papers

Publications (5)

cs.CL2026

Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pretraining

Jeffrey Li, Josh Gardner, Doug Kang +10

One of the first pre-processing steps for constructing web-scale LLM pretraining datasets involves extracting text from HTML. Despite the immense diversity of web content, existing…

cs.LG2025

Apple Intelligence Foundation Language Models: Tech Report 2025

Ethan Li, Anders Boesen Lindbo Larsen, Chen Zhang +395

We introduce two multilingual, multimodal foundation language models that power Apple Intelligence features across Apple devices and services: i a 3B-parameter on-device model opti…

cs.CV2024

MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

Brandon McKinzie, Zhe Gan, Jean-Philippe Fauconnier +29

In this work, we discuss building performant Multimodal Large Language Models (MLLMs). In particular, we study the importance of various architecture components and data choices. T…

cs.AI2026

Apple Intelligence Foundation Language Models

Tom Gunter, Zirui Wang, Chong Wang +152

We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large serv…

cs.LG2025

LikeBench: Evaluating Subjective Likability in LLMs for Personalization

Md Awsafur Rahman, Adam Gabrys, Doug Kang +3

A personalized LLM should remember user facts, apply them correctly, and adapt over time to provide responses that the user prefers. Existing LLM personalization benchmarks are lar…