Jonathan Berant

7

Papers

89

Total Citations

1

Affiliations

Affiliations

Tel-Aviv University and Google DeepMind

Papers (7)

Theoretical guarantees on the best-of-n alignment policy

Transforming and Combining Rewards for Aligning Large Language Models

Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction

Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing

Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge

Diagonal State Spaces are as Effective as Structured State Spaces

From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces