collaborators

5 papers

cs.CV2025

Mirage: Unveiling Hidden Artifacts in Synthetic Images with Large Vision-Language Models

Pranav Sharma, Shivank Garg, Durga Toshniwal

Recent advances in image generation models have led to models that produce synthetic images that are increasingly difficult for standard AI detectors to identify, even though they…

cs.CL2024

Improving Multi-Domain Task-Oriented Dialogue System with Offline Reinforcement Learning

Dharmendra Prajapat, Durga Toshniwal

Task-oriented dialogue (TOD) system is designed to accomplish user-defined tasks through dialogues. The TOD system has progressed towards end-to-end modeling by leveraging pre-trai…

cs.CL2024

Modeling Text-Label Alignment for Hierarchical Text Classification

Ashish Kumar, Durga Toshniwal

Hierarchical Text Classification (HTC) aims to categorize text data based on a structured label hierarchy, resulting in predicted labels forming a sub-hierarchy tree. The semantics…

cs.CL2024

Unveiling Themes in Judicial Proceedings: A Cross-Country Study Using Topic Modeling on Legal Documents from India and the UK

Krish Didwania, Durga Toshniwal, Amit Agarwal

Legal documents are indispensable in every country for legal practices and serve as the primary source of information regarding previous cases and employed statutes. In today's wor…

cs.CV2024

Snowy Scenes,Clear Detections: A Robust Model for Traffic Light Detection in Adverse Weather Conditions

Shivank Garg, Abhishek Baghel, Amit Agarwal +1

With the rise of autonomous vehicles and advanced driver-assistance systems (ADAS), ensuring reliable object detection in all weather conditions is crucial for safety and efficienc…