大模型推理能力 - arXivDaily 专题

2505.08084 2025-05-14 cs.CV 78%

Visually Interpretable Subtask Reasoning for Visual Question Answering

Yu Cheng, Arushi Goel, Hakan Bilen

机构 * University of Edinburgh（爱丁堡大学）； NVIDIA（英伟达）

专题命中复杂问题求解：reasoning(title,abstract)

2505.06832 2025-05-13 cs.RO 78%

UniDiffGrasp: A Unified Framework Integrating VLM Reasoning and VLM-Guided Part Diffusion for Open-Vocabulary Constrained Grasping with Dual Arms

Xueyang Guo, Hongwei Hu, Chengye Song, Jiale Chen, Zilin Zhao, Yu Fu, Bowen Guan, Zhenze Liu

机构 * School of Communication Engineering, Jilin University（吉林大学通信工程学院）； College of Software Engineering, Jilin University（吉林大学软件工程学院）； School of Mathematics, Jilin University（吉林大学数学学院）； College of Electronic Science and Engineering, Jilin University（吉林大学电子科学工程学院）

专题命中复杂问题求解：reasoning(title,abstract)

Comments 8 pages, 5 figures

2504.15032 2025-05-01 cs.CV 78%

DyST-XL: Dynamic Layout Planning and Content Control for Compositional Text-to-Video Generation

Weijie He, Mushui Liu, Yunlong Yu, Zhao Wang, Chao Wu

机构 * Zhejiang University（浙江大学）

专题命中复杂问题求解：planning(title)；reasoning(abstract)

Comments 9 pages, 6 figures

2403.03452 2025-04-29 cs.CV 78%

D4C: Improving Negative Example Quality to Enhance Machine Abstract Reasoning Ability

Ruizhuo Song, Beiming Yuan

专题命中复杂问题求解：reasoning(title,abstract)

Comments 14 pages, 15 figures, 13 tables

2504.15909 2025-04-25 cs.IR 78%

Synergizing RAG and Reasoning: A Systematic Review

Yunfan Gao, Yun Xiong, Yijie Zhong, Yuxi Bi, Ming Xue, Haofen Wang

专题命中复杂问题求解：reasoning(title,abstract)

2503.07433 2025-04-23 cs.NI 78%

DRESS: Diffusion Reasoning-based Reward Shaping Scheme For Intelligent Networks

Feiran You, Hongyang Du, Xiangwang Hou, Yong Ren, Kaibin Huang

专题命中复杂问题求解：reasoning(title,abstract)

2503.14674 2025-03-20 cs.CV 78%

Elevating Visual Question Answering through Implicitly Learned Reasoning Pathways in LVLMs

Liu Jing, Amirul Rahman

专题命中复杂问题求解：reasoning(title,abstract)

2503.09968 2025-03-14 cs.CV 78%

Style Evolving along Chain-of-Thought for Unknown-Domain Object Detection

Zihao Zhang, Aming Wu, Yahong Han

专题命中复杂问题求解：chain-of-thought(title,abstract)

2503.07832 2025-03-12 cs.AI cs.CL cs.LG cs.SE 78%

RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code

Dhruv Gautam, Spandan Garg, Jinu Jang, Neel Sundaresan, Roshanak Zilouchian Moghaddam

专题命中复杂问题求解：reasoning(title)；分类 cs.CL、cs.AI、cs.LG

Comments ICLR 2025 Camera Ready

2412.04237 2025-03-12 cs.CV 78%

VASCAR: Content-Aware Layout Generation via Visual-Aware Self-Correction

Jiahao Zhang, Ryota Yoshihashi, Shunsuke Kitada, Atsuki Osanai, Yuta Nakashima

专题命中复杂问题求解：self-correction(title,abstract)

2501.09307 2025-03-11 cs.RO 78%

RoboReflect: A Robotic Reflective Reasoning Framework for Grasping Ambiguous-Condition Objects

Zhen Luo, Yixuan Yang, Yanfu Zhang, Feng Zheng

专题命中复杂问题求解：reasoning(title)；planning(abstract)

2503.00778 2025-03-04 cs.RO 78%

AffordGrasp: In-Context Affordance Reasoning for Open-Vocabulary Task-Oriented Grasping in Clutter

Yingbo Tang, Shuaike Zhang, Xiaoshuai Hao, Pengwei Wang, Jianlong Wu, Zhongyuan Wang, Shanghang Zhang

