影响力指数

-/100

发表论文5 篇

平均评分4.4

年均产出1.7 篇/年

Diyuan Shi

PhD student@Westlake University·中国·OpenReview

研究方向

Reinforcement Learning · Imitation Learning · Machine Learning · Deep Learning

NFPO: Stabilized Policy Optimization of Normalizing Flow for Robotic Policy Learning

ICLR 2026Rejected

Memory-Efficient Algorithm Distillation for In-context Reinforcement Learning

ICLR 2025Rejected

Decoupled Offline to Online finetuning via Dynamics Model

ICLR 2025Rejected

Revisiting the Design Choices in Max-Return Sequence Modeling

ICLR 2025Rejected

合作者 (10)

博士导师5 篇