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
39.95/100
前 14.5%
全站排名 #9,310
发表论文9 篇
平均评分
年均产出3.0 篇/年
Krishna P. Gummadi
研究方向
Fairness · Explainability · Accountability · Interpretability · Robustness · Safety · Computational Social Science · Ethics
14
Hubble: a Model Suite to Advance the Study of LLM Memorization
ICLR 2026Oral
16
Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs
ICLR 2026Poster
20
In Agents We Trust, but Who Do Agents Trust? Latent Source Preferences Steer LLM Generations
ICLR 2026Poster
6
Revisiting Privacy, Utility, and Efficiency Trade-offs when Fine-Tuning Large Language Models
ICLR 2026Rejected
通讯15
Learning without Memorizing Considered Infeasible: Rethinking Memorization in LLMs
ICLR 2026Rejected