stable-diffusion-3.5-large
Hugging Face model with 3700 likes. Tags: diffusers, safetensors, text-to-image, stable-diffusion, en, arxiv:2403.03206, license:other, diffusers:StableDiffusion3Pipeline, region:us
Papers50
We present SynLaD, a latent diffusion framework for small-molecule generation that unifies ligand-based drug design obje
paperAccelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference TechniquesDiffusion large language models (dLLMs) offer a theoretical advantage in parallel generation over standard autoregressiv
paperDiffusion-GR2: Diffusion Generative Reasoning Re-rankerGenerative reasoning re-rankers achieve strong recommendation accuracy by emitting a chain-of-thought before re-ordering
paperExact and Calibrated Diffusion Reconstruction for Digital Breast TomosynthesisLimited-angle digital breast tomosynthesis (DBT) reconstructs a volume from a few low-dose projections over a narrow arc
paperDARTree: Speculative Diffusion Decoding with Autoregressive Draft TreesSpeculative decoding losslessly accelerates autoregressive language models by verifying multiple draft tokens in paralle
paperScore Accuracy Along the Forward Diffusion Does Not Certify Numerical Stability in Diffusion SamplingScore matching controls average error under the forward marginals, but a discretized reverse-time sampler evaluates the
paperTexture++: Elevating 3D Asset Texture Resolution with a Region-Aware Diffusion ModelNumerous 3D assets are discarded due to low texture resolution, while current super-resolution models ignore texture map
paperEvolving Cache Schedules for Fast Diffusion Policy InferenceDiffusion policies achieve strong visuomotor control by iteratively denoising action chunks, but repeated denoising make