Fangwei Zhong

Peking University — China

Computer Science · Physical Sciences

14h-index1.1kcitations57works0.52yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Video Surveillance and Tracking Methods(18), Reinforcement Learning in Robotics(13), Human Pose and Action Recognition(10), Advanced Neural Network Applications(6), Robot Manipulation and Learning(6)

Publications57 total

Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia
arXiv (Cornell University)·2025Open Access
VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language Models
2025· 1 cited
TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking
arXiv (Cornell University)·2025Open Access
DualGF: Example-Driven Path Planning via Dual Gradient Fields
Lecture notes in computer science·2025
Reinforced Context Order Recovery for Adaptive Reasoning and Planning
arXiv (Cornell University)·2025Open Access
ReDMan: reliable dexterous manipulation with safe reinforcement learning
Machine Learning·2025· 1 cited
EmbRACE-3K: Embodied Reasoning and Action in Complex Environments
arXiv (Cornell University)·2025Open Access
TrackVLA: Embodied Visual Tracking in the Wild
arXiv (Cornell University)·2025Open Access
Communication-Efficient Desire Alignment for Embodied Agent-Human Adaptation
arXiv (Cornell University)·2025Open Access
VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language Models
arXiv (Cornell University)·2025Open Access
Hierarchical Instruction-aware Embodied Visual Tracking
arXiv (Cornell University)·2025Open Access
Clinical Inspired MRI Lesion Segmentation
2025
Clinical Inspired MRI Lesion Segmentation
arXiv (Cornell University)·2025Open Access
CoMet: Metaphor-Driven Covert Communication for Multi-Agent Language Games
2025Open Access
Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective
2025Open Access
Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective
arXiv (Cornell University)·2024Open Access
UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI
arXiv (Cornell University)·2024Open Access
Empowering Embodied Visual Tracking with Visual Foundation Models and Offline RL
Lecture notes in computer science·2024· 2 cited
SocialGFs: Learning Social Gradient Fields for Multi-Agent Reinforcement Learning
arXiv (Cornell University)·2024Open Access
Empowering Embodied Visual Tracking with Visual Foundation Models and Offline RL
arXiv (Cornell University)·2024Open Access
page 1 of 3Next →

Frequent Co-authors

Yizhou Wang(33), Wenhan Luo(8), Peng Sun(8), Churan Wang(6), Hai Ci(5), Mingdong Wu(5), Kui Wu(5), Weichao Qiu(4), Tong Zhang(4), Tingyun Yan(4), Jing Xu(4), Yaodong Yang(4), Hao Chen(4), Zhoujun Li(4), Wei Liu(3), Hao Dong(3), Yiming Zuo(3), Lingxi Xie(3), Alan Yuille(3), Jianwei Zhang(3)