刘利斌｜北京大学｜学者主页

期刊论文

2026

DexterCap: Affordable and Automated Capture of Complex Hand‐Object Interactions

Yutong Liang, Shiyi Xu, Y.Q. Zhang, Bowen Zhan, He Zhang, Libin Liu

Computer Graphics Forum

DOI

2025

Learning and aggregating principal semantics for semantic edge detection in images

Lijun Dong, Wei Ma, Libin Liu, Hongbin Zha

Expert Systems With Applications，Vol. 265

DOI

2025

Social Agent: Mastering Dyadic Nonverbal Behavior Generation via Conversational LLM Agents

Zeyi Zhang, Yan-Jun Zhou, Heyuan Yao, Teng-Long Ao, Xiaohang Zhan, Libin Liu

ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia

DOI

2025

Towards Reliable Human Evaluations in Gesture Generation: Insights from a Community-Driven State-of-the-Art Benchmark

Rajmund Nagy, Hendric Voss, Thanh Hoang-Minh, Mihail Tsakov, Teodor Nikolov, Zeyi Zhang, Teng-Long Ao, Si-Cheng Yang, Shao-Li Huang, Yongkang Cheng, M. Mughal, Rishabh Dabral, Kiran Chhatre, C. Theobalt, Libin Liu, Stefan Kopp, Rachel McDonnell, Michael Neff, T. Kucherenko, Youngwoo Yoon, Gustav Eje Henter Kth Royal Institute of Technology, Bielefeld University, U. O. S. -. Vnuhcm, Independent Researcher, AB Motorica, Peking University, Huawei Technologies Co. Ltd., Astribot, Max Planck Institute for Informatics, Šić, T. C. Dublin, U. California, Davis, S. Arts, Electronics, Telecommunications Research Institute

2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition- FINDINGS Track (CVPRF)

DOI

2025

Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds

Weihao Tan, Xiangyang Li, Yun-Hao Fang, Heyuan Yao, Shi Yan, Hao Luo, Teng-Long Ao, Huihui Li, Hongbin Ren, Bai-Ren Yi, Yujia Qin, Bo An, Libin Liu, Guang Shi

arXiv.org

DOI

2025

Graph Canvas for Controllable 3D Scene Generation

Libin Liu, Shen Chen, Sen Jia, Jing-Zhe Shi, Can Jin, Zongkai Wu, Jenq-Neng Hwang, Lei Li

ACM Multimedia

DOI

2025

Learning Uniformly Distributed Embedding Clusters of Stylistic Skills for Physically Simulated Characters

Nian Liu, Zilong Zhang, Zi Wang, Tengyu Liu, Hongzhao Xie, Xinyi Tong, Libin Liu, Yaodong Yang, Zhaofeng He

ACM International Conference on Multimedia (ACM MM)

DOI

2024

室内场景拟人交互研究进展

杜韬，胡瑞珍，刘利斌，弋力，赵昊

《中国图象图形学报》

2024

CPoser: An Optimization-after-Parsing Approach for Text-to-Pose Generation Using Large Language Models

Yumeng Li, Bohong Chen, Zhong Ren, Yao-Xiang Ding, Libin Liu, Tianjia Shao, Kun Zhou

ACM Transactions on Graphics

DOI

2024

Semantic Gesticulator: Semantics-Aware Co-Speech Gesture Synthesis

Zeyi Zhang, Tenglong Ao, Yuyao Zhang, Qingzhe Gao, Chuan Lin, Baoquan Chen, Libin Liu

ACM Transactions on Graphics

DOI

2024

MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations

Heyuan Yao, Zhenhua Song, Yuyang Zhou, Tenglong Ao, Baoquan Chen, Libin Liu

ACM Transactions on Graphics

DOI

2023

Robust Dancer: Long-term 3D Dance Synthesis Using Unpaired Data

Bin Feng, Teng-Long Ao, Zequn Liu, Wei Ju, Libin Liu, Ming Zhang

arXiv.org

DOI

2023

GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents

Teng-Long Ao, Ze-Yi Zhang, Libin Liu

ACM Transactions on Graphics

DOI

2022

MotionBERT: A Unified Perspective on Learning Human Motion Representations

Wenjie Zhu, Xiaoxuan Ma, Zhaoyang Liu, Libin Liu, Wayne Wu, Yi-Zhou Wang

IEEE International Conference on Computer Vision

DOI

2022

Learning to use chopsticks in diverse gripping styles

Ze-Shi Yang, Kang-Kang Yin, Libin Liu

ACM Transactions on Graphics

DOI

2022

Rhythmic Gesticulator

Teng-Long Ao, Qingzhe Gao, Yuke Lou, Bao-Quan Chen, Libin Liu

ACM Transactions on Graphics

DOI

2022

ControlVAE

Heyuan Yao, Zhenhua Song, Bao-Quan Chen, Libin Liu

ACM Transactions on Graphics

DOI

2022

Neural3Points: Learning to Generate Physically Realistic Full‐body Motion for Virtual Reality Users