专题命中复杂问题求解：reasoning(title,abstract)

2412.01694 2025-02-14 cs.CV 78%

Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillation

Yudi Shi, Shangzhe Di, Qirui Chen, Weidi Xie

专题命中复杂问题求解：reasoning(title,abstract)

2406.03376 2025-02-04 cs.SE 78%

Log Parsing using LLMs with Self-Generated In-Context Learning and Self-Correction

Yifan Wu, Siyu Yu, Ying Li

专题命中复杂问题求解：self-correction(title,abstract)

Comments Accepted by the 33rd IEEE/ACM International Conference on Program Comprehension (ICPC'25)

2412.06324 2025-01-03 cs.CV 78%

World knowledge-enhanced Reasoning Using Instruction-guided Interactor in Autonomous Driving

Mingliang Zhai, Cheng Li, Zengyuan Guo, Ningrui Yang, Xiameng Qin, Sanyuan Zhao, Junyu Han, Ji Tao, Yuwei Wu, Yunde Jia

专题命中复杂问题求解：reasoning(title,abstract)

Comments AAAI 2025. 14 pages. Supplementary Material

2411.08510 2024-11-14 cs.SE 78%

CorrectBench: Automatic Testbench Generation with Functional Self-Correction using LLMs for HDL Design

Ruidi Qiu, Grace Li Zhang, Rolf Drechsler, Ulf Schlichtmann, Bing Li

专题命中复杂问题求解：self-correction(title,abstract)

2409.05556 2024-09-10 cs.AI cond-mat.dis-nn cond-mat.mtrl-sci cs.CL cs.LG 78%

SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning

Alireza Ghafarollahi, Markus J. Buehler

专题命中复杂问题求解：reasoning(title)；分类 cs.CL、cs.AI、cs.LG

2409.02611 2024-09-05 cs.CV 78%

GoT-CQA: Graph-of-Thought Guided Compositional Reasoning for Chart Question Answering

Lingling Zhang, Muye Huang, QianYing Wang, Yaxian Wang, Wenjun Wu, Jun Liu

专题命中复杂问题求解：reasoning(title,abstract)

2408.17006 2024-09-02 cs.CV 78%

Retrieval-Augmented Natural Language Reasoning for Explainable Visual Question Answering

Su Hyeon Lim, Minkuk Kim, Hyeon Bae Kim, Seong Tae Kim

专题命中复杂问题求解：reasoning(title,abstract)

Comments ICIP Workshop 2024

2407.03008 2024-07-04 cs.CV 78%

Align and Aggregate: Compositional Reasoning with Video Alignment and Answer Aggregation for Video Question-Answering

Zhaohe Liao, Jiangtong Li, Li Niu, Liqing Zhang

专题命中复杂问题求解：reasoning(title,abstract)

Comments 10 pages,CVPR

Journal ref CVPR (2024) 13395-13404

2405.03272 2024-05-07 cs.CV 78%

WorldQA: Multimodal World Knowledge in Videos through Long-Chain Reasoning

Yuanhan Zhang, Kaichen Zhang, Bo Li, Fanyi Pu, Christopher Arif Setiadharma, Jingkang Yang, Ziwei Liu

专题命中复杂问题求解：reasoning(title,abstract)

2312.01598 2023-12-12 cs.CV 78%

Good Questions Help Zero-Shot Image Reasoning

Kaiwen Yang, Tao Shen, Xinmei Tian, Xiubo Geng, Chongyang Tao, Dacheng Tao, Tianyi Zhou

专题命中复杂问题求解：reasoning(title,abstract)

2311.03964 2023-11-08 cs.CV 78%

Enhancing Multimodal Compositional Reasoning of Visual Language Models with Generative Negative Mining

Ugur Sahin, Hang Li, Qadeer Khan, Daniel Cremers, Volker Tresp

专题命中复杂问题求解：reasoning(title,abstract)

Comments Accepted to WACV

2303.08128 2023-03-15 cs.CV 78%

ViperGPT: Visual Inference via Python Execution for Reasoning

Dídac Surís, Sachit Menon, Carl Vondrick

专题命中复杂问题求解：reasoning(title,abstract)

