Search papers, labs, and topics across Lattice.
4
0
7
3
Pixel-space diffusion models can now rival latent-space counterparts while achieving up to 4.75 times faster inference.
Achieving high visual fidelity while ensuring physical consistency in video generation could redefine the standards for simulating realistic interactions in AI-generated content.
Z-Reward achieves 41.3% better human preference alignment in text-to-image generation by transforming complex reasoning into efficient score distributions.
Naively plugging in a powerful LLM text encoder into one-step image generators like MeanFlow fails, but this work shows how to make it work.
