THE RESEARCH ATLAS

Google DeepMind Papers & Recent Research

Global research organization · Google / Google DeepMind 🇺🇸 United States · 🇬🇧 United Kingdom

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 research source ↗GitHub ↗
2026-10-13 · Google · Model cardGlobal research organization · Google / Google DeepMind 🇺🇸 United States · 🇬🇧 United Kingdom

Gemini 4 Argon — Model Card

Official model documentation covering evaluation, limitations and safety considerations. The date records the listed model-card update.

2026-10-06 · Google · Model cardGlobal research organization · Google / Google DeepMind 🇺🇸 United States · 🇬🇧 United Kingdom

Nano Banana 2.1 — Model Card

Official documentation for an image-and-text model, including inputs, outputs, architecture dependencies and safety evaluation.

2025-10 · Google · Technical reportGlobal research organization · Google / Google DeepMind 🇺🇸 United States · 🇬🇧 United Kingdom

Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer

The report combines embodied reasoning, interleaved thinking and motion transfer across robot embodiments.

2025-07 · Google · Technical reportGlobal research organization · Google / Google DeepMind 🇺🇸 United States · 🇬🇧 United Kingdom

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

An industrial model-family report covering reasoning, multimodal input, long contexts and agent-related evaluations.

2025-03 · Google · Technical reportGlobal research organization · Google / Google DeepMind 🇺🇸 United States · 🇬🇧 United Kingdom

Gemini Robotics: Bringing AI into the Physical World

Gemini-based models address robot manipulation and embodied reasoning, connecting multimodal understanding with physical control.

2023-07 · Google · Research paperGlobal research organization · Google / Google DeepMind 🇺🇸 United States · 🇬🇧 United Kingdom

RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

Vision-language models are trained to produce robot actions, exploring transfer from web-scale learning to robotic control.

2022-03 · Google · Research paperCredited institutions · DeepMind 🇬🇧 United Kingdom

Training Compute-Optimal Large Language Models

The study examines how to allocate a training-compute budget between model size and training data.

2018-10 · Google · Research paperCredited institutions · Google AI Language 🇺🇸 United States

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Masked-language pretraining learns bidirectional representations that can be adapted to language-understanding tasks.

2017-06 · Google · Research paperCredited institutions · Google / University of Toronto 🇺🇸 United States · 🇨🇦 Canada

Attention Is All You Need

The Transformer replaces recurrent sequence processing with attention, creating a foundation for many later language and multimodal models.

What this index holds from Google DeepMind

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.

Related work on the same topics

These records come from other institutions but address the same topics, so the lab can be read in context.