Jiaxiang Li

~Jiaxiang_Li1

4

论文总数

2.0

年均投稿

5.5

平均评分

接收情况3/4

会议分布

NeurIPS

2

ICLR

2

发表论文 (4 篇)

20252 篇

Policy optimization can be memory-efficient: LLM Alignment Through Successive Policy Re-weighting (SPR)

ICLR 2025Rejected

Joint Reward and Policy Learning with Demonstrations and Human Feedback Improves Alignment

ICLR 2025Spotlight

20242 篇

Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment

NeurIPS 2024Poster

SLTrain: a sparse plus low rank approach for parameter and memory efficient pretraining

NeurIPS 2024Poster

合作者 (14)

Mingyi Hong4 篇

Siliang Zeng3 篇

Alfredo Garcia2 篇

Chenliang Li2 篇

Kaixiang Lin1 篇

Xinnan Zhang1 篇

Akiko Takeda1 篇