ForcingBooster halves computation of autoregressive video diffusion with patch-wise denoising
VAST-AI · hf · 2026-10-16
ForcingBooster proposes an adaptive patch-wise denoising framework to speed up autoregressive video diffusion: denoising steps are dynamically allocated to video patches based on difficulty, cutting computation by half while preserving quality.
The paper demos two applications: interactive video generation (with WASD-style input controlling the denoising schedule) and video world models (e.g., a first-person riding scene), showing the method extends to interactive generative world models.
More from Multimodal
- Pollo AI launches Recast video restyling, 60% off for launch — SimplyAnnisa · 2026-10-16
- Tripo hosts first world-building hackathon in SF with World Labs and Runway talks — mhdfaran · 2026-10-16
- Kling 4.0 boosts text-to-video with character consistency and lip sync — CurieuxExplorer · 2026-10-16
- 5.8M-param Speech Event Detector adds laughs, breaths and背景 sounds to Whisper transcripts — Ayush Kumar Bar · 2026-10-16
- Huawei's SUPRA-Tex turns one image into relightable 3D materials with WYSIWYG fidelity — Chen Yang · 2026-10-16
- Giant Michael Jackson AI fashion images show the power of extreme proportions — OVolosin82152 · 2026-10-16