大模型推理能力 - arXivDaily 专题

2508.12396 2025-08-19 cs.CV 50%

DeCoT: Decomposing Complex Instructions for Enhanced Text-to-Image Generation with Large Language Models

Xiaochuan Lin, Xiangyong Chen, Xuan Li, Yichen Su

机构 * Henan Polytechnic University（河南理工大学）

专题命中复杂问题求解：CoT(abstract)

2508.08987 2025-08-13 cs.CV cs.HC 50%

ColorGPT: Leveraging Large Language Models for Multimodal Color Recommendation

Ding Xia, Naoto Inoue, Qianru Qiu, Kotaro Kikuchi

机构 * The University of Tokyo（东京大学）； CyberAgent AI Lab（CyberAgent AI实验室）

专题命中复杂问题求解：reasoning(abstract)

Comments Accepted to ICDAR2025

2508.08155 2025-08-12 eess.AS cs.SD 50%

MSU-Bench: Towards Understanding the Conversational Multi-talker Scenarios

Shuai Wang, Zhaokai Sun, Zhennan Lin, Chengyou Wang, Zhou Pan, Lei Xie

机构 * MSU（密歇根州立大学）

专题命中复杂问题求解：reasoning(abstract)

2506.01663 2025-08-12 cs.CV 50%

Zoom-Refine: Boosting High-Resolution Multimodal Understanding via Localized Zoom and Self-Refinement

Xuan Yu, Dayan Guan, Yanfeng Gu

机构 * Harbin Institute of Technology（哈尔滨工业大学）

专题命中复杂问题求解：reasoning(abstract)

Comments Code is available at https://github.com/xavier-yu114/Zoom-Refine

2508.06168 2025-08-11 cs.IR 50%

Improving Table Retrieval with Question Generation from Partial Tables

Hsing-Ping Liang, Che-Wei Chang, Yao-Chung Fan

专题命中复杂问题求解：reasoning(abstract)

Comments TRL@ACL2025

2508.05585 2025-08-08 cs.CV 50%

DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition

Haijing Liu, Tao Pu, Hefeng Wu, Keze Wang, Liang Lin

机构 * Sun Yat-sen University（中山大学）

专题命中复杂问题求解：reasoning(abstract)

Comments Accepted by ACM MM 2025

2508.04031 2025-08-07 cs.DB 50%

BridgeScope: A Universal Toolkit for Bridging Large Language Models and Databases

Lianggui Weng, Dandan Liu, Rong Zhu, Bolin Ding, Jingren Zhou

专题命中复杂问题求解：reasoning(abstract)

Comments 6 pages, 6 figures

2505.22053 2025-08-06 cs.SD cs.MA cs.MM eess.AS 50%

AudioGenie: A Training-Free Multi-Agent Framework for Diverse Multimodality-to-Multiaudio Generation

Yan Rong, Jinting Wang, Guangzhi Lei, Shan Yang, Li Liu

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））； Tencent AI Lab（腾讯人工智能实验室）

专题命中复杂问题求解：self-correction(abstract)

2508.01169 2025-08-05 cs.CY 50%

WIP: Enhancing Game-Based Learning with AI-Driven Peer Agents

Chengzhang Zhu, Cecile H. Sam, Yanlai Wu, Ying Tang

专题命中复杂问题求解：reasoning(abstract)

2504.10011 2025-08-05 cs.RO 50%

KeyMPs: One-Shot Vision-Language Guided Motion Generation by Sequencing DMPs for Occlusion-Rich Tasks

Edgar Anarossi, Yuhwan Kwon, Hirotaka Tahara, Shohei Tanaka, Keisuke Shirai, Masashi Hamaya, Cristian C. Beltran-Hernandez, Atsushi Hashimoto, Takamitsu Matsubara

机构 * Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology（信息科学系，科学技术研究生学校，科学技术研究所）； Department of Electrical and Electronic Engineering, Faculty of Engineering Science, Kansai University（电气电子工程系，工学科学大学）； Department of Electronics, Kobe City College of Technology（电子系，神户市立技术学院）； OMRON SINIC X Corporation（OMRON SINIC X公司）

专题命中复杂问题求解：reasoning(abstract)

Comments Published in IEEE Access, Jul 14 2025

Journal ref IEEE Access, vol. 13, pp. 125420-125441, 2025

2412.20451 2025-08-01 cs.RO 50%

CoA-VLA: Improving Vision-Language-Action Models via Visual-Textual Chain-of-Affordance

Jinming Li, Yichen Zhu, Zhibin Tang, Junjie Wen, Minjie Zhu, Xiaoyu Liu, Chengmeng Li, Ran Cheng, Yaxin Peng, Yan Peng, Feifei Feng

机构 * Shanghai University（上海大学）； Midea Group（美的集团）； East China Normal University（华东师范大学）

