LLMs) and multi-modal LLMs have been remarkable. However, these models still rely solely on their parametric knowledge, which limits their ability to generate up-to-date information and increases the risk of producing erroneous content. Retrieval-Augmented Generation (RAG) partially mitigates these challenges by incorporating external data sources, yet the reliance on databases and retrieval systems can introduce irrelevant or inaccurate documents, ultimately undermining both performance and reasoning quality. In this paper, we propose Multi-Modal Knowledge-Based Retrieval-Augmented Generation (MMKB-RAG), a novel multi-modal RAG framework that leverages the inherent knowledge boundaries of models to dynamically generate semantic tags for the retrieval process. This strategy enables the joint filtering of retrieved documents, retaining only the most relevant and accurate references. Extensive experiments on knowledge-based visual question-answering tasks demonstrate the efficacy of our approach: on the E-VQA dataset, our method improves performance by +4.2% on the Single-Hop subset and +0.4% on the full dataset, while on the InfoSeek dataset, it achieves gains of +7.8% on the Unseen-Q subset, +8.2% on the Unseen-E subset, and +8.1% on the full dataset. These results highlight significant enhancements in both accuracy and robustness over the current state-of-the-art MLLM and RAG frameworks.
Vision-language models (VLMs) show promise for autonomous driving but often lack transparent reasoning capabilities that are critical for safety. We investigate whether explicitly modeling reasoning during fine-tuning enhances VLM performance on driving decision tasks. Using GPT-4o, we generate structured reasoning chains for driving scenarios from the DriveLM benchmark with category-specific prompting strategies. We compare reasoning-based fine-tuning, answer-only fine-tuning, and baseline instruction-tuned models across multiple small VLM families (Llama 3.2, Llava 1.5, and Qwen 2.5VL). Our results demonstrate that reasoning-based fine-tuning consistently outperforms alternatives, with Llama3.2-11B-reason achieving the highest performance. Models fine-tuned with reasoning show substantial improvements in accuracy and text generation quality, suggesting explicit reasoning enhances internal representations for driving decisions. These findings highlight the importance of transparent decision processes in safety-critical domains and offer a promising direction for developing more interpretable autonomous driving systems.