Fast-WAM
World-action model from Tsinghua IIIS and Galaxea AI that co-trains on video during training but skips future-frame generation at inference, predicting actions in a single forward pass. It is the base of several later WAMs (CSWAM, DiffWAM, RelayWAM, Elastic-WAM). The RoboTwin and RoboDojo teams run it as a baseline on their boards.
Tsinghua University & Galaxea AI · Mar 17, 2026 · World-actionReport an error
97.6%LIBERO · #44 of 83
39.8%RoboTwin 2 · #24 of 33
2.0%Dojo Sim · #53 of 71
6BParameters
Benchmark results3
RoboDojo (sim)Simulation
- Official leaderboard ↗Jul 6, 2026
#53 of 712.0%
- 39.8%Official leaderboard ↗Aug 10, 2026· n = 10000
- 91.8%, self-reported by the authors, not a leaderboard entryPaper / model card ↗Mar 2026· self-reported, 50 clean + 500 randomized demos· n = 10000· non-standard
#24 of 3339.8%
- Paper / model card ↗Mar 2026· n = 2000
#44 of 8397.6%, self-reported by the authors, not a leaderboard entry
Not reported on 12 benchmarks
Wrong or missing number? Report an error