New labs

Sergey Levine

Physical Intelligence and UC Berkeley

Why we track: Robot learning

Career moves

No published career moves.

Papers

Paper2026-10-06 · arXiv (Cornell University)

Clarifying the Relationship between Environmental Control and Structural Centrality in AI Agents

The Geometry of Empowerment

Sergey Levine +3 more

What: Researchers revealed the relationship between empowerment, which refers to an AI agent's ability to control its surrounding environment, and structural centralization, which grants broad access to future outcomes.
Key result: They proposed a new geometric structure capable of interpreting and analyzing this by connecting empowerment maximization with skill-learning methods.
Why it matters: Provides theoretical implications necessary for building scalable empowerment maximization methods.AI summary

Agents & coding

Full summary Read paper ↗ PDF ↗

Paper2026-10-05 · arXiv (Cornell University)

Development of a new benchmark to study the phenomenon of AI behavioral cloning technology

Behavioral Cloning Mystery

Sergey Levine +1 more

What: Proposed OCBench, a robot manipulation evaluation tool with characteristics similar to human demonstrations.
Key result: Showed that this tool enables scientific research on various phenomena related to behavioral cloning and hypothesis testing in graphics processing unit (GPU) based environments.
Why it matters: Provides a foundation for analyzing previously unclear phenomena in robot learning technology within a controlled environment.AI summary

Robotics & physical AI

Full summary Read paper ↗ PDF ↗

Paper2026-08-24

Learning to Act While the Robot Thinks

Learning to Act While Waiting: RL Finetuning of Generalist Robot Policies Under Inference Latency

Sergey Levine +19 more

What: Researchers have developed ARLI, a latency-aware reinforcement learning framework that solves problems caused by the thinking time (inference latency) of robot models.
Key result: This new method enables robots to successfully continue learning even in environments with latency, showing performance equal to or better than an ideal latency-free environment.
Why it matters: It opens up the possibility for complex and massive robot AI to autonomously improve performance in real-world fields without freezing or stuttering.AI summary

Inference efficiency Robotics & physical AI

Full summary Read paper ↗ PDF ↗

Paper2026-08-03

Uncovering Why Action Chunking Improves Performance in Robotic Control

Why Does Action Chunking Improve Behavioral Cloning Performance in Robotic Control?

Sergey Levine +5 more

What: Through experiments, the study analyzed the causes of performance improvement in 'action chunking', a technique where robotic control predicts and executes multiple actions at once.
Key result: It showed that existing hypotheses are incorrect, revealed that the core success factor of action chunking is the 'implicit ensembling' effect which learns various temporal relationships, and proposed a new policy utilizing this.
Why it matters: By uncovering the key factors that enhance the performance of robotic control technology, it provides a theoretical foundation for developing efficient robot learning models in the future.AI summary

Robotics & physical AI

Full summary Read paper ↗ PDF ↗

Paper2026-06-11 · arXiv.org

Development of a new technology to more accurately guide robot behavior

Improving Robotic Generalist Policies via Flow Reversal Steering

Sergey Levine +4 more

What: To improve the performance of robotic generalist policies trained on diverse robot datasets, a method called Flow Reversal Steering (FRS), which transforms suboptimal actions into better ones, was evaluated in control settings.
Key result: Using FRS can translate rough instructions from humans or vision-language models into good robot behavior, showing an absolute task success rate improvement of up to 95% with less than 1 minute of training.
Why it matters: It demonstrates the potential to help robots perform better in new tasks by utilizing human instructions or existing techniques.AI summary

Robotics & physical AI

Full summary Read paper ↗ PDF ↗

This page compiles published papers, official announcements and press reports for information only. Paper summaries are written by AI from the abstract and reviewed by the editor; they may differ from the original, so check the paper for anything important. Nothing here is a recommendation to buy or sell any security or investment advice. Career moves cite official announcements or major press reports; some career records come from Wikidata (CC0). Summaries on this page were translated by AI from the editor-reviewed Korean version.