Undergraduate Student · Tsinghua University
Building language systems that reason, plan, and act with people.
I'm Zixuan (Alex) Wang, a Physics undergraduate at Tsinghua University working on AI Agents and Human-centered AI with special interests in alignment and agentic reinforcement learning, currently a research assistant at CMU supervised by Andrea Zanette.
I am Zixuan Wang, a Physics undergraduate at Tsinghua University (class of 2023). My research aims toward human-centered AI and autonomous agentic systems — LLMs that reason, plan, and act with people.
I am a remote research assistant at Carnegie Mellon University (ECE), advised by Prof. Andrea Zanette. During my Fall 2025 exchange at UC San Diego, I was an undergraduate researcher at the UCSD MixLab (HDSI) with Dr. Zhen Wang. Earlier, I was an AI intern at MiroMind AI, mentored by Dr. Yuntao Chen.
Traveling and experiencing diverse cultures — including an unforgettable Christmas 2025 by the seaside in La Jolla.
Tinker Robot Team, RoboCup@Home 2025 in Salvador, Brazil — an LLM-driven domestic service robot, 8th place globally.
Summer 2024 research visits in Singapore: A*STAR, Nanyang Technological University, and the National University of Singapore.
Saxophone in the Tsinghua University Symphonic Band — performances, festivals, and campus events.
Volleyball, swimming, and the gym — ideally all three in one week.
I work on LLM algorithms that enable more reliable, adaptive, and autonomous interaction with humans — leveraging synthetic data, structured supervision, and preference-based training to improve models' understanding of human intent, while ensuring privacy and safety.
Agentic LLM Systems
Long-context reasoning, planning, tool use, and self-refinement in real-world grounded environments.
LLM Alignment
Synthetic data, structured supervision, and preference-based training for human intent — with privacy and safety built in.
RL for LLMs
Training agents for sustained multi-turn interaction and long-horizon task completion.
Papers
Submission
S³-Sim: Simulating Humans for Personalized Language Modeling
Submission
Lightweight Neural Refinement for Drift Calibration in Eye Tracking Systems
Technical Reports
Preprint
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents
Course Projects
Course
Ego-embodied Reasoner: Egocentric Embodied Reasoning and Planning with MLLM via Reinforcement Learning
Course
EgoHOI: Prior-Guided 3D Hand-Object Interaction Reconstruction from Monocular Egocentric RGB Video
Course
Unconditional and Image-conditioned 3D Generation
Course
Human Skeleton and Skin Generation
Course
Machine Learning Course Notes - Learning Theory
Comprehensive notes on learning theory, covering PAC learning, VC dimension, and statistical learning foundations.
3D Visual Computing Course Notes
Notes on 3D visual computing, including geometry processing, rendering, and 3D reconstruction techniques.
I build with agents, and agents run on tokens. Every chart below is live telemetry from my own machines — every token my coding agents have read, cached, and written.