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
36.72/100
前 17.1%
全站排名 #10,989
发表论文4 篇
平均评分
年均产出4.0 篇/年
Reza Bayat
研究方向
memorization · generalization · mechanistic interpretability · llm reasoning
20
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
NeurIPS 2025Poster
三作17
Steering Large Language Model Activations in Sparse Spaces
COLM 2025Poster
一作29
The Pitfalls of Memorization: When Memorization Hurts Generalization
ICLR 2025Poster
一作14
Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones
ICLR 2025Withdrawn
二作