Researchers: Astra is more 3D-aware than other frontier multimodal models, likely trained on 3D data
georgiagkioxari · x · 2026-09-18
Georgia Gkioxari and Michael Black discuss Google's Astra model's spatial understanding. Black notes Astra isn't "natively" 3D/4D but understands enough to help scale 3D/4D data collection. Gkioxari adds that Astra is more 3D-aware than other frontier multimodal models, and since such capabilities generally come from pretraining or RLVR, 3D data was likely included in the training mix — which she argues is the sensible choice. The exchange touches on where spatial reasoning in multimodal models comes from.
More from Models
- Skeptical deep dive confirms Humanity's Last Exam errors; official o3-mini grader marked right answers wrong every time — paul_cal · 2026-09-20
- Matt Shumer asks if Jev could help with scalable oversight and alignment checks — mattshumer_ · 2026-09-20
- FrontierSWE v2 opens 24.1-point gap: Claude Fable 5.1 scores 56.29% vs GPT-5.6's 32.2% — geoffwolfe · 2026-09-20
- 22M local model beats JEV 93% vs 80% on Banking77 in 8ms on CPU — Prompt Engineering · 2026-09-20
- Jev loses to Gemini on 1,565-email classification benchmark, but dev still wants it in production — socialwithaayan · 2026-09-20
- Jev Detector scans ~10,000 words for AI slop in ~2 seconds, free with no sign-up — socialwithaayan · 2026-09-20