Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration
Hyperparameter tuning can dramatically impact training stability and final performance of large-scale models. Recent works…
Category: Machine Learning
Faster Rates For Federated Variational Inequalities
In this paper, we study federated optimization for solving stochastic variational inequalities (VIs), a problem…
A Small-Scale System for Autoregressive Program Synthesis Enabling Controlled Experimentation
What research can be pursued with small models trained to complete true programs? Typically, researchers…
Gemini 3 Deep Think: Advancing science, research and engineering
We’re releasing a major upgrade to Gemini 3 Deep Think, our specialized reasoning mode.
Choosing Between PCA and t-SNE for Visualization
For data scientists, working with high-dimensional data is part of daily life.
Accelerating science with AI and simulations
Associate Professor Rafael Gómez-Bombarelli has spent his career applying AI to improve scientific discovery. Now…
Trace Length is a Simple Uncertainty Signal in Reasoning Models
Uncertainty quantification for LLMs is a key research direction towards addressing hallucination and other issues…
Mapping the Design Space of User Experience for Computer Use Agents
Large language model (LLM)-based computer use agents execute user commands by interacting with available UI…
The Machine Learning Practitioner’s Guide to Speculative Decoding
Large language models generate text one token at a time.
9 fun questions to try asking Google Photos
Learn more about Google Photos’ new Ask button as well as other functions of its…