# General Science Published articles for General Science. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Transfer learning for genomic prediction in underrepresented populations DevFeed: [Transfer learning for genomic prediction in underrepresented populations]() Original publisher: [Read original article]() Published: 2026-09-03T18:20:31Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Fine-tuning](), [Model Development](), [Google](), [datasets]() Tags: [datasets](), [evaluation](), [general-science](), [google](), [healthcare](), [learning](), [machine-intelligence](), [research](), [training]() ### AI overview Google Research evaluates transfer learning for polygenic risk-score prediction across populations. European-cohort transfer learning improves prediction for small underrepresented target cohorts but can reduce accuracy as target cohorts grow, particularly for population-specific traits. ### Source excerpt General Science ## A connectomics milestone: Mapping the complete male fruit fly brain DevFeed: [A connectomics milestone: Mapping the complete male fruit fly brain]() Original publisher: [Read original article]() Published: 2026-09-03T16:00:03Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [datasets](), [Google]() Tags: [ai](), [datasets](), [general-science](), [google](), [health-bioscience](), [machine-intelligence](), [open-source](), [open-source-models-datasets](), [research](), [science]() ### AI overview Google Research describes a complete wiring map of the male fruit fly's brain and central nervous system, containing over 166,000 neurons and 125 million synaptic connections. The connectome was produced through a decade-long partnership using computing and AI, and is available to explore and download via Neuroglancer. ### Source excerpt General Science ## Seeing beyond BMI: Estimating cardiometabolic risk with smartphone imagery DevFeed: [Seeing beyond BMI: Estimating cardiometabolic risk with smartphone imagery]() Original publisher: [Read original article]() Published: 2026-08-17T10:34:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Deep neural networks](), [Deep learning](), [Machine learning](), [Google]() Tags: [deep-learning](), [general-science](), [google](), [health](), [health-bioscience](), [machine-intelligence](), [machine-learning](), [monitoring](), [multimodal](), [science]() ### AI overview Google Research presents PhotoScan, a deep learning approach that estimates body composition from smartphone photos and predicts insulin resistance with accuracy comparable to DXA scans in a clinical research setting. The article explains how body-composition measures such as fat distribution and visceral fat may complement wearable data for earlier cardiometabolic risk assessment. ### Source excerpt General Science ## Science One Framework: A verifiable autonomous research framework via Chain-of-Evidence DevFeed: [Science One Framework: A verifiable autonomous research framework via Chain-of-Evidence]() Original publisher: [Read original article]() Published: 2026-07-30T20:36:36Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Artificial Intelligence](), [Google](), [AI-generated research reports](), [Large language models (LLMs)](), [Hallucination detection](), [LLM evaluation / benchmarking]() Tags: [agents](), [ai](), [autonomous-agents](), [benchmarks](), [evaluation](), [general-science](), [google](), [hallucinations](), [language-models](), [machine-intelligence](), [natural-language-processing](), [research](), [research-prototype]() ### AI overview Google Research introduces the Science One Framework, an experimental autonomous research prototype built around Chain-of-Evidence. It is designed to make AI-generated research verifiable by linking claims to supporting evidence and by auditing papers against their code and evidence. The article reports that the framework eliminates phantom references and produces fully verifiable scores in the described evaluations. ### Source excerpt General Science ## SymptomAI: Towards a conversational AI agent for everyday symptom assessment DevFeed: [SymptomAI: Towards a conversational AI agent for everyday symptom assessment]() Original publisher: [Read original article]() Published: 2026-07-22T21:32:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [AI Agent](), [Artificial Intelligence](), [Language models](), [Chat Bot](), [Google](), [LLM evaluation / benchmarking]() Tags: [ai](), [ai-agent](), [benchmarking](), [conversational-ai](), [general-science](), [google](), [health-bioscience](), [healthcare](), [language-models](), [natural-language-processing](), [research](), [responsible-ai]() ### AI overview Google Research presents SymptomAI, a study of conversational AI agents for everyday symptom interviews and differential-diagnosis assessment. The national-scale study involved 13,917 participants interacting with one of five Gemini Flash 2.0 SymptomAI agents, with performance compared against clinical assessments for research benchmarking. ### Source excerpt General Science ## A New Era of Discovery: Google Research at I/O 2026 DevFeed: [A New Era of Discovery: Google Research at I/O 2026]() Original publisher: [Read original article]() Published: 2026-05-28T20:58:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Artificial