Dani Yogatama

DeLLMa: Decision Making Under Uncertainty with Large Language Models

The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities

(Pre-)training Dynamics: Scaling Generalization with First-Order Logic

Interpretable Diffusion via Information Decomposition

IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations

Understanding In-context Learning with a Pelican Soup Hypothesis