Tencent ARC's Future Chunk Prediction Boosts Physical Plausibility in Video Diffusion
TencentARC · hf · 2026-10-22
Nanjing University and Tencent ARC Lab introduce Future Chunk Prediction (FCP), an auxiliary objective for autoregressive video diffusion that predicts temporally separated future chunks without accessing intervening content. FCP needs no extra visual encoder, leaves inference unchanged, and achieves better physical plausibility with lower training compute. Code is open-sourced.
More from Multimodal
- Indie dev uses AI to 1:1 recreate his own RV for his fourth game — ezshine · 2026-10-22
- User Shows Off Cinematic AI Video Made with Seedance 2.5 — SimplyAnnisa · 2026-10-22
- Seedance 2.5 video demo goes viral for 'pure cinematic perfection' quality — SimplyAnnisa · 2026-10-22
- Fudan's TextRIRO enables scene text editing with self-paired real data only — Fudan-University · 2026-10-22
- StreamEval benchmarks streaming video generation: best model scores just 36.90 on task execution — StreamEval Team · 2026-10-22
- Spline launches ChatGPT integration to create and edit interactive 3D scenes in chat — algo_diver · 2026-10-22