1 citations · 1 across the 8 of their papers we have counts for
3 papers · 1 filter
Architectural Sampling: Test-Time Scaling via Computational Diversity in Frozen Vision-Language Models
Akshit Singh, Shyam Marjit, Wei Lin +2
Test-time scaling often seeks better answers by sampling multiple responses from a frozen model, yet conventional temperature sampling generates every candidate along the same fixe…
Image Classifiers are Efficient Self-Supervised Video Representation Learners
Owais Iqbal, Sudipta Sarkar, Shyam Marjit +3
We introduce VideoMSN, a Masked Siamese Network framework for efficient self-supervised spatio-temporal representation learning in videos. Instead of relying on heavy 3D architectu…
DynEval: Holistic Evaluations of T2I Generative Models in the Wild
Shyam Marjit, Dheeraj Baiju, Anuj Shikarkhane +3
Recent advances in text-to-image (T2I) generation have led to models capable of producing highly realistic images. Yet, reliably evaluating their outputs remains challenging, espec…