Tuhina Tripathi
Scholar

Tuhina Tripathi

Google Scholar ID: xC53J0QAAAAJ
University of Massachusetts Amherst
Reinforcement LearningLarge-language modelsAI-safety
Citations & Impact
All-time
Citations
2
 
H-index
1
 
i10-index
0
 
Publications
4
 
Co-authors
5
list available
Resume (English only)
Academic Achievements
  • Papers: 'Pairwise or Pointwise?' accepted at COLM 2025; Successfully defended Master's thesis titled 'Breaking the Tie: Evaluating human preferences in Reinforcement Learning'; Participated in research projects including dynamic obstacle avoidance in shared Human-Robot workspace.
Research Experience
  • Current member of the SCALAR Lab at UMass Amherst; Former master's student at the CAIRO Lab, CU Boulder.
Education
  • PhD: University of Massachusetts Amherst, advised by Professor Scott Niekum; Master's: University of Colorado Boulder, advised by Professor Bradley Hayes; Bachelor's: Delhi Technological University, major in Information Technology.
Background
  • Research Interests: Preference-based reinforcement learning, improving model alignment and decision-making in large language models through the incorporation of human feedback. Field: Computer Science.
Miscellany
  • Previously worked as a Software Developer with Citicorp Services India Pvt. Ltd.; Links to Twitter and GitHub available on personal website.