相关论文: See the Forest and the Trees: A Synergistic Reason…

Leveraging outputs from multiple large language models (LLMs) is emerging as a method for harnessing their power across a wide range of tasks while mitigating their capacity for making errors, e.g., hallucinations. However, current…

Zero-shot visual question answering (ZS-VQA), an emerged critical research area, intends to answer visual questions without providing training samples. Existing research in ZS-VQA has proposed to leverage knowledge graphs or large language…

Open-ended question answering requires models to find appropriate evidence to form wellreasoned, comprehensive and helpful answers. In practical applications, models also need to engage in extended discussions on potential scenarios closely…

Large language models equipped with retrieval-augmented generation (RAG) represent a burgeoning field aimed at enhancing answering capabilities by leveraging external knowledge bases. Although the application of RAG with language-only…

Despite recent advancements in Multi-modal Large Language Models (MLLMs) on diverse understanding tasks, these models struggle to solve problems which require extensive multi-step reasoning. This is primarily due to the progressive dilution…

Document Visual Question Answering (DocVQA) requires models to jointly understand textual semantics, spatial layout, and visual features. Current methods struggle with explicit spatial relationship modeling, inefficiency with…

Large language models (LLMs) have demonstrated strong reasoning capabilities. Nevertheless, they still suffer from factual errors when tackling knowledge-intensive tasks. Retrieval-augmented reasoning represents a promising approach.…

Current roadside perception systems mainly focus on instance-level perception, which fall short in enabling interaction via natural language and reasoning about traffic behaviors in context. To bridge this gap, we introduce RoadSceneVQA, a…

Knowledge-based visual question answering is a very challenging and widely concerned task. Previous methods adopts the implicit knowledge in large language models (LLM) to achieve excellent results, but we argue that existing methods may…

Vision-Language Models (VLMs) have shown strong multimodal reasoning capabilities on Visual-Question-Answering (VQA) benchmarks. However, their robustness against textual misinformation remains under-explored. While existing research has…

It is challenging for models to understand complex, multimodal content such as television clips, and this is in part because video-language models often rely on single-modality reasoning and lack interpretability. To combat these issues we…

Visual Question Answering (VQA) has emerged as a pivotal task in the intersection of computer vision and natural language processing, requiring models to understand and reason about visual content in response to natural language questions.…

The rapid development of large language and vision models (LLVMs) has been driven by advances in visual instruction tuning. Recently, open-source LLVMs have curated high-quality visual instruction tuning datasets and utilized additional…

Zero-shot Visual Question Answering (VQA) is a prominent vision-language task that examines both the visual and textual understanding capability of systems in the absence of training data. Recently, by converting the images into captions,…

Inspired by human categorization, object property reasoning involves identifying and recognizing low-level details and higher-level abstractions. While current visual question answering (VQA) studies consider multiple object properties,…

Multimodal large language models (MLLMs) have emerged as powerful tools for visual question answering (VQA), enabling reasoning and contextual understanding across visual and textual modalities. Despite their advancements, the evaluation of…

Document Visual Question Answering (DocVQA) faces dual challenges in processing lengthy multimodal documents (text, images, tables) and performing cross-modal reasoning. Current document retrieval-augmented generation (DocRAG) methods…

Recent advances in multimodal large language models (MLLMs) have demonstrated remarkable capabilities in vision-language tasks, yet they often struggle with vision-centric scenarios where precise visual focus is needed for accurate…

Multimodal Large Language Models (MLLMs) have achieved remarkable success in open-vocabulary perceptual tasks, yet their ability to solve complex cognitive problems remains limited, especially when visual details are abstract and require…

Large Multimodal Models (LMMs) are increasingly capable of answering medical questions that require joint reasoning over images and text, yet training general medical VQA systems is impeded by the lack of large, openly usable, high-quality…