Aishni Parab

I study how humans perceive, represent, and reason about the visual and physical world under uncertainty. My work explores how structured representations can explain perception and enable resource-rational, generalizable reasoning.

My research work is centered around three key directions:

• Studying how programs can serve as an interpretable form of knowledge representation
• Developing Probabilistic and Deep Learning methods that jointly reason over images and programs
• Enhancing Search and Inference with Large Language Models (LLMs)

Bio:

I am a PhD Candidate in the Department of Statistics and Data Science at the University of California, Los Angeles, supervised by Hongjing Lu and Ying Nian Wu. I am currently a Research Intern on the Program Synthesis team at Microsoft.

I obtained a M.S. in Computer Science from UCLA with generous support from Google Deepmind. I completed my B.S. in Computer Science from UC Santa Cruz.

Prior to joining UCLA, I was a Software Engineer at the Tangible Media Group at MIT Media Lab developing AI solutions for Shima Seiki Japan’s WholeGarment 3D knitting technology. I acquired certified training to design and produce knitwear on the MACH2XS knitting machine (samples available on request). Before that, I worked in the Human-Centered AI group with Lex Fridman on autonomous vehicles research.

Outside of research, I enjoy exploring the arts and spending time in nature. In my free time, I practice Ashtanga yoga, Hindustani Classical vocals, and the piano. I also love playing tennis and reading. If you’re looking for books, consider supporting local bookstores: : Books Inc, Palo Alto; Book Soup, 8818 Sunset Blvd.