The authors trained a flow-matching model over video states and actions, assigning independent noise levels to each modality and timestep.
Flexible block-causal models sustain efficient long-horizon action-conditioned rollouts
FLEX-WAM uses one checkpoint to predict futures, generate actions and support planning across variable context and prediction lengths.
Big Tech
R. Khorrambakht · Joseph Amigo · Félix Lebel · Leon Seetoo · Jean Ponce · Zhenzhen Li · +1 more
Center for Robotics and Embodied Intelligence (CREO), New York University · Courant Institute of Mathematical Sciences · Center for Data Science, New York University · Ecole normale supérieure - PSL · NVIDIA
Research Digest··2 min read
Khorrambakht and colleagues introduce FLEX-WAM, a joint generative model of states and actions designed for efficient, open-loop simulation over long horizons.
Why this paper
From NVIDIA and 5 others
In one line
A block-causal world-action model enables real-time, stable long-horizon imagination and planning, solving benchmark tasks entirely in imagination.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors (2 noted)
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§