Research

* equal contribution   ✉ corresponding author

Preprints

Teaser for Afford-X: A Generalizable and Slim Affordance Reasoning Framework for Task-oriented Manipulation

Afford-X: A Generalizable and Slim Affordance Reasoning Framework for Task-oriented Manipulation

*  Yuyang Li *  Leiyao Cui     Huan-ang Gao   Yixin Zhu ✉  Hao Zhao ✉ 

We develop Afford-X, an end-to-end trainable affordance reasoning model that incorporates Verb Attention and Bi-Fusion modules to improve multi-modal understanding.

arXiv Code Video Website
Citation history for Afford-X: A Generalizable and Slim Affordance Reasoning Framework for Task-oriented Manipulation 5 citations
Preprint 2025

Publications

Teaser for Taccel: Scaling Up Vision-based Tactile Robotics via High-performance GPU Simulation

Taccel: Scaling Up Vision-based Tactile Robotics via High-performance GPU Simulation

Yuyang Li *  Wenxin Du *  Chang Yu *  Puhao Li   Zihang Zhao   Tengyu Liu   Chenfanfu Jiang ✉  Yixin Zhu ✉  Siyuan Huang ✉ 

Taccel is a high-performance GPU-based simulator, combining ABD and IPC, for simulating robots with vision-based tactile sensors.

Paper Code Website / Docs Video Mention in NVIDIA Tech Blog Mention in Linux Foundation Mention in GTC Paris
Citation history for Taccel: Scaling Up Vision-based Tactile Robotics via High-performance GPU Simulation 11 citations
NeurIPS 2025 (Spotlight) 2025
Teaser for RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning

RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning

Haoran Geng *  Feishi Wang *  Songlin Wei *  Yuyang Li *  Bangjun Wang *  Boshi An *  Charlie Tianyue Cheng *  Haozhe Lou   Peihao Li   Yen-Jen Wang   Yutong Liang   Dylan Goetting   Chaoyi Xu   Haozhe Chen   Yuxi Qian   Yiran Geng   Jiageng Mao   Weikang Wan   Mingtong Zhang   Jiangran Lyu   Siheng Zhao   Jiazhao Zhang   Jialiang Zhang   Chengyang Zhao   Haoran Lu   Yufei Ding   Ran Gong     Yuxuan Kuang   Ruihai Wu   Baoxiong Jia   Carlo Sferrazza   Hao Dong   Siyuan Huang     Yue Wang   Jitendra Malik   Pieter Abbeel  

A comprehensive framework comprising a simulation platform, a synthetic dataset, and unified benchmarks.

Paper Code Website Docs
Citation history for RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning 35 citations
Robotics: Science and Systems (R:SS) 2025 2025
Teaser for GenDexGrasp: Generalizable Dexterous Grasping

GenDexGrasp: Generalizable Dexterous Grasping

Puhao Li *  Tengyu Liu *  Yuyang Li   Yiran Geng   Yaodong Yang   Yixin Zhu   Siyuan Huang ✉ 

We propose GenDexGrasp, a versatile dexterous grasping method that can generalize to out-of-domain robotic hands. In addition, we contribute MultiDex, a large-scale synthetic dexterous grasping dataset.

Website arXiv PDF Code
Citation history for GenDexGrasp: Generalizable Dexterous Grasping 131 citations
ICRA 2023 2023
Teaser for Embedding high-resolution touch across robotic hands enables adaptive human-like grasping

Embedding high-resolution touch across robotic hands enables adaptive human-like grasping

Zihang Zhao *  Wanlin Li *  Yuyang Li *  Tengyu Liu *  Boren Li   Meng Wang   Kai Du   Hangxin Liu ✉  Yixin Zhu ✉  Qining Wang   Kaspar Althoefer ✉  Song-Chun Zhu  

We design F-TAC Hand, a five-finger biomimetic hand featuring high-resolution tactile sensing across the hand. This design enables adaptive human-like grasping and unlocks more capabilities.

arXiv Code Website Video Science Robotics Editors' Choice 人民日报 新华网 中国新闻网 光明网 TechXplore 中国科技网 中国科学报 北大新闻网 北大新工科 北大AI院官微 北大AI院官网
Citation history for Embedding high-resolution touch across robotic hands enables adaptive human-like grasping 57 citations
Nature Machine Intelligence 2025
Teaser for ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning

ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning

Kailin Li   Puhao Li   Tengyu Liu   Yuyang Li   Siyuan Huang ✉ 

A novel two-stage method for efficiently transferring human bimanual skills to dexterous robotic hands in simulation.

Website arXiv Code Data
Citation history for ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning 65 citations
CVPR 2025 2025