77 skills (27 production-ready) + 8,000 Galaxy tools + 2,027 tests + benchmark validation. Local-first. No cloud. No guessing. v0.5.0 released (4 Apr 2026): Validation and Benchmark Infrastructure. AD ...
Abstract: Generalizing beyond the training domain in image-based behavior cloning remains challenging. Existing methods address individual axes of generalization, workspace shifts, viewpoint changes, ...