影响力指数

51.73/100

前 7.7%

全站排名 #4,972

发表论文6 篇

平均评分5.6

年均产出2.0 篇/年

Yuxiao Qu

PhD student@Carnegie Mellon University·美国·OpenReview

研究方向

Large Language Models · Reinforcement Learning

RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems

ICLR 2026Poster

Learning to Reason on Hard Problems with Privileged On-Policy Exploration

ICLR 2026Rejected

Teaching LLMs When to Stop Seeking and Start Acting

ICLR 2026Rejected

Optimizing Test-Time Compute via Meta Reinforcement Finetuning

ICML 2025Poster

Harnessing Webpage UIs for Text-Rich Visual Understanding

ICLR 2025Poster

合作者 (20)

博士导师5 篇

Ruslan Salakhutdinov