Home

I’m a second year PhD student at Cornell University studying Computer Science, advised by Sainyam Galhotra. Prior to Cornell, I received my bachelor’s degree in Computer Science from The Ohio State University. I am supported by the 2025–2026 Bowers CIS–LinkedIn Fellowship.

I am broadly interested in responsible machine learning, with a particular focus on how interpretability can provide leverage on broader sociotechnical challenges such as fairness, robustness, and AI safety.

Research

• Shifting Mechanisms: How Positional Encoding Choice Shapes Long-Context Retrieval
  Eric Enouen, Sainyam Galhotra
  Under Review

• Concept Bottleneck Diffusion for Steerable Generation
  Eric Enouen, Sainyam Galhotra
  UCRL Workshop @ ICLR 2026

• Debugging Concept Bottleneck Models through Removal and Retraining
  Eric Enouen, Sainyam Galhotra
  ICLR 2026

• DisGUIDE: Disagreement-Guided Data-Free Model Extraction
  Jonathan Rosenthal, Eric Enouen, Hung Viet Pham, Lin Tan
  AAAI 2023

• Efficient Multiple Objective Optimization for Fair Misinformation Detection
  Eric Enouen*, Katja Mathesius*, Sean Wang*, Arielle Carr, Sihong Xie
  IEEE Big Data 2022

News

• Presented CBDebug and CBDiffuse at ICLR (Apr 2026)
• Presented at the EnCORE Workshop on Interpretability in Modern AI, UC San Diego (Feb 2026)
• Awarded the 2025–2026 Bowers CIS–LinkedIn Fellowship (Aug 2025)
• Started PhD in Computer Science at Cornell University (Aug 2024)