iiinova — where your digital self keeps evolving

Reposted by Ulyana Piterbarg

Kanishk Gandhi @gandhikanishk.bsky.social · 04/03/2025

1/13 New Paper!! We try to understand why some LMs self-improve their reasoning while others hit a wall. The key? Cognitive behaviors! Read our paper on how the right cognitive behaviors can make all the difference in a model's ability to improve with RL! 🧵

25817

Reposted by Ulyana Piterbarg

Lerrel Pinto @lerrelpinto.com · 18/02/2025

Thank you to @sloanfoundation.bsky.social for this generous award to our lab. Hopefully this will bring us closer to building truly general-purpose robots!

3234

Ulyana Piterbarg @upiter.bsky.social · 12/02/2025

Our paper showing that LMs benefit from human-like abstractions for code synthesis was accepted to ICLR! 🇸🇬 We show that order matters in code gen. -- casting code synthesis as a sequential edit problem by preprocessing examples in SFT data improves LM test-time scaling laws

1102

Reposted by Ulyana Piterbarg

gaoyuezhou.bsky.social @gaoyuezhou.bsky.social · 31/01/2025

Can we extend the power of world models beyond just online model-based learning? Absolutely! We believe the true potential of world models lies in enabling agents to reason at test time. Introducing DINO-WM: World Models on Pre-trained Visual Features for Zero-shot Planning.

1208

Reposted by Ulyana Piterbarg

Jack Parker-Holder @jparkerholder.bsky.social · 04/12/2024

Introducing 🧞Genie 2 🧞 - our most capable large-scale foundation world model, which can generate a diverse array of consistent worlds, playable for up to a minute. We believe Genie 2 could unlock the next wave of capabilities for embodied agents 🧠.

1523461

Reposted by Ulyana Piterbarg

Tim Rocktäschel @handle.invalid · 20/11/2024

Now that @jeffclune.bsky.social and @joelbot3000.bsky.social are here, time for an Open-Endedness starter pack. go.bsky.app/MdVxrtD

1610632