Yingxiang Yang

~Yingxiang_Yang2

5

论文总数

2.5

年均投稿

5.4

平均评分

接收情况3/5

会议分布

ICLR

3

ICML

1

NeurIPS

1

发表论文 (5 篇)

20253 篇

Reward-Augmented Data Enhances Direct Preference Alignment of LLMs

ICLR 2025Rejected

Reward-Augmented Data Enhances Direct Preference Alignment of LLMs

ICML 2025Poster

How Can LLM Guide RL? A Value-Based Approach

ICLR 2025withdrawn

20242 篇

Let Models Speak Ciphers: Multiagent Debate through Embeddings

ICLR 2024Poster

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

NeurIPS 2024Poster

合作者 (20)

Zhaoran Wang5 篇

Shenao Zhang4 篇

Zhihan Liu4 篇

Yongfei Liu2 篇

Yufeng Zhang2 篇