Skip to content
AI Engineer Guide.

Track

Multimodal, vision & voice

Vision, speech, real-time voice, and document understanding.

  1. Multimodal modelsconcept · T1
  2. Image understandingconcept · T1
  3. VLMsconcept · T2
  4. Document understandingconcept · T1
  5. Image generationconcept · T2
  6. Image patchesconcept · T2
  7. Audio representationsconcept · T2
  8. Audio tokensconcept · T2
  9. Audio understandingconcept · T2
  10. ASRconcept · T1
  11. TTSconcept · T1
  12. Speech-to-speechconcept · T2
  13. VADconcept · T2
  14. Streaming audioconcept · T2
  15. Voice agentsconcept · T2
  16. Turn detectionconcept · T2
  17. Video understandingconcept · T2
  18. Spatial & motionconcept · T3
  19. Multimodal embeddingsconcept · T2
  20. Cross-modal retrievalconcept · T2
  21. Multimodal safetyconcept · T1
  22. Voice UXconcept · T3