Search papers, labs, and topics across Lattice.
2
0
4
21
Ditch the feature extraction pipeline: GenMask directly generates segmentation masks with a diffusion transformer, achieving SOTA results by harmonizing mask and image generation in a single model.
DLLM inference gets a 2-8x speed boost without quality loss thanks to ReMix, a training-free method that cleverly mixes continuous representations into discrete decoding.
