Adithya Bhaskar
Scholar

Adithya Bhaskar

Google Scholar ID: TS0_Du0AAAAJ
Ph.D. student, Princeton University
Language modelsPost-trainingPretrainingReasoningInterpretability
Citations & Impact
All-time
Citations
224
 
H-index
6
 
i10-index
6
 
Publications
10
 
Co-authors
18
list available
Resume (English only)
Academic Achievements
  • Presenting Edge Pruning paper at NeurIPS (spotlight); Presenting Heuristic Core paper at ACL (Oral, Main); Gave an invited talk at Amazon AWS (Responsible AI team); Named a Hisashi and Masae Kobayashi '67 Fellow; Awarded the Thomas A. Dooie Class of 1974 Research Award for Bachelor's Thesis.
Research Experience
  • Conducting research as a PhD candidate at Princeton University; Interned at UT Austin under Prof. Greg Durrett; Interned at Uppsala University under Prof. Parosh Abdulla.
Education
  • PhD: Princeton University, Advisor: Prof. Danqi Chen; B.Tech: IIT Bombay, Advisor: Prof. Sunita Sarawagi.
Background
  • Research Interests: The inner workings of language models, porting human knowledge of natural language (e.g., linguistic structure, disambiguation of context) to a Language Model, and the best ways to train a language model. Professional Field: Natural Language Processing.
Miscellany
  • Interests include thinking about scaling laws, post-training, and the social impacts of language models.