Zhihan Liu

~Zhihan_Liu1

11

论文总数

5.5

年均投稿

5.1

平均评分

接收情况4/11

会议分布

ICLR

8

ICML

2

NeurIPS

1

发表论文 (11 篇)

20258 篇

Reward-Augmented Data Enhances Direct Preference Alignment of LLMs

ICLR 2025Rejected

Reward-Augmented Data Enhances Direct Preference Alignment of LLMs

ICML 2025Poster

Progressive LLM Alignments Using Two-Player Games

ICLR 2025Rejected

Hindsight Planner: A Closed-loop few-shot planner for Embodied Instruction Following

ICLR 2025withdrawn

Provably Efficient and Practical Self-Play for Better LLM Alignment

ICLR 2025Rejected

How Can LLM Guide RL? A Value-Based Approach

ICLR 2025withdrawn

Self-Exploring Language Models: Active Preference Elicitation for Online Alignment

ICLR 2025withdrawn

BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning

ICML 2025Poster

20243 篇

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

NeurIPS 2024Poster

Reason for Future, Act for Now: A Principled Architecture for Autonomous LLM Agents

ICLR 2024Rejected

Sample-Efficient Multi-Agent RL: An Optimization Perspective

ICLR 2024Poster

合作者 (20)

Zhaoran Wang11 篇

Shenao Zhang9 篇

Hongyi Guo4 篇

Yingxiang Yang4 篇

Xiaojun Xu2 篇