ImageBind
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
Key pointsMeta's joint embedding across six modalities at once.
01
Six-modality embedding: Learns a joint embedding space across images, text, audio, depth, thermal, and IMU data.
02
Implicit binding via images: Images are the "central" modality that binds others - without requiring all-pairs training data.
03
Zero-shot emergent capabilities: Enables cross-modal retrieval, arithmetic composition of modalities, and cross-modal generation/detection.
04
Multi-modal foundation: Influenced 2024's unified multimodal models (Chameleon, GPT-4o) by showing the viability of unified embedding spaces.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack