Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
P-PatchDiff achieves 80脳 faster low-light image enhancement by dynamically adjusting patch sizes, ensuring coherent brightness across varying scales.
State-of-the-art video generation and editing now hinges on a surprisingly simple division of labor: MLLMs for semantic planning, diffusion models for photorealistic rendering.
Forget noisy samples, RL can now directly optimize the *gradients* of diffusion distillation, leading to SOTA few-step image generation.
