Search papers, labs, and topics across Lattice.
Thanks:
3
0
4
Lever-Edit shows that you can effectively optimize image editing policies using T2I rewards, bypassing the need for costly editing-specific rewards altogether.
Joint online post-training in GenTrack boosts humanoid tracking accuracy and expands zero-shot capabilities without requiring new data.
Pixel-Space Diffusion Transformers could redefine high-fidelity image generation by integrating visual understanding and generation in a unified model.
