अंकुश गुप्ताAnkush Gupta

I work as a research scientist at Google DeepMind, London.

mail@ankushgupta.org

Recent work

  1. Genie 4: Audio-visual interactive world model.
  2. Omni: Audio, video and text generative model.
  3. Veo 3: Audio-visual generative model.
  4. Video-to-audio: Generating audio for video.