paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

SL

Sergey Levine

NeurIPS 2026×5社会与人本对齐与偏好安全评测与基准强化学习与后训练

新星分资深

26

一作贡献0

核心/参与15

方向广度10

合作网络6

0 一作 · 5 篇 · NeurIPS 2026

获取完整研究档案

首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。

联系方式

实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。

2026 顶会论文

5

作者位次 #3/4NeurIPS 2026Poster

Offline Materials Optimization with CliqueFlowmer

Jakub Grudzien Kuba · Benjamin K Miller · Sergey Levine · Pieter Abbeel

作者位次 #3/4NeurIPS 2026Poster

Bridging the Simulation-to-Experiment Gap with Adversarial Distribution Alignment

Kai Nelson · Tobias Kreiman · Sergey Levine · Aditi Krishnapriyan

对齐与偏好安全社会与人本OpenReview

作者位次 #5/7NeurIPS 2026Poster

Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors

Shuhaib Mehri · Philippe Laban · Sumuk Shashidhar · Marwa Abdulhai · Sergey Levine · Michel Galley · Dilek Hakkani-Tur

评测与基准社会与人本OpenReview

作者位次 #4/4NeurIPS 2026Poster

Diffusion Guidance Is a Controllable Policy Improvement Operator

Kevin Frans · Seohong Park · Pieter Abbeel · Sergey Levine

作者位次 #7/7NeurIPS 2026Poster· Reinforcement Learning / Deep RL

Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning

Zhiyuan (Paul) Zhou · Andy Peng · Charles Xu · Qiyang Li · Jost Springenberg · Kevin Frans · Sergey Levine

强化学习与后训练OpenReview

常见合作者

PAPieter Abbeel×2 KFKevin Frans×2 JKJakub Grudzien Kuba BMBenjamin K Miller KNKai Nelson TKTobias Kreiman AKAditi Krishnapriyan SMShuhaib Mehri PLPhilippe Laban SSSumuk Shashidhar MAMarwa Abdulhai MGMichel Galley