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
54.45/100
前 6.7%
全站排名 #4,284
发表论文10 篇
平均评分
年均产出3.3 篇/年
Swarnadeep Saha
研究方向
Alignment · Reasoning · Large Language Models · Natural Language Processing
14
J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning
ICLR 2026Poster
通讯16
Hybrid Reinforcement: when reward is sparse, better to be dense
ICLR 2026Poster
三作12
OptimalThinkingBench: Evaluating Over and Underthinking in LLMs
ICLR 2026Poster
通讯15
Jointly Reinforcing Diversity and Quality in Language Model Generations
ICLR 2026Rejected
7
The Majority is not always right: RL training for solution aggregation
ICLR 2026Rejected
三作6
Bridging Offline and Online Reinforcement Learning for LLMs
ICLR 2026Rejected