Hafeez Khan
Welcome! I am a Ph.D. student in Computer Science at Florida Tech, working on self-supervised learning, vision-language models, and novel view synthesis. My PhD advisor is Siddhartha Bhattacharyya, and I am funded by NASA Langley Research Center, where I am co-advised by Natasha Neogi.
Alongside my PhD, I have collaborated closely with mentors from Microsoft Research, American Heart Association, and Collins Aerospace, gaining experience in multi-modal learning and 3D reconstruction. I recently won 1st place in a Meta-hosted competition at ICCV 2025, developing a lossy 3DGS compression algorithm that achieved a 95.6% reduction in model sizes.
Previously, I earned my B.Tech. in Computer Science from BITS Pilani Dubai, graduating with an Excellence in Research Award under Raja Muthalaghu.
Please reach out by email if our interests align and you’d like to collaborate!
news
| Feb 09, 2026 | Accepted Summer 2026 Internship Offer from Collins Aerospace, and will be working on Agentic Vision Language Models! |
|---|---|
| Oct 20, 2025 | Won 1st Place in the ICCV 2025, Computationally Optimal Gaussian Splatting (COGS) Competition hosted by Meta and University of Toronto. |
| Aug 21, 2025 | Recognized for outstanding academic achievement and invited to join Upsilon Pi Epsilon (UPE), the international honor society for computing sciences! |
| Jul 13, 2025 | Test-time Prompt Refinement for Text-to-Image Models accepted at ICCV 2025 (MARS2 Workshop, Oral Presentation)! |
selected publications
-
Test-time Prompt Refinement for Text-to-Image ModelsIn Workshop on Multimodal Reasoning and Slow Thinking in Large Model Era at ICCV, 2025 -
NORA: A Nephrology-Oriented Representation Learning Approach Towards Chronic Kidney Disease ClassificationIn Under Submission at International Conference in Machine Learning and Applications (ICMLA), 2025 -
Adapt, But Don’t Forget: Modular Fine-Tuning and Contrastive Routing for Lane Detection Under Distribution ShiftIn Workshop on Out Of Label Hazard Detection in Autonomous Driving at ICCV, 2025 -
Modular Test-time Input-Space Refinement for Few-Shot SegmentationIn Under submission in Neural Information Processing Systems (NeurIPS), 2025 -
ALINA: Advanced Line Identification and Notation AlgorithmIn Workshop on Vision Datasets Understanding at CVPR, 2024