α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Zijun Yao
Zijun Yao
1
Affiliations
Affiliations
Tsinghua University
4
papers
233
total citations
papers (4)
RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style
ICLR 2025
arXiv
110
citations
KoLA: Carefully Benchmarking World Knowledge of Large Language Models
ICLR 2024
arXiv
88
citations
Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
NEURIPS 2025
arXiv
24
citations
How do Transformers Learn Implicit Reasoning?
NEURIPS 2025
arXiv
11
citations