Google DeepMind · Visual Understanding
Sign Language to Text (SL2T)
Launched 12 August on Pixel 11 at no cost: on-device MediaPipe pose tracking feeds a translation model that maps coordinate sequences straight to text, skipping the intermediate gloss annotation the field has leaned on. Scores 70 BLEURT zero-shot on FLEURS-ASL, well above any previously reported figure. Trained on 100,000+ hours across 50+ sign languages.
Open the source ↗Similar Vision & Image releases
- WeVisOne-VL
WeChat Vision, Tencent · Vision-Language Model · Week 44, 2026
- Nemotron 3.5 Super VL
NVIDIA · Open Multimodal MoE · Week 43, 2026
- Vision Demos
jeremyipark · Sports Vision Demos · Week 41, 2026
- PixelUMM
NVIDIA and University of Waterloo · Encoder-Free Unified Model · Week 41, 2026
- Ovis-Embedding
ATH-MaaS · Ovis Embedding Models · Week 40, 2026
- RADAR
RADAR-Generalist team, published in Science · Abdominal CT Vision Model · Week 40, 2026
More from Google DeepMind
- Gemini 4 Carbon
Google DeepMind · Frontier cyber LLM · Week 45, 2026
- Genie 4
Google DeepMind · Interactive world model · Week 45, 2026
- Gemini 4 Argon
Google DeepMind · Frontier Model · Week 43, 2026
- AlphaProtein Novo
Google DeepMind · De Novo Enzyme Design · Week 42, 2026
- EmbeddingGemma 2
Google DeepMind · Multimodal Embeddings · Week 42, 2026
- Nano Banana 2.1
Google DeepMind · Image Generation Model · Week 42, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.