Hamish Ivison

~Hamish_Ivison1

5

论文总数

2.5

年均投稿

6.7

平均评分

接收情况5/5

会议分布

COLM

3

NeurIPS

2

发表论文 (5 篇)

20253 篇

The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains

COLM 2025Poster

Tulu 3: Pushing Frontiers in Open Language Model Post-Training

COLM 2025Poster

2 OLMo 2 Furious (COLM’s Version)

COLM 2025Poster

20242 篇

Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback

NeurIPS 2024Poster

Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning

NeurIPS 2024Spotlight

合作者 (20)

Hannaneh Hajishirzi3 篇

Nathan Lambert3 篇

Noah A. Smith3 篇

Valentina Pyatkin3 篇

Christopher Wilhelm2 篇

Faeze Brahman2 篇

Jacob Morrison2 篇

Jiacheng Liu2 篇