Micah Carroll
Scholar

Micah Carroll

Google Scholar ID: MeNbzgIAAAAJ
PhD student, UC Berkeley
AI AlignmentAI InfluenceRecommender systemsHuman-AI Collaboration
Citations & Impact
All-time
Citations
2,271
 
H-index
13
 
i10-index
13
 
Publications
17
 
Co-authors
9
list available
Resume (English only)
Academic Achievements
  • Published multiple papers on AI safety, recommender systems, and cooperative AI, with some papers appearing in top conferences and journals such as ICLR, Philosophical Studies, ICML, EAAMO, TMLR, PNAS Nexus, and FAccT.
Research Experience
  • Deeply involved in research on human-AI collaboration, particularly in the area of recommender systems and the impact of algorithm choice on users. Participated in multiple research projects and published several papers in relevant international conferences.
Education
  • 5th year Artificial Intelligence PhD student at Berkeley, advised by Anca Dragan and Stuart Russell within BAIR and CHAI. Supported by the NSF Fellowship.
Background
  • Interested in humans' preference, value, and belief changes, and how they may be affected by interactions with AI systems. Studied this both in generality (with the language of DR-MDPs) and more specifically in the context of recommender systems, investigating how the choice of algorithm might affect us users. Best known for work on human-AI collaboration and developing the Overcooked-AI benchmark.
Miscellany
  • Personal interests include inline skating, watching movies, and discovering new music. Grew up in the chaotic city of Livorno, Italy, before immigrating to the US.