✳flâneur — a map of the web's best reading
2312.10812
arxiv.org · 8,018 words · saved by 1 readers
N/A
Published as a conference paper at ICLR 2024 L EARNING TO ACT WITHOUT ACTIONS Dominik Schmidt∗ Minqi Jiang Weco AI FAIR at Meta AI A BSTRACT Pre-training large models on vast amounts of web data has proven to be an ef-…
Explore this link on the map →saved by
related reading
- 45d74e190008c7bff2845ffc8e3facd3-Paper-Conference.pdfproceedings.iclr.cc
- The First Fully General Computer Action Model | blogsi.inc
- [2206.11795] Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videosarxiv.org
- World Models | Rohit Bandarurohitbandaru.github.io
- [2410.11758] Latent Action Pretraining from Videosarxiv.org
- Ch. 21 - Imitation Learningunderactuated.mit.edu
- [2206.11795] Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videosarxiv.org
- State of Robot Learning, December 2025vedder.io
- Pretrained to Imagine, Fine-Tuned to Act: The Rise of World-Action Models | NVIDIA Technical Blogdeveloper.nvidia.com
- pistar06.pdfpi.website
- Causal Video Models Are Data-Efficient Robot Policy Learners | Rhoda AIrhoda.ai
- World Action Model Atlasjoeclinton.me