影响力指数

4.99/100

超过 15.5%

全站排名 #54,368

发表论文2 篇

平均评分4.5

年均产出2.0 篇/年

Jianglin Qiao

Postdoc@University of Sydney, University of Sydney·澳大利亚·OpenReview

SSVPO: Effective Step-Level Credit Assignment for RL Training of Language Models

ICLR 2026Poster

SatBench: Satellite Coordination Benchmark Based on Multi-Agent Reinforcement Learning

ICLR 2026Withdrawn

合作者 (6)

Mahardhika Pratama

Ryszard Kowalczyk