Picture for Tamara von Glehn

Tamara von Glehn

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

Add code
Mar 08, 2024
Viaarxiv icon

Categorical Deep Learning: An Algebraic Theory of Architectures

Add code
Feb 23, 2024
Viaarxiv icon

Gemini: A Family of Highly Capable Multimodal Models

Add code
Dec 19, 2023
Viaarxiv icon

Asynchronous Algorithmic Alignment with Cocycles

Add code
Jun 28, 2023
Viaarxiv icon

Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback

Add code
Nov 21, 2022
Viaarxiv icon

Evaluating Multimodal Interactive Agents

Add code
May 26, 2022
Figure 1 for Evaluating Multimodal Interactive Agents
Figure 2 for Evaluating Multimodal Interactive Agents
Figure 3 for Evaluating Multimodal Interactive Agents
Figure 4 for Evaluating Multimodal Interactive Agents
Viaarxiv icon

Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning

Add code
Dec 07, 2021
Figure 1 for Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning
Figure 2 for Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning
Figure 3 for Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning
Figure 4 for Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning
Viaarxiv icon

Formalising Concepts as Grounded Abstractions

Add code
Jan 13, 2021
Figure 1 for Formalising Concepts as Grounded Abstractions
Figure 2 for Formalising Concepts as Grounded Abstractions
Figure 3 for Formalising Concepts as Grounded Abstractions
Figure 4 for Formalising Concepts as Grounded Abstractions
Viaarxiv icon

Grounded Language Learning Fast and Slow

Add code
Sep 15, 2020
Figure 1 for Grounded Language Learning Fast and Slow
Figure 2 for Grounded Language Learning Fast and Slow
Figure 3 for Grounded Language Learning Fast and Slow
Figure 4 for Grounded Language Learning Fast and Slow
Viaarxiv icon