α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Runlong Zhou
Runlong Zhou
1
Affiliations
Affiliations
Tsinghua University
5
papers
63
total citations
papers (5)
Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret
NEURIPS 2021
arXiv
38
citations
Extragradient Preference Optimization (EGPO): Beyond Last-Iterate Convergence for Nash Learning from Human Feedback
COLM 2025
arXiv
13
citations
Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning
ICLR 2024
arXiv
11
citations
Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs
NEURIPS 2025
arXiv
1
citations
Transformers are Efficient Compilers, Provably
COLM 2025
arXiv
0
citations