newsHacker NewsTrust 52 · CommunityPublished yesterdayLive · yesterday
Flux 3 X Mimic: The Next Generation of Video-Action Models
199points24comments
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) · 58%Native Video-Action Pretraining for Generalizable Robot Control →
- PossiblePossibly related (embedding) · 53%lucidrains/mimic-video →
- PossiblePossibly related (embedding) · 52%FlowWAM: Optical Flow as a Unified Action Representation for World Action Models →
- PossiblePossibly related (embedding) · 49%Masked Visual Actions for Unified World Modeling →
- PossiblePossibly related (embedding) · 48%HarmoHOI: Harmonizing Appearance and 3D Motion for Multi-view Hand-Object Interaction Synthesis →
Covers
paperNative Video-Action Pretraining for Generalizable Robot Controlrepolucidrains/mimic-videopaperFlowWAM: Optical Flow as a Unified Action Representation for World Action ModelspaperMasked Visual Actions for Unified World ModelingpaperHarmoHOI: Harmonizing Appearance and 3D Motion for Multi-view Hand-Object Interaction Synthesis
Related across the graph
paperNative Video-Action Pretraining for Generalizable Robot Controlrepolucidrains/mimic-videopaperFlowWAM: Optical Flow as a Unified Action Representation for World Action ModelspaperHarmoHOI: Harmonizing Appearance and 3D Motion for Multi-view Hand-Object Interaction SynthesispaperMasked Visual Actions for Unified World Modeling