Jacob Andreas

23

Papers

338

Total Citations

2

Affiliations

Affiliations

MITMicrosoft

Papers (23)

Linearity of Relation Decoding in Transformer Language Models

Eliciting Human Preferences with Language Models

Learning How Hard to Think: Input-Adaptive Allocation of LM Computation

The Surprising Effectiveness of Test-Time Training for Few-Shot Learning

The Consensus Game: Language Model Generation via Equilibrium Search

Learning Linear Attention in Polynomial Time

Toward a Visual Concept Vocabulary for GAN Latent Space

On the Accuracy of Self-Normalized Log-Linear Models

Learning to Reason: End-To-End Module Networks for Visual Question Answering

A Multimodal Automated Interpretability Agent

Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling

In-Context Language Learning: Architectures and Algorithms

Neural Module Networks

Modeling Relationships in Referential Expressions With Compositional Modular Networks

Speaker-Follower Models for Vision-and-Language Navigation

Compositional Explanations of Neurons

A Benchmark for Systematic Generalization in Grounded Language Understanding

Teachable Reinforcement Learning via Advice Distillation

Pre-Trained Language Models for Interactive Decision-Making

The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks

FIND: A Function Description Benchmark for Evaluating Interpretability Methods

Modular Multitask Reinforcement Learning with Policy Sketches

Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?