中文
相关论文

相关论文: Your Reasoning Benchmark May Not Test Reasoning: R…

200 篇论文

Modern Vision-Language Models (VLMs) exhibit a critical flaw in compositional reasoning, often confusing "a red cube and a blue sphere" with "a blue cube and a red sphere". Disentangling the visual and linguistic roots of these failures is…

计算机视觉与模式识别 · 计算机科学 2026-02-03 Cristian Sbrolli , Matteo Matteucci , Toshihiko Yamasaki

Fully comprehending scientific papers by machines reflects a high level of Artificial General Intelligence, requiring the ability to reason across fragmented and heterogeneous sources of information, presenting a complex and practically…

计算与语言 · 计算机科学 2025-06-30 Yang Tian , Zheng Lu , Mingqi Gao , Zheng Liu , Bo Zhao

Multimodal large language models have recently shown promising progress in visual mathematical reasoning. However, their performance is often limited by a critical yet underexplored bottleneck: inaccurate visual perception. Through…

人工智能 · 计算机科学 2026-03-10 Peijin Xie , Zhen Xu , Bingquan Liu , Baoxun Wang

Understanding a program's runtime reasoning behavior, meaning how intermediate states and control flows lead to final execution results, is essential for reliable code generation, debugging, and automated reasoning. Although large language…

软件工程 · 计算机科学 2025-12-02 Mohammad Abdollahi , Khandaker Rifah Tasnia , Soumit Kanti Saha , Jinqiu Yang , Song Wang , Hadi Hemmati

Although large visual-language models (LVLMs) have demonstrated strong performance in multimodal tasks, errors may occasionally arise due to biases during the reasoning process. Recently, reward models (RMs) have become increasingly pivotal…

计算机视觉与模式识别 · 计算机科学 2025-03-11 Jiacheng Ruan , Wenzhen Yuan , Xian Gao , Ye Guo , Daoxin Zhang , Zhe Xu , Yao Hu , Ting Liu , Yuzhuo Fu

Recent studies have shown that Large Language Models (LLMs) can achieve strong reasoning performance by incorporating functional symbolic representations that abstractly describe graph traversal algorithms and step-by-step reasoning in…

人工智能 · 计算机科学 2026-05-28 Phuong Minh Nguyen , Tien Huu Dang , Naoya Inoue

Multimodal large language models (MLLMs) often struggle to ground reasoning in perceptual evidence. We present a systematic study of perception strategies-explicit, implicit, visual, and textual-across four multimodal benchmarks and two…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Yizhuo Ding , Mingkang Chen , Zhibang Feng , Tong Xiao , Wanying Qu , Wenqi Shao , Yanwei Fu

ARC-AGI and ARC-AGI-2 measure generalization-through-composition on small color-quantized grids, and their prize competitions make progress on these harder held-out tasks a meaningful proxy for systematic generalization. Recent…

人工智能 · 计算机科学 2025-11-21 Bo Wen , Chen Wang , Erhan Bilal

Analogical reasoning is a fundamental capacity of human cognition that allows us to reason abstractly about novel situations by relating them to past experiences. While it is thought to be essential for robust reasoning in AI systems,…

人工智能 · 计算机科学 2023-06-06 Xiaoyang Hu , Shane Storks , Richard L. Lewis , Joyce Chai

Recent multimodal large language models (MLLMs) show strong capabilities in visual-language reasoning, yet their performance on ultra-high-resolution imagery remains largely unexplored. Existing visual question answering (VQA) benchmarks…

计算机视觉与模式识别 · 计算机科学 2026-01-14 Siqi Li , Xinyu Cai , Jianbiao Mei , Nianchen Deng , Pinlong Cai , Licheng Wen , Yufan Shen , Xuemeng Yang , Botian Shi , Yong Liu

Recent advancements in multimodal large language models have driven breakthroughs in visual question answering. Yet, a critical gap persists, `conceptualization'-the ability to recognize and reason about the same concept despite variations…

