About Me

• PhD student at Stony Brook University, NY, USA advised by Michael Ryoo.
• Former Student Researcher at Google Research with Srikumar Ramalingam.
• Former Research Intern at Meta with Tsung-Yu Lin.
• Former Research Intern at Apple with Jonathon Shlens and Alexander Toshev.
• Prior to PhD, Research Assistant at MBZUAI with Salman Khan, Muzammal Naseer, and Fahad Khan.
• Interested in Computer Vision and Machine Learning with focus on the subdomains of Self-Supervised Learning, Video Understanding, and Vision-Language Representations.
• Enjoy ballroom dancing, cooking, and theatre during my leisure time.

Have a look at my Curriculum Vitae for more details and Google Scholar for full list of papers.

Updates

• MVU for Long Video QnA accepted to ICLR’25!
• LLaRA: Large Language and Robotics Assistant accepted to ICLR’25!
• Checkout LatentCRF for efficient text-to-image generation.

Selected Publications

• Dec 2023: Localization in Visual-LLMs Improves Reasoning, CVPR 2024.
• May 2023: Language-based Video Self-Supervised Learning, NeurIPS 2023.
• November 2022: T2I Diffusion Models are Zero-Shot Segmentors, CVPR workshop 2023.
• October 2022: Perceptual Grouping in Contrastive VLMs, ICCV 2023.
• November 2021: Self-supervised Video Transformers, CVPR 2022 (oral).
• July 2021: Adversarial Transferability of Vision Transformers, ICLR 2022 (spotlight).
• May 2021: Intriguing Properties of Vision Transformers, NeurIPS 2021 (spotlight).
• March 2021: Orthogonal Projection Loss, ICCV 2021.
• January, 2021: Conditional Generative Modeling, ICLR 2021.
• September 2019: Activity Recognition in Videos, TCSVT journal.

Featured Work

• Our Diffusion Illusions work (CVPR ‘23 Best Demo) featured on Stony Brook News.