Kandinsky 5.0 Video Lite Collection Kandinsky 5.0 Video Lite is a lightweight 2B model that generates up to 10-second SD videos from English and Russian prompts with high visual quality. • 9 items • Updated 3 days ago • 18
Kandinsky 5.0 Image Lite Collection Kandinsky 5.0 Image Lite is a 6B DiT-based model that generates and edits HD images from English and Russian text prompts with high visual quality. • 4 items • Updated 3 days ago • 27
Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation Paper • 2610.05608 • Published 5 days ago • 158
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It Paper • 2609.36585 • Published 10 days ago • 78
MuScriptor: An Open Model for Multi-Instrument Music Transcription Paper • 2607.08168 • Published Jul 9 • 18
NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction Paper • 2609.10715 • Published about 1 month ago • 331
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions Paper • 2609.04199 • Published Sep 3 • 333
Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published Sep 7 • 376
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills Paper • 2609.02749 • Published Sep 2 • 408
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation Paper • 2609.11638 • Published 29 days ago • 707
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence Paper • 2609.17488 • Published 24 days ago • 817
Muscriptor Collection Developed in collaboration with Mirelo (AI https://www.mirelo.ai/), MuScriptor is an open-weight model for multi-instrument automatic transcription • 4 items • Updated 7 days ago • 2
ERNIE-Image Collection The serieas of image generation models, including text2img、img2img. • 4 items • Updated May 20 • 25