Please confirm you are human
This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.
A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.
News
Science One Framework: A verifiable autonomous research framework via Chain-of-Evidence
1+ hour, 9+ min ago (407+ words) Rui Meng, Research Scientist, and Tomas Pfister, Director, Google Cloud Introducing the Science One Framework, an experimental research prototype designed to eliminate hallucinations by natively building verifiable evidence chains, and CoE Audit, an automated protocol to evaluate the integrity of…...
Introducing TabFM: A zero-shot foundation model for tabular data
1+ mon, 1+ hour ago (223+ words) Weihao Kong and Abhimanyu Das, Research Scientists, Google Research We’ve seen a massive shift in how people handle time-series forecasting since we launched TimesFM. Now, we’re bringing that same "zero-shot" logic to tabular data. We introduce TabFM, a new foundation…...
Accelerating Gemini Nano models on Pixel with frozen Multi-Token Prediction
1+ mon, 4+ day ago (531+ words) MTP builds upon the evolution of speculative decoding. In a traditional setup, generating N tokens requires N forward passes of the large model. Speculative decoding decouples this process into two parts: This architecture, which uses a deep exit layer for…...
From pixels to planning: Earth AI for nature restoration
1+ mon, 2+ week ago (392+ words) We developed a high-resolution deep learning framework to reveal fine-scale ecological features, like hedgerows and copses, that are typically invisible to standard satellite detection. This precise vector data offers a new pathway to address the climate and biodiversity crises on…...
Empirical Research Assistance (ERA): From Nature publication to catalyzing Computational Discovery
2+ mon, 1+ week ago (275+ words) Published today in Nature, Empirical Research Assistance (ERA) is an AI tool for expert-level scientific coding that helped build the Computational Discovery prototype, now available through a trusted tester program in Google Labs. As part of our wider science announcements…...
Improving the academic workflow: Introducing two AI agents for better figures and peer review
3+ mon, 3+ week ago (345+ words) Jinsung Yoon, Research Scientist, and Tomas Pfister, Director, Google Cloud Introducing two AI agents to streamline academic research. These include: PaperVizAgent, a visualizer agent for drawing academic figures, and ScholarPeer, a reviewer agent that automatically and rigorously evaluates academic papers....
Building better AI benchmarks: How many raters are enough?
3+ mon, 4+ week ago (563+ words) Flip Korn and Chris Welty, Research Scientists, Google Research We introduce an evaluation framework for ML models, based on “gold” ratings data, that optimizes the trade-off between the number of items and raters per item, providing a roadmap for building…...
Exploring the feasibility of conversational diagnostic AI in a real-world clinical study
4+ mon, 2+ week ago (417+ words) We present insights from a first-of-its-kind research study in partnership with Beth Israel Deaconess Medical Center towards prospective real-world assessment of AMIE, our conversational medical AI for clinical reasoning and dialogue. Translating AI systems into clinical practice requires assessment in…...
Teaching LLMs to reason like Bayesians
4+ mon, 3+ week ago (444+ words) Sjoerd van Steenkiste and Tal Linzen, Research Scientists, Google Research We teach LLMs to reason in a Bayesian manner by training them to mimic the predictions of an optimal Bayesian model. The goal of the assistant was to recommend the…...
Towards a science of scaling agent systems: When and why agent systems work
6+ mon, 2+ day ago (720+ words) We strive to create an environment conducive to many different types of research across many different time scales and levels of risk. Our researchers drive advancements in computer science through both fundamental and applied research. We regularly open-source projects with…...