Hi! I am Jianxiong Li, studying embodied AI and Reinforcement Learning (RL). I am a 4th-year PhD candidate at AIR, Tsinghua University, advised by Prof. Xianyuan Zhan and Prof. Ya-Qin Zhang. I got my bachelor's degree in 2021 from the School of Mechanical Engineering, Xi'an Jiaotong University, where I did lots of projects on mechanical design and robotics.
My dream is to develop robots that are universally deployable across diverse real-world environments. Towards this goal, my current work primarily focused on:
- (Efficient Pretrain) How to build robotic foundation models efficiently when robotics data are limited?
- (Fast Post-train) How to fastly enhance robot peformance given limited budget?
- (RL+X) How to use RL to reach super-human performance on diverse domains, like robots, VLMs or LLMs?
I am actively looking for postdoc and full time research positions on robot learning. Weclome to drop me an email if interested.
Some links: Github / Twitter / Google Scholar / li-jx21@mails.tsinghua.edu.cn
News
- One paper (LBP) on efficient latent planning is accepted to ICML 2025.
- One paper (UniAct) on cross-embodiment universal actions is accepted to CVPR 2025.
- πDiffusion-Planner is selected as oral presentation at ICLR 2025.
- Two papers on fast post-train (PSEC) and autonomous driving (Diffusion-Planner) are accepted to ICLR 2025.
- One paper (Robo-MUTUAL) on embodied representations is accepted to ICRA 2025.
- πOne paper (RSP) on offline RL is accepted to AAAI 2025 as oral.
- πIVM and DecisionNCE are selected as Outstanding Paper at MFM-EAI workshop @ ICML 2024.
- One paper (IVM) on embodied foundation multimodal models is accepted to NeurIPS 2024.
- One paper (DecisionNCE) on embodied multimodal representations is accepted to ICML 2024.
- πQPA is selected as spotlight presentation at ICLR 2024.
- Two papers on RLHF (QPA) and safe offline RL (FISOR) are accepted to ICLR 2024.
- πThree papers on offline RL (IVR, DOGE) and offline RL with imperfect rewards (RGM) are accepted to ICLR 2023, including one oral paper (IVR).
- πOne paper (POR) on offline RL is accepted to NeurIPS 2022 as oral.
Publications (* marks equal contribution)
- Universal Actions for Enhanced Embodied Foundation Models CVPR 2025 2025 Paper | Code | Page
- Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning ICRA 2025 2025 Paper | Code | Page
- Skill Expansion and Composition in Parameter Space ICLR 2025 2025 Paper | Code | Page | Dataset | Model
- Instruction Guided Visual Masking NeurIPS 2024 (Outstanding Paper @ ICML 2024 MFM-EAI Workshop) 2024 Paper | Code | Page | Dataset | Model
- DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning ICML 2024 (Outstanding Paper @ ICML 2024 MFM-EAI Workshop) 2024 Paper | Code | Page
- Query-Policy Misalignment in Preference-Based Reinforcement Learning ICLR 2024 (Spotlight, Top 5%) 2024 Paper | Code
- Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model ICLR 2024 2024 Paper | Code | Page
- When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning ICLR 2023 2023 Paper | Code
- Mind the Gap: Offline Policy Optimization for Imperfect Rewards ICLR 2023 2023 Paper | Code
- Universal Actions for Enhanced Embodied Foundation Models CVPR 2025 2025 Paper | Code | Page
- Efficient Robotic Policy Learning via Latent Space Backward Planning ICML 2025 2025
- Pushing the Limit of Sample-Efficient Offline Reinforcement Learning ICLR 2025 @ WWM Workshop 2025
- Reachability-Aware Reinforcement Learning for Collision Avoidance in Human-Machine Shared Control Under Review 2025
- Diffusion-Based Planning for Autonomous Driving with Flexible Guidance ICLR 2025 (Oral, Top 2%) 2025 Paper | Code | Page
- Skill Expansion and Composition in Parameter Space ICLR 2025 2025 Paper | Code | Page | Dataset | Model
- Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning ICRA 2025 2025 Paper | Code | Page
- Are Expressive Models Truly Necessary for Offline RL? AAAI 2025 (Oral, Top 5%) 2024 Paper | Code
- xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing NeurIPS 2024 OWA Workshop 2024 Paper | Code | Page
- Instruction Guided Visual Masking NeurIPS 2024 (Outstanding Paper @ ICML 2024 MFM-EAI Workshop) 2024 Paper | Code | Page | Dataset | Model
- DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning ICML 2024 (Outstanding Paper @ ICML 2024 MFM-EAI Workshop) 2024 Paper | Code | Page
- Query-Policy Misalignment in Preference-Based Reinforcement Learning ICLR 2024 (Spotlight, Top 5%) 2024 Paper | Code
- Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model ICLR 2024 2024 Paper | Code | Page
- PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning Preprint 2023 Paper | Code
- A Fully Data-Driven Approach for Realistic Traffic Signal Control Using Offline Reinforcement Learning Preprint 2023 Paper
- Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization ICLR 2023 (Oral, Notable Top 5%) 2023 Paper | Code
- Mind the Gap: Offline Policy Optimizaiton for Imperfect Rewards ICLR 2023 2023 Paper | Code
- When data geometry meets deep function: Generalizing offline reinforcement learning ICLR 2023 2023 Paper | Code
- A Policy-Guided Imitation Approach for Offline Reinforcement Learning NeurIPS 2022 (Oral, Top 2%) 2022 Paper | Code | Slides | Media
- Vehicle Extreme Control based on Offline Reinforcement Leaning CAC 2022 2022
- Offline Reinforcement Learning with Soft Behavioral Regularization NeurIPS 2021 Offline RL Workshop 2021 Paper | Code
- Universal Actions for Enhanced Embodied Foundation Models CVPR 2025 2025 Paper | Code | Page
- Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning ICRA 2025 2025 Paper | Code | Page
- Instruction Guided Visual Masking NeurIPS 2024 (Outstanding Paper @ ICML 2024 MFM-EAI Workshop) 2024 Paper | Code | Page | Dataset | Model
- DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning ICML 2024 (Outstanding Paper @ ICML 2024 MFM-EAI Workshop) 2024 Paper | Code | Page
- xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing NeurIPS 2024 OWA Workshop 2024 Paper | Code | Page
- Skill Expansion and Composition in Parameter Space ICLR 2025 2025 Paper | Code | Page | Dataset | Model
- Diffusion-Based Planning for Autonomous Driving with Flexible Guidance ICLR 2025 (Oral, Top 2%) 2025 Paper | Code | Page
- PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning Preprint 2023 Paper | Code
- Diffusion-Based Planning for Autonomous Driving with Flexible Guidance ICLR 2025 (Oral, Top 2%) 2025 Paper | Code | Page
- Are Expressive Models Truly Necessary for Offline RL? AAAI 2025 (Oral, Top 5%) 2024 Paper | Code
- Instruction Guided Visual Masking NeurIPS 2024 (Outstanding Paper @ ICML 2024 MFM-EAI Workshop) 2024 Paper | Code | Page | Dataset | Model
- Query-Policy Misalignment in Preference-Based Reinforcement Learning ICLR 2024 (Spotlight, Top 5%) 2024 Paper | Code
- Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model ICLR 2024 2024 Paper | Code | Page
- A Fully Data-Driven Approach for Realistic Traffic Signal Control Using Offline Reinforcement Learning Preprint 2023 Paper
- Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization ICLR 2023 (Oral, Notable Top 5%) 2023 Paper | Code
- Mind the Gap: Offline Policy Optimizaiton for Imperfect Rewards ICLR 2023 2023 Paper | Code
- When data geometry meets deep function: Generalizing offline reinforcement learning ICLR 2023 2023 Paper | Code
- A Policy-Guided Imitation Approach for Offline Reinforcement Learning NeurIPS 2022 (Oral, Top 2%) 2022 Paper | Code | Slides | Media
- Vehicle Extreme Control based on Offline Reinforcement Leaning CAC 2022 2022
- Offline Reinforcement Learning with Soft Behavioral Regularization NeurIPS 2021 Offline RL Workshop 2021 Paper | Code
Professional Services
Reviewer for ICLR 24-25, ICML 24-25, NeurIPS 23-25 (Top Reviewer), AAAI 24-25, IJCAI 24, IROS, TMLR, ICLR 2025 Workshop @ World Models, ICLR 2024 workshop @ DMLR