专题命中复杂问题求解：reasoning(abstract)

Comments Project webpage is available at https://chain-of-affordance.github.io

2507.18165 2025-07-25 cs.HC 50%

ProactiveVA: Proactive Visual Analytics with LLM-Based UI Agent

Yuheng Zhao, Xueli Shu, Liwen Fan, Lin Gao, Yu Zhang, Siming Chen

专题命中复杂问题求解：reasoning(abstract)

Comments 11 pages, 8 figures

2507.17226 2025-07-24 cs.HC 50%

A "watch your replay videos" reflection assignment on comparing programming without versus with generative AI: learning about programming, critical AI use and limitations, and reflection

Sarah "Magz" Fernandez, Greg L Nelson

专题命中复杂问题求解：planning(abstract)

2507.06605 2025-07-23 cs.RO 50%

Growing Trees with an Agent: Accelerating RRTs with Learned, Multi-Step Episodic Exploration

Xinyu Wu

专题命中复杂问题求解：planning(abstract)

2507.09910 2025-07-15 cs.CV 50%

IGD: Instructional Graphic Design with Multimodal Layer Generation

Yadong Qu, Shancheng Fang, Yuxin Wang, Xiaorui Wang, Zhineng Chen, Hongtao Xie, Yongdong Zhang

机构 * University of Science and Technology of China（中国科学技术大学）； YuanShi Technology（元世科技）； Institute of Trustworthy Embodied AI, Fudan University（复旦大学可信具身人工智能研究院）

专题命中复杂问题求解：reasoning(abstract)

Comments ICCV 2025

2507.08244 2025-07-14 econ.GN q-fin.EC 50%

Advancing AI Capabilities and Evolving Labor Outcomes

Jacob Dominski, Yong Suk Lee

专题命中复杂问题求解：reasoning(abstract)

2405.14341 2025-07-08 cs.HC 50%

How do Observable Users Decompose D3 Code? A Qualitative Study

Melissa Lin, Heer Patel, Medina Lamkin, Hannah Bako, Leilani Battle

专题命中复杂问题求解：reasoning(abstract)

Comments Conditionally accepted by the 2025 IEEE International Conference on Visualization

2507.03224 2025-07-08 cs.NI 50%

RCA Copilot: Transforming Network Data into Actionable Insights via Large Language Models

Alexander Shan, Jasleen Kaur, Rahul Singh, Tarun Banka, Raj Yavatkar, T. Sridhar

专题命中复杂问题求解：reasoning(abstract)

Comments 6 page, IEEE ICC 2025, Jun 8 12, 2025, Montreal, Canada

2507.02699 2025-07-04 cs.CR 50%

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents

Jiangrong Wu, Yuhong Nan, Jianliang Wu, Zitong Yao, Zibin Zheng

专题命中复杂问题求解：reasoning(abstract)

2506.22028 2025-06-30 cs.RO 50%

LMPVC and Policy Bank: Adaptive voice control for industrial robots with code generating LLMs and reusable Pythonic policies

Ossi Parikka, Roel Pieters

机构 * Cognitive Robotics group, Unit of Automation Technology and Mechanical Engineering, Tampere University（认知机器人组、自动化技术与机械工程单位、塔尔皮奥大学）

专题命中复杂问题求解：reasoning(abstract)

Comments Accepted by the 2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN). For further information, videos and code, see https://github.com/ozzyuni/LMPVC

2506.21101 2025-06-27 cs.CV 50%

OracleFusion: Assisting the Decipherment of Oracle Bone Script with Structurally Constrained Semantic Typography

Caoshuo Li, Zengmao Ding, Xiaobin Hu, Bang Li, Donghao Luo, AndyPian Wu, Chaoyang Wang, Chengjie Wang, Taisong Jin, SevenShu, Yunsheng Wu, Yongge Liu, Rongrong Ji

机构 * Xiamen University（厦门大学）； Tencent（腾讯）； Anyang Normal University（安阳师范学院）

专题命中复杂问题求解：reasoning(abstract)

Comments Accepted to ICCV 2025

2506.16101 2025-06-23 cs.SE 50%

Regression Testing Optimization for ROS-based Autonomous Systems: A Comprehensive Review of Techniques

Yupeng Jiang, Shuaiyi Sun, Xi Zheng

专题命中复杂问题求解：reasoning(abstract)

2412.04431 2025-06-18 cs.CV 50%

Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

Jian Han, Jinlai Liu, Yi Jiang, Bin Yan, Yuqi Zhang, Zehuan Yuan, Bingyue Peng, Xiaobing Liu

机构 * ByteDance（字节跳动）

专题命中复杂问题求解：self-correction(abstract)

Comments 17 pages, 14 figures

2506.13663 2025-06-17 cs.SE 50%

DesignCoder: Hierarchy-Aware and Self-Correcting UI Code Generation with Large Language Models