Intelligence](), [Google](), [agentic-coding](), [coding](), [GitHub]() Tags: [agent](), [agentic](), [agentic-coding](), [ai](), [coding](), [developers](), [general-science](), [generative-ai](), [github](), [global](), [google](), [models](), [quantum](), [research](), [validation]() ### AI overview Google Research highlights its work presented at Google I/O 2026, including Gemini for Science, the ERA coding system, and Co-Scientist, a Gemini-based multi-agent system. The article describes AI tools intended to accelerate scientific discovery through hypothesis generation, computational experimentation, and collaboration with researchers. ### Source excerpt General Science ## Empirical Research Assistance (ERA): From Nature publication to catalyzing Computational Discovery DevFeed: [Empirical Research Assistance (ERA): From Nature publication to catalyzing Computational Discovery]() Original publisher: [Read original article]() Published: 2026-05-19T17:52:00Z Content type: news Language: en Sources: [The latest research from Google]() Topics: [Artificial Intelligence](), [coding](), [Google](), [Benchmark](), [Data Science](), [Software](), [Time Series](), [Mathematics]() Tags: [ai](), [benchmark](), [benchmarks](), [code](), [coding](), [drive](), [general-science](), [google](), [machine-intelligence](), [natural-language-processing](), [open-source-models-datasets](), [time-series]() ### AI overview Google Research introduces Empirical Research Assistance (ERA), an AI tool that uses Gemini to write and optimize scientific code. ERA searches literature, explores solutions, evaluates results, and uses tree search to optimize code for computational experiments. Tests across genomics, public health, satellite imagery, neuroscience, time-series forecasting, and mathematics show expert-level benchmark performance. ERA also helped build the Computational Discovery prototype, which is being made available through Google Labs and Gemini for Science. ### Source excerpt General Science ## Catalyzing scientific impact through global partnerships and open resources DevFeed: [Catalyzing scientific impact through global partnerships and open resources]() Original publisher: [Read original article]() Published: 2026-05-01T16:37:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Open Source](), [datasets](), [Google](), [Transformer architecture]() Tags: [apis](), [architecture](), [australia](), [collaboration](), [community](), [data-mining-modeling](), [developers](), [general-science](), [global](), [google](), [health-bioscience](), [india](), [japan](), [open](), [open-source](), [open-source-models-datasets](), [partnerships](), [publications](), [research](), [science](), [software](), [technology](), [transformer-architecture]() ### AI overview Google Research describes an open-science approach centered on responsible research, open-source software, open-access datasets, and partnerships with scientific organizations and consortia worldwide. It highlights shared technologies and datasets, including Transformer architecture and specialized models used across fields such as medicine, genomics, neuroscience, climate, and energy. ### Source excerpt Data Mining & Modeling ## Four ways Google Research scientists have been using Empirical Research Assistance DevFeed: [Four ways Google Research scientists have been using Empirical Research Assistance]() Original publisher: [Read original article]() Published: 2026-04-29T21:07:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Google](), [Artificial Intelligence](), [Data Mining & Modeling](), [datasets](), [Benchmark](), [Monitoring](), [real-time]() Tags: [accelerate](), [ai](), [benchmark](), [data](), [data-mining-modeling](), [experiment](), [general-science](), [generate](), [generative-ai](), [go](), [google](), [insights](), [machine-intelligence](), [monitoring](), [real-time](), [research](), [science](), [software]() ### AI overview Google Research scientists are using Empirical Research Assistance (ERA) to develop expert-level empirical software and explore AI-assisted scientific discovery across epidemiology, geospatial analysis, cosmology, atmospheric monitoring, and neuroscience. The article highlights ERA's use in computational modeling, interpretable solutions, and real-time forecasts for COVID-19, influenza, and RSV. ### Source excerpt Data Mining & Modeling ## AI-generated synthetic neurons speed up brain mapping DevFeed: [AI-generated synthetic neurons speed up brain mapping]() Original publisher: [Read original article]() Published: 2026-04-16T12:18:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Artificial Intelligence](), [AI Models](), [Google](), [Point cloud](), [Training AI Models](), [datasets](), [neuron](), [data]() Tags: [3d](), [accelerate](), [ai](), [classification](), [errors](), [general-science](), [generation](), [google](), [health-bioscience](), [iclr](), [iclr-2026](), [images](), [machine-intelligence](), [mapping](), [model](), [models](), [neuron](), [partners](), [research](), [scale](), [science](), [synthetic](), [visualization]() ### AI overview Google Research describes how MoGen generates synthetic neuronal shapes to improve AI models that reconstruct brain wiring maps. Adding synthetic training