Priyank Pathak

I am a final year Ph.D. Candidate (Jan'23 - Aug'26) from Center for Research in Computer Vision (University of Central Florida) under Prof. Yogesh S. Rawat. My research focuses on Noise Robustness, Person Re-Identification (ReID) and efficient Deep Learning. Prior to UCF, I earned my Master’s in Computer Science from New York University (NYU) Courant Institute, where I completed my thesis under the guidance of Prof. Rob Fergus. I hold Dual Bachelor of Technology (B.Tech) degrees in Electrical Engineering and Computer Science from the Indian Institute of Technology (IIT) Kanpur.

priyank@ucf.edu / pp1953@nyu.edu

Research

My research centers around efficient training in computer vision, with a strong emphasis on improving robustness to real world noise, like autonomous driving scenarios of fog, rain, and snow. My primary focus lies in Zero Shot learning and VLMs (transformers) , with a specific emphasis on object detection. I also have substantial experience in interpretable and explainable AI and Visualization, enabling easy to understand insights into models. In parallel, I have been actively working on Person Re Identification (ReID) for the past seven years, which was the core of my Master’s thesis as well.

	LR0.FM: Low-Res Benchmark and Improving Robustness for Zero-Shot Classification in Foundation Models Priyank Pathak, Shyam Marjit, Shruti Vyas, Yogesh S. Rawat ICLR'25 \|\| ICCV'25 (Non-Proceedings) 🎙️ Paper / Project Page / Code / Arxiv Noise Robustness Zero-shot Images VLMs Prompts Benchmark
	Colors See Colors Ignore: Clothes Changing ReID with Color Disentanglement Priyank Pathak, Yogesh S. Rawat ICCV'25 \|\| Patent filed 📜 Paper / Project Page / Code / Arxiv Person ReID Self-Attention Video & Image Efficiency
	Coarse Attribute Prediction with Task Agnostic Distillation for Real World Clothes Changing ReID Priyank Pathak, Yogesh S. Rawat BMVC'25 Paper / Code / Arxiv Person ReID Real World Noisy Images ResNets
	Video person re-id: Fantastic techniques and where to find them Priyank Pathak, Amir Erfan Eshratifar, Michael Gormish AAAI'20 Paper / Code / Arxiv Person ReID Video & Image Techniques Novel Loss
	Peeling Layers of Zero-Shot Object Detection for Robustness *Priyank Pathak,** Mukilan Karuppasamy, Aaditya Baranwal, 3 more authors equal contribution Under Review 🔒 OpenReview Object Detectors Zero-shot Analysis Opening Black Box Noises
	Incremental Scene Graph Updates in VLMs Shresth Grover, Priyank Pathak, Akash Kumar, Vibhav Vineet, Yogesh S Rawat Under Review 🔒 Project Page / Code / Arxiv LLMs Resoning Technique Benchmark Sequence Error
	Efficinet Test-Time Training for Dense Task Prediction Rajat Modi, Xin Liang, Priyank Pathak, Yogesh S Rawat Under Review 🔒 Test Time Training VLMs Efficinet Distillation Dense Task
	Zero-shot robustness in real-world Priyank Pathak, Yogesh S Rawat Preprint 🤫 Zero-Shot VLMs Object Detectors Robustness

Work Experience

May'26 – Aug'26

Applied Scientist Intern

Incoming

Sunnyvale, California

Aug'22 – Dec'22

Research Assistant

National University of Singapore

Singapore

June'20 - Aug'21

Research Engineer

Amobee

New York (Remote) / Redwood City, California

May'19 - Sept'19

Deep Learning Research Intern

Clarifai

San Francisco, California

May'17 - Aug'17

Deep Learning Research Intern

Rice University

Houston, Texas

May'16 - Aug'16

Summer SDE Intern

Reliance Jio

Gurugram, India

Miscellaneous

Service	Reviewer, CVPR 2026 Reviewer, ICLR 2026 Reviewer, AAAI 2026 Reviewer, Neurips 2025 Reviewer, BMVC 2025 Reviewer, CVPR 2025 (Outstanding Reviewer) Reviewer, ICLR 2025 (Outstanding Reviewer)
Pre-Prints	Fine-Grained Re-Identification (Master's Thesis) Local Learning on Transformers via Feature Reconstruction
Misc Projects I sometimes open-source implementation of others' papers.	Success of Filmmaking (JS & Novel Visuals) [Youtube Feature \| Online \| GIF ] Beautiful Customizable plots for Research Papers [GitHub] Faster RCNN tutorial [ Githhub] Reinforcement learning tutorial [Web Page] Spatial Transformers for traffic signal detection [Github] Video-Action-Transformer-Network [Github] Online softmining loss [Github]

"Aloo has no place in Biryani" - Every Desi Foodie

Built upon Jon Barron's template, and modified upon Rohit Gupta