About Me
I’m an M.S. student in Electrical and Computer Engineering at the
University of Illinois Urbana-Champaign, advised by
Prof. Varun Chandrasekaran. I
received my B.S. in Computer Engineering with a minor in Statistics from
UIUC in 2026.
I’m interested in when language models make confident but unreliable
judgments, and how to design evaluations that catch those failures. I’m
also exploring how AI agents use tools, check their work and recover when
a plan fails, and how embodied agents use feedback from simulation and
the physical world.
Research interests: LLM safety, LLM agent evaluation, Multi-agent collaboration, Simulation for embodied AI.
🔥 News
- Fall 2026 Started my M.S. in Electrical and Computer Engineering at UIUC, advised by Prof. Varun Chandrasekaran.
- 2026 Our paper Do AI Reviewers Converge? was accepted to Findings of EMNLP 2026.
- Summer 2026 Joined Shanghai AI Laboratory to build Isaac Sim scenes and 3D assets for chemistry experiments with dual-arm robots.
- 2026 Graduated from UIUC with a B.S. in Computer Engineering and a minor in Statistics.
📝 Publications
EMNLP 2026 Findings 
Xuzhe Hou, Shengxin Zhang, Riley Stacy, Emily Black, Varun Chandrasekaran
Findings of EMNLP 2026
[ACL Anthology][OpenReview][Code][Video]
- Built an asynchronous evaluation pipeline for five LLMs, comparing 10,172 model-generated reviews with 1,943 human reviews across 509 ICLR papers.
- Measured praise-to-critique balance and semantic similarity. Specialized review agents reduced review convergence, though some effects persisted.
🔬 Research Experience
Shanghai AI Laboratory Summer 2026
Scientific simulation and 3D asset generation
- Developed Isaac Sim scenes and 3D scientific assets for chemical experiments, including boiling, precipitation and dissolution, in dual-arm robot simulations.
University of Illinois Urbana-Champaign Ongoing
LLM training data provenance
- Designing controlled experiments to test whether black-box audits can detect the use of marked training examples after paraphrasing, with model utility evaluated separately.
Westlake University 2025
Multimodal biometric representation, with Prof. Yandong Wen
- Built a voice-to-face pipeline for uncertainty-aware 3D facial estimation.
Carnegie Mellon University Summer 2023
Fairness under distribution shift, with Prof. Pradeep Ravikumar
- Tested a fairness-aware PyTorch model under demographic and other distribution shifts.
🛠️ Projects
Autonomous parallel parking Spring 2026
University of Illinois Urbana-Champaign
Used LiDAR and odometry to detect parking spaces and implemented a finite-state controller for parallel parking in ROS 2, tested in Gazebo and on a Polaris GEM vehicle.
ROS 2GazeboLiDAR
Two-player FPGA game
FPGA hardware project
A real-time two-player game in SystemVerilog with keyboard controls, missiles, shields and live health bars, deployed with Vitis.
SystemVerilogFPGA
CS 411 course project
Order tracking, sales forecasting and inventory analytics with a React frontend, a Flask backend and SQL transaction logic.
ReactFlaskSQL
📖 Education
University of Illinois Urbana-Champaign In progress
M.S. in Electrical and Computer Engineering
Advisor: Prof. Varun Chandrasekaran
University of Illinois Urbana-Champaign 2026
B.S. in Computer Engineering, Minor in Statistics
GPA 3.85 / 4.00
👨🏫 Teaching
- Graduate Teaching Assistant, ECE 385 (Digital Systems Laboratory)
- Course Assistant, CS 124, ECE 110 and STAT 400
💻 Skills
Python, C/C++, PyTorch, scikit-learn, Isaac Sim, ROS 2, Gazebo, Git, SystemVerilog