arXiv AI
Direct Forcing: Single-Stage Training with Representation-Space Supervision for Few-Step Autoregressive Video Generation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
5d ago
Direct Forcing: A Single-Stage Training Recipe for Few-Step Autoregressive Text-to-Video Generation
Direct Forcing is a single‑stage training framework for few‑step autoregressive text‑to‑video generation that eliminates the need for separate causal adaptation and distribution matching stages. It uses reference videos both as paired examples for causal continuation alignment and as a target distribution for rollout distribution matching, with dynamic gradient balancing to adjust their contributions during training. Starting from a bidirectional Wan2.1‑1.3B model, Direct Forcing trains a four‑step generator in only 250 updates, achieving state‑of‑the‑art VBench scores without additional initialization or diffusion‑score supervision.
arXiv Computer Vision
1d ago
Mix Forcing: Causal Pre-Training via Mixture Attention for Interactive World Models
arXiv:2610.33589v1 Announce Type: new Abstract: While interactive video world models require autoregressive generation, directly adapting pretrained bidirectional video diffusion models into autoregr...
arXiv Computer Vision
Sep 25
ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation
ViRDM is a new post‑training method for few‑step causal video generation that eliminates the need for a large teacher model and an online critic. By applying representation distribution matching (RDM) with a precomputed target distribution, a lightweight VAE decoder, and staged vector–Jacobian products, ViRDM overcomes memory, optimization, and temporal dynamics challenges. The approach reduces GPU memory usage and training time, achieving state‑of‑the‑art VBench performance with only 20 generator updates and 16 A100 GPU‑hours.
Hugging Face Trending Papers
Sep 24
ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation
Few-step autoregressive (AR) video diffusion enables low-latency streaming generation, but existing post-training methods predominantly rely on Distribution Matching Distillation (DMD), requiring both...
arXiv Computer Vision
Oct 9
Connected Self Forcing: Beyond Local Learning in Video Autoregression
The paper introduces Connected Self Forcing, a training framework that reconnects gradient paths across autoregressive video chunks to improve long‑horizon visual quality and temporal consistency. It allows feedback from later predictions to influence earlier context generation, using shortcut gradient replay to keep memory usage manageable. The method is combined with distribution‑matching distillation and shows experimental gains without altering the inference procedure.
arXiv AI
Oct 15
Prospective Forcing: Learning to Look Ahead for Autoregressive Long Video Diffusion
arXiv:2610.14654v1 Announce Type: cross Abstract: Autoregressive video generators synthesize long videos through chunk-wise rollouts, yet they are typically trained to predict only the immediate futu...