Comments Website: https://viper.cs.columbia.edu/

2208.00361 2022-10-28 cs.CV 78%

One for All: One-stage Referring Expression Comprehension with Dynamic Reasoning

Zhipeng Zhang, Zhimin Wei, Zhongzhen Huang, Rui Niu, Peng Wang

专题命中复杂问题求解：reasoning(title,abstract)

Comments 27 pages, 6 figures

2210.10300 2022-10-20 cs.CV 78%

Dense but Efficient VideoQA for Intricate Compositional Reasoning

Jihyeon Lee, Wooyoung Kang, Eun-Sol Kim

专题命中复杂问题求解：reasoning(title,abstract)

Comments Accepted to WACV'23

2209.10049 2022-09-22 cs.MA 78%

Introducing emotions in the reasoning cycle ofnormative aware agents

Daniel Perez, Estefania Argente, Elena Del Val, Soledad Valero

专题命中复杂问题求解：reasoning(title,abstract)

Comments 39 pages, 10 figures, 4 tables

2112.05892 2022-07-26 cs.CV 78%

COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality

Honglu Zhou, Asim Kadav, Aviv Shamsian, Shijie Geng, Farley Lai, Long Zhao, Ting Liu, Mubbasir Kapadia, Hans Peter Graf

专题命中复杂问题求解：reasoning(title,abstract)

Comments ECCV 2022

2103.10574 2021-03-23 cs.CV 78%

Hopper: Multi-hop Transformer for Spatiotemporal Reasoning

Honglu Zhou, Asim Kadav, Farley Lai, Alexandru Niculescu-Mizil, Martin Renqiang Min, Mubbasir Kapadia, Hans Peter Graf

专题命中复杂问题求解：reasoning(title,abstract)

1801.09718 2018-01-31 cs.CV 78%

Object-based reasoning in VQA

Mikyas T. Desta, Larry Chen, Tomasz Kornuta

专题命中复杂问题求解：reasoning(title,abstract)

Comments 10 pages, 15 figures, published as a conference paper at 2018 IEEE Winter Conf. on Applications of Computer Vision (WACV'2018)

1. 复杂问题求解 5001 篇

Visually Interpretable Subtask Reasoning for Visual Question Answering

UniDiffGrasp: A Unified Framework Integrating VLM Reasoning and VLM-Guided Part Diffusion for Open-Vocabulary Constrained Grasping with Dual Arms

DyST-XL: Dynamic Layout Planning and Content Control for Compositional Text-to-Video Generation

D4C: Improving Negative Example Quality to Enhance Machine Abstract Reasoning Ability

Synergizing RAG and Reasoning: A Systematic Review

DRESS: Diffusion Reasoning-based Reward Shaping Scheme For Intelligent Networks

Elevating Visual Question Answering through Implicitly Learned Reasoning Pathways in LVLMs

Style Evolving along Chain-of-Thought for Unknown-Domain Object Detection

RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code

VASCAR: Content-Aware Layout Generation via Visual-Aware Self-Correction

RoboReflect: A Robotic Reflective Reasoning Framework for Grasping Ambiguous-Condition Objects

AffordGrasp: In-Context Affordance Reasoning for Open-Vocabulary Task-Oriented Grasping in Clutter

Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillation

Log Parsing using LLMs with Self-Generated In-Context Learning and Self-Correction

World knowledge-enhanced Reasoning Using Instruction-guided Interactor in Autonomous Driving

CorrectBench: Automatic Testbench Generation with Functional Self-Correction using LLMs for HDL Design

SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning

GoT-CQA: Graph-of-Thought Guided Compositional Reasoning for Chart Question Answering

Retrieval-Augmented Natural Language Reasoning for Explainable Visual Question Answering

Align and Aggregate: Compositional Reasoning with Video Alignment and Answer Aggregation for Video Question-Answering

WorldQA: Multimodal World Knowledge in Videos through Long-Chain Reasoning

Good Questions Help Zero-Shot Image Reasoning

Enhancing Multimodal Compositional Reasoning of Visual Language Models with Generative Negative Mining

ViperGPT: Visual Inference via Python Execution for Reasoning

One for All: One-stage Referring Expression Comprehension with Dynamic Reasoning

Dense but Efficient VideoQA for Intricate Compositional Reasoning

Introducing emotions in the reasoning cycle ofnormative aware agents

COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality

Hopper: Multi-hop Transformer for Spatiotemporal Reasoning

Object-based reasoning in VQA