FlowWAM: Optical Flow as a Unified Action Representation for World Action Models
World Action Models (WAMs) are able to leverage pretrained video generators for both world modeling and action prediction. However, directly leveraging such video generators for control raises a new challenge: how to represent actions in a suitable form that aligns with pretrained video generators while carrying enough motion cues for accurate control. Existing numerical actions fail to satisfy the former, and prior visual action representations overlook the temporal motion structure across frames. We address this issue with FlowWAM, a dual-stream diffusion framework that adopts optical flow a
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 52%Flux 3 X Mimic: The Next Generation of Video-Action Models →
- LinkedLinked via arxiv author · 85%Yixiang Chen →
“FlowWAM: Optical Flow as a Unified Action Representation for World Action Models”
- LinkedLinked via arxiv author · 85%Peiyan Li →
“FlowWAM: Optical Flow as a Unified Action Representation for World Action Models”
- LinkedLinked via arxiv author · 85%Yuan Xu →
“FlowWAM: Optical Flow as a Unified Action Representation for World Action Models”
- LinkedLinked via arxiv author · 85%Qisen Ma →
“FlowWAM: Optical Flow as a Unified Action Representation for World Action Models”
- LinkedLinked via arxiv author · 85%Jiabing Yang →
“FlowWAM: Optical Flow as a Unified Action Representation for World Action Models”
- LinkedLinked via arxiv author · 85%Zhaokai Wang →
“FlowWAM: Optical Flow as a Unified Action Representation for World Action Models”
- LinkedLinked via arxiv author · 85%Jianhua Yang →
“FlowWAM: Optical Flow as a Unified Action Representation for World Action Models”