1B Vision Model Beats Google and NVIDIA in Depth Estimation
thetripathi58 · x · 2026-07-08
According to the post, the 1B vision model LingBot-Vision, trained by Robbyantbrain, outperforms Google SigLIP 2 and NVIDIA AM-RADIO on the NYU-Depth v2 depth estimation benchmark with a lower RMSE.
The author emphasizes that this performance gap primarily stems from the pre-training objectives rather than just model scale.
Related event: Ant Robbyant Open-Sources LingBot Vision Models, Topping Depth Benchmarks(18 posts)→
More from Embodied
- NVIDIA open-sources FLORA, a robotics data engine ~125x cheaper than GPT-6 Astra — nvidia · 2026-10-27
- Embodied AI startups need a different operational discipline, investor says — ___Mufasaa · 2026-10-27
- π0.5 study: raising demos from 10 to 438 lifts Place Ball in Bowl success from 7% to 83% — stingning · 2026-10-27
- GPT-6 Astra controls dexterous hands zero-shot at just 5.2% success in 500 trials — stingning · 2026-10-27
- HandsOn benchmark: 66 verified tasks and 18,000 human demos for dexterous manipulation — stingning · 2026-10-27
- DexPort: a handheld interface with a real robot hand for dexterous-hand data collection — pabbeel · 2026-10-27