Humanoid robotics · Whole-body control· Reinforcement learning

Junli Ren 任峻立

I am a final-year PhD student at HKU MMLab, advised by Prof. Ping Luo. My research focuses on whole-body control, reinforcement learning, and human–object interaction. I am currently visiting BAIR at UC Berkeley under the supervision of Prof. Masayoshi Tomizuka.

Previously, I was a research intern with the Humanoid Research team at Shanghai AI Lab, working with Dr. Jiangmiao Pang and Dr. Jingbo Wang. I received my M.Eng. and B.Eng. from Tsinghua University under Prof. Guijin Wang, where I also interned in Bytedance and Tsinghua AIR.

Email Google Scholar X / Twitter LinkedIn

Selected publications

01

Locomotion

Robust and agile mobility across challenging terrain.

VB-Com project preview
ICRA 2026

VB-Com: Learning Vision-Blind Composite Humanoid Locomotion Against Deficient Perception

Junli Ren, Tao Huang, Huayi Wang, Zirui Wang, Qingwei Ben, Junfeng Long, Yanchao Yang, Jiangmiao Pang†, Ping Luo†

A composite framework that switches between vision and blind policies under perceptual deficiency.

ProjectPaperVideoBibTeX
BeamDojo project preview
RSS 2025

BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds

Huayi Wang, Zirui Wang, Junli Ren, Qingwei Ben, Tao Huang, Weinan Zhang, Jiangmiao Pang†

Agile real-world locomotion with precise foot placement on sparse footholds.

ProjectPaperVideoBibTeX
HoST project preview
RSS 2025Best Systems Paper Finalist

Learning Humanoid Standing-up Control across Diverse Postures

Tao Huang, Junli Ren, Huayi Wang, Zirui Wang, Qingwei Ben, Muning Wen, Xiao Chen, Jianan Li, Jiangmiao Pang†

HoST learns smooth, robust standing-up control from scratch across diverse real-world postures.

ProjectPaperVideoCodeBibTeX
PIM project preview
ICRA 2025

Learning Humanoid Locomotion with Perceptive Internal Model

Junfeng Long*, Junli Ren*, Moji Shi*, Zirui Wang, Tao Huang, Ping Luo, Jiangmiao Pang†

Perceptive internal models estimate environmental disturbances for agile, robust humanoid locomotion.

ProjectPaperCodeBibTeX
03

High-dynamic whole-body sports

Fast, expressive interaction that couples perception with full-body control.

SMASH humanoid outdoor table tennis
IEEE T-RO

SMASH: Mastering Scalable Whole-Body Skills for Humanoid Ping-Pong with Egocentric Vision

Junli Ren†,*, Yinghui Li†,*, Kai Zhang*, Penglin Fu*, Haoran Jiang, Yixuan Pan, Guangjun Zeng, Tao Huang, Weizhong Guo, Peng Lu, Tianyu Li, Jingbo Wang, Li Chen, Hongyang Li, Ping Luo†

Scalable whole-body skill learning and onboard egocentric vision for agile humanoid table tennis.

ProjectPaperVideoBibTeX
Humanoid Goalkeeper project preview
Preprint

Humanoid Goalkeeper: Learning from Position Conditioned Task-Motion Constraints

Junli Ren*, Junfeng Long*, Tao Huang, Huayi Wang, Zirui Wang, Feiyu Jia, Wentao Zhang, Jingbo Wang†, Ping Luo†, Jiangmiao Pang†

A single end-to-end policy performs agile, human-like ball interception and evasive motions.

ProjectPaperVideoCode
AdaMimic project preview
ICRA 2026 · Oral

AdaMimic: Towards Adaptable Humanoid Control via Adaptive Motion Tracking

Tao Huang, Huayi Wang, Junli Ren, Kangning Yin, Zirui Wang, Xiao Chen, Feiyu Jia, Wentao Zhang, Junfeng Long, Jingbo Wang†, Jiangmiao Pang†

Adaptive motion tracking enables diverse humanoid behaviors from a single reference motion.

ProjectPaperVideoCode
04

General whole-body tasks

Adaptable skills for scene interaction and contact-rich manipulation.

CLIFT paper preview
Preprint · 2026

CLIFT: Turning Gemini Robotics On-Device into Humanoid Specialists via Non-Invasive Closed-Loop Iterative Fine-Tuning

Yuxin Chen, Hari Srikanth, Nathan Jew, Menglin Wu, Pengcheng Wang, Junli Ren, Masayoshi Tomizuka, Peng Xu, Jinyu Xie, Thomas Tian

Closed-loop reward feedback becomes API-compatible supervised data for contact-rich humanoid specialization.

PaperPDF
PhysHSI motion, interaction and deployment framework
Preprint

PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System

Huayi Wang*, Wentao Zhang*, Runyi Yu*, Tao Huang, Junli Ren, Feiyu Jia, Zirui Wang, Xiaojie Niu, Xiao Chen, Jiahe Chen, Qifeng Chen†, Jingbo Wang†, Jiangmiao Pang†

A physical-world system for diverse, natural, and autonomous humanoid-scene interaction.

ProjectPaperVideoCode
WeChat QR code for renjunli