Gemini 4 Argon — Model Card
Official model documentation covering evaluation, limitations and safety considerations. The date records the listed model-card update.
Gemini · Science · Robotics. Selected primary papers, reports, model cards and official technical articles. Checked 2026-10-25. Product announcements are not presented as papers.
Official model documentation covering evaluation, limitations and safety considerations. The date records the listed model-card update.
Official documentation for an image-and-text model, including inputs, outputs, architecture dependencies and safety evaluation.
The report combines embodied reasoning, interleaved thinking and motion transfer across robot embodiments.
An industrial model-family report covering reasoning, multimodal input, long contexts and agent-related evaluations.
Gemini-based models address robot manipulation and embodied reasoning, connecting multimodal understanding with physical control.
Vision-language models are trained to produce robot actions, exploring transfer from web-scale learning to robotic control.
The study examines how to allocate a training-compute budget between model size and training data.
Masked-language pretraining learns bidirectional representations that can be adapted to language-understanding tasks.
The Transformer replaces recurrent sequence processing with attention, creating a foundation for many later language and multimodal models.
This index currently holds 9 records attributed to Google DeepMind (2017–2026). Each entry links to the primary source; product announcements and news posts are not counted as papers.
These records come from other institutions but address the same topics, so the lab can be read in context.