About Me
I’m a 5th-year Ph.D. candidate at the Institute for AI Industry Research (AIR), Tsinghua University, advised by Prof. Yunxin Liu and working closely with Prof. Ting Cao. I received my B.E. in Electronic Engineering from Tsinghua University in 2022. I was at EESAST and NICS-EFC Lab as an undergraduate.
I work on self-evolving physical AI (PSI, physical self-improvement): how agents can be deployed and act efficiently in the physical world, and continually improve through real-world interaction and feedback. I hope to connect algorithmic breakthroughs with the underlying infrastructure to accelerate this loop. Recent projects I have led or contributed to include:
- Training and inference infra (OxyGen, Cosmos Lite, Embodied.cpp, Patchwork)
- Runtime failure detection and in-context learning (ActProbe, Zeva)
- Closed-loop learning and agent improvement (SteerDistill, Zetta ζ)
OxyGen has been accepted to NeurIPS 2026, and Zetta ζ has received over 1,000 GitHub stars.
My earlier work focused on efficient inference systems for edge devices (FlexNN, Vec-LUT). Vec-LUT received MobiSys 2026 Best Paper Award Runner-Up recognition. I also led the Efficiency section of the Personal LLM Agents survey, which has received over 500 citations.
Feel free to connect, exchange ideas, or collaborate: lixiangy22@mails.tsinghua.edu.cn.
News
- 2026/11 SteerDistill: Quantizing LLM Agents via Closed-Loop Teacher Steering released. Paper Code Page
- 2026/10 Personal LLM Agents (survey & position paper) has reached 500 citations on Google Scholar! Congrats to Prof. Yuanchun Li. Paper Page 机器之心
- 2026/10 Replicate What Varies: Resource Sharing for Domain-Randomized Embodied Simulation released. Paper
- 2026/09 OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism accepted to NeurIPS 2026. Paper Blog Code Page
- 2026/08 Zeva: In-Context Causal Learning for Generalizable Embodied Manipulation released. Congrats to Fu Chen and Xin Ding. Paper Code Page 量子位
- 2026/08 Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence released. Congrats to team. Paper Code Page 机器之心
- 2026/08 Invited talk and panel on the new paradigm of edge–cloud collaboration, co-hosted by Next Capital and Z.ai. Event
- 2026/08 Embodied.cpp v1.0 released: a portable C++ inference runtime for embodied AI models. Congrats to Borui Li and Hao Wu. Paper Code
- 2026/07 Cosmos Lite released: efficient deployment and rollout on consumer-grade GPUs for Cosmos 3 robot policies. Blog Code Models
- 2026/07 DWI: Efficient On-Device LLM Decoding Through Dynamic Width Selection on Nested Models accepted to IEEE TMC. Congrats to Weining Chen. Paper
- 2026/06 Vec-LUT received Best Paper Award Runner-Up at ACM MobiSys 2026. Awesome work with Chengyu Yin! Paper Blog Code Slides
- 2026/06 ActProbe: Action-Space Probe for Early Failure Detection of Generative Robot Policies released. Paper Code Page
- 2026/05 EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agents released. Paper Code
- 2026/04 Building Efficient Inference Systems for Resource-Constrained Edge AI Deployment accepted to the Rising Stars Forum of ACM MobiSys 2026. Paper
- 2026/03 Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices accepted to ACM MobiSys 2026. Paper Blog Code
- 2025/08 An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint accepted to EMNLP 2025. Congrats to Yi Sun. Paper Page
- 2025/07 Squeezer: Efficient Multi-DNN Inference for Edge Video Analytics via Cross-Model Scheduling accepted to IEEE TMC. Congrats to Xiang Wang. Paper
- 2024/01 Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security (survey & position paper) released. Paper Page 机器之心
- 2023/11 FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge Devices accepted to ACM MobiCom 2024. Paper Code Slides
- 2022/03 DIMMining: Pruning-Efficient and Parallel Graph Mining on Near-Memory-Computing accepted to ISCA 2022. Congrats to Guohao Dai and Zhenhua Zhu. Paper
Awards
- 惠妍英才奖学金, 2026/10
- ACM MobiSys 2026 Best Paper Award Runner-Up, 2026/06
- ACM MobiSys 2026 Student Travel Grant, 2026/05
- 清华之友-智能产业研究院清智奖学金, 2025/12
- 清华之友-济宁英才奖学金, 2024/11
- 清华大学社会工作优秀奖学金, 2021/12
- 第三十六届全国部分地区大学生物理竞赛非物理类A组特等奖（北京物理学会）, 2019/12
- 优秀艺术博物馆讲解志愿者（清华大学艺术博物馆、紫荆志愿者服务总队）, 2019/05
- 清华大学2018级新生二等奖学金, 2018/12
- 第三十四届全国中学生物理竞赛决赛三等奖（中国物理学会）, 2017/11
Experiences
Internship
- ByteDance, Big Data (Serverless/FaaS) Infrastructure Development, 2021/06–2021/09
Social Practice
- Student Association for Science and Technology, EE, THU (EESAST), 2019/07–2022/06
- 清华大学研究生社会实践中铁四局支队（蒙古乌兰巴托），2024/07–2024/09
- 清华大学电子工程系“E方水土·寻秘数据”支队（北京、上海），2019/08
Teaching Assistant
- Tsinghua University, Computer Program Design (undergraduate), 2025 Spring & Summer
- Tsinghua University, Basic Music Theory and Vocal Practice, 2023 Fall