About Me
I am a Graduate Research Assistant at Carnegie Mellon University under the supervision of Professor Deepak Pathak with close mentorship from Mihir Prabhudesai. I received my M.S. in Electrical and Computer Engineering from CMU. Before coming to CMU, I completed my B.E. in Software Engineering at Beijing Jiaotong University, supervised by Professor Ruipeng Gao.
My research interests lie in Natural Language Processing, Computer Vision, and Generative Modeling for Robotics. I am currently interested in the fundamental principles of generative modeling, specifically in architectures and training objectives that can generalize to complex reasoning tasks with scaling abilities. In addition, I want to explore the trade-off between training data, token memory and compute.
Feel free to reach out if you’d like to connect!
Selected Publications (Full publication list available here)
Diffusion Beats Autoregressive in Data-Constrained Settings
Mihir Prabhudesai*, Mengning Wu*, Amir Zadeh, Katerina Fragkiadaki, Deepak Pathak
* Equal contribution
NeurIPS 2025
Can LLMs Lie? Investigation beyond Hallucination
Haoran Huan*, Mihir Prabhudesai*, Mengning Wu*, Shantanu Jaiswal, Deepak Pathak
arXiv preprint
Education
Carnegie Mellon University
M.S. in Electrical and Computer Engineering
Pittsburgh, PA, Sep 2023 - May 2025
GPA: 4.0/4.0
Beijing Jiaotong University
B.E. in Software Engineering
Beijing, China, Sep 2019 - May 2023
GPA: 3.9/4.0 (Top 3%) Advisor: Prof. Ruipeng Gao