Search papers, labs, and topics across Lattice.
3
1
6
5
Achieve near-lossless 60% attention latency reduction in video editing by exploiting query sharpness to dynamically route attention.
Aligning diffusion models with just 100 carefully selected samples can beat state-of-the-art preference optimization methods trained on thousands, and converge up to 220x faster.
By explicitly detecting and escaping "Forbidden Zones" during training, AMD unlocks significant gains in sample fidelity and training robustness for few-step generative models like SDXL.
