From Scores to Samples: Elastic Forcing for Autoregressive Video Generation
cs.CV, cs.AI
Submitted: 2026-09-28
Updated: 2026-09-30
Code: https://github.com/krea-ai/realtime-video
Project page: https://video-examples-m8r2v6.pages.dev
Terminology
Sources
- MAGI-1: Autoregressive Video Generation at Scale
- Maximum Mean Discrepancy Gradient Flow
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- Revisiting Feature Prediction for Learning Visual Representations from Video
- The Cramer Distance as a Solution to Biased Wasserstein Gradients
- Demystifying MMD GANs
- GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
- Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
- SkyReels-V2: Infinite-length Film Generative Model
- Context Forcing: Consistent Autoregressive Video Generation with Long Context
- Training Deep Nets with Sublinear Memory Cost
- Autoregressive Video Generation without Vector Quantization
- Generative Modeling via Drifting
- Training generative neural networks via Maximum Mean Discrepancy optimization
- Representation Distribution Matching for One-Step Visual Generation
- Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing
- Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup
- End-to-End Training for Autoregressive Video Diffusion via Self-Resampling
- LTX-Video: Realtime Video Latent Diffusion
- Masked Autoencoders Are Scalable Vision Learners
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