Tianqi Liu

~Tianqi_Liu1

10

论文总数

5.0

年均投稿

5.7

平均评分

接收情况5/10

会议分布

ICLR

7

ICML

1

COLM

1

NeurIPS

1

发表论文 (10 篇)

20254 篇

RRM: Robust Reward Model Training Mitigates Reward Hacking

ICLR 2025Poster

Reward-Guided Prompt Evolving in Reinforcement Learning for LLMs

ICML 2025Poster

Evolving Alignment via Asymmetric Self-Play

ICLR 2025Rejected

Building Math Agents with Multi-Turn Iterative Preference Learning

ICLR 2025Poster

20246 篇

Statistical Rejection Sampling Improves Preference Optimization

ICLR 2024Poster

Knowledge Distillation with Perturbed Loss: From a Vanilla Teacher to a Proxy Teacher

ICLR 2024Rejected

Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learning

ICLR 2024withdrawn

LAMPO: Large Language Models as Preference Machines for Few-shot Ordinal Classification

COLM 2024Poster

Direct Language Model Alignment from Online AI Feedback

NeurIPS 2024Rejected

Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting

ICLR 2024withdrawn

合作者 (20)

Jiaming Shen6 篇

Rishabh Joshi5 篇

Bilal Piot3 篇

Mohammad Saleh3 篇