Revision History
RT-2 · 7 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: Corrected RT-2's training data (RT-1 data, not Open X-Embodiment, and no Bridge Data), the Language-Table result (a 3B model on simulated tabletop tasks, not long-horizon tasks), and the model-size and co-fine-tuning ablation claims, which misstated how the PaLI-X and PaLM-E variants compared (plus 23 minor fixes)
Version 7 · Nov 4, 2026, 04:06 PM
- Improve internal links (2026-10-13)
Version 5 · Oct 13, 2026, 10:20 AM
- Added 6 contextual internal links
Version 4 · Jul 23, 2026, 03:29 PM