赵峰｜中国科学技术大学｜学者主页

2026

融合多尺度上下文与 Mamba 时序建模的 Himawari-8/9 卫星火点检测

张本硕，柯枫，安志勇，于晓宁，韩忠伟，赵峰

《中国图象图形学报》

2026

动态自适应的3D高斯溅射稠密视觉SLAM算法

王险峰，赵峰，王忠越，赵梓恒

《微电子学与计算机》

2026

Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs

Yu Li, Xiao-Ran Shang, Qizhi Pei, Yun Zhu, Xin Gao, Hong-Lin Lin, Zhanping Zhong, Zhuo-Shi Pan, Zheng Liu, Xiao-Yang Wang, Cong-Hui He, Da-Hua Lin, Feng Zhao, Li-Jun Wu

Annual Meeting of the Association for Computational Linguistics

DOI

2026

Breaking Block Boundaries: Anchor-based History-stable Decoding for Diffusion Large Language Models

Shu Zou, Yong Wang, Ze-Hui Chen, Lin Chen, Chong-Yang Tao, Feng Zhao, Xiangxiang Chu

Annual Meeting of the Association for Computational Linguistics

DOI

2026

SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents

Ziao Zhang, Kou Shi, Shi-Ting Huang, Avery Nie, Yu Zeng, Yi-Ming Zhao, Zhen-Long Fang, Qi-Sheng Su, Haibo Qiu, Wei Yang, Qing-Nan Ren, Shu Zou, Wen-Xuan Huang, Lin Chen, Ze-Hui Chen, Feng Zhao

arXiv.org

DOI

2026

Scaling Agentic Data for Long-Horizon Terminal Intelligence

Shun Zou, Zi-Yu Ma, Yi Zou, Yong Wang, Lin Chen, Ze-Hui Chen, Guan-Hua Chen, Xiang-Xiang Chu, Feng Zhao

2026

GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis

Qi-Sheng Su, Han-Chen Wang, Guang Zhu, Hui Jiang, Qiuyinzhe Zhang, Kou Shi, Zhen Fang, Ziao Zhang, Qing-Nan Ren, Honglin Guo, Ze-Hui Chen, Tao Gui, Feng Zhao

2026

Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent

Zhen Fang, Yu Zeng, Wen-Xuan Huang, Yi-Ming Zhao, Shi-Ting Huang, Tian-Fei Ren, Qiutinglu Lu, Qing-Nan Ren, Qi-Sheng Su, Lionel Z. Wang, Qingyu Yin, Shuang Chen, Ze-Hui Chen, Lin Chen, Zhenfei Yin, Yao Hu, Shaohui Lin, Wan-Li Ouyang, Shao-Sheng Cao, Feng Zhao

2026

SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering

Qing-Nan Ren, Shunyu Zou, Shi-Ting Huang, Ziao Zhang, Kou Shi, Zhen Fang, Yi-Ming Zhao, Yu Zeng, Qi-Sheng Su, Lin Chen, Yong Wang, Ze-Hui Chen, Xiangxiang Chu, Feng Zhao

arXiv.org

DOI

2026

Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models

Shi-Ting Huang, Ze-Cheng Li, Yu Zeng, Qing-Nan Ren, Zhen Fang, Qi-Sheng Su, K. Shi, Lin Chen, Ze-Hui Chen, Feng Zhao

arXiv.org

DOI

2026

AsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task Scenarios

Kou Shi, Ziao Zhang, Shi-Ting Huang, Avery Nie, Zhen Fang, Qiuchen Wang, Lin Chen, Huaian Chen, Ze-Hui Chen, Feng Zhao

arXiv.org

DOI

2026

PRG-Fusion: Orchestrating Generative Priors with Reconstruction Evidence for Driving View Synthesis

Si-Peng He, Jia-Lei Chen, Zhen Fang, Dong-Chun Ren, Feng Zhao

2026

VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation

Yi-Ming Zhao, Yu Zeng, Wen-Xuan Huang, Zhen Fang, Qing Miao, Qi Su, Jiawei Zhao, Jia-Yin Cai, Lin Chen, Ze-Hui Chen, Yukun Qi, Yao Hu, Xiao-Long Jiang, Feng Zhao

