About Me
I am currently a third-year undergraduate student in Institute for Interdisciplinary Information Sciences (IIIS, Yao Class) at Tsinghua University, majoring in Artificial Intelligence. Prior to this, I was a member of the China National Physics Olympiad Training Team.
In terms of academic performance, my average GPA is 3.83/4.00. I am currently working with Professor Mengdi Xu, and previously I had the honor of conducting research under the supervision of Professor Li Yi. My research focuses on robotics.
Outside of research, I enjoy 🏊♂️ swimming, ⚾ softball, 🏸 badminton, 🎤 singing, 📖 reading, and 🌍 traveling. Next semester, I plan to start learning 🎾 tennis and 🇫🇷 French. I truly value meaningful conversations and collaborations—if you share similar interests or would like to connect on research or beyond, I would be delighted to hear from you!✨
Research Interests
My long-term research interest lies in combining Reinforcement Learning (RL) with Embodied Foundation Models, focusing on leveraging large-model priors to supercharge RL post-training. I am particularly excited about three directions:
- World Models: Building universal world models for decision-making, and co-optimizing world models, value functions, and policies for real-world deployment.
- RL Post-Training: Designing mechanisms for fast adaptation, continual learning, and exploiting real-world data feedback loops.
- Generalizable Representations: Learning robust, reusable representations to bridge the gap between linguistic concepts and physical observations, enhancing policy generalization.
Publications
-
CVPR 2026 Workshop on 3D-LLM/VLA
Projects
-
Surveyed the development, variants, and practical performance of approximation algorithms for the Facility Location Problem, highlighting theoretical advances and implementation insights. -
Proposed STAMP—a dual approach combining targeted prompt engineering with a pluggable memory-augmented adapter—for controllable translation from modern to Classical Chinese. -
Investigated photorealistic image synthesis through a from-scratch C++ path tracing renderer, analyzing acceleration structures, sampling strategies, and material modeling to evaluate efficiency and quality. -
It's a platform that allows operators, sellers, and regulators to manage and interact with goods and services in an online marketplace.Language: Scala, TypeScript, HTML, CSS -
Introduced MagicDance, a fascinating pipeline that can automatically produce personalized dance videos from an arbitrary music clip and a single reference image of a dancer.PDF Team awarded second place! -
We solved the art-style-classification problem by a two-stage architecture where a DNN extracts features from image patches and an SNN adapter makes the final classification.
Selected Awards
2025
2024
Second-Class Scholarship of the Xi'an Institute of Interdisciplinary Information Core Technology. Advanced Individual in Social Work. Champion of the Softball (Slowpitch Division) at the Capital Universities Games.
2023
Experience
-
2026.2 - presentAdvised by Prof. Mengdi Xu (Tsinghua University)
Excited to further explore the intersection of RL and reward modeling.
Action tokenization for VLA. Failure-aware progress estimation. -
2025.6 - 2026.1Advised by Prof. Li Yi (Tsinghua University)
Developing a perception-policy disentanglement framework for sim2real post-training to enhance policy performance while keeping generalizability. Extensive experience in both simulation and real-world robot experiments. -
2025.2 - 2025.8Algorithm Intern
Enhanced the physics-reasoning capabilities of multi-modal large language models through reinforcement learning.
Powered by Jekyll and Minimal Light theme.
Template source from Yitang.
Last updated: 2026-07-07 14:38:38 +0000