Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration Paper • 2603.24800 • Published 4 days ago • 55
VIVAT: Virtuous Improving VAE Training through Artifact Mitigation Paper • 2506.07863 • Published Jun 9, 2025 • 3
OpenAutoNLU: Open Source AutoML Library for NLU Paper • 2603.01824 • Published 28 days ago • 50
SLIME: Stabilized Likelihood Implicit Margin Enforcement for Preference Optimization Paper • 2602.02383 • Published Feb 2 • 30
Green-VLA: Staged Vision-Language-Action Model for Generalist Robots Paper • 2602.00919 • Published Jan 31 • 319
Kandinsky 5.0 Video Pro Diffusers Collection Kandinsky 5.0 Video Pro is a 19B model that generates high-quality HD videos from English and Russian prompts with controllable camera motion. • 4 items • Updated Dec 14, 2025 • 12