most citedExplainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models

2 citations · 2 across the 2