Yuheng Tu

I am a first-year MSCS student at UCLA. I was an undergrad from Southeast University (SEU). I was a visiting student at UC Berkeley EECS during 24 Spring.

I have the privilege of working with Prof. Sanmi Koyejo. Before this, I was fortunate to be advised by Prof. Bo Li during 24 summer and Prof. Qiao Wang at SEU.

I am a CS self-learning advocate and my study notes are presented in CS-self-learning. I led SEU Flybook 2025, an open-source guide for SEU students applying to MS/PhD programs abroad.

My recent research focuses on AI Evaluation, drawing on insights from statistics, psychology, and measurement theory. My study interests lie in CS/AI, CS/Theory, and Statistics.

Email  /  CV  /  Scholar  /  Github / LinkedIn

profile photo

Research

Item Response Scaling Laws: A Measurement Theory Approach to Generalizable Neural Performance Prediction
Sang Truong*, Yuheng Tu*, Rylan Schaeffer, Sanmi Koyejo
Under Review
PDF / Code


Fantastic Bugs and Where to Find Them in AI Benchmarks
Sang Truong*, Yuheng Tu*, Michael Hardy*, Anka Reuel, Zeyu Tang, Jirayu Burapacheep, Jonathan Perera, Chibuike Uwakwe, Benjamin W. Domingue, Nick Haber, Sanmi Koyejo
NeurIPS 2025 D&B
PDF / Code / Data / PR to HELM


Reliable and Efficient Amortized Model-based Evaluation
Sang Truong, Yuheng Tu, Percy Liang, Bo Li, Sanmi Koyejo
ICML 2025
Openreview / Code / Data / PR to HELM / HELM Blog / Stanford Report / Talk


AIR-BENCH 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies
Yi Zeng*, Yu Yang*, Andy Zhou*, Jeffrey Ziwei Tan*, Yuheng Tu*, Yifan Mai*, Kevin Klyman, Minzhou Pan, Ruoxi Jia, Dawn Song, Percy Liang, Bo Li
ICLR 2025 Spotlight
Openreview / Code / Data / Wired Article / Blog


NQFL: Nonuniform Quantization for Communication Efficient Federated Learning
Guojun Chen, Kaixuan Xie, Yuheng Tu, Tiecheng Song, Yinfei Xu, Jing Hu, Lun Xin
IEEE Communications Letters (COMML)
PDF / Code / COMML



Website template