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
AI model
MolmoAct2
- Mentions · 7d1
- Mentions · 30d3
- All mentions5
- First seenSep 12, 2026
- Last mentioned4d ago
Timeline
5 articles · newest firstVLA-Rolling reuses action tails to cut VLA denoising steps
Across 16 frozen model-benchmark pairs it lowered chunk inference cost, with up to 1.48 times speedup and higher success in 14.
42
FastOPD: On-Policy Distillation for Lightweight VLA Deployment
FastOPD distills large vision-language-action models into few-step students that keep most performance at much lower latency.
52
GPT-6 Astra and Claude Fable turn robot arms into slapstick killer robots in new safety benchmark
RoboHarm benchmark found GPT-6 Astra, Claude Fable 5.1, and MolmoAct2 rarely refuse dangerous robot-arm commands, completing most harmful physical tasks.
48
GPT-6 Astra appears to show a "step change" in spatial reasoning based on early benchmarks
Early StationeryBench robotics results show OpenAI's GPT-6 Astra far ahead of Ai2's MolmoAct2 at dual-arm manipulation, completing 7 of 100 tasks versus zero.
48
Appears with
- GPT-6 Astraai model · 3
- pi0.5ai model · 2
- LIBEROproduct · 1
- ZAPai model · 1
- Inspect Robotsproduct · 1
- Anthropicvendor · 1
- Robocurveorganization · 1
- MolmoAct2product · 1
- Claude Fable 5.1product · 1
- Frankaproduct · 1
- Ai2vendor · 1
- X-VLAai model · 1
- Cornellorganization · 1
- GPT-6 Astraproduct · 1
- OpenAIvendor · 1
- Claude Fable 5.1ai model · 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.