Fred Hohman

Apple Intelligence Foundation Language Models: Tech Report 2025

Embedding Atlas: Low-Friction, Interactive Embedding Visualization

A Scalable Approach to Clustering Embedding Projections

Exploring Empty Spaces: Human-in-the-Loop Data Augmentation

AI Policy Projector: Grounding LLM Policy Design in Iterative Mapmaking

Compress and Compare: Interactively Evaluating Efficiency and Behavior Across ML Model Compression Experiments

Apple Intelligence Foundation Language Models

Biscuit: Scaffolding LLM-Generated Code with Ephemeral UIs in Computational Notebooks

Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences

Talaria: Interactively Optimizing Machine Learning Models for Efficient Inference