影响力指数

23.04/100

前 35%

全站排名 #22,517

发表论文3 篇

平均评分6.1

年均产出1.5 篇/年

Tao Sun

Research Scientist@ByteDance·OpenReview

研究方向

Reinforcement Learning · Probabilistic Modeling · Large Language Models

Reward-Augmented Data Enhances Direct Preference Alignment of LLMs

ICML 2025Poster

Reward-Augmented Data Enhances Direct Preference Alignment of LLMs

ICLR 2025Rejected

$\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis

ICLR 2024Spotlight

合作者 (11)