examples reduced reconstruction errors by 4.4%, potentially saving 157 person-years of manual proofreading for a complete mouse brain. ### Source excerpt General Science ## Testing LLMs on superconductivity research questions DevFeed: [Testing LLMs on superconductivity research questions]() Original publisher: [Read original article]() Published: 2026-03-16T17:31:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Large Language Model](), [World models](), [Human-AI evaluation](), [Benchmark](), [AI Research](), [Artificial Intelligence](), [Google]() Tags: [ai](), [analysis](), [benchmark](), [education-innovation](), [evaluation](), [general-science](), [google](), [large-language-model](), [llms](), [machine-intelligence](), [natural-language-processing](), [research](), [testing]() ### AI overview Google Research reports an expert evaluation of six large language models on challenging high-temperature superconductivity questions. Experts graded the responses, finding that NotebookLM and a custom system performed best when drawing on certified, quality-controlled sources, while all systems showed areas for improvement. The study aims to inform the development of trustworthy AI tools for scientific discovery. ### Source excerpt Education Innovation ## NeuralGCM harnesses AI to better simulate long-range global precipitation DevFeed: [NeuralGCM harnesses AI to better simulate long-range global precipitation]() Original publisher: [Read original article]() Published: 2026-01-12T17:52:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Machine Learning & Artificial Intelligence](), [Artificial Intelligence](), [Neural Network](), [Google](), [Earth AI](), [AI Research]() Tags: [ai](), [climate-sustainability](), [earth-ai](), [general-science](), [global](), [google](), [machine-intelligence](), [machine-learning](), [nasa](), [open](), [open-source-models-datasets](), [research](), [science](), [sustainability]() ### AI overview Google Research presents NeuralGCM, a hybrid atmospheric model that combines physics-based modeling with a neural network trained on NASA satellite precipitation observations. The model improves global precipitation simulations, including average rainfall, extreme events, and daily weather cycles, while supporting longer-range weather and climate research. ### Source excerpt Climate & Sustainability ## Exploring a space-based, scalable AI infrastructure system design DevFeed: [Exploring a space-based, scalable AI infrastructure system design]() Original publisher: [Read original article]() Published: 2025-11-04T16:58:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [AI Infrastructure](), [Google](), [AI Platform](), [AI Research]() Tags: [2025](), [ai](), [ai-infrastructure](), [compute](), [engineering](), [general-science](), [google](), [machine-learning](), [modular](), [orbit](), [paper](), [research](), [responsible-ai](), [science](), [solar](), [space]() ### AI overview Google describes Project Suncatcher, a research moonshot exploring solar-powered satellite constellations equipped with TPUs and connected by free-space optical links. The proposed system aims to scale machine learning compute in space while addressing communication, orbital dynamics, radiation, and modular satellite design challenges. ### Source excerpt General Science ## Teaching Gemini to spot exploding stars with just a few examples DevFeed: [Teaching Gemini to spot exploding stars with just a few examples]() Original publisher: [Read original article]() Published: 2025-10-20T09:19:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Google](), [genai](), [multimodal](), [Large Language Model](), [Machine learning](), [datasets]() Tags: [datasets](), [gemini](), [genai](), [general-science](), [generative-ai](), [google](), [human-computer-interaction-and-visualization](), [image](), [large-language-models](), [machine-learning](), [multimodal](), [science]() ### AI overview The article describes how Google's Gemini model was adapted into an astronomy assistant that classifies transient cosmic events and explains its reasoning in plain language. Using few-shot learning with 15 annotated examples per survey, the approach achieved 93% accuracy across three datasets and addresses the limitations of opaque specialized machine learning models. ### Source excerpt General Science ## Using AI to identify genetic variants in tumors with DeepSomatic DevFeed: [Using AI to identify genetic variants in tumors with DeepSomatic]() Original publisher: [Read original article]() Published: 2025-10-16T16:33:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Artificial Intelligence](), [Google](), [Deep neural networks](), [datasets](), [Machine Learning & Artificial Intelligence]() Tags: [2025](), [ai](), [general-science](), [google](), [health-bioscience](), [machine-learning](), [neural-networks](), [open-source-models-datasets](), [research](), [training]() ### AI overview Google Research presents DeepSomatic, an AI-powered tool that uses convolutional neural networks to identify cancer-related genetic variants in tumor sequencing data. The tool supports major sequencing platforms and sample-processing methods, and its software and training dataset are openly available to researchers. ### Source excerpt General Science