The latest research from Google
- Posts
- 124 from 11 Dec 2006 to 27 Oct 2026
- Posting
- weekly (105 in the last year)
- Kind
- company blog
- Feed
- https://research.google/blog/rss/
2026 91
- The sleep framework: A new way for LLMs to retain knowledge in continual learning
- Bringing foundational models to the front lines of TB screening
- Empowering frontline maternal care with AI-assisted ultrasound
- Grounding AI agents in biological reality: Building blocks for autonomous wet labs
- 2026
- Putting Earth AI to work: Geospatial agents for our planet's biggest challenges
- Analyzing technical documents with Deep Review
- Research@ 2026: 10 ways we're amplifying human ingenuity
- Does better work always mean better workers?
- Unlocking Earth AI’s planetary geospatial foundation models for global public health
- Open and Emergent Problems in Agentic Privacy and Security: A Contextual Angle
- Toward provably private learning from federated data
- How Diffusion Controller unifies and simplifies AI image generation
- Automating coherent long-form video generation
- MilleMiglia: A realistic instance generator for middle-mile logistics
- The future of practice: Enabling teachers to create learning interactives with generative UI
- Bypassing inference bottlenecks: Accelerating complex AI search with Retrieve-for-Train
- ToolGrad: Efficient tool-use dataset generation with textual "gradients"
- Transfer learning for genomic prediction in underrepresented populations
- A connectomics milestone: Mapping the complete male fruit fly brain
- Mapping global methane emissions from space with deep learning
- TimesFM-3: A zero-shot foundation model for multivariate forecasting
- Planetary prediction engine: Automating global models via Earth AI
- GlucoFM: Foundation model for continuous glucose monitoring
- AgentHands: Generating interactive hand gestures for spatially grounded agent conversations in XR
- An AI tool for prioritizing candidate biomarkers from wearable sensor data
- How mobility gives language models a deeper understanding of place
- Seeing beyond BMI: Estimating cardiometabolic risk with smartphone imagery
- Empty shelves or lost keys? Recall is the bottleneck for parametric factuality
- Advancing AMIE towards expert-level audio-visual clinical consultations
- Science One Framework: A verifiable autonomous research framework via Chain-of-Evidence
- SymptomAI: Towards a conversational AI agent for everyday symptom assessment
- Towards a quantum computer that learns from its errors
- Towards demystifying the creativity of diffusion models
- SensorFM: Towards a general intelligence and interface for wearable health data
- The power of collaboration: How we can reduce traffic congestion
- Expanding our Heat Resilience data to 50+ global cities
- Introducing TabFM: A zero-shot foundation model for tabular data
- Accelerating Gemini Nano models on Pixel with frozen Multi-Token Prediction
- Optimizing cloud economics with linear elastic caching
- Thinking to recall: How reasoning unlocks parametric knowledge in LLMs
- From pixels to planning: Earth AI for nature restoration
- Research into how AI can help users understand skin conditions
- A low-carbon computing platform from your retired phones
- New framework for auditing machine unlearning
- Unlocking dependable responses with Gemini Enterprise Agent Platform’s Agentic RAG
- Towards passive heart health monitoring via smartphone camera
- The next chapter in flood resilience: Open sourcing Google’s hydrology framework
- A New Era of Discovery: Google Research at I/O 2026
- Private analytics via zero-trust aggregation
- Empirical Research Assistance (ERA): From Nature publication to catalyzing Computational Discovery
- Catalyzing scientific impact through global partnerships and open resources
- Four ways Google Research scientists have been using Empirical Research Assistance
- It's all about the angle: Your photos, re-composed
- ReasoningBank: Enabling agents to learn from experience
- Designing synthetic datasets for the real world: Mechanism design and reasoning from first principles
- AI-generated synthetic neurons speed up brain mapping
- Towards developing future-ready skills with generative AI
- ConvApparel: Measuring and bridging the realism gap in user simulators
- Improving the academic workflow: Introducing two AI agents for better figures and peer review
- Evaluating alignment of behavioral dispositions in LLMs
- Building better AI benchmarks: How many raters are enough?
- Safeguarding cryptocurrency by disclosing quantum vulnerabilities responsibly
- Vibe Coding XR: Accelerating AI + XR prototyping with XR Blocks and Gemini
- TurboQuant: Redefining AI efficiency with extreme compression
- Mapping the modern world: How S2Vec learns the language of our cities
- Google Research at The Check Up: from healthcare innovation to real-world care settings
- Improving breast cancer screening workflows with machine learning
- Testing LLMs on superconductivity research questions
- Protecting cities with AI-driven flash flood forecasting
- Introducing Groundsource: Turning news reports into data with Gemini
- Exploring the feasibility of conversational diagnostic AI in a real-world clinical study
- WAXAL: A large-scale open resource for African language speech technology
- Where wild things roam: Identifying wildlife with SpeciesNet
- Teaching LLMs to reason like Bayesians
- Teaching AI to read a map
- Scheduling in a changing world: Maximizing throughput with time-varying capacity
- Beyond one-on-one: Authoring, simulating, and testing dynamic human-AI group conversations
- How AI trained on birds is surfacing underwater mysteries
- How AI tools can redefine universal design to increase accessibility
- Sequential Attention: Making AI models leaner and faster without sacrificing accuracy
- Collaborating on a nationwide randomized study of AI in real-world virtual care
- Towards a science of scaling agent systems: When and why agent systems work
- ATLAS: Practical scaling laws for multilingual models
- Introducing GIST: The next stage in smart sampling
- Small models, big results: Achieving superior intent extraction through decomposition
- Unlocking health insights: Estimating advanced walking metrics with smartwatches
- Hard-braking events as indicators of road segment crash risk
- Next generation medical image interpretation with MedGemma 1.5 and medical speech to text with MedASR
- Dynamic surface codes open new avenues for quantum error correction
- NeuralGCM harnesses AI to better simulate long-range global precipitation
2025 14
- Google Research 2025: Bolder breakthroughs, bigger impact
- 2025
- Gemini-backed Paper Assistant Tool provides automated feedback for theoretical computer scientists at STOC 2026
- Spotlight on innovation: Google-sponsored Data Science for Health Ideathon across Africa
- A differentially private framework for gaining insights into AI chatbot use
- Titans + MIRAS: Helping AI have long-term memory
- From Waveforms to Wisdom: The New Benchmark for Auditory Intelligence
- Reducing EV range anxiety: How a simple AI model predicts port availability
- Real-time speech-to-speech translation
- Generative UI: A rich, custom, visual interactive user experience for any prompt
- Separating natural forests from other tree cover with AI for deforestation-free supply chains
- A new quantum toolkit for optimization
- Differentially private machine learning at scale with JAX-Privacy
- Introducing Nested Learning: A new ML paradigm for continual learning