Search Results - "Levine, Sergey"

Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better

Driess, Danny, Springenberg, Jost Tobias, Ichter, Brian, Yu, Lili, Li-Bell, Adrian, Pertsch, Karl, Ren, Allen Z., Walke, Homer, Vuong, Quan, Shi, Lucy Xiaoyang, Levine, Sergey

Diffusion Guidance Is a Controllable Policy Improvement Operator

Frans, Kevin, Park, Seohong, Abbeel, Pieter, Levine, Sergey

Learning to Reason without External Rewards

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

Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL

Hong, Joey, Dragan, Anca, Levine, Sergey

Training Strategies for Efficient Embodied Reasoning

Chen, William, Belkhale, Suneel, Mirchandani, Suvir, Mees, Oier, Driess, Danny, Pertsch, Karl, Levine, Sergey

Learning to Drive Anywhere with Model-Based Reannotation

Hirose, Noriaki, Ignatova, Lydia, Stachowicz, Kyle, Glossop, Catherine, Levine, Sergey, Shah, Dhruv

$\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization

Intelligence, Physical, Black, Kevin, Brown, Noah, Darpinian, James, Dhabalia, Karan, Driess, Danny, Esmail, Adnan, Equi, Michael, Finn, Chelsea, Fusai, Niccolo, Galliker, Manuel Y., Ghosh, Dibya, Groom, Lachy, Hausman, Karol, Ichter, Brian, Jakubczak, Szymon, Jones, Tim, Ke, Liyiming, LeBlanc, Devin, Levine, Sergey, Li-Bell, Adrian, Mothukuri, Mohith, Nair, Suraj, Pertsch, Karl, Ren, Allen Z., Shi, Lucy Xiaoyang, Smith, Laura, Springenberg, Jost Tobias, Stachowicz, Kyle, Tanner, James, Vuong, Quan, Walke, Homer, Walling, Anna, Wang, Haohuan, Yu, Lili, Zhilinsky, Ury

HiLMa-Res: A General Hierarchical Framework via Residual RL for Combining Quadrupedal Locomotion and Manipulation

Huang, Xiaoyu, Liao, Qiayuan, Ni, Yiming, Li, Zhongyu, Smith, Laura, Levine, Sergey, Peng, Xue Bin, Sreenath, Koushil

2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

AutoEval: Autonomous Evaluation of Generalist Robot Manipulation Policies in the Real World

Zhou, Zhiyuan, Atreya, Pranav, Tan, You Liang, Pertsch, Karl, Levine, Sergey

ViVa: Video-Trained Value Functions for Guiding Online RL from Diverse Data

Dashora, Nitish, Ghosh, Dibya, Levine, Sergey

SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks

Zhou, Yifei, Jiang, Song, Tian, Yuandong, Weston, Jason, Levine, Sergey, Sukhbaatar, Sainbayar, Li, Xian

Dynamic Search for Inference-Time Alignment in Diffusion Models

Li, Xiner, Uehara, Masatoshi, Su, Xingyu, Scalia, Gabriele, Biancalani, Tommaso, Regev, Aviv, Levine, Sergey, Ji, Shuiwang

Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models

Shi, Lucy Xiaoyang, Ichter, Brian, Equi, Michael, Ke, Liyiming, Pertsch, Karl, Vuong, Quan, Tanner, James, Walling, Anna, Wang, Haohuan, Fusai, Niccolo, Li-Bell, Adrian, Driess, Danny, Groom, Lachy, Levine, Sergey, Finn, Chelsea

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

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

Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA Design

Uehara, Masatoshi, Su, Xingyu, Zhao, Yulai, Li, Xiner, Regev, Aviv, Ji, Shuiwang, Levine, Sergey, Biancalani, Tommaso

Scaling Test-Time Compute Without Verification or RL is Suboptimal

Setlur, Amrith, Rajaraman, Nived, Levine, Sergey, Kumar, Aviral

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

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

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

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

Value-Based Deep RL Scales Predictably

Rybkin, Oleh, Nauman, Michal, Fu, Preston, Snell, Charlie, Abbeel, Pieter, Levine, Sergey, Kumar, Aviral

Flow Q-Learning

Park, Seohong, Li, Qiyang, Levine, Sergey