Sim-trained ZAP robot policy hits 96.7% on real tasks
A 27B vision-language model fine-tuned only in simulation matches GPT-6 Astra and beats MolmoAct2's 33.3% in the same harness.
48
- Mentions · 7d1
- Mentions · 30d1
- All mentions1
- First seenOct 26, 2026
- Last mentioned4d ago
Timeline
1 articles · newest firstAppears with
- MolmoAct2ai model · 1
- GPT-6 Astraai model · 1
- Frankaproduct · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.