Skip to content
About me
Publications
Publications
Publications
* equal contribution. Also on
Google Scholar
.
2026
NeurIPS
Provable Test-Time Scaling for Beam Search in LLM Reasoning
Q. He*,
Y. Huang*
, Y. Cheng*, Y. Chen, Y. Liang
ICML
On the Emergence of Implicit Curriculum in RLVR Learning Dynamics
Y. Huang*
, Z. Wen*, Y. Chi, Y. Wei, A. Singh, Y. Liang, Y. Chen
ICML
ConvexBench: Can LLMs Recognize Convex Functions?
Y. Liu,
Y. Huang
, Y.-X. Wang, Y. Liang, Y. Bu
arXiv
TCSAlgBench: Benchmarking Automated Proving for Research-Level Theoretical Computer Science
C. Yang, X. Zhang,
Y. Huang
, B. Han, S. Kong, S. Zhang, V. P. Patil, Z. Han, M. Bohlke-Schneider, B. Wang
arXiv
Agentic Transformers Provably Learn to Search via Reinforcement Learning
T. Yang,
Y. Huang
, Y. Liang, Y. Chi
arXiv
Preconditioning Benefits of Spectral Orthogonalization in Muon
J. Ma,
Y. Huang
, Y. Chi, Y. Chen
2025
NeurIPS
Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization
Y. Huang*
, Z. Wen*, A. Singh, Y. Chi, Y. Chen
NeurIPS
Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent
T. Yang,
Y. Huang
, Y. Liang, Y. Chi
ICLR
A Theoretical Analysis of Self-Supervised Learning for Vision Transformers
Y. Huang*
, Z. Wen*, Y. Chi, Y. Liang
ACL Findings
Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?
C. Lu, X. Fan,
Y. Huang
, R. Xu, J. Li, W. Xu
SIAM J. Optim.
Fast Computation of Optimal Transport via Entropy-Regularized Extragradient Methods
G. Li, Y. Chen,
Y. Huang
, Y. Chi, H. V. Poor, Y. Chen
arXiv
Transformers Meet In-Context Learning: A Universal Approximation Theory
G. Li, Y. Jiao,
Y. Huang
, Y. Wei, Y. Chen
Major revision, Annals of Statistics
arXiv
Transformers Provably Learn Directed Acyclic Graphs via Kernel-Guided Mutual Information
Y. Cheng*,
Y. Huang*
, Z. Xiong, Y. Liang, V. Y. F. Tan
2024
NeurIPS
In-Context Learning with Representations: Contextual Generalization of Trained Transformers
T. Yang,
Y. Huang
, Y. Liang, Y. Chi
ICML
Accelerating Convergence of Score-Based Diffusion Models, Provably
G. Li*,
Y. Huang*
, T. Efimov, Y. Wei, Y. Chi, Y. Chen
ICML
In-Context Convergence of Transformers
Y. Huang
, Y. Cheng, Y. Liang
Oral, NeurIPS M3L Workshop 2023
2023
TMLR
Online Min-max Problems with Non-convexity and Non-stationarity
Y. Huang*
, Y. Cheng*, Y. Liang, L. Huang
2022
NeurIPS
Provable Generalization of Overparameterized Meta-learning Trained with SGD
Y. Huang
, Y. Liang, L. Huang
Spotlight
ICML
Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)
Y. Huang
, J. Lin, C. Zhou, H. Yang, L. Huang
2021
NeurIPS
What Makes Multi-modal Learning Better than Single (Provably)
Y. Huang*
, C. Du*, Z. Xue, X. Chen, H. Zhao, L. Huang
2020
IFIP Performance
Heavy Traffic Analysis of Approximate Max-Weight Matching Algorithms for Input-Queued Switches
Y. Huang
, L. Huang