Zongqing Lu

Peking University — China

Computer Science · Physical Sciences

25h-index2.2kcitations183works1.12yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Reinforcement Learning in Robotics(43), Advanced Vision and Imaging(17), Advanced Image and Video Retrieval Techniques(14), Caching and Content Delivery(13), Advanced Neural Network Applications(12)

Publications183 total

Universal Dexterous Functional Grasping via Demonstration-Editing Reinforcement Learning
arXiv (Cornell University)·2025Open Access
Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos
arXiv (Cornell University)·2025Open Access
GTR-Turbo: Merged Checkpoint is Secretly a Free Teacher for Agentic VLM Training
arXiv (Cornell University)·2025Open Access
Robust Motion Generation using Part-level Reliable Data from Videos
arXiv (Cornell University)·2025Open Access
DiG-Flow: Discrepancy-Guided Flow Matching for Robust VLA Models
arXiv (Cornell University)·2025Open Access
CROSSER: Learning Generalizable Humanoid Locomotion Through Inverse Dynamics-Guided Cross-Simulator Adaptation
IEEE Robotics and Automation Letters·2025
NOLO: Navigate Only Look Once
2025
Towards Proprioception-Aware Embodied Planning for Dual-Arm Humanoid Robots
arXiv (Cornell University)·2025Open Access
Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos
ArXiv.org·2025Open Access
Unified Multimodal Understanding via Byte-Pair Visual Encoding
arXiv (Cornell University)·2025Open Access
RL from Physical Feedback: Aligning Large Motion Models with Humanoid Control
arXiv (Cornell University)·2025Open Access
From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robots
arXiv (Cornell University)·2025Open Access
Micro-ring resonator assisted spiking neural network for efficient object detection
Optics Letters·2025· 1 cited
JAEGER: Dual-Level Humanoid Whole-Body Controller
arXiv (Cornell University)·2025Open Access
UV Gaussians: Joint learning of mesh deformation and Gaussian textures for human avatar modeling
Knowledge-Based Systems·2025· 7 cited
Taking Notes Brings Focus? Towards Multi-Turn Multimodal Dialogue Learning
2025Open Access
VideoOrion: Tokenizing Object Dynamics in Videos
arXiv (Cornell University)·2024Open Access
Reinforcement Learning Friendly Vision-Language Model for Minecraft
Lecture notes in computer science·2024· 2 cited
Pre-trained Visual Dynamics Representations for Efficient Policy Learning
arXiv (Cornell University)·2024Open Access
Visual Grounding for Object-Level Generalization in Reinforcement Learning
Lecture notes in computer science·2024· 3 cited
page 1 of 10Next →

Frequent Co-authors

Thomas La Porta(10), Guohong Cao(8), Jiechuan Jiang(7), Yonggang Wen(7), Xiao Sun(6), Kevin Chan(6), Swati Rallapalli(3), Ben Niu(3), Xiu Li(3), Qingmin Liao(2), Jing‐Hao Xue(2), Chen Dun(2), Weizhan Zhang(2), Qinghua Zheng(2), Tiejun Huang(2), Jiechuang Jiang(2), Yaodong Yang(2), Hui Li(2), Hao Dong(2), Shiliang Pu(2)