activity
20242026
collaborators

9 papers

cs.AI2026

TopoBench: Benchmarking LLMs on Hard Topological Reasoning

Mayug Maniparambil, Nils Hoehing, Janak Kapuriya +5

Solving topological grid puzzles requires reasoning over global spatial invariants such as connectivity, loop closure, and region symmetry and remains challenging for even the most…

cs.MM2025

A Progressive Evaluation Framework for Multicultural Analysis of Story Visualization

Janak Kapuriya, Ali Hatami, Paul Buitelaar

Recent advancements in text-to-image generative models have improved narrative consistency in story visualization. However, current story visualization models often overlook cultur…

cs.CV2025

Semantic Frame Aggregation-based Transformer for Live Video Comment Generation

Anam Fatima, Yi Yu, Janak Kapuriya +2

Live commenting on video streams has surged in popularity on platforms like Twitch, enhancing viewer engagement through dynamic interactions. However, automatically generating cont…

cs.CV2025

Enhancing Scientific Visual Question Answering via Vision-Caption aware Supervised Fine-Tuning

Janak Kapuriya, Anwar Shaikh, Arnav Goel +8

In this study, we introduce Vision-Caption aware Supervised FineTuning (VCASFT), a novel learning paradigm designed to enhance the performance of smaller Vision Language Models(VLM…

cs.AI2025

Spiritual-LLM : Gita Inspired Mental Health Therapy In the Era of LLMs

Janak Kapuriya, Aman Singh, Jainendra Shukla +1

Traditional mental health support systems often generate responses based solely on the user's current emotion and situations, resulting in superficial interventions that fail to ad…

cs.IR2025

Exploring the Role of Diversity in Example Selection for In-Context Learning

Janak Kapuriya, Manit Kaushik, Debasis Ganguly +1

In-Context Learning (ICL) has gained prominence due to its ability to perform tasks without requiring extensive training data and its robustness to noisy labels. A typical ICL work…