Stanford CS25: Transformers United V6 I From Language Models to Native Multimodal Intelligence

Explains how models move from next-token prediction over text to natively multimodal training, useful for engineers choosing and building on multimodal systems.

• multimodal — A model that works with more than text — reading images, audio, or video, and sometimes generating them too.
• LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
• token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.

• videoStanford CS329A Self-Improving AI Agents | Part 2 | Test-Time Compute Scaling
• videoStanford CS153 Frontier Systems | The AI Native Company: How One Founder Becomes a 1000x Engineer
• videoStanford CS25: V5 I Large Language Model Reasoning, Denny Zhou of Google Deepmind
• videoStanford CME295 Transformers & LLMs | Autumn 2026 | Lecture 1 - Transformers

• articleMultimodality and Large Multimodal Models (LMMs)Chip Huyen
• postA Component-by-Component Walkthrough of How Transformer LLMs WorkAndrew Ng
• videoStanford CME295 Transformers & LLMs | Autumn 2026 | Lecture 1 - TransformersStanford Online

Checking sign-in…

Loading comments…