Ameet Talwalkar (original) (raw)

• Home
• Research
• Group
• Teaching
• Contact

	I am an associate professor in the Machine Learning Departmentat CMU and Chief Scientist at Datadog. My current research interests include AI for science, human-AI interaction, and developing specialized foundation models and agents. Here is my Google scholarpage and formal bio.

Selected Recent Work

• Copilot Arena: A Platform for Code LLM Evaluation in the Wild (pdf)
  W. Chi, V. Chen, A. Angelopoulos, W. Chiang, A. Mittal, N. Jain, T. Zhang, I. Stoica, C. Donahue, A. Talwalkar

• Specialized Foundation Models Struggle to Beat Supervised Baselines (pdf)
  Z. Xu, R. Gupta, W. Cheng, A. Shen, J. Shen, A. Talwalkar, M. Khodak
  International Conference on Learning Representations (ICLR), 2025

• The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers (pdf)
  H. Mozannar, V. Chen, M. Alsobay, S. Das, S. Zhao, D. Wei, M. Nagireddy, P. Sattigeri, A. Talwalkar, D. Sontag
  Transactions on Machine Learning Research (TMLR), 2025

• ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data (pdf, blog)
  J. Shen, A. Jain, Z. Xiao, I. Amlekar, M. Hadji, A. Podolny, A. Talwalkar

• UPS: Towards Foundation Models for PDE Solving via Cross-Modal Adaptation (pdf)
  J. Shen, T. Marwah, A. Talwalkar
  Transactions on Machine Learning Research (TMLR), 2024

• L2G: Repurposing Language Models for Genomics Tasks (pdf)
  W. Cheng, J. Shen, M. Khodak, J. Ma, A. Talwalkar

• Cross-Modal Fine-Tuning: Align then Refine (pdf)
  J. Shen, L. Li, L. Dery, C. Staten, M. Khodak, G. Neubig, A. Talwalkar
  International Conference on Machine Learning (ICML), 2023

• Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learning (pdf, website, blog)
  A. Cabrera, E. Fu, D. Bertucci, K. Hostein, A. Talwalkar, J. Hong, A. Perer
  Conference on Human Factors in Computing Systems (CHI), 2023

• Efficient Architecture Search for Diverse Tasks (pdf, blog)
  J. Shen, M. Khodak, A. Talwalkar
  Neural Information Processing Systems (NeurIPS), 2022

• Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability (pdf)
  J. Cohen, S. Kaur, Y. Li, Z. Kolter, A. Talwalkar
  International Conference on Learning Representations (ICLR), 2021