Search papers, labs, and topics across Lattice.
3
0
7
Dynamic token editing in image synthesis could redefine how we approach high-resolution generative models.
A single generalist model outperforms specialized systems, achieving over 35% improvement in real-world robotic task success.
Get up to 1.79x faster ViT inference on high-resolution images without sacrificing accuracy by surgically replacing full-attention blocks with cheaper alternatives *after* pre-training.
