Search papers, labs, and topics across Lattice.
3
0
6
0
Diffusion-based RL gets a boost: training-free critic guidance unlocks state-of-the-art performance and, for the first time, real-world robot manipulation.
Streaming audio-driven character animation can finally handle abrupt tempo changes and user edits in real-time, thanks to a diffusion-forcing approach that prioritizes both responsiveness and long-term coherence.
Humanoid states, not low-level actions, are the key to unlocking text-driven control, enabling a diffusion model to generate more natural and semantically aligned behaviors.
