def about():

allen chang(he/him)

/ / /
cylumn๐Ÿคฏseas.upenn.educurriculum vitae

def about():

I am a PhD student at Penn NLP , where I have the privilege to be advised by Mark Yatskar. My research has included work on language and vision and evaluating language models.

My work is generously supported by the NSF Graduate Research Fellowship.


Previously, I completed a BS in Computer Science and BS in Applied Math at USC Viterbi . I am very fortunate to have worked with Maja Matariฤ‡, Jesse Thomason, and Stefanos Nikolaidis. I have had the pleasure to intern at the CMU Robotics Institute with Jean Oh, MIT Haystack Observatory with Mary Knapp, and Tsinghua University with Shaoxu Song.

I am extremely grateful for my peers, collaborators, and community who have helped me immensely, including Leena Mathur, Lauren Klein, Tejas Srinivasan, Serena Booth, Matthew Fontaine, Beverley-Claire Okogwu, Peter Schaldenbrand, Eliot Xing, members and alumni from CAIS++ and our advisor Bistra Dilkina.

Ctrl + F news

$ srun publications.sh

RESEARCHQA: Evaluating Scholarly Question Answering Across 75 Fields with Survey-Mined Questions and RubricsLi S. Yifei *, Allen Chang *, Chaitanya Malaviya, and Mark Yatskar.arXiv preprint, 2025.PAL: Designing Conversational Agents as Scalable, Cooperative Patient Simulators for Palliative-Care TrainingNeil K. R. Sehgal *, Hita Kambhamettu *, Allen Chang *, Andrew Zhu *, Lyle Ungar, and Sharath C. Guntuku.Computer-Supported Cooperative Work and Social Computing (CSCW), 2025.Quality-Diversity Generative Sampling for Learning with Synthetic DataAllen Chang, Matthew C. Fontaine, Serena Booth, Maja J. Matariฤ‡, and Stefanos Nikolaidis.Conference on Artificial Intelligence (AAAI), 2024.Multimodal Speech Recognition for Language-Guided Embodied AgentsAllen Chang, Xiaoyuan Zhu, Aarav Monga, Seoho Ahn, Tejas Srinivasan, and Jesse Thomason.Conference of the International Speech Communication Association (INTERSPEECH), 2023. [Oral]Removing Radio Frequency Interference from Auroral Kilometric Radiation with Stacked AutoencodersAllen Chang, Mary Knapp, James LaBelle, John Swoboda, Ryan Volz, and Philip J. Erickson.International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023.Evaluating Temporal Patterns in Applied Infant Affect RecognitionAllen Chang *, Lauren Klein *, Marcelo R. Rosales, Weiyang Deng, Beth A. Smith, and Maja J. Matariฤ‡.Affective Computing and Intelligent Interaction (ACII), 2022. [Oral]
* Equal contribution.

n o t e s