Mochi 1: Open-source video generation model
Mochi 1: A new SOTA in open-source video generation models
Recent Articles
How memories are formed: Breaking DNA and repairing it
Memories are made by breaking DNA — and fixing it
Stable Diffusion 3.5 Update
Today we are releasing Stable Diffusion 3.5, our most powerful models yet.
Runway releases Act-One: Video and Voice Performance Generating Animation
A new way to generate expressive character performances using simple video inputs.
"State of AI Report 2024" (4) - LLM Related
Perhaps it’s neither about revenue nor margin: vibes are all you need (to recover your share price)
Anthropic's Claude can directly operate a computer
Developing a computer use model
"State of AI Report 2024" (3) - AI research in gaming agents, code testing, and enterprise automation fields
Enterprise automation set to get an AI-first upgrade
"State of AI Report 2024" (2) - AI in Neuroscience: BrainLM / MindEye / BCI
The first time we tried the system, he cried with joy as the words he was trying to say correctly appeared on-screen.
"State of AI Report 2024" (1) - AlphaGeometry, Synthetic Data, RAG
Foundation models demonstrate their ability to break out of language as multimodal research.