影响力指数

39.88/100

前 14.5%

全站排名 #9,333

发表论文6 篇

平均评分5.8

年均产出2.0 篇/年

Mingxiao Li

Senior Researcher@Horizon Robotics·中国·OpenReview

研究方向

World Model · MultiModal Large Language Model · Large Language Model

Entropy-Guided k-Guard Sampling for Long-Horizon Autoregressive Video Generation

ICLR 2026Desk Rejected

RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents

ICLR 2026Poster

On a Connection Between Imitation Learning and RLHF

ICLR 2025Poster

SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters

ICLR 2025Poster

SePPO: Semi-Policy Preference Optimization for Diffusion Alignment

ICLR 2025Withdrawn

合作者 (20)

Vasant G Honavar

Christopher Brinton