Bilal Piot

~Bilal_Piot1

6

论文总数

3.0

年均投稿

6.2

平均评分

接收情况5/6

会议分布

ICLR

4

NeurIPS

2

发表论文 (6 篇)

20253 篇

Learning from negative feedback, or positive feedback or both

ICLR 2025Spotlight

Building Math Agents with Multi-Turn Iterative Preference Learning

ICLR 2025Poster

RRM: Robust Reward Model Training Mitigates Reward Hacking

ICLR 2025Poster

20243 篇

Multi-turn Reinforcement Learning with Preference Human Feedback

NeurIPS 2024Poster

Unlocking the Power of Representations in Long-term Novelty-based Exploration

ICLR 2024Spotlight

Direct Language Model Alignment from Online AI Feedback

NeurIPS 2024Rejected

合作者 (20)

Rishabh Joshi3 篇

Tianqi Liu3 篇

Daniele Calandriello3 篇

Jiaming Shen2 篇

Mohammad Saleh2 篇

Aviv Rosenberg2 篇