collaborators

5 papers

cs.CL2025

Pooling Attention: Evaluating Pretrained Transformer Embeddings for Deception Classification

Sumit Mamtani, Abhijeet Bhure

This paper investigates fake news detection as a downstream evaluation of Transformer representations, benchmarking encoder-only and decoder-only pre-trained models (BERT, GPT-2, T…

cs.LG2025

Axial-UNet: A Neural Weather Model for Precipitation Nowcasting

Sumit Mamtani, Maitreya Sonawane

Accurately predicting short-term precipitation is critical for weather-sensitive applications such as disaster management, aviation, and urban planning. Traditional numerical weath…

cs.CV2025

Fine-Grained Classification: Connecting Metadata via Cross-Contrastive Pre-Training

Sumit Mamtani, Yash Thesia

Fine-grained visual classification aims to recognize objects belonging to many subordinate categories of a supercategory, where appearance alone often fails to distinguish highly s…

cs.CV2025

Enhancing Transformer-Based Vision Models: Addressing Feature Map Anomalies Through Novel Optimization Strategies

Sumit Mamtani

Vision Transformers (ViTs) have demonstrated superior performance across a wide range of computer vision tasks. However, structured noise artifacts in their feature maps hinder dow…

cs.CL2025

Token-free Models for Sarcasm Detection

Sumit Mamtani, Maitreya Sonawane, Kanika Agarwal +1

Tokenization is a foundational step in most natural language processing (NLP) pipelines, yet it introduces challenges such as vocabulary mismatch and out-of-vocabulary issues. Rece…