大模型推理能力

CyberV: Cybernetics for Test-time Scaling in Video Understanding

Jiahao Meng, Shuyang Sun, Yue Tan, Lu Qi, Yunhai Tong, Xiangtai Li, Longyin Wen

机构 * Peking University（北京大学） ； ByteDance（字节跳动） 纠错

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

VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary

Kevin Qinghong Lin, Mike Zheng Shou

机构 * Show Lab, National University of Singapore（新加坡国立大学展示实验室） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)

Comments Accepted by CVPR 2025. Github: https://github.com/showlab/VLog

CyLens: Towards Reinventing Cyber Threat Intelligence in the Paradigm of Agentic Large Language Models

Xiaoqun Liu, Jiacheng Liang, Qiben Yan, Jiyong Jang, Sicheng Mao, Muchao Ye, Jinyuan Jia, Zhaohan Xi

专题命中 复杂问题求解 ：reasoning(abstract)

Which Prompting Technique Should I Use? An Empirical Investigation of Prompting Techniques for Software Engineering Tasks

E. G. Santana, Gabriel Benjamin, Melissa Araujo, Harrison Santos, David Freitas, Eduardo Almeida, Paulo Anselmo da M. S. Neto, Jiawei Li, Jina Chun, Iftekhar Ahmed

专题命中 复杂问题求解 ：reasoning(abstract)

HASHIRU: Hierarchical Agent System for Hybrid Intelligent Resource Utilization

Kunal Pai, Parth Shah, Harshil Patel

专题命中 复杂问题求解 ：reasoning(abstract)

Comments Submitted as part of the Research Track at AgentX 2025, organized by Berkeley RDI

Improving LLM-Based Fault Localization with External Memory and Project Context

Inseok Yeo, Duksan Ryu, Jongmoon Baik

专题命中 复杂问题求解 ：reasoning(abstract)

Comments 12 Pages, 7 figures

Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency

Hongyu Li, Songhao Han, Yue Liao, Junfeng Luo, Jialin Gao, Shuicheng Yan, Si Liu

机构 * BUAA（北京航空航天大学） ； NUS（国立大学新加坡） ； Meituan（美团） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)

Urban Safety Perception Assessments via Integrating Multimodal Large Language Models with Street View Images

Jiaxin Zhang, Yunqin Li, Tomohiro Fukuda, Bowen Wang

专题命中 复杂问题求解 ：reasoning(abstract)

Comments 15 pages, 10 figures

Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model

Yuting Zhang, Hao Lu, Qingyong Hu, Yin Wang, Kaishen Yuan, Xin Liu, Kaishun Wu

机构 * The Hong Kong University of Science & Technology (Guangzhou)（香港科技大学（广州）） ； The Hong Kong University of Science & Technology（香港科技大学） ； Zhejiang University（浙江大学） ； Lappeenranta-Lahti University of Technology（拉佩兰塔-拉赫蒂技术大学） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)

Comments Accepted by CVPR 2025

FinRipple: Aligning Large Language Models with Financial Market for Event Ripple Effect Awareness

Yuanjian Xu, Jianing Hao, Kunsheng Tang, Jingnan Chen, Anxian Liu, Peng Liu, Guang Zhang

专题命中 复杂问题求解 ：reasoning(abstract)

Making Sense of the Unsensible: Reflection, Survey, and Challenges for XAI in Large Language Models Toward Human-Centered AI

Francisco Herrera

专题命中 复杂问题求解 ：reasoning(abstract)

Comments 30 pages, 1 figure

MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval

Rong-Cheng Tu, Zhao Jin, Jingyi Liao, Xiao Luo, Yingjie Wang, Li Shen, Dacheng Tao

机构 * College of Computing and Data Science, Nanyang Technological University, Singapore（南洋理工大学计算机与数据科学学院） ； Department of Computer Science, University of California, Los Angeles, USA（加州大学洛杉矶分校计算机科学系） ； Sun Yat-sen University Shenzhen Campus, School of Cyber Science and Technology, Shenzhen, China（中山大学深圳校区信息科学与技术学院） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)

MIND-Edit: MLLM Insight-Driven Editing via Language-Vision Projection

Shuyu Wang, Weiqi Li, Qian Wang, Shijie Zhao, Jian Zhang

机构 * School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院） ； ByteDance Inc.（字节跳动公司） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)

ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

Fanbin Lu, Zhisheng Zhong, Shu Liu, Chi-Wing Fu, Jiaya Jia

机构 * The Chinese University of Hong Kong（香港中文大学） ； SmartMore ； Hong Kong University of Science and Technology（香港理工大学） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)

Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perception

Yuanchen Wu, Lu Zhang, Hang Yao, Junlong Du, Ke Yan, Shouhong Ding, Yunsheng Wu, Xiaoqiang Li

机构 * School of Computer Engineering & Science, Shanghai University（上海大学计算机工程与科学学院） ； Tencent YouTu Lab（腾讯优图实验室） 纠错