计算机视觉与模式识别 · 计算机科学 2025-06-09 Zahra Babaiee , Peyman M. Kiasari , Daniela Rus , Radu Grosu

Extracting structured information from visual documents (Visual Information Extraction, VIE) is a cornerstone of business automation. While recent Multimodal Large Language Models (MLLMs) have shown promising capabilities, existing…

计算机视觉与模式识别 · 计算机科学 2026-05-22 Yandi Wang , Libin Zhan , Ziwei Huang , Tiancheng Luo , Yuxuan Jiang , Wang Dong , Leilei Gan , Jun Chen

Large Language Models are commonly judged by their scores on standard benchmarks, yet such scores often overstate real capability since they mask the mix of skills a task actually demands. For example, ARC is assumed to test reasoning,…

计算与语言 · 计算机科学 2025-10-03 Dongjun Kim , Gyuho Shim , Yongchan Chun , Minhyuk Kim , Chanjun Park , Heuiseok Lim

In this paper, we offer a guide for researchers on evaluating reasoning in language models, building the case that reasoning should be assessed through evidence of adaptive, multi-step search rather than final-answer accuracy alone. Under…

人工智能 · 计算机科学 2026-05-05 Munachiso Samuel Nwadike , Zangir Iklassov , Kareem Ali , Rifo Genadi , Kentaro Inui

Large vision-language models (LVLMs) have witnessed significant progress on visual understanding tasks. However, they often prioritize language knowledge over image information on visual reasoning tasks, incurring performance degradation.…

计算机视觉与模式识别 · 计算机科学 2025-10-16 Jingqi Zhou , Sheng Wang , Jingwei Dong , Kai Liu , Lei Li , Jiahui Gao , Jiyue Jiang , Lingpeng Kong , Chuan Wu

Large vision-language models (VLMs) have garnered increasing interest in autonomous driving areas, due to their advanced capabilities in complex reasoning tasks essential for highly autonomous vehicle behavior. Despite their potential,…

计算机视觉与模式识别 · 计算机科学 2024-07-23 Ming Nie , Renyuan Peng , Chunwei Wang , Xinyue Cai , Jianhua Han , Hang Xu , Li Zhang

Adaptive multimodal reasoning has emerged as a promising frontier in Vision-Language Models (VLMs), aiming to dynamically modulate between tool-augmented visual reasoning and text reasoning to enhance both effectiveness and efficiency.…

计算机视觉与模式识别 · 计算机科学 2026-04-09 Xintong Zhang , Xiaowen Zhang , Jingrong Wu , Zhi Gao , Shilin Yan , Zhenxin Diao , Kunpeng Gao , Xuanyan Chen , Yuwei Wu , Yunde Jia , Qing Li

Large audio-language models (LALMs) have achieved near-human performance in sentence-level transcription and emotion recognition. However, existing evaluations focus mainly on surface-level perception, leaving the capacity of models for…

计算与语言 · 计算机科学 2025-08-05 Wanqi Yang , Yanda Li , Yunchao Wei , Meng Fang , Ling Chen

Visual Commonsense Reasoning (VCR), deemed as one challenging extension of the Visual Question Answering (VQA), endeavors to pursue a more high-level visual comprehension. It is composed of two indispensable processes: question answering…

计算机视觉与模式识别 · 计算机科学 2023-07-26 Zhenyang Li , Yangyang Guo , Kejie Wang , Yinwei Wei , Liqiang Nie , Mohan Kankanhalli

Recent reinforcement-learning frameworks for visual perception policy usually incorporate intermediate reasoning chains expressed in natural language. Empirical observations indicate that such purely linguistic intermediate reasoning often…

计算机视觉与模式识别 · 计算机科学 2026-05-28 Wei Tang , Yanpeng Sun , Shan Zhang , Weihao Bo , Xiaofan Li , Piotr Koniusz , Wei Li , Na Zhao , Zechao Li