中文
相关论文

相关论文: Watch Wider and Think Deeper: Collaborative Cross-…

200 篇论文

Large Language Models (LLMs) face significant accuracy degradation due to insufficient reasoning ability when dealing with complex and abstract tasks. Thought structures such as Chain of Thought (CoT) and Tree of Thought (ToT) focus on…

计算与语言 · 计算机科学 2025-09-29 Fengxiao Tang , Yufeng Li , Zongzong Wu , Ming Zhao

Chain of Thought (CoT) of multi-step benefits from the logical structure of the reasoning steps and task-specific actions, significantly enhancing the mathematical reasoning capabilities of large language models. As the prevalence of long…

人工智能 · 计算机科学 2025-03-07 Wen Yang , Minpeng Liao , Kai Fan

Geospatial chain of thought (CoT) reasoning is essential for advancing Visual Question Answering (VQA) on satellite imagery, particularly in climate related applications such as disaster monitoring, infrastructure risk assessment, urban…

计算机视觉与模式识别 · 计算机科学 2025-11-17 Shambhavi Shanker , Manikandan Padmanaban , Jagabondhu Hazra

Vision-language models benefit from high-resolution images, but the increase in visual-token count incurs high compute overhead. Humans resolve this tension via foveation: a coarse view guides "where to look", while selectively acquired…

计算机视觉与模式识别 · 计算机科学 2026-04-24 Juhong Min , Lazar Valkov , Vitali Petsiuk , Hossein Souri , Deen Dayal Mohan

Reasoning methods, best exemplified by the well-known Chain-of-Thought (CoT), empower the reasoning abilities of Large Language Models (LLMs) by eliciting them to solve complex tasks in a step-by-step manner. Although they are achieving…

计算与语言 · 计算机科学 2024-06-24 Leonardo Ranaldi , Giulia Pucci , Federico Ranaldi , Elena Sofia Ruzzetti , Fabio Massimo Zanzotto

Multimodal Chain-of-Thought (CoT) reasoning requires large vision-language models to construct reasoning trajectories that interleave perceptual grounding with multi-step inference. However, existing Reinforcement Learning with Verifiable…

计算机视觉与模式识别 · 计算机科学 2026-03-25 Yunheng Li , Hangyi Kuang , Hengrui Zhang , Jiangxia Cao , Zhaojie Liu , Qibin Hou , Ming-Ming Cheng

Large Language Models have demonstrated remarkable abilities across various tasks, with Chain-of-Thought (CoT) prompting emerging as a key technique to enhance reasoning capabilities. However, existing research primarily focuses on…

人工智能 · 计算机科学 2024-10-07 Lijie Hu , Liang Liu , Shu Yang , Xin Chen , Zhen Tan , Muhammad Asif Ali , Mengdi Li , Di Wang

Thinking with Images improves fine-grained VQA for MLLMs by emphasizing visual cues. However, tool-augmented methods depend on the capacity of grounding, which remains unreliable for MLLMs. In parallel, attention-driven methods to crop the…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Zhaodong Wu , Haochen Xue , Qi Cao , Wenqi Mo , Yu Pei , Wenqi Xu , Jionglong Su , Yang Liu

Robot chain-of-thought reasoning (CoT) -- wherein a model predicts helpful intermediate representations before choosing actions -- provides an effective method for improving the generalization and performance of robot policies, especially…

机器人学 · 计算机科学 2025-05-20 William Chen , Suneel Belkhale , Suvir Mirchandani , Oier Mees , Danny Driess , Karl Pertsch , Sergey Levine

Compressing long chains of thought (CoT) into compact latent tokens is crucial for efficient reasoning with large language models (LLMs). Recent studies employ autoencoders to achieve this by reconstructing textual CoT from latent tokens,…

计算机视觉与模式识别 · 计算机科学 2026-02-02 Xiaoshu Chen , Sihang Zhou , Ke Liang , Taichun Zhou , Xinwang Liu

In recent years, video question answering based on multimodal large language models (MLLM) has garnered considerable attention, due to the benefits from the substantial advancements in LLMs. However, these models have a notable deficiency…

计算机视觉与模式识别 · 计算机科学 2025-10-17 Jinglei Zhang , Yuanfan Guo , Rolandos Alexandros Potamias , Jiankang Deng , Hang Xu , Chao Ma

Recent advances in multimodal reasoning models have demonstrated impressive capabilities across text and vision. However, even leading models exhibit redundant self-reflection when generating lengthy reasoning chains. While training-free…

计算机视觉与模式识别 · 计算机科学 2025-11-24 Yuan Zhang , Ming Lu , Junwen Pan , Tao Huang , Kuan Cheng , Qi She , Shanghang Zhang

Large language models (LLMs) have demonstrated strong reasoning capabilities in text-based mathematical problem solving; however, when adapted to visual reasoning tasks, particularly geometric problem solving, their performance…

人工智能 · 计算机科学 2025-10-28 Nannan Shi , Chuanyu Qin , Shipeng Song , Man Luo

Recent advances in Chain-of-Thought (CoT) reasoning have improved complex video understanding, but existing methods often struggle to adapt to domain-specific skills (e.g., event detection, spatial relation understanding, emotion…

计算机视觉与模式识别 · 计算机科学 2025-10-27 Daeun Lee , Jaehong Yoon , Jaemin Cho , Mohit Bansal

Accurate tumor analysis is central to clinical radiology and precision oncology, where early detection, reliable lesion characterization, and pathology-level risk assessment guide diagnosis and treatment planning. Chain-of-Thought (CoT)…

Chain-of-Thought (CoT) techniques have significantly enhanced reasoning in Vision-Language Models (VLMs). Extending this paradigm, Visual CoT integrates explicit visual edits, such as cropping or annotating regions of interest, into the…

机器学习 · 计算机科学 2025-09-30 Chunxue Xu , Yiwei Wang , Yujun Cai , Bryan Hooi , Songze Li

Large language models (LLMs) achieve strong performance on code generation, but the mechanisms by which Chain-of-Thought (CoT) prompting helps remain unclear. We present a systematic empirical and information-theoretic study of CoT…

软件工程 · 计算机科学 2025-12-11 Naizhu Jin , Zhong Li , Guang Yang , Tian Zhang , Qingkai Zeng

Chain-of-thought (CoT) has emerged as a critical mechanism for enhancing reasoning capabilities in large language models (LLMs), with self-consistency demonstrating notable promise in boosting performance. However, inherent linguistic…

计算与语言 · 计算机科学 2025-04-03 Zhiwei Yu , Tuo Li , Changhong Wang , Hui Chen , Lang Zhou

Recent advancements in large language models (LLMs) have demonstrated their impressive abilities in various reasoning and decision-making tasks. However, the quality and coherence of the reasoning process can still benefit from enhanced…

计算与语言 · 计算机科学 2025-01-24 Shihao Ji , Zihui Song , Fucheng Zhong , Jisen Jia , Zhaobo Wu , Zheyi Cao , Tianhao Xu

The advancement of Chain-of-Thought (CoT) reasoning has significantly enhanced the capabilities of large language models (LLMs) and large vision-language models (LVLMs). However, a rigorous evaluation framework for video CoT reasoning…

计算机视觉与模式识别 · 计算机科学 2025-04-11 Yukun Qi , Yiming Zhao , Yu Zeng , Xikun Bao , Wenxuan Huang , Lin Chen , Zehui Chen , Jie Zhao , Zhongang Qi , Feng Zhao