Connected Self Forcing: Beyond Local Learning in Video Autoregression

arXiv:2610.12156 · cs.CV · Submitted 2026-10-08 · Read on arXiv

cs.CV

Submitted: 2026-10-08

Updated: 2026-10-08

Code: https://github.com/MiniMax-AI/MiniMax-H3

Terminology

• Self Forcing — 36× in this paper
• Consistency — 35× in this paper · explained in 3 episodes
• Connected Self Forcing — 19× in this paper
• Diffusion Model — 19× in this paper · explained in 8 episodes
• Diffusion Models — 18× in this paper · explained in 6 episodes
• Distillation — 10× in this paper · explained in 2 episodes
• Transformer — 8× in this paper · explained in 2 episodes
• Distribution Matching — 7× in this paper · explained in 2 episodes
• Temporal consistency — 5× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Conference on Computer Vision and Pattern Recognition — 4× in this paper
• Distribution Matching Distillation — 4× in this paper
• Gradient Flow — 4× in this paper · explained in 2 episodes
• Self Gradient Forcing — 4× in this paper
• Adam — 3× in this paper · explained in 2 episodes
• Generative Model — 3× in this paper · explained in 2 episodes
• Generative Models — 3× in this paper · explained in 2 episodes
• KV cache — 3× in this paper · explained in 3 episodes
• World Model — 3× in this paper · explained in 7 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Aggregation — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Flow Matching — 2× in this paper · explained in 8 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Allocator — 1× in this paper · explained in 1 episode
• Consistency Distillation — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Exposure Bias — 1× in this paper · explained in 2 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Latent Diffusion Model — 1× in this paper · explained in 2 episodes
• Latent Diffusion Models — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes

Sources

• Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
• SkyReels-V2: Infinite-length Film Generative Model
• VideoCrafter1: Open Diffusion Models for High-Quality Video Generation
• Context Forcing: Consistent Autoregressive Video Generation with Long Context
• LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation
• LongVie 2: Multimodal Controllable Ultra-Long Video World Model
• AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
• Latent Video Diffusion Models for High-Fidelity Long Video Generation
• Imagen Video: High Definition Video Generation with Diffusion Models
• CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers
• Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraft
• Vid2World: Crafting Video Diffusion Models to Interactive World Models
• VideoPoet: A Large Language Model for Zero-Shot Video Generation
• HunyuanVideo: A Systematic Framework For Large Video Generative Models
• Video Generators are Robot Policies
• VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation
• Latte: Latent Diffusion Transformer for Video Generation
• TetherCache: Stabilizing Autoregressive Long-Form Video Generation with Gated Recall and Trusted Alignment
• Movie Gen: A Cast of Media Foundation Models
• Progressive Distillation for Fast Sampling of Diffusion 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