ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation

arXiv:2609.28923 · cs.CV · Submitted 2026-09-24 · Read on arXiv

cs.CV

Submitted: 2026-09-24

Updated: 2026-09-24

Code: https://github.com/madebyollin/taehv

Terminology

• Distribution Matching — 30× in this paper · explained in 2 episodes
• Distillation — 26× in this paper · explained in 2 episodes
• Regularization — 21× in this paper · explained in 3 episodes
• Consistency — 19× in this paper · explained in 3 episodes
• Representation Distribution Matching — 18× in this paper
• Diffusion Model — 17× in this paper · explained in 8 episodes
• Diffusion Models — 13× in this paper · explained in 6 episodes
• Computer Vision and Pattern Recognition — 9× in this paper
• Distribution Matching Distillation — 7× in this paper
• Alignment — 6× in this paper · explained in 1 episode
• Consistency Distillation — 4× in this paper · explained in 2 episodes
• Generative Model — 4× in this paper · explained in 2 episodes
• World Model — 4× in this paper · explained in 7 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• Generative Modeling — 3× in this paper · explained in 3 episodes
• Generative Models — 3× in this paper · explained in 3 episodes
• In International Conference on Learning Representations — 3× in this paper
• International Conference on Machine Learning — 3× in this paper
• Trace — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Decode — 2× in this paper · explained in 2 episodes
• Flow Matching — 2× in this paper · explained in 8 episodes
• Gradient Flow — 2× in this paper · explained in 2 episodes
• Optical Flow — 2× in this paper · explained in 2 episodes
• Adaptive Sampling — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Causal Inference — 1× in this paper · explained in 4 episodes
• Closed-Loop Control — 1× in this paper · explained in 3 episodes
• Copula — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• KV cache — 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
• Quantization — 1× in this paper · explained in 12 episodes
• Self-Distillation — 1× in this paper · explained in 7 episodes
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Variational Bayes — 1× in this paper · explained in 2 episodes

Sources

• Layer Normalization
• Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation
• Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
• Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
• SkyReels-V2: Infinite-length Film Generative Model
• Generative Modeling via Drifting
• One-Forcing: Towards Stable One-Step Autoregressive Video Generation
• Representation Distribution Matching for One-Step Visual Generation
• Vidarc: Embodied Video Diffusion Model for Closed-loop Control
• Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing
• AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss
• Seedance 1.0: Exploring the Boundaries of Video Generation Models
• LTX-Video: Realtime Video Latent Diffusion
• One-Step Generative Modeling via Wasserstein Gradient Flows
• Imagen Video: High Definition Video Generation with Diffusion Models
• RELIC: Interactive Video World Model with Long-Horizon Memory
• ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer
• Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
• Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
• VBench: Comprehensive Benchmark Suite for Video Generative 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