paper-with-me

Papers

Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning

2024-12-18 · Yingjie Zhu, Xuefeng Bai, Kehai Chen, Yang Xiang, Min Zhang

Large Vision-Language Models (LVLMs) have demonstrated remarkable performance across diverse tasks. Despite great success, recent studies show that LVLMs encounter substantial limitations when engaging with visual graphs. To study the reason behind these limitations, we propose VGCure, a comprehensive benchmark covering 22 tasks for examining the fundamental graph understanding and reasoning capacities of LVLMs. Extensive evaluations conducted on 14 LVLMs reveal that LVLMs are weak in basic graph understanding and reasoning tasks, particularly those concerning relational or structurally complex information. Based on this observation, we propose a structure-aware fine-tuning framework to enhance LVLMs with structure learning abilities through 3 self-supervised learning tasks. Experiments validate the effectiveness of our method in improving LVLMs' zero-shot performance on fundamental graph learning tasks, as well as enhancing the robustness of LVLMs against complex visual graphs.

📄 PDF Abstract BibTeX arXiv:2412.13540

Code (1)

aaandy-zhu/vgcure 공식 구현

Tasks

BenchmarkingGraph LearningSelf-Supervised Learning

Similar Papers 제목 키워드 기반

SeePhys: Does Seeing Help Thinking? -- Benchmarking Vision-Based Physics Reasoning

2025-05-25 · Kun Xiang, Heng Li, Terry Jingchen Zhang, Yinya Huang 외

We present SeePhys, a large-scale multimodal benchmark for LLM reasoning grounded in physics questions ranging from middle school to PhD qualifying exams. The benchmark covers 7 fundamental domains spanning the physics d…

BenchmarkingVisual Reasoning

VisFactor: Benchmarking Fundamental Visual Cognition in Multimodal Large Language Models

2025-02-23 · Jen-tse Huang, Dasen Dai, Jen-Yuan Huang, Youliang Yuan 외

Multimodal Large Language Models (MLLMs) have demonstrated remarkable advancements in multimodal understanding; however, their fundamental visual cognitive abilities remain largely underexplored. To bridge this gap, we i…

BenchmarkingSpatial ReasoningVisual Reasoning

SVHalluc: Benchmarking Speech-Vision Hallucination in Audio-Visual Large Language Models

2026-05-31 · Chenshuang Zhang, Kyeong Seon Kim, Chengxin Liu, Tae-Hyun Oh arxiv

Despite the success of audio-visual large-language models (LLMs), they can produce plausible but ungrounded outputs, termed hallucination. Existing benchmarks focus on environmental sounds (e.g., dog barking) to indicate…

AutoViVQA: A Large-Scale Automatically Constructed Dataset for Vietnamese Visual Question Answering

2026-03-10 · Nguyen Anh Tuong, Phan Ba Duc, Nguyen Trung Quoc, Tran Dac Thinh 외 arxiv

Visual Question Answering (VQA) is a fundamental multimodal task that requires models to jointly understand visual and textual information. Early VQA systems relied heavily on language biases, motivating subsequent work …

Visual Question AnsweringRepresentation LearningMachine TranslationImage Captioning

Benchmarking Direct Preference Optimization for Medical Large Vision-Language Models

2026-01-25 · Dain Kim, Jiwoo Lee, Jaehoon Yun, Yong Hoe Koo 외 arxiv

Large Vision-Language Models (LVLMs) hold significant promise for medical applications, yet their deployment is often constrained by insufficient alignment and reliability. While Direct Preference Optimization (DPO) has …