Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
4
0
10
3
Decentralized agent swarms can learn to self-orchestrate their collective behavior and individual capabilities simultaneously, outperforming fixed coordination strategies.
A simple reconstruction pre-training stage unlocks state-of-the-art one-step generative modeling with 10x less compute.
Generative models, when framed as proposal distributions for planning, unlock efficient long-horizon reasoning in model-based RL, outperforming diffusion policies and model-free methods.
Achieving superior zero-shot generalization, the World Action Planner outperforms leading policy models by leveraging the reasoning power of Vision-Language Models.