ImageBind: Holistic AI learning across six modalities

ImageBind is the first AI model capable of binding information from six modalities.

ImageBind: Holistic AI learning across six modalities Products AI Research Resources About Get Llama Try Meta AI Computer Vision ImageBind: Holistic AI learning across six modalities May 9, 2023 Share on Facebook Share on Twitter When humans absorb information from the world, we innately use multiple senses, such as seeing a busy street and hearing the sounds of car engines. Today, we’re introducing an approach that brings machines one step closer to humans’ ability to learn simultaneously, holistically, and directly from many different forms of information — without the need for explicit supe

saved by

• jeremy h
• Saad Khalid

related reading

• Unified Multimodal Models as Auto-Encodersarxiv.org
• Training Multimodalnimapourjafar.com
• 2403.09611.pdfarxiv.org
• Interaction Models: A Scalable Approach to Human-AI Collaboration - Thinking Machines Labthinkingmachines.ai
• [2301.13823] Grounding Language Models to Images for Multimodal Generationarxiv.org
• Inkling: Our Open-Weights Model - Thinking Machines Labthinkingmachines.ai
• Replicate - Run AI with an APIreplicate.com
• Welcome Inkling by Thinking Machineshuggingface.co
• [2606.02800] Cosmos 3: Omnimodal World Models for Physical AIarxiv.org
• cs.unc.edu/~mbansal/teaching/nlp-comp790-590-spring23.htmlcs.unc.edu
• Composing Zero-Shot Multimodal Reasoning with Languagesocraticmodels.github.io
• 2023-ConceptFusion.pdfconcept-fusion.github.io