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

Comments Accepted to CVPR 2025

A Comprehensive Survey of Large AI Models for Future Communications: Foundations, Applications and Challenges

Feibo Jiang, Cunhua Pan, Li Dong, Kezhi Wang, Merouane Debbah, Dusit Niyato, Zhu Han

专题命中 复杂问题求解 ：CoT(abstract)

Compositional Image-Text Matching and Retrieval by Grounding Entities

Madhukar Reddy Vongala, Saurabh Srivastava, Jana Košecká

机构 * Department of Computer Science, George Mason University（计算机科学系，乔治·马歇尔大学） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)

Comments Accepted at CVPR-W

Audo-Sight: Enabling Ambient Interaction For Blind And Visually Impaired Individuals

Bhanuja Ainary

专题命中 复杂问题求解 ：reasoning(abstract)

Comments This thesis was conducted under the guidance of Mohsen Amini Salehi. Special thanks to Minseo Kim and Jacob Bradshaw for their valuable contributions and support throughout the research process. 60 pages, 13 Figures, 2 Tables

Inferring Questions from Programming Screenshots

Faiz Ahmed, Xuchen Tan, Folajinmi Adewole, Suprakash Datta, Maleknaz Nayebi

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

Journal ref MSR 2025

Assessing and Learning Alignment of Unimodal Vision and Language Models

Le Zhang, Qian Yang, Aishwarya Agrawal

机构 * Mila - Quebec AI Institute（魁北克人工智能研究所） ； Université de Montréal（蒙特利尔大学） ； Canada CIFAR AI Chair（加拿大CIFAR人工智能 chair） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)

Comments CVPR 2025 Highlight

Cellular-X: An LLM-empowered Cellular Agent for Efficient Base Station Operations

Liujianfu Wang, Xinyi Long, Yuyang Du, Xiaoyan Liu, Kexin Chen, Soung Chang Liew

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

Comments MobiSys ’25, June 23-27, 2025, Anaheim, CA, USA

Kernel-Aware Graph Prompt Learning for Few-Shot Anomaly Detection

Fenfang Tao, Guo-Sen Xie, Fang Zhao, Xiangbo Shu

专题命中 复杂问题求解 ：reasoning(abstract)

Comments Accepted to AAAI 2025

Deep Learning in Concealed Dense Prediction

Pancheng Zhao, Deng-Ping Fan, Shupeng Cheng, Salman Khan, Fahad Shahbaz Khan, David Clifton, Peng Xu, Jufeng Yang

专题命中 复杂问题求解 ：reasoning(abstract)

Comments Technique Report

Perception in Reflection

Yana Wei, Liang Zhao, Kangheng Lin, En Yu, Yuang Peng, Runpei Dong, Jianjian Sun, Haoran Wei, Zheng Ge, Xiangyu Zhang, Vishal M. Patel

专题命中 复杂问题求解 ：reasoning(abstract)

LLM-IFT: LLM-Powered Information Flow Tracking for Secure Hardware

Nowfel Mashnoor, Mohammad Akyash, Hadi Kamali, Kimia Azar

专题命中 复杂问题求解 ：reasoning(abstract)

Comments This paper is presented at IEEE VLSI Test Symposium (VTS) 2025

Transfer between Modalities with MetaQueries

Xichen Pan, Satya Narayan Shukla, Aashu Singh, Zhuokai Zhao, Shlok Kumar Mishra, Jialiang Wang, Zhiyang Xu, Jiuhai Chen, Kunpeng Li, Felix Juefei-Xu, Ji Hou, Saining Xie

专题命中 复杂问题求解 ：reasoning(abstract)

Comments Project Page: https://xichenpan.com/metaquery

BT-ACTION: A Test-Driven Approach for Modular Understanding of User Instruction Leveraging Behaviour Trees and LLMs

Alexander Leszczynski, Sarah Gillet, Iolanda Leite, Fethiye Irmak Dogan

专题命中 复杂问题求解 ：reasoning(abstract)

Can LLMs Assist Computer Education? an Empirical Case Study of DeepSeek

Dongfu Xiao, Chen Gao, Zhengquan Luo, Chi Liu, Sheng Shen

专题命中 复杂问题求解 ：reasoning(abstract)

What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond

Wenchao Gu, Juntao Chen, Yanlin Wang, Tianyue Jiang, Xingzhe Li, Mingwei Liu, Xilin Liu, Yuchi Ma, Zibin Zheng

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

Enhanced Bloom's Educational Taxonomy for Fostering Information Literacy in the Era of Large Language Models

Yiming Luo, Ting Liu, Patrick Cheong-Iao Pang, Dana McKay, Ziqi Chen, George Buchanan, Shanton Chang

专题命中 复杂问题求解 ：reasoning(abstract)

Comments 25 Pages, 5 figures, submitted to the journal Computers & Education, currently under peer review