Sergey Levine

Sergey Levine on Hugging Face Daily Papers: 8 papers, 1 in the top 3 of their day, 260 upvotes.

1. SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks 8 upvotes, #16 of 2025-03-20
2. Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation 11 upvotes, #13 of 2025-02-25
3. SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training 100 upvotes, #1 of 2025-01-29
4. FAST: Efficient Action Tokenization for Vision-Language-Action Models 22 upvotes, #6 of 2025-01-17
5. Predicting Emergent Capabilities by Finetuning 6 upvotes, #22 of 2024-11-26
6. Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration 4 upvotes, #16 of 2024-10-28
7. DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning 17 upvotes, #11 of 2024-06-21
8. OpenVLA: An Open-Source Vision-Language-Action Model 28 upvotes, #5 of 2024-06-14

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.