Researcher — paper.dinq.me

2026 顶会论文

作者位次 #4/4ICLR 2026Poster· Reinforcement Learning / Batch/Offline

Scalable Offline Model-Based RL with Action Chunks

Kwanyoung Park · Seohong Park · Youngwoon Lee · Sergey Levine

强化学习与后训练OpenReview

作者位次 #3/4ICLR 2026Poster· Reinforcement Learning / Deep RL

Intention-Conditioned Flow Occupancy Models

Chongyi Zheng · Seohong Park · Sergey Levine · Benjamin Eysenbach

强化学习与后训练OpenReview

作者位次 #4/4ICLR 2026Poster· Reinforcement Learning / Everything Else

Scaling Goal-conditioned Reinforcement Learning with Multistep Quasimetric Distances

Bill Zheng · Vivek Myers · Benjamin Eysenbach · Sergey Levine

强化学习与后训练OpenReview

作者位次 #2/3ICLR 2026Poster· Applications / Chemistry and Drug Discovery

Leveraging Discrete Function Decomposability for Scientific Design

James Bowden · Sergey Levine · Jennifer Listgarten

OpenReview

作者位次 #5/5ICLR 2026Poster· Applications / Robotics

Robust Fine-tuning of Vision-Language-Action Robot Policies via Parameter Merging

Yajat Yadav · Zhiyuan Zhou · Andrew Wagenmaker · Karl Pertsch · Sergey Levine

多模态强化学习与后训练OpenReview

作者位次 #2/2ICLR 2026Poster· Reinforcement Learning / Batch/Offline

Q-Learning with Adjoint Matching

Qiyang Li · Sergey Levine

强化学习与后训练OpenReview

作者位次 #4/4ICLR 2026Poster· Reinforcement Learning / Deep RL

Transitive RL: Value Learning via Divide and Conquer

Seohong Park · Aditya Oberai · Pranav Atreya · Sergey Levine

强化学习与后训练OpenReview

作者位次 #4/5ICLR 2026Poster· Reinforcement Learning / Deep RL

RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks

Mian Wu · Gavin Zhang · Sewon Min · Sergey Levine · Aviral Kumar

强化学习与后训练安全OpenReview

作者位次 #3/3ICLR 2026Poster· Reinforcement Learning / Batch/Offline

Decoupled Q-Chunking

Qiyang Li · Seohong Park · Sergey Levine

强化学习与后训练OpenReview

作者位次 #3/3ICLR 2026Poster· Reinforcement Learning / Deep RL

Dual Goal Representations

Seohong Park · Deepinder Mann · Sergey Levine

强化学习与后训练可解释性OpenReview

作者位次 #4/5ICLR 2026Poster

Learning to Reason without External Rewards

Xuandong Zhao · Zhewei Kang · Aosong Feng · Sergey Levine · Dawn Song

推理OpenReview

作者位次 #6/6ICLR 2026Poster· Reinforcement Learning / Planning

Zero-Overhead Introspection for Adaptive Test-Time Compute

Rohin Manvi · Joey Hong · Tim Seyde · Maxime Labonne · Mathias Lechner · Sergey Levine

推理强化学习与后训练OpenReview

作者位次 #4/4ICRA 2026Oral· Robotics & Automation

OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot Navigation

Noriaki Hirose · Catherine Glossop · Dhruv Shah · Sergey Levine

多模态OpenReview

作者位次 #6/6ICRA 2026Oral· Robotics & Automation

Learning Affordances at Inference-Time for Vision-Language-Action Models

Ameesh Shah · William Chen · Adwait Godbole · Federico Mora · Sanjit A. Seshia · Sergey Levine

多模态效率与系统OpenReview

作者位次 #3/3AAAI 2026Poster· Artificial Intelligence

Cliqueformer: Model-Based Optimization with Structured Transformers

Jakub Grudzien Kuba · Pieter Abbeel · Sergey Levine

OpenReview

Sergey Levine

获取完整研究档案

联系方式

2026 顶会论文

Scalable Offline Model-Based RL with Action Chunks

Intention-Conditioned Flow Occupancy Models

Scaling Goal-conditioned Reinforcement Learning with Multistep Quasimetric Distances

Leveraging Discrete Function Decomposability for Scientific Design

Robust Fine-tuning of Vision-Language-Action Robot Policies via Parameter Merging

Q-Learning with Adjoint Matching

Transitive RL: Value Learning via Divide and Conquer

RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks

Decoupled Q-Chunking

Dual Goal Representations

Learning to Reason without External Rewards

Zero-Overhead Introspection for Adaptive Test-Time Compute

OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot Navigation

Learning Affordances at Inference-Time for Vision-Language-Action Models

Cliqueformer: Model-Based Optimization with Structured Transformers

常见合作者