Bias, Misalignment, and AI Safety Collection Human Values Alignment, Jailbreaking Prevention, Bias Mitigation • 15 items • Updated 2 days ago
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 6 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 6 days ago • 27
Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation Paper • 2610.05608 • Published 8 days ago • 167
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It Paper • 2609.36585 • Published 13 days ago • 71
MuScriptor: An Open Model for Multi-Instrument Music Transcription Paper • 2607.08168 • Published Jul 9 • 18
Chat-Style and Reasoning Datasets Collection Data from Models: Claude Opus 4.5, Deepseek R1, Qwen 3, GLM 4.7, GPT 5, GPT Codex, Gemini 3 Pro • 86 items • Updated 9 days ago • 1
NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction Paper • 2609.10715 • Published Sep 9 • 269
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions Paper • 2609.04199 • Published Sep 3 • 332
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