World Action Models (WAMs) use the predictive knowledge of pretrained video diffusion models for robot control through future video prediction. However, iterative video denoising is costly, and inaccu
DreamFree repurposes a pretrained video diffusion model as a predictive visual encoder through representation distillation, enabling real-time robot action prediction without generating future videos and improving control and learning from video demonstrations.
World Action Models (WAMs) use the predictive knowledge of pretrained video diffusion models for robot control through future video prediction. However, iterative video denoising is costly, and inaccurate visual predictions can compromise action prediction. Our key idea is to make this predictive knowledge available through visual representations computed from the current observation, enabling action prediction without generating future videos. We introduce DreamFree, a WAM that repurposes a pretrained video diffusion model as a predictive visual encoder through representation distillation. The visual encoder learns to predict a frozen video diffusion model's representation using only the…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Future Representation Distillation for Imagination-free World Action Models was first seen on Hugging Face · Daily papers on Nov 6, 2026. Since then it has appeared in 25 checks on 3 different days. Its best position was #21 of 30, reached on Nov 7, 01:28 UTC. It is #27 right now, slipping from #24 to #27 over the last 6 checks.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
▲ as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Yes. As of Nov 8, 15:28 UTC it is #27, slipping from #24 to #27 over the last 6 checks.
#21 on Hugging Face · Daily papers, on Nov 7, 01:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Nov 6, 2026 and has been on the list on 3 days (25 checks) since.