Tamar Rott Shaham
Scholar

Tamar Rott Shaham

Google Scholar ID: YRJ-ePMAAAAJ
Postdoctoral fellow, MIT
Machine LearningMachine PerceptionLarge Language ModelsComputer Vision
Citations & Impact
All-time
Citations
1,659
 
H-index
11
 
i10-index
13
 
Publications
20
 
Co-authors
0
 
Resume (English only)
Academic Achievements
  • Published multiple papers, including a new paper on language models using a 'double pointer'-like mechanism to track beliefs, SketchAgent (a language-driven agent that creates and refines sketches through interactions with users), MAIA (a Multimodal Automated Interpretability Agent). Won ICCV'19 Best Paper Award (Marr Prize), Adobe Research Fellowship, etc.
Research Experience
  • Incoming assistant professor at the Department of Mathematics and Computer Science at Weizmann Institute of Science. Currently a postdoctoral fellow with Antonio Torralba at CSAIL, MIT.
Education
  • PhD: Electrical & Computer Engineering, Technion, Advisor: Tomer Michaeli.
Background
  • Research interests: understanding, controlling, and enhancing AI models; developing tools that automatically discover and explain the internal operations of machine-learning models and use gained insights to control model behavior, enhance performance, and prevent undesired outcomes.
Miscellany
  • Hosting pro bono office hours, participating in various academic conferences and workshops.
Co-authors
0 total
Co-authors: 0 (list not available)