arXiv.org

DOI

2026

Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning

Qi-Sheng Su, Shi-Ting Huang, Zhen Fang, Zian Chen, Ze-Hui Chen, Feng Zhao

Annual Meeting of the Association for Computational Linguistics

DOI

2026

Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models

Wen-Xuan Huang, Yu Zeng, Qiuchen Wang, Zhen Fang, Shao-Sheng Cao, Zheng Chu, Qingyu Yin, Shuang Chen, Zhenfei Yin, Lin Chen, Ze-Hui Chen, Xu Tang, Yao Hu, Shaohui Lin, P. Torr, Feng Zhao, Wan-Li Ouyang

arXiv.org

DOI

2026

SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation

Tian-Fei Ren, Zhipeng Yan, Yi-Ming Zhao, Zhen Fang, Yu Zeng, Guo-Hui Zhang, Hang Xu, Xiaoxiao Ma, Shi-Ting Huang, Ke Xu, Wen-Xuan Huang, Lionel Z. Wang, Lin Chen, Ze-Hui Chen, Jie Huang, Feng Zhao

arXiv.org

DOI

2026

VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

Hao-Dong Li, Tian-Fei Ren, Xiao-Xiao Ma, Chun-Mei Qing, Zhen Fang, Si-Peng He, Ziyu Guo, Hao-Yu Wu, Juan-Xi Tian, Yihang Zou, Rui-Chuan An, Dongzhi Jiang, Bo-Xue Yang, Ji Xie, Xuanyun Huang, Wen-Hao Yan, Jialv Zou, Zheng-Rong Yue, Ya-Xin Luo, Xiao-Tong Li, Yuzhu Wang, Jun-Yan Ye, Jin-Jing Zhao, Ze-Hui Chen, Lin Chen, Ren-Ye Yan, Feng Zhao, Pheng-Ann Heng

arXiv.org

DOI

2026

ACC: Compiling Agent Trajectories for Long-Context Training

Qi-Sheng Su, Zhen Fang, Shi-Ting Huang, Yu Zeng, Yi-Ming Zhao, Kou Shi, Ziao Zhang, Lin Chen, Ze-Hui Chen, Lijun Wu, Feng Zhao

arXiv.org

DOI

2026

ADORA: Training Reasoning Models with Dynamic Advantage Estimation on Reinforcement Learning

Qing-Nan Ren, Shi-Ting Huang, Zhen Fang, Ze-Hui Chen, Lin Chen, Lijun Li, Feng Zhao

arXiv.org

DOI

2026

UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision

R. Han, Zhen Fang, Xin-Yu Sun, Yuchen Ma, Zi-Heng Wang, Yu Zeng, Ze-Hui Chen, Lin Chen, Wen-Xuan Huang, Wei-Jie Xu, Yi Cao, Feng Zhao

Annual Meeting of the Association for Computational Linguistics

DOI

2026

Flow-OPD: On-Policy Distillation for Flow Matching Models

Zhen Fang, Wen-Xuan Huang, Yu Zeng, Yi-Ming Zhao, Shuang Chen, Kai-Tuo Feng, Yunlong Lin, Lin Chen, Ze-Hui Chen, Shao-Sheng Cao, Feng Zhao

arXiv.org

DOI

2026

FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis

Kou Shi, Zun Wang, Qi-Sheng Su, Shi-Ting Huang, Ziao Zhang, Zhen Fang, Qing-Nan Ren, Jin Liu, Yu Zeng, Yi-Ming Zhao, Lin Chen, Ze-Hui Chen, Feng Zhao

2026

ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling

Xin-Ge Peng, Zhen Fang, Rui-Bing Wang, Yong-Xuan Lv, Hao-Dong Li, Guo-Hui Zhang, Xiao-Xiao Ma, Yi-Ting Lu, Lin Chen, Ze-Hui Che, Feng Zhao

2025

《中国图象图形学报》视觉状态空间模型及应用专栏简介

王兴刚，张长青，任文琦，傅雪阳，周涛，赵峰，石争浩，陈秀妍

《中国图象图形学报》

2025

VFM-Adapter: Adapting Visual Foundation Models for Dense Prediction with Dynamic Hybrid Operation Mapping

Zheng Chen, Yu Zeng, Ze-Hui Chen, Hongzhi Gao, Lin Chen, Jiaming Liu, Feng Zhao

AAAI Conference on Artificial Intelligence

DOI

2025

Enhancing Large Vision-Language Models with Ultra-Detailed Image Caption Generation

Yu Zeng, Yukun Qi, Yi-Ming Zhao, Xikun Bao, Lin Chen, Ze-Hui Chen, Shi-Ting Huang, Jie Zhao, Feng Zhao

