papers

Publications (12)

cs.CV2024

Imagen 3

Imagen-Team-Google, :, Jason Baldridge +257

We introduce Imagen 3, a latent diffusion model that generates high quality images from text prompts. We describe our quality and responsibility evaluations. Imagen 3 is preferred…

cs.LG2023

The Hydra Effect: Emergent Self-repair in Language Model Computations

Thomas McGrath, Matthew Rahtz, Janos Kramar +2

We investigate the internal structure of language model computations using causal analysis and demonstrate two motifs: (1) a form of adaptive computation where ablations of one att…

cs.LG2022

Safe Deep RL in 3D Environments using Human Feedback

Matthew Rahtz, Vikrant Varma, Ramana Kumar +3

Agents should avoid unsafe behaviour during both training and deployment. This typically requires a simulator and a procedural specification of unsafe behaviour. Unfortunately, a s…

cs.LG2023

Tracr: Compiled Transformers as a Laboratory for Interpretability

David Lindner, János Kramár, Sebastian Farquhar +3

We show how to "compile" human-readable programs into standard decoder-only transformer models. Our compiler, Tracr, generates models with known structure. This structure can be us…

cs.CL2025

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…

cs.CL2025

Gemini: A Family of Highly Capable Multimodal Models

Gemini Team, Rohan Anil, Sebastian Borgeaud +1340

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consist…

cs.LG2019

An Extensible Interactive Interface for Agent Design

Matthew Rahtz, James Fang, Anca D. Dragan +1

In artificial intelligence, we often specify tasks through a reward function. While this works well in some settings, many tasks are hard to specify this way. In deep reinforcement…

cs.LG2024

Evaluating Frontier Models for Dangerous Capabilities

Mary Phuong, Matthew Aitchison, Elliot Catt +24

To understand the risks posed by a new AI system, we must understand what it can and cannot do. Building on prior work, we introduce a programme of new "dangerous capability" evalu…

cs.CL2024

Gemma 2: Improving Open Language Models at a Practical Size

Gemma Team, Morgane Riviere, Shreya Pathak +195

In this work, we introduce Gemma 2, a new addition to the Gemma family of lightweight, state-of-the-art open models, ranging in scale from 2 billion to 27 billion parameters. In th…

cs.CY2024

A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI

Seliem El-Sayed, Canfer Akbulut, Amanda McCroskery +17

Recent generative AI systems have demonstrated more advanced persuasive capabilities and are increasingly permeating areas of life where they can influence decision-making. Generat…

cs.CL2024

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Gemini Team, Petko Georgiev, Ving Ian Lei +1132

In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over…

cs.LG2023

Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla

Tom Lieberum, Matthew Rahtz, János Kramár +4

\emph{Circuit analysis} is a promising technique for understanding the internal mechanisms of language models. However, existing analyses are done in small models far from the stat…