Google Research introduces the planetary prediction engine (PPE), an experimental research capability under the Google Earth AI initiative that autonomously executes the full geospatial modeling…
Google Research announces GlucoFM, a lightweight self-supervised foundation model for continuous glucose monitoring that uses a dual-stream design to separate slower glycemic trends from short-term…
AgentHands is a research prototype that uses LLMs to generate synchronized hand gestures for AI agents in XR, enabling spatially grounded conversations.
Google Research introduces the Biomarker Discovery Framework, a multi-agent system that prioritizes candidate biomarkers from wearable sensor data through iterative hypothesis generation, statistical…
Google Research introduces a dynamic, mobility-informed framework called Mobility-Embedded POIs (ME-POIs) that enriches language model place representations by incorporating aggregated and anonymized…
Google Research introduces PhotoScan, a deep learning framework that estimates body composition metrics (body fat percentage, A/G ratio, V/S ratio) from standard 2D smartphone photos, achieving…
Google Research introduces knowledge profiling, a behavioral framework that distinguishes encoding failures from recall failures in LLMs.
Google Research announces AMIE (Video), a real-time video configuration of its research medical AI system AMIE, built on Gemini and Project Astra, which conducts synchronous clinical video…
Google Research introduces the Science One Framework, an experimental research prototype that uses Chain-of-Evidence (CoE) to eliminate hallucinations by building verifiable evidence chains, and CoE…
Google Research presents SymptomAI, a research study of conversational AI agents for symptom assessment and differential diagnosis, using Gemini Flash 2.0.
Google Research demonstrated a reinforcement learning framework for quantum error correction that allows a quantum computer to continuously adapt to drift and remain stable during long computations,…
Google Research published a paper showing that the creativity of diffusion models is a mathematical consequence of neural networks learning a smoothed version of the score function, which causes…
Google Research presents SensorFM, a foundation model for wearable health data pre-trained on over one trillion minutes of sensor data from five million people.
Google Research published a study in Nature Cities showing that coordinating a small fraction of trips via navigation apps can improve traffic speeds and reduce emissions across entire cities.
Google Research expands building-level rooftop reflectivity dataset to over 50 global cities, and launches a new Heat Resilience Earth Engine App to make the data accessible.
Google Research introduces TabFM, a zero-shot foundation model for tabular data that performs classification and regression without traditional training.
Google Research introduces a method to retrofit Multi-Token Prediction onto frozen Gemini Nano v3 models, accelerating on-device inference on Pixel 9 and 10 series without separate drafters.
Google Research announces linear elastic caching, a new approach to cache management that treats memory as a variable cost and uses a ski rental formulation to dynamically adjust cache size.
Google Research presents a study on how reasoning helps LLMs recall simple facts even when step-by-step reasoning is unnecessary, identifying two mechanisms: a computational buffer effect and factual…
Google Research developed a high-resolution deep learning framework to map fine-scale ecological features like hedgerows and copses, and released a vectorized dataset (Vectorized Farmscapes 2020) for…
Google Research published findings showing that an AI-powered informational tool significantly improves laypeople's ability to identify and name skin conditions, with accuracy nearly three times…
Researchers at UC San Diego, with Google support, are building a low-carbon computing platform by repurposing retired Pixel smartphones into a datacenter cluster.
Google Research introduces Regularized f-Divergence Kernel Tests, a new framework for auditing machine unlearning that uses statistical divergence measures to verify whether a model has forgotten…
Google Research introduces a new agentic RAG framework that breaks down complex enterprise queries, iteratively searches for sufficient context, and includes a Sufficient Context Agent to ensure…
Google Research introduces a passive heart rate monitoring system (PHRM) that uses a smartphone's front-facing camera to measure heart rate and resting heart rate from facial video during everyday…
Google Research has open-sourced its hydrology modeling framework on GitHub, which includes two versions of the hydrological model: the original version and an upgraded v2 model using ME-LSTM…
Google Research announces Gemini for Science, a suite of experimental tools for scientific discovery, including Computational Discovery, Hypothesis Generation, Literature Insights, and Science…
Google Research introduces a private analytics solution that combines a new cryptographic aggregation protocol with trusted execution environments (TEEs) to achieve zero-trust security, enabling…
Google Research announces the publication of Empirical Research Assistance (ERA) in Nature, an AI tool that uses Gemini to write and optimize scientific code for expert-level computational modeling.
Google Research publishes a blog post describing its open science philosophy, partnerships with scientific organizations, and a catalog of open-source tools and datasets across genomics,…
Google Research scientists have been using Empirical Research Assistance (ERA) for real-world applications in epidemiology, cosmology, atmospheric monitoring, and neuroscience, including generating…
Google Research introduces a new method for re-composing photos by changing the camera angle after the photo is taken, using 3D scene estimation and generative inpainting.
ReasoningBank is a novel agent memory framework that uses successful and failed experiences to distill generalizable reasoning strategies, enabling agents to learn continuously after deployment.
Google Research introduces Simula, a framework that reframes synthetic data generation as dataset-level mechanism design, using reasoning to architect datasets from first principles with fine-grained…
Google Research introduces MoGen, a model that generates synthetic neuron shapes to improve AI reconstruction models for brain mapping, reducing reconstruction errors by 4.4%.
Google Research announces Vantage, a research experiment that uses generative AI to assess future-ready skills through simulated conversations, now available on Google Labs.
Google Research introduces ConvApparel, a dataset and evaluation framework to measure and bridge the realism gap in LLM-based user simulators, using a dual-agent protocol and counterfactual…
Google Research introduces two AI agents, PaperVizAgent for generating academic figures and ScholarPeer for automated peer review, both outperforming existing baselines.
Google Research introduces a systematic evaluation framework that converts psychological questionnaires into situational judgment tests to measure how closely LLMs' behavioral dispositions align with…
Google Research introduces an evaluation framework for ML models that optimizes the trade-off between the number of items and raters per item to build reproducible AI benchmarks that capture human…
Google Research publishes a whitepaper with updated quantum resource estimates for breaking elliptic curve cryptography, showing a 20-fold reduction in physical qubits needed, and proposes a…
Google Research announces Vibe Coding XR, a workflow that combines Gemini with the open-source XR Blocks framework to let users create interactive WebXR applications from natural language prompts in…
Google Research introduces TurboQuant, a compression algorithm for large language models and vector search engines, achieving massive compression with zero accuracy loss, along with the QJL and…
Google Research introduces S2Vec, a self-supervised framework that transforms complex geospatial data into general-purpose embeddings to predict socioeconomic and environmental patterns across the…
Google Research at The Check Up event presented multiple AI healthcare innovations including Personal Health Agent (PHA) for personalized health, AI for breast cancer detection and diabetic…
Google Research published two studies in Nature Cancer evaluating an AI-based breast cancer detection system.
Google Research published a study testing six LLMs on expert-level questions about high-temperature superconductivity.
Google Research announces the roll-out of Urban Flash Flood forecasts on Flood Hub, using a new AI-powered methodology that provides up to 24 hours advance notice for flash floods in urban areas.
Google Research introduces Groundsource, a methodology that uses the Gemini LLM to extract structured historical disaster data from news reports, starting with a publicly available dataset of 2.6…
Google Research and Google DeepMind, in partnership with Beth Israel Deaconess Medical Center, conducted a prospective single-center feasibility study of AMIE, a conversational medical AI for…