landscape
Search⌘KSubmit a productSign in

Map / Core AI / Multimodal & Perception

Multimodal & Perception

29 tools+ 2 community

Models that see and hear: vision-language models like InternVL and LLaVA, computer vision systems like SAM and Detectron2, and speech recognition engines like Whisper and Deepgram. Pure perception lives here; generative image and audio model weights belong to Foundation Models.

  • Solid: curated by our editors.
  • Dashed: added by makers, not reviewed yet.
  • Seal: Verified maker.

Vision-Language Models 9

Computer Vision 11+ 2 community

Speech Recognition 9

Built something for Multimodal & Perception? Submit it and it appears here with a dashed edge. When an editor adds it to the map, it gets the solid one.

Submit a tool

Questions

How many Multimodal & Perception tools are there?

The map has 29 tools in Multimodal & Perception, plus 2 added by makers that are not reviewed yet, sorted into 3 sub-lines: Vision-Language Models, Computer Vision and Speech Recognition.

How does AI Landscape rank Multimodal & Perception?

By use, not votes: each member who marks a tool "I use this" counts once. Until enough members have marked them, the list here goes by sub-line and name. Editors place curated tools on the map; makers can submit their own, which appear with a dashed edge until reviewed.

Next stop Benchmarks & Leaderboards 27 tools