From zero research experience to ISEF 2026 Qualifier
Mubashir tackled a structural barrier in astrophysics: gravitational-wave machine learning normally needs $50,000 or more per year in GPU infrastructure. He trained a lightweight CNN of roughly 92,000 parameters on LIGO-Virgo detector strain data using free Google Colab, then engineered a peer-to-peer distributed training framework so that 100 standard laptops can match a single NVIDIA V100 GPU. The work qualified him for ISEF 2026.
Physics & Astronomy
Regeneron ISEF 2026 Qualifier
Regeneron ISEF, 2026
Mubashir Suhail, YRI Fellow
High school student in Karachi passionate about physics and computer science, with no prior research experience.
Won Best of Subject Category at the National Science and Engineering Fair Pakistan 2025 and qualified to represent Pakistan at Regeneron ISEF 2026 in Phoenix, Arizona.
“I was obsessed with gravitational waves and wanted to build a detection system without expensive hardware. My mentor helped me work through the signal processing and turn my idea into a real research paper. Making it to ISEF with something I actually cared about was surreal.”
Qualified to represent Pakistan at Regeneron ISEF 2026 in Phoenix, Arizona
Won Best of Subject Category at the National Science and Engineering Fair Pakistan 2025
Trained a lightweight CNN of roughly 92,000 parameters on free Google Colab
Built the P2P-DTF framework letting 100 laptops match one NVIDIA V100 GPU
Achieved 80x gradient compression for training on low-bandwidth connections
Aditya Singla, Best Oral Presentation, IEEE AAIML 2026 Tokyo