Alex Wilf

5719 Gates Hillman

awilf [at] cs.cmu.edu

I am a PhD student at Carnegie Mellon University in the Language Technologies Institute advised by Louis-Philippe Morency. I work on multimodal machine learning, specifically applied to creating autonomous code generation systems.

Prior to CMU, I worked with Emily Mower Provost at the University of Michigan, where I completed my B.S. in Computer Science. “In the wild”, I can be found attempting overly complex french recipes, marveling at the crafstmanship of a particularly well made piece of outerwear, or appreciating the perfect chocolate chip cookie.

News

[May, 2025]	I’ll be visiting Paul Liang and the Multisensory Intelligence group at the MIT Media Lab this summer. If you’re in Boston, reach out!
[May, 2024]	I’ll be interning at Meta Reality Labs & FAIR Research this summer, in Seattle.
[Oct, 2023]	Our Difference-Masking paper was accepted to findings of EMNLP ‘23!
[Oct, 2023]	I co-organized the Social-IQ 2.0 Challenge and Artificial Social Intelligence Workshop at ICCV ‘23. Thank you for everyone who organized, submitted, attended, and spoke!

Work

2026

Literati: Cursor for Zotero

Alex Wilf

2026.

Learn More
From Reproduction to Replication: Evaluating Research Agents with Progressive Code Masking

Gyeongwon James Kim, Alex Wilf, Louis-Philippe Morency, and 1 more author

ICLR [Forthcoming], 2026.

PDF Code

2025

Propose, Solve, Verify: Self-Play Through Formal Verification

Alex Wilf, Pranjal Aggarwal, Bryan Parno, and 4 more authors

arXiv preprint arXiv:2512.18160, 2025.

PDF Code

2023

Comparative Knowledge Distillation

Alex Wilf, Alex Tianyi Xu, Paul Pu Liang, and 3 more authors

WACV 2024, 2023.

PDF Code
Think Twice: Perspective-Taking Improves Large Language Models’ Theory-of-Mind Capabilities

Alex Wilf, Sihyun Shawn Lee, Paul Pu Liang, and 1 more author

ACL 2024, 2023.

PDF Code
Difference-Masking: Choosing What to Mask in Continued Pretraining

Alex Wilf*, Syeda Nahida Akter*, Leena Mathur, and 5 more authors

Findings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.

PDF Code
Face-to-Face Contrastive Learning for Social Intelligence Question-Answering

Alex Wilf*, Martin Q Ma*, Paul Pu Liang, and 2 more authors

International Conference on Automatic Face and Gesture Recognition (FG), 2023.

PDF

2021

Towards Noise-Robust Speech Emotion Recognition Using Dynamic Layer Customization

Alex Wilf, and Emily Mower Provost

International Conference on Affective Computing and Intelligent Interaction (ACII), 2021.

PDF