Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation

arXiv:2610.05608 · cs.CV, cs.AI, cs.LG, cs.MM · Submitted 2026-10-04 · Read on arXiv

cs.CV, cs.AI, cs.LG, cs.MM

Submitted: 2026-10-04

Updated: 2026-10-04

Code: https://github.com/kandinskylab/kandinsky-6

Project page: https://kandinskylab.ai

Terminology

• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes

Sources

• Wan: Open and Advanced Large-Scale Video Generative Models
• TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment
• VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
• Improved Distribution Matching Distillation for Fast Image Synthesis
• pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation
• Parallel Decoding Distillation for Fast Image and Video Generation
• Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation
• Directly Fine-Tuning Diffusion Models on Differentiable Rewards
• Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
• Movie Gen: A Cast of Media Foundation Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models