Yunnong Chen, Shixian Ding, YingYing Zhang, Wenkai Chen, Jinzhou Du, Lingyun Sun, Liuqing Chen

专题命中复杂问题求解：self-correction(abstract)

Comments 11 pages,6 figures

2506.12687 2025-06-17 cs.IR 50%

Device-Cloud Collaborative Correction for On-Device Recommendation

Tianyu Zhan, Shengyu Zhang, Zheqi Lv, Jieming Zhu, Jiwei Li, Fan Wu, Fei Wu

专题命中复杂问题求解：self-correction(abstract)

Comments To be published in IJCAI-2025

2410.02627 2025-06-17 cs.SE 50%

Preparing for Super-Reactivity: Early Fault-Detection in the Development of Exceedingly Complex Reactive Systems

David Harel, Assaf Marron

专题命中复杂问题求解：planning(abstract)

Journal ref MODELSWARD (2025). pp.321-329

2502.20104 2025-06-16 cs.CV 50%

New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration

Xuzheng Yang, Junzhuo Liu, Peng Wang, Guoqing Wang, Yang Yang, Heng Tao Shen

机构 * University of Electronic Science and Technology of China（电子科技大学）； Tongji University（同济大学）

专题命中复杂问题求解：reasoning(abstract)

Comments Accepted by TPAMI 2025

2506.10175 2025-06-13 cs.CR 50%

AURA: A Multi-Agent Intelligence Framework for Knowledge-Enhanced Cyber Threat Attribution

Nanda Rani, Sandeep Kumar Shukla

专题命中复杂问题求解：reasoning(abstract)

2506.09055 2025-06-12 physics.ed-ph 50%

Learn Like Feynman: Developing and Testing an AI-Driven Feynman Bot

Akshaya Rajesh, Sumbul Khan

专题命中复杂问题求解：reasoning(abstract)

Comments 8 pages

Journal ref 2024 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE)

2406.08648 2025-06-11 cs.RO 50%

LLM-Craft: Robotic Crafting of Elasto-Plastic Objects with Large Language Models

Alison Bartsch, Amir Barati Farimani

机构 * With the Department of Mechanical Engineering, Carnegie Mellon University（卡内基梅隆大学机械工程系）

专题命中复杂问题求解：reasoning(abstract)

1. 复杂问题求解 5035 篇

DeCoT: Decomposing Complex Instructions for Enhanced Text-to-Image Generation with Large Language Models

ColorGPT: Leveraging Large Language Models for Multimodal Color Recommendation

MSU-Bench: Towards Understanding the Conversational Multi-talker Scenarios

Zoom-Refine: Boosting High-Resolution Multimodal Understanding via Localized Zoom and Self-Refinement

Improving Table Retrieval with Question Generation from Partial Tables

DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition

BridgeScope: A Universal Toolkit for Bridging Large Language Models and Databases

AudioGenie: A Training-Free Multi-Agent Framework for Diverse Multimodality-to-Multiaudio Generation

WIP: Enhancing Game-Based Learning with AI-Driven Peer Agents

KeyMPs: One-Shot Vision-Language Guided Motion Generation by Sequencing DMPs for Occlusion-Rich Tasks

CoA-VLA: Improving Vision-Language-Action Models via Visual-Textual Chain-of-Affordance

ProactiveVA: Proactive Visual Analytics with LLM-Based UI Agent

A "watch your replay videos" reflection assignment on comparing programming without versus with generative AI: learning about programming, critical AI use and limitations, and reflection

Growing Trees with an Agent: Accelerating RRTs with Learned, Multi-Step Episodic Exploration

IGD: Instructional Graphic Design with Multimodal Layer Generation

Advancing AI Capabilities and Evolving Labor Outcomes

How do Observable Users Decompose D3 Code? A Qualitative Study

RCA Copilot: Transforming Network Data into Actionable Insights via Large Language Models

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents

LMPVC and Policy Bank: Adaptive voice control for industrial robots with code generating LLMs and reusable Pythonic policies

OracleFusion: Assisting the Decipherment of Oracle Bone Script with Structurally Constrained Semantic Typography

Regression Testing Optimization for ROS-based Autonomous Systems: A Comprehensive Review of Techniques

Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

DesignCoder: Hierarchy-Aware and Self-Correcting UI Code Generation with Large Language Models

Device-Cloud Collaborative Correction for On-Device Recommendation

Preparing for Super-Reactivity: Early Fault-Detection in the Development of Exceedingly Complex Reactive Systems

New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration

AURA: A Multi-Agent Intelligence Framework for Knowledge-Enhanced Cyber Threat Attribution

Learn Like Feynman: Developing and Testing an AI-Driven Feynman Bot

LLM-Craft: Robotic Crafting of Elasto-Plastic Objects with Large Language Models