|
Aaryan Garg I'm a fourth year undergraduate student at BITS Pilani studying Computer Science. I have an interest in Deep Learning on the whole, but have recently spent most of my time playing with vision and multimodal models. I've been a research intern at CRCV at UCF since November 2023 working with Dr. Yogesh S Rawat. At CRCV, my research has spanned adaptive classification models, efficient transformer based segmentation and most recently spatio-temporal video grounding. I'm always looking for new things to work on, so if you have an interesting project or idea, please reach out! Email / Scholar / Github / CV / Blog |
|
Updates
Mar'25:
STPro is accepted to
PixFoundation & MAR workshops at
CVPR |
TalksApril'25: Building effective tools for LLM based agents (DevRev Community Event) - Slides | Recording |
ResearchSome representative papers are highlighted. |
|
STPro: Spatial & Temporal Progressive Learning for
Weakly Supervised Spatio-Temporal Video Grounding
Computer Vision & Pattern Recognition (CVPR) - 2025 (Poster) 🎨 PixFoundation Workshop 🧠 Multimodal Algorithmic Reasoning Workshop 🏛️ Multimodal Foundation Models Workshop 👁️ Emergent Visual Abilities & Limits of Foundation Models Workshop 🌐 Domain Generalization Workshop Aaryan Garg, Akash Kumar, Yogesh S Rawat 🛠️ Project page / 
/
🤗 HuggingFace
Improved VLMs grounding capabilities via action composition and complex spatio-temporal scene understanding. |
Other |