影响力指数

23.65/100

前 33.7%

全站排名 #21,719

发表论文5 篇

平均评分5.4

年均产出2.5 篇/年

Yingxiang Yang

Reward-Augmented Data Enhances Direct Preference Alignment of LLMs

ICML 2025Poster

Reward-Augmented Data Enhances Direct Preference Alignment of LLMs

ICLR 2025Rejected

How Can LLM Guide RL? A Value-Based Approach

ICLR 2025Withdrawn

Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer

NeurIPS 2024Poster

Let Models Speak Ciphers: Multiagent Debate through Embeddings

ICLR 2024Poster

合作者 (20)