Publications (11)
Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agents
Joel Z. Leibo, Cyprien de Masson d'Autume, Daniel Zoran +10
Psychlab is a simulated psychology laboratory inside the first-person 3D game world of DeepMind Lab (Beattie et al. 2016). Psychlab enables implementations of classical laboratory…
Generative Temporal Models with Memory
Mevlana Gemici, Chia-Chun Hung, Adam Santoro +5
We consider the general problem of modeling temporal data with long-range dependencies, wherein new observations are fully or partially predictable based on temporally-distant, pas…
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…
The sub--domination number of a graph with applications to -domination
David Amos, John Asplund, Boris Brimkov +1
In this paper we introduce and study a new graph invariant derived from the degree sequence of a graph , called the sub--domination number and denoted . We show tha…
Upper bounds on the k-forcing number of a graph
David Amos, Yair Caro, Randy Davila +1
Given a simple undirected graph and a positive integer , the -forcing number of , denoted , is the minimum number of vertices that need to be initially colored…
AMIE: An annotation model for information research
Charles A. Robert, David Amos
The objective of most users for consulting any information database, information warehouse or the internet is to resolve one problem or the other. Available online or offline annot…
Probing Physics Knowledge Using Tools from Developmental Psychology
Luis Piloto, Ari Weinstein, Dhruva TB +6
In order to build agents with a rich understanding of their environment, one key objective is to endow them with a grasp of intuitive physics; an ability to reason about three-dime…
Collaborative Knowledge Creation and Management in Information Retrieval
Victor Odumuyiwa, David Amos
The final goal of Information Retrieval (IR) is knowledge production. However, it has been argued that knowledge production is not an individual effort but a collaborative effort.…
Towards a Definition of Disentangled Representations
Irina Higgins, David Amos, David Pfau +4
How can intelligent agents solve a diverse set of tasks in a data-efficient manner? The disentangled representation learning approach posits that such an agent would benefit from s…
Unsupervised Predictive Memory in a Goal-Directed Agent
Greg Wayne, Chia-Chun Hung, David Amos +21
Animals execute goal-directed behaviours despite the limited range and scope of their sensors. To cope, they explore environments and store memories maintaining estimates of import…
Can Neural Networks Understand Logical Entailment?
Richard Evans, David Saxton, David Amos +2
We introduce a new dataset of logical entailments for the purpose of measuring models' ability to capture and exploit the structure of logical expressions against an entailment pre…