Yong-Jing Ye, Libin Liu, Lei Hu, Shihong Xia

Computer graphics forum (Print)

DOI

2021

Camera keyframing with style and control

Hongda Jiang, M. Christie, Xi Wang, Libin Liu, Bin Wang, Bao-Quan Chen

ACM Transactions on Graphics

DOI

2021

Learning skeletal articulations with neural blend shapes

Peizhuo Li, Kfir Aberman, Rana Hanocka, Libin Liu, O. Sorkine-Hornung, Bao-Quan Chen

ACM Transactions on Graphics

DOI

2018

Learning basketball dribbling skills using trajectory optimization and deep reinforcement learning

Libin Liu, J. Hodgins

ACM Transactions on Graphics

DOI

2018

Simulation for Control

Kang-Kang Yin, Libin Liu, M. van de Panne

Humanoid Robotics: A Reference

DOI

2017

Learning to schedule control fragments for physics-based characters using deep Q-learning

Libin Liu, J. Hodgins

TOGS

DOI

2017

Learning to Schedule Control Fragments for Physics-Based Characters Using Deep Q-Learning

Libin Liu, J. Hodgins

ACM Transactions on Graphics

DOI

2016

Guided Learning of Control Graphs for Physics-Based Characters

Libin Liu, M. van de Panne, Kang-Kang Yin

ACM Transactions on Graphics

DOI

2015

Learning reduced-order feedback policies for motion skills

Kai Ding, Libin Liu, M. van de Panne, Kang-Kang Yin

Symposium on Computer Animation

DOI

2015

Improving Sampling‐based Motion Control

Libin Liu, Kang-Kang Yin, B. Guo

Computer graphics forum (Print)

DOI

2013

Simulation and control of skeleton-driven soft body characters

Libin Liu, Kang-Kang Yin, Bin Wang, B. Guo

ACM Transactions on Graphics

DOI

2012

Terrain runner

Libin Liu, Kang-Kang Yin, M. van de Panne, B. Guo

ACM Transactions on Graphics

DOI

2010

Sampling-based contact-rich motion control

Libin Liu, Kang-Kang Yin, M. van de Panne, Tian-Jia Shao, Weiwei Xu

ACM Transactions on Graphics

DOI

预印本

2026

MuGen: Multi-Skill Generative Locomotion Controller for Humanoid Robots

Yusen Feng, Xiang Wang, Heyuan Yao, Zixi Kang, Xinyu Huo, Boyang Yu, Pengyun Qiu, Ruijie Zhao, Baoquan Chen, Libin Liu

arXiv (Cornell University)

DOI

2026

ProAct: Harnessing Streaming Motion Generation and Agentic Reasoning for Real-Time Embodied Social Interaction

Zeyi Zhang, Kang, Zixi, Ruijie Zhao, Yusen Feng, Jiang, Biao, Hanyu Ji, Libin Liu

arXiv (Cornell University)

DOI

刘利斌

精选作品

期刊论文

DexterCap: Affordable and Automated Capture of Complex Hand‐Object Interactions

Learning and aggregating principal semantics for semantic edge detection in images

Social Agent: Mastering Dyadic Nonverbal Behavior Generation via Conversational LLM Agents

Towards Reliable Human Evaluations in Gesture Generation: Insights from a Community-Driven State-of-the-Art Benchmark

Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds

Graph Canvas for Controllable 3D Scene Generation

Learning Uniformly Distributed Embedding Clusters of Stylistic Skills for Physically Simulated Characters

室内场景拟人交互研究进展

CPoser: An Optimization-after-Parsing Approach for Text-to-Pose Generation Using Large Language Models

Semantic Gesticulator: Semantics-Aware Co-Speech Gesture Synthesis

MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations

Robust Dancer: Long-term 3D Dance Synthesis Using Unpaired Data

GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents

MotionBERT: A Unified Perspective on Learning Human Motion Representations

Learning to use chopsticks in diverse gripping styles

Rhythmic Gesticulator

ControlVAE

Neural3Points: Learning to Generate Physically Realistic Full‐body Motion for Virtual Reality Users

Camera keyframing with style and control

Learning skeletal articulations with neural blend shapes

Learning basketball dribbling skills using trajectory optimization and deep reinforcement learning

Simulation for Control

Learning to schedule control fragments for physics-based characters using deep Q-learning

Learning to Schedule Control Fragments for Physics-Based Characters Using Deep Q-Learning

Guided Learning of Control Graphs for Physics-Based Characters

Learning reduced-order feedback policies for motion skills

Improving Sampling‐based Motion Control

Simulation and control of skeleton-driven soft body characters

Terrain runner

Sampling-based contact-rich motion control

预印本

MuGen: Multi-Skill Generative Locomotion Controller for Humanoid Robots

ProAct: Harnessing Streaming Motion Generation and Agentic Reasoning for Real-Time Embodied Social Interaction

研究方向