影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
40.82/100
前 13.9%
全站排名 #8,949
发表论文6 篇
平均评分
年均产出2.0 篇/年
Yaru Hao
研究方向
Interpretability of NLP · Language Model Pre-training
10
Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective
ICLR 2026Poster
15
Geometric-Mean Policy Optimization
ICLR 2026Poster
5
Towards Stable and Effective Reinforcement learning for Mixture-of-Experts
ICLR 2026Withdrawn
5
On-Policy RL with Optimal Reward Baseline
ICLR 2026Withdrawn
一作