1 citations · 1 across the 8 of their papers we have counts for
10 papers
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…
O3SLM: Open Weight, Open Data, and Open Vocabulary Sketch-Language Model
Rishi Gupta, Mukilan Karuppasamy, Shyam Marjit +2
While Large Vision Language Models (LVLMs) are increasingly deployed in real-world applications, their ability to interpret abstract visual inputs remains limited. Specifically, th…
FedSCAl: Leveraging Server and Client Alignment for Unsupervised Federated Source-Free Domain Adaptation
M Yashwanth, Sampath Koti, Arunabh Singh +2
We address the Federated source-Free Domain Adaptation (FFreeDA) problem, with clients holding unlabeled data with significant inter-client domain gaps. The FFreeDA setup constrain…
TTRV: Test-Time Reinforcement Learning for Vision Language Models
Akshit Singh, Shyam Marjit, Wei Lin +7
Existing methods for extracting reward signals in Reinforcement Learning typically rely on labeled data and dedicated training splits, a setup that contrasts with how humans learn…
LR0.FM: Low-Res Benchmark and Improving Robustness for Zero-Shot Classification in Foundation Models
Priyank Pathak, Shyam Marjit, Shruti Vyas +1
Visual-language foundation Models (FMs) exhibit remarkable zero-shot generalization across diverse tasks, largely attributed to extensive pre-training on largescale datasets. Howev…
DiffuseKronA: A Parameter Efficient Fine-tuning Method for Personalized Diffusion Models
Shyam Marjit, Harshit Singh, Nityanand Mathur +3
In the realm of subject-driven text-to-image (T2I) generative models, recent developments like DreamBooth and BLIP-Diffusion have led to impressive results yet encounter limitation…
CLIPDraw++: Text-to-Sketch Synthesis with Simple Primitives
Nityanand Mathur, Shyam Marjit, Abhra Chaudhuri +1
With the goal of understanding the visual concepts that CLIP associates with text prompts, we show that the latent space of CLIP can be visualized solely in terms of linear transfo…
Limited Data, Unlimited Potential: A Study on ViTs Augmented by Masked Autoencoders
Srijan Das, Tanmay Jain, Dominick Reilly +6
Vision Transformers (ViTs) have become ubiquitous in computer vision. Despite their success, ViTs lack inductive biases, which can make it difficult to train them with limited data…