M. Pawan Kumar

~M._Pawan_Kumar1

3

论文总数

1.5

年均投稿

6.0

平均评分

接收情况2/3

会议分布

ICLR

3

发表论文 (3 篇)

20251 篇

Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models

ICLR 2025Poster

20242 篇

Expressive Losses for Verified Robustness via Convex Combinations

ICLR 2024Poster

Efficient Certification of Physics-Informed Neural Networks

ICLR 2024Rejected

合作者 (9)

Francisco Eiras2 篇

Krishnamurthy Dj Dvijotham2 篇

Philip Torr2 篇

Rudy R Bunel2 篇

Aleksandar Petrov1 篇

Alessandro De Palma1 篇

Alessio Lomuscio1 篇