Princeton University · Computer Science

ARORA Research Lab

Our research lab develops conceptual understanding of AI models, including training techniques, datasets, model interpretability and model evaluations. Recent works involve new ways of training and evaluating models using "skills", which are themselves elicited from powerful AI models, and in turn can be used to generate very effective pipelines for improving AI models using synthetic training data. Many of our papers involve mathematical analysis as well as experiments.

  • LLM Training Dynamics
  • Optimization & Theory
  • Skills & Synthetic Data
  • Alignment & Reward Models
  • Reasoning
  • Interpretability & Evaluation
Arora Research Lab group photo, 2024
05/2025
Paper New paper On the Power of Context-Enhanced Learning in LLMs was accepted to ICML 2025 (Spotlight).
05/2025
03/2025
Award Congrats to Abhishek Panigrahi on being named 2025 Apple Scholar in AIML!
01/2025
Paper New paper Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning was accepted to ICLR 2025.
01/2025
Paper New paper Progressive distillation induces an implicit curriculum was accepted to ICLR 2025 (Oral).
01/2025
Paper New paper Provable unlearning in topic modeling and downstream tasks was accepted to ICLR 2025.
01/2025
01/2025
Paper New paper MUSE: Machine Unlearning Six-Way Evaluation for Language Models was accepted to ICLR 2025.

Selected Talks