中文
相关论文

相关论文: Chart-R1: Chain-of-Thought Supervision and Reinfor…

200 篇论文

Charts are essential to data analysis, transforming raw data into clear visual representations that support human decision-making. Although current vision-language models (VLMs) have made significant progress, they continue to struggle with…

Recently, large language models have shown remarkable reasoning capabilities through long-chain reasoning before responding. However, how to extend this capability to visual reasoning tasks remains an open challenge. Existing multimodal…

计算与语言 · 计算机科学 2025-06-13 Caijun Jia , Nan Xu , Jingxuan Wei , Qingli Wang , Lei Wang , Bihui Yu , Junnan Zhu

Multimodal large language models (MLLMs) have shown considerable potential in chart understanding and reasoning tasks. However, they still struggle with high information density (HID) charts characterized by multiple subplots, legends, and…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Hongkun Pan , Yuwei Wu , Wanyi Hong , Shenghui Hu , Qitong Yan , Yi Yang , Rufei Han , Changju Zhou , Minfeng Zhu , Dongming Han , Wei Chen

Visual reasoning abilities play a crucial role in understanding complex multimodal data, advancing both domain-specific applications and artificial general intelligence (AGI). Existing methods enhance Vision-Language Models (VLMs) through…

计算机视觉与模式识别 · 计算机科学 2025-10-07 Huajie Tan , Yuheng Ji , Xiaoshuai Hao , Xiansheng Chen , Pengwei Wang , Zhongyuan Wang , Shanghang Zhang

Chart understanding presents a critical test to the reasoning capabilities of Vision-Language Models (VLMs). Prior approaches face critical limitations: some rely on external tools, making them brittle and constrained by a predefined…

计算机视觉与模式识别 · 计算机科学 2025-09-12 Bohao Tang , Yan Ma , Fei Zhang , Jiadi Su , Ethan Chern , Zhulin Hu , Zhixin Wang , Pengfei Liu , Ya Zhang

Accurate chart comprehension represents a critical challenge in advancing multimodal learning systems, as extensive information is compressed into structured visual representations. However, existing vision-language models (VLMs) frequently…

机器学习 · 计算机科学 2026-03-10 Xin Zhang , Xingyu Li , Rongguang Wang , Ruizhong Miao , Zheng Wang , Dan Roth , Chenyang Li

Chart reasoning is a critical capability for Vision Language Models (VLMs). However, the development of open-source models is severely hindered by the lack of high-quality training data. Existing datasets suffer from a dual challenge:…

计算机视觉与模式识别 · 计算机科学 2026-04-30 Zheng Liu , Honglin Lin , Chonghan Qin , Xiaoyang Wang , Xin Gao , Yu Li , Mengzhang Cai , Yun Zhu , Zhanping Zhong , Qizhi Pei , Zhuoshi Pan , Xiaoran Shang , Bin Cui , Conghui He , Wentao Zhang , Lijun Wu

The recent advancements in Vision Language Models (VLMs) have demonstrated progress toward true intelligence requiring robust reasoning capabilities. Beyond pattern recognition, linguistic reasoning must integrate with visual comprehension,…

人工智能 · 计算机科学 2026-04-06 Yunfei Bai , Amit Dhanda , Shekhar Jain

The capabilities of Large Vision-Language Models (LVLMs) have reached state-of-the-art on many visual reasoning tasks, including chart reasoning, yet they still falter on out-of-distribution (OOD) data, and degrade further when asked to…

计算机视觉与模式识别 · 计算机科学 2025-10-14 Sanchit Sinha , Oana Frunza , Kashif Rasul , Yuriy Nevmyvaka , Aidong Zhang

Charts are very popular for analyzing data, visualizing key insights and answering complex reasoning questions about data. To facilitate chart-based data analysis using natural language, several downstream tasks have been introduced…

计算与语言 · 计算机科学 2023-10-12 Ahmed Masry , Parsa Kavehzadeh , Xuan Long Do , Enamul Hoque , Shafiq Joty

Recent advances in large language models have significantly improved textual reasoning through the effective use of Chain-of-Thought (CoT) and reinforcement learning. However, extending these successes to vision-language tasks remains…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Minheng Ni , Zhengyuan Yang , Linjie Li , Chung-Ching Lin , Kevin Lin , Wangmeng Zuo , Lijuan Wang

Charts provide visual representations of data and are widely used for analyzing information, addressing queries, and conveying insights to others. Various chart-related downstream tasks have emerged recently, such as question-answering and…

计算与语言 · 计算机科学 2024-03-15 Ahmed Masry , Mehrad Shahmohammadi , Md Rizwan Parvez , Enamul Hoque , Shafiq Joty

Complex chart understanding tasks demand advanced visual recognition and reasoning capabilities from multimodal large language models (MLLMs). However, current research provides limited coverage of complex chart scenarios and…

计算机视觉与模式识别 · 计算机科学 2025-11-05 Duo Xu , Hao Cheng , Xin Lin , Zhen Xie , Hao Wang

Recently, long-thought reasoning models achieve strong performance on complex reasoning tasks, but often incur substantial inference overhead, making efficiency a critical concern. Our empirical analysis reveals that the benefit of using…

人工智能 · 计算机科学 2025-05-22 Haotian Luo , Haiying He , Yibo Wang , Jinluan Yang , Rui Liu , Naiqiang Tan , Xiaochun Cao , Dacheng Tao , Li Shen

Automated chart summarization is crucial for enhancing data accessibility and enabling efficient information extraction from visual data. While recent advances in visual-language models (VLMs) have demonstrated promise, existing methods…

计算与语言 · 计算机科学 2025-02-26 Raymond Choi , Frank Burns , Chase Lawrence

Chain-of-Thought (CoT) reasoning has been widely adopted to enhance Large Language Models (LLMs) by decomposing complex tasks into simpler, sequential subtasks. However, extending CoT to vision-language reasoning tasks remains challenging,…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Luozheng Qin , Jia Gong , Yuqing Sun , Tianjiao Li , Mengping Yang , Xiaomeng Yang , Chao Qu , Zhiyu Tan , Hao Li

Charts are high-density visualization carriers for complex data, serving as a crucial medium for information extraction and analysis. Automated chart understanding poses significant challenges to existing multimodal large language models…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Muye Huang , Lingling Zhang , Jie Ma , Han Lai , Fangzhi Xu , Yifei Li , Wenjun Wu , Yaqiang Wu , Jun Liu

While Reinforcement Learning with Verifiable Reward (RLVR) significantly advances image reasoning in Large Vision-Language Models (LVLMs), its application to complex video reasoning remains underdeveloped. This gap stems primarily from a…

计算机视觉与模式识别 · 计算机科学 2025-10-02 Congzhi Zhang , Zhibin Wang , Yinchao Ma , Jiawei Peng , Yihan Wang , Qiang Zhou , Jun Song , Bo Zheng

Large vision-language models (LVLMs) struggle to reliably detect visual primitives in charts and align them with semantic representations, which severely limits their performance on complex visual reasoning. This lack of perceptual…

人工智能 · 计算机科学 2026-03-13 Eunsoo Lee , Jeongwoo Lee , Minki Hong , Jangho Choi , Jihie Kim

Tabular data serves as the backbone of modern data analysis and scientific research. While Large Language Models (LLMs) fine-tuned via Supervised Fine-Tuning (SFT) have significantly improved natural language interaction with such…

‹ 上一页 1 2 3 10 下一页 ›