Search papers, labs, and topics across Lattice.
bytedance
3
0
6
0
Ditching diffusion's noise-denoising, RLFSeg uses Rectified Flow to directly predict segmentation masks from text prompts, unlocking zero-shot performance gains.
Forget generic assistants – EgoSelf learns your habits from your first-person view data to predict your future interactions.
Robots get a spatial reasoning boost: ReMAP-DP fuses multi-view images and point clouds in a diffusion policy, achieving state-of-the-art manipulation performance with surprisingly little data.
