Misha Khalman

~Misha_Khalman1

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

2

NeurIPS

1

发表论文 (3 篇)

20251 篇

Building Math Agents with Multi-Turn Iterative Preference Learning

ICLR 2025Poster

20242 篇

Statistical Rejection Sampling Improves Preference Optimization

ICLR 2024Poster

Direct Language Model Alignment from Online AI Feedback

NeurIPS 2024Rejected

合作者 (20)

Tianqi Liu3 篇

Bilal Piot2 篇

Mohammad Saleh2 篇

Rishabh Joshi2 篇

Aviv Rosenberg1 篇

Chengshuai Shi1 篇