Viraj Mehta

~Viraj_Mehta1

3

论文总数

1.5

年均投稿

5.6

平均评分

接收情况2/3

会议分布

ICLR

1

COLM

1

NeurIPS

1

发表论文 (3 篇)

20251 篇

Sample Efficient Preference Alignment in LLMs via Active Exploration

COLM 2025Poster

20242 篇

Sample Efficient Reinforcement Learning from Human Feedback via Active Exploration

ICLR 2024Rejected

Group Robust Preference Optimization in Reward-free RLHF

NeurIPS 2024Poster

合作者 (14)

Ilija Bogunovic3 篇

Jeff Schneider2 篇

Ojash Neopane2 篇

Vikramjeet Das2 篇

Willie Neiswanger2 篇

Haitham Bou Ammar1 篇

Iason Chaimalas1 篇