Hugging Face Daily Papers·· 2026-10-19AI score48
Fréchet Forcing: Training long-horizon streaming world models with short videos
Frechet Forcing: Training Long-Horizon Streaming World Models from Short Clips
AI briefing
Researchers propose Fréchet Forcing, which fine-tunes a world model and its multi-step sampler through three constraints—generation anchoring, context fidelity, and realism matching—without needing a teacher model, online discriminator, or long videos. MiniWorld-1B, pretrained on 253-frame clips, after fine-tuning for up to 36 GPU hours on 381-frame clips, can roll out stably for more than 4,000 frames and consistently follows action instructions in robotic manipulation and camera-control exploration.
Open original arxiv.org