*Shortcut models* are a plug-and-play replacement for diffusion models that can generate in a single step (or more). This speeds up inference by up to 128x. Shortcut models are trained end-to-end, and do not require a separate distillation phase or learning schedules.

Introducing Mochi 1 preview. A new SOTA in open-source video generation. Apache 2.0. magnet:?xt=urn:btih:441da1af7a16bcaa4f556964f8028d7113d21cbb&dn=weights&tr=udp://tracker.opentrackr.org:1337/announce

Accurate and controllable scene generation has been difficult with natural language alone. You instead need a language for scenes. Introducing the Scene Language — a visual representation for high-quality 3D/4D generation by integrating programs, words, and embeddings — 🧵(1/6)

1/🧬 Excited to share PLAID, our new approach for co-generating sequence and all-atom protein structures by sampling from the latent space of ESMFold. This requires only sequences during training, which unlocks more data and annotations: bit.ly/plaid-proteins 🧵

Introducing CoordTok, a scalable video tokenizer that can encode a 128-frame video into only 1k tokens. CoordTok learns a mapping from (x, y, t) coordinates to the corresponding patches of input videos. 🧵[1/6] project page: huiwon-jang.github.io/coordtok/

The ultimate test of any physics simulator is its ability to deliver real-world results. With MuJoCo Playground, we’ve combined the very best: MuJoCo’s rich and thriving ecosystem, massively parallel GPU-accelerated simulation, and real-world results across a diverse range of

Excited to share that DreamerV3 has been published in Nature! Dreamer solves control tasks by imagining the future outcomes of its actions inside of a continuously learned world model 🌏 It's the first agent to find diamonds in Minecraft from scratch without human data! 💎 👇

Excited to introduce Dreamer 4, an agent that learns to solve complex control tasks entirely inside of its scalable world model! 🌎🤖 Dreamer 4 pushes the frontier of world model accuracy, speed, and learning complex tasks from offline datasets. co-led with Wilson Yan