Tagged articles

generative diffusion

2 articles · Page 1 of 1
Kuaishou Audio & Video Technology
Kuaishou Audio & Video Technology
Jun 9, 2026 · Artificial Intelligence

CVPR NTIRE 2026 UGC Short‑Video Restoration Challenge: Winning Solutions and Highlights

The CVPR NTIRE 2026 challenge introduced the KwaiVIR benchmark for real‑world UGC short‑video degradation, attracted 95 registered teams with 12 final submissions from 14 universities and 5 companies, evaluated on subjective human scores and objective metrics (PSNR, SSIM, LPIPS, MUSIQ, WarpError), and saw RedMediaTech achieve the top overall performance with a subjective score of 3.8525 and the best objective results (PSNR 30.7610, SSIM 0.8504, LPIPS 0.1910), while detailed analyses of the leading three methods reveal diverse two‑stage diffusion and generative pipelines.

CVPRDeep LearningNTIRE
0 likes · 10 min read
CVPR NTIRE 2026 UGC Short‑Video Restoration Challenge: Winning Solutions and Highlights
HyperAI Super Neural
HyperAI Super Neural
Dec 31, 2025 · Artificial Intelligence

How RFdiffusion3 Achieves a Generative Breakthrough in Full‑Atom Protein Design

RFdiffusion3, the open‑source model from David Baker’s lab, extends diffusion‑based protein design to full‑atom resolution—including ligands and nucleic acids—by explicitly modeling all polymer atoms, cutting Pairformer layers from 48 to 2, and offering a lightweight 168 M‑parameter architecture that can be deployed with a single‑click tutorial on HyperAI.

AI protein modelingAlphaFold3 comparisonComputational Efficiency
0 likes · 5 min read
How RFdiffusion3 Achieves a Generative Breakthrough in Full‑Atom Protein Design