Sergey Levine

Computer Science · Physical Sciences

109h-index63.0kcitations869works6.32yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Reinforcement Learning in Robotics(441), Robot Manipulation and Learning(192), Domain Adaptation and Few-Shot Learning(126), Adversarial Robustness in Machine Learning(103), Multimodal Machine Learning Applications(95)

Publications867 total

RoboReward: General-Purpose Vision-Language Reward Models for Robotics
ArXiv.org·2026Open Access
RoboReward: General-Purpose Vision-Language Reward Models for Robotics
arXiv (Cornell University)·2026Open Access
Emergence of Human to Robot Transfer in Vision-Language-Action Models
arXiv (Cornell University)·2025Open Access
Emergence of Human to Robot Transfer in Vision-Language-Action Models
ArXiv.org·2025Open Access
PolaRiS: Scalable Real-to-Sim Evaluations for Generalist Robot Policies
arXiv (Cornell University)·2025Open Access
PolaRiS: Scalable Real-to-Sim Evaluations for Generalist Robot Policies
ArXiv.org·2025Open Access
Decoupled Q-Chunking
arXiv (Cornell University)·2025Open Access
Training-Time Action Conditioning for Efficient Real-Time Chunking
arXiv (Cornell University)·2025Open Access
Learning to Drive Anywhere With Model-Based Reannotation
IEEE Robotics and Automation Letters·2025
Natural Language Actor-Critic: Scalable Off-Policy Learning in Language Space
arXiv (Cornell University)·2025Open Access
Zero-Overhead Introspection for Adaptive Test-Time Compute
ArXiv.org·2025Open Access
$π^{*}_{0.6}$: a VLA That Learns From Experience
arXiv (Cornell University)·2025Open Access
Multistep Quasimetric Learning for Scalable Goal-conditioned Reinforcement Learning
ArXiv.org·2025Open Access
Leveraging Discrete Function Decomposability for Scientific Design
arXiv (Cornell University)·2025Open Access
RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks
arXiv (Cornell University)·2025Open Access
Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning
arXiv (Cornell University)·2025Open Access
Learning Affordances at Inference-Time for Vision-Language-Action Models
arXiv (Cornell University)·2025Open Access
Training LLM Agents to Empower Humans
arXiv (Cornell University)·2025Open Access
Compute-Optimal Scaling for Value-Based Deep RL
arXiv (Cornell University)·2025Open Access
Precise and dexterous robotic manipulation via human-in-the-loop reinforcement learning
Science Robotics·2025· 21 cited
page 1 of 44Next →

Frequent Co-authors

Pieter Abbeel(22), Chelsea Finn(18), George Tucker(6), Tuomas Haarnoja(5), Aurick Zhou(5), Vincent Vanhoucke(5), Yevgen Chebotar(5), Karol Hausman(5), Tianhe Yu(5), Jitendra Malik(4), Dmitry Kalashnikov(4), Alex Irpan(4), Peter Pástor(4), Julian Ibarz(4), Deirdre Quillen(4), Pierre Sermanet(4), Jasmine Hsu(4), Brian Ichter(4), Fei Xia(4), Shixiang Gu(3)