Salt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
The Flow has not summarised this story yet — read it at arXiv AI.
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:2610.35594v1 Announce Type: new Abstract: Few-step distillation is essential for deploying modern video diffusion models. Among existing approaches, Distribution Matching Distillation (DMD) has...
arXiv:2606. 25473v1 Announce Type: cross Abstract: Autoregressive video diffusion with causal diffusion transformers has emerged as a major paradigm for real-time streaming video generation and action-conditioned interactive world models.
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:2610.30861v2 Announce Type: replace-cross Abstract: Few-step autoregressive video generation enables low-latency streaming, yet prevailing training pipelines separate causal adaptation from dis...
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...