Rohit Gandikota

(he/him)

PhD Student

  • AI safety
  • Artificial intelligence
  • Computer vision
  • Machine learning
  • Model editing
  • Natural language processing
  • MS in Artificial Intelligence, Northeastern University
  • BTech in Electronics and Communications Engineering, Indian Institute of Space Science and Technology

Rohit Gandikota is a doctoral student in the Khoury College of Computer Sciences at Northeastern University, based in Boston. He is advised by David Bau.

Gandikota is focused on understanding and controlling generative AI systems. His research centers on developing methods for precise control over AI models, as well as mapping their learned knowledge. Gandikota has published work on concept erasure and control sliders at conferences such as ICCV, WACV, and ECCV, and some of his findings have been adopted in industry.

Before joining Northeastern in 2023, Gandikota was a scientist at the Indian Space Research Organisation, where his applied his AI skills to enhance satellite data analysis and flood management technologies. Outside of research, he enjoys teaching and mentoring undergraduate students.

  • Erasing Concepts from Diffusion Models

    Citation: Rohit Gandikota, Joanna Materzynska, Jaden Fiotto-Kaufman, David Bau. (2023). Erasing Concepts from Diffusion Models ICCV, 2426-2436. https://doi.org/10.1109/ICCV51070.2023.00230