Search papers, labs, and topics across Lattice.
3
0
4
10
Robots can now learn manipulation skills from human videos with greater morphological accuracy and temporal consistency, thanks to a new method that disentangles task and embodiment.
Autoregressive Transformers can now generate high-fidelity, animatable 4D Gaussian avatars from single portrait images, offering a new paradigm for controllable avatar creation.
Tired of color bleeding and unpredictable results in multi-modal image editing? CARE-Edit dynamically routes diffusion tokens to specialized experts, finally untangling conflicting conditions for cleaner edits.
