Sergey Levine

Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design

Chenyu Wang, Masatoshi Uehara, Yichun He, Amy Wang, Tommaso Biancalani, Avantika Lal, Tommi Jaakkola, Sergey Levine, Hanchen Wang, Aviv Regev

Comments ICLR 2025

Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making

Vivek Myers, Chongyi Zheng, Anca Dragan, Sergey Levine, Benjamin Eysenbach

Comments Proceedings of the 41st International Conference on Machine Learning (ICML 2024)

Journal ref Proceedings of the 41st International Conference on Machine Learning (ICML 2024)

Robotic Control via Embodied Chain-of-Thought Reasoning

Michał Zawalski, William Chen, Karl Pertsch, Oier Mees, Chelsea Finn, Sergey Levine

Comments Project Website: https://embodied-cot.github.io. Updated funding information

The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes?

Roberto Calandra, Andrew Owens, Manu Upadhyaya, Wenzhen Yuan, Justin Lin, Edward H. Adelson, Sergey Levine

Comments 10 pages, published at the 1st Annual Conference on Robot Learning (CoRL), Code and dataset available at: https://lasr.org/research/feeling-of-success

Language Guided Skill Discovery

Seungeun Rho, Laura Smith, Tianyu Li, Sergey Levine, Xue Bin Peng, Sehoon Ha

Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance

Mitsuhiko Nakamoto, Oier Mees, Aviral Kumar, Sergey Levine

Comments Conference on Robot Learning (CoRL) 2024. Project Page: https://nakamotoo.github.io/V-GPS

Autonomous Improvement of Instruction Following Skills via Foundation Models

Zhiyuan Zhou, Pranav Atreya, Abraham Lee, Homer Walke, Oier Mees, Sergey Levine

Comments 2024 Conference on Robot Learning (CoRL)

Journal ref Conference on Robot Learning 2024

Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation

Yunhai Feng, Jiaming Han, Zhuoran Yang, Xiangyu Yue, Sergey Levine, Jianlan Luo

Adding Conditional Control to Diffusion Models with Reinforcement Learning

Yulai Zhao, Masatoshi Uehara, Gabriele Scalia, Sunyuan Kung, Tommaso Biancalani, Sergey Levine, Ehsan Hajiramezanali

Comments ICLR 2025

Digi-Q: Learning Q-Value Functions for Training Device-Control Agents

Hao Bai, Yifei Zhou, Li Erran Li, Sergey Levine, Aviral Kumar

Comments Accepted to ICLR 2025

Scaling Test-Time Compute Without Verification or RL is Suboptimal

Amrith Setlur, Nived Rajaraman, Sergey Levine, Aviral Kumar

OGBench: Benchmarking Offline Goal-Conditioned RL

Seohong Park, Kevin Frans, Benjamin Eysenbach, Sergey Levine

Comments ICLR 2025

Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following

Vivek Myers, Bill Chunyuan Zheng, Anca Dragan, Kuan Fang, Sergey Levine

Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Review

Masatoshi Uehara, Yulai Zhao, Chenyu Wang, Xiner Li, Aviv Regev, Sergey Levine, Tommaso Biancalani

Comments We plan to add more content and codes. Please let us know if there are any comments or missing citations

FAST: Efficient Action Tokenization for Vision-Language-Action Models

Karl Pertsch, Kyle Stachowicz, Brian Ichter, Danny Driess, Suraj Nair, Quan Vuong, Oier Mees, Chelsea Finn, Sergey Levine

Comments Website: https://www.pi.website/research/fast

Learning to Assist Humans without Inferring Rewards

Vivek Myers, Evan Ellis, Sergey Levine, Benjamin Eysenbach, Anca Dragan

Comments Conference on Neural Information Processing Systems (NeurIPS), 2024

Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language Grounding

Joshua Jones, Oier Mees, Carmelo Sferrazza, Kyle Stachowicz, Pieter Abbeel, Sergey Levine

Policy Adaptation via Language Optimization: Decomposing Tasks for Few-Shot Imitation

Vivek Myers, Bill Chunyuan Zheng, Oier Mees, Sergey Levine, Kuan Fang

Comments 27 pages, 14 figures

Journal ref Conference on Robot Learning, 2024

Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control

Vivek Myers, Andre He, Kuan Fang, Homer Walke, Philippe Hansen-Estruch, Ching-An Cheng, Mihai Jalobeanu, Andrey Kolobov, Anca Dragan, Sergey Levine

Comments 15 pages, 5 figures

Journal ref Conference on Robot Learning (CoRL), 2023

Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents

Yifei Zhou, Qianlan Yang, Kaixiang Lin, Min Bai, Xiong Zhou, Yu-Xiong Wang, Sergey Levine, Erran Li

RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning

Charles Xu, Qiyang Li, Jianlan Luo, Sergey Levine

Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning

Joey Hong, Anca Dragan, Sergey Levine

Comments 17 pages, 4 figures

Predicting Emergent Capabilities by Finetuning

Charlie Snell, Eric Wallace, Dan Klein, Sergey Levine

What Do Learning Dynamics Reveal About Generalization in LLM Reasoning?

Katie Kang, Amrith Setlur, Dibya Ghosh, Jacob Steinhardt, Claire Tomlin, Sergey Levine, Aviral Kumar

Traversability-Aware Legged Navigation by Learning from Real-World Visual Data

Hongbo Zhang, Zhongyu Li, Xuanqi Zeng, Laura Smith, Kyle Stachowicz, Dhruv Shah, Linzhu Yue, Zhitao Song, Weipeng Xia, Sergey Levine, Koushil Sreenath, Yun-hui Liu

Interactive Dialogue Agents via Reinforcement Learning on Hindsight Regenerations

Joey Hong, Jessica Lin, Anca Dragan, Sergey Levine

Comments 23 pages, 5 figures

Is Value Learning Really the Main Bottleneck in Offline RL?

Seohong Park, Kevin Frans, Sergey Levine, Aviral Kumar

Comments NeurIPS 2024

GHIL-Glue: Hierarchical Control with Filtered Subgoal Images

Kyle B. Hatch, Ashwin Balakrishna, Oier Mees, Suraj Nair, Seohong Park, Blake Wulfe, Masha Itkina, Benjamin Eysenbach, Sergey Levine, Thomas Kollar, Benjamin Burchfiel

Comments Code, model checkpoints and videos can be found at https://ghil-glue.github.io

Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding

Xiner Li, Yulai Zhao, Chenyu Wang, Gabriele Scalia, Gokcen Eraslan, Surag Nair, Tommaso Biancalani, Shuiwang Ji, Aviv Regev, Sergey Levine, Masatoshi Uehara

Comments The code is available at https://github.com/masa-ue/SVDD

Functional Graphical Models: Structure Enables Offline Data-Driven Optimization

Jakub Grudzien Kuba, Masatoshi Uehara, Pieter Abbeel, Sergey Levine