activity
20242026
collaborators

9 papers

cs.AI2026

MuCRASP: Multimodal Chain-of-thought Reasoning aware Structured Pruning

Aritra Dutta, Somak Aditya

Vision-language models (VLMs) increasingly rely on chain-of-thought (CoT) reasoning to solve complex multimodal tasks, but their large parameter sizes make deployment expensive. St…

cs.SE2026

AFGNN: API Misuse Detection using Graph Neural Networks and Clustering

Ponnampalam Pirapuraj, Tamal Mondal, Sharanya Gupta +3

Application Programming Interfaces (APIs) are crucial to software development, enabling integration of existing systems with new applications by reusing tried and tested code, savi…

cs.CV2026

AD: Analysis and Detection of Adversarial Threats in Visual Perception for End-to-End Autonomous Driving Systems

Ishan Sahu, Somnath Hazra, Somak Aditya +1

End-to-end autonomous driving systems have achieved significant progress, yet their adversarial robustness remains largely underexplored. In this work, we conduct a closed-loop eva…

cs.AI2025

PragWorld: A Benchmark Evaluating LLMs' Local World Model under Minimal Linguistic Alterations and Conversational Dynamics

Sachin Vashistha, Aryan Bibhuti, Atharva Naik +2

Real-world conversations are rich with pragmatic elements, such as entity mentions, references, and implicatures. Understanding such nuances is a requirement for successful natural…

cs.CL2025

EduVidQA: Generating and Evaluating Long-form Answers to Student Questions based on Lecture Videos

Sourjyadip Ray, Shubham Sharma, Somak Aditya +1

As digital platforms redefine educational paradigms, ensuring interactivity remains vital for effective learning. This paper explores using Multimodal Large Language Models (MLLMs)…

cs.CL2025

TEXT2AFFORD: Probing Object Affordance Prediction abilities of Language Models solely from Text

Sayantan Adak, Daivik Agrawal, Animesh Mukherjee +1

We investigate the knowledge of object affordances in pre-trained language models (LMs) and pre-trained Vision-Language models (VLMs). A growing body of literature shows that PTLMs…