Conference on Empirical Methods in Natural Language Processing

DOI

2025

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

Qiuchen Wang, Rui-Xue Ding, Yu Zeng, Ze-Hui Chen, Lin Chen, Shi-Hang Wang, Peng-Jun Xie, Fei Huang, Feng Zhao

Neural Information Processing Systems

DOI

2025

V2P-Bench: Evaluating Video-Language Understanding with Visual Prompts for Better Human-Model Interaction

Yi-Ming Zhao, Yu Zeng, Yukun Qi, Yao-Yang Liu, Xikun Bao, Lin Chen, Ze-Hui Chen, Qing Miao, Chen-Xi Liu, Jie Zhao, Feng Zhao

arXiv.org

DOI

2025

VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning

Yukun Qi, Yi-Ming Zhao, Yu Zeng, Xikun Bao, Wenxuan Huang, Lin Chen, Ze-Hui Chen, Jie Zhao, Zhongang Qi, Feng Zhao

arXiv.org

DOI

2025

CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios

Shi-Ting Huang, Zhen Fang, Ze-Hui Chen, Siyu Yuan, Junjie Ye, Yu Zeng, Lin Chen, Qiqi Mao, Feng Zhao

Conference on Empirical Methods in Natural Language Processing

DOI

2025

DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Action

Zhen Fang, Zhuo-Yang Liu, Jiaming Liu, Hao Chen, Yu Zeng, Shi-Ting Huang, Ze-Hui Chen, Lin Chen, Shang-Hang Zhang, Feng Zhao

arXiv.org

DOI

2025

Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models

Yu Zeng, Wen-Xuan Huang, Shi-Ting Huang, Xikun Bao, Yukun Qi, Yi-Ming Zhao, Qiuchen Wang, Lin Chen, Ze-Hui Chen, Huaian Chen, Wan-Li Ouyang, Feng Zhao

arXiv.org

DOI

2025

Gaussian Variation Field Diffusion for High-Fidelity Video-to-4D Synthesis

Bowen Zhang, Sicheng Xu, Chuxin Wang, Jiaolong Yang, Feng Zhao, Dong Chen, Baining Guo

IEEE/CVF International Conference on Computer Vision (ICCV)

DOI

2024

基于改进目标检测的动态场景SLAM研究

史蓝兮，颜文旭，倪宏宇，赵峰

《系统仿真学报》

DOI

2024

MindSearch: Mimicking Human Minds Elicits Deep AI Searcher

Ze-Hui Chen, Kui-Kun Liu, Qiuchen Wang, Jiang-Ning Liu, Wen-Wei Zhang, Kai Chen, Feng Zhao

International Conference on Learning Representations

DOI

2024

Are We on the Right Way for Evaluating Large Vision-Language Models?

Lin Chen, Jinsong Li, Xiao-Wen Dong, Pan Zhang, Yuhang Zang, Ze-Hui Chen, Haodong Duan, Jiaqi Wang, Yu Qiao, Da-Hua Lin, Feng Zhao

Neural Information Processing Systems

DOI

2024

Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models

Zehui Chen, Kuikun Liu, Qiuchen Wang, Wenwei Zhang, Jiangning Liu, Dahua Lin, Kai Chen, Feng Zhao

DOI

2024

ShareGPT4Video: Improving Video Understanding and Generation with Better Captions

Lin Chen, Xilin Wei, Jinsong Li, Xiao-Wen Dong, Pan Zhang, Yuhang Zang, Ze-Hui Chen, Haodong Duan, Bin Lin, Zhen-Yu Tang, Li Yuan, Yu Qiao, Da-Hua Lin, Feng Zhao, Jiaqi Wang

Neural Information Processing Systems

DOI

2023

一种新的分段式细粒度正则化的鲁棒跟踪算法

安志勇，梁顺楷，李博，赵峰，窦全胜，相忠良

《自动化学报》

DOI

2023

T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step

Zehui Chen, Weihua Du, Wen-Wei Zhang, Kui-Kun Liu, Jiang-Ning Liu, Miao Zheng, Jing-Ming Zhuo, Song-Yang Zhang, Da-Hua Lin, Kai Chen, Feng Zhao

Annual Meeting of the Association for Computational Linguistics

DOI

2023

ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

Lin Chen, Jinsong Li, Xiao-Wen Dong, Pan Zhang, Cong-Hui He, Jiaqi Wang, Feng Zhao, Da-Hua Lin

European Conference on Computer Vision

DOI

2022

RelCLIP: Adapting Language-Image Pretraining for Visual Relationship Detection via Relational Contrastive Learning

Yi Zhu, Zhaoqing Zhu, Bingqian Lin, Xiaodan Liang, Feng Zhao, Jianzhuang Liu

Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI

2018

基于多识别区域融合的机动车驾驶员检测框架

霍星，檀结庆，赵峰，景永俊，邵堃

《模式识别与人工智能》

2013

流数据概念漂移的检测算法

张杰，赵峰

《控制与决策》

2012

复杂背景中红外弱小目标检测技术研究

赵峰

《上海航天(中英文)》

2010

一种基于奇异值分解的图像匹配算法

赵峰，黄庆明，高文

《计算机研究与发展》

2008

基于核空间中最优变换和聚类中心的鉴别特征提取

张宏怡，张军英，赵峰

《计算机研究与发展》

2008

基于核最优变换与聚类中心的雷达目标识别

赵峰，张军英，刘敬

《控制与决策》

2008

一种改善支撑向量域描述性能的核优化算法

赵峰，张军英，刘敬

《自动化学报》

2008

基于direct LDA的幅度谱子空间雷达目标识别

刘敬，张军英，赵峰

《系统工程与电子技术》

2008

基于Gamma-SLC混合密度估计的雷达目标识别

赵峰，张军英，刘敬，梁军利

《系统工程与电子技术》

2007

基于SVM与非参数LDA的雷达自动目标识别

刘敬，张军英，赵峰

《控制与决策》

DOI

2007

一种KPCA的快速算法

赵峰，张军英

《控制与决策》

2007

天空背景下红外小目标检测算法

左康怀，赵峰

《科技资讯》

2001

一种基于雷达回波序列相关特征的目标检测方法

张晨，王永良，赵峰

《空天预警研究学报》

2001

红外精跟踪高帧频数字图像信号实时处理技术的研究

赵峰，吴常泳，李范鸣

《红外》

精选作品

期刊论文

融合多尺度上下文与 Mamba 时序建模的 Himawari-8/9 卫星火点检测

动态自适应的3D高斯溅射稠密视觉SLAM算法

Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs

Breaking Block Boundaries: Anchor-based History-stable Decoding for Diffusion Large Language Models

SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents

Scaling Agentic Data for Long-Horizon Terminal Intelligence

GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis

Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent

SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering

Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models

AsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task Scenarios

PRG-Fusion: Orchestrating Generative Priors with Reconstruction Evidence for Driving View Synthesis

VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation

Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning

Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models

SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation

VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

ACC: Compiling Agent Trajectories for Long-Context Training

ADORA: Training Reasoning Models with Dynamic Advantage Estimation on Reinforcement Learning

UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision

Flow-OPD: On-Policy Distillation for Flow Matching Models

FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis

ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling

《中国图象图形学报》视觉状态空间模型及应用专栏简介

VFM-Adapter: Adapting Visual Foundation Models for Dense Prediction with Dynamic Hybrid Operation Mapping

Enhancing Large Vision-Language Models with Ultra-Detailed Image Caption Generation

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

V2P-Bench: Evaluating Video-Language Understanding with Visual Prompts for Better Human-Model Interaction

VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning

CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios

DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Action

Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models

Gaussian Variation Field Diffusion for High-Fidelity Video-to-4D Synthesis

基于改进目标检测的动态场景SLAM研究

MindSearch: Mimicking Human Minds Elicits Deep AI Searcher

Are We on the Right Way for Evaluating Large Vision-Language Models?

Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models

ShareGPT4Video: Improving Video Understanding and Generation with Better Captions

一种新的分段式细粒度正则化的鲁棒跟踪算法

T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step

ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

RelCLIP: Adapting Language-Image Pretraining for Visual Relationship Detection via Relational Contrastive Learning

基于多识别区域融合的机动车驾驶员检测框架

流数据概念漂移的检测算法

复杂背景中红外弱小目标检测技术研究

一种基于奇异值分解的图像匹配算法

基于核空间中最优变换和聚类中心的鉴别特征提取

基于核最优变换与聚类中心的雷达目标识别

一种改善支撑向量域描述性能的核优化算法

基于direct LDA的幅度谱子空间雷达目标识别

基于Gamma-SLC混合密度估计的雷达目标识别

基于SVM与非参数LDA的雷达自动目标识别

一种KPCA的快速算法

天空背景下红外小目标检测算法

一种基于雷达回波序列相关特征的目标检测方法

红外精跟踪高帧频数字图像信号实时处理技术的研究

会议论文

RGB-D Indoor Object Recognition Algorithm Based on Fusion Convolutional Neural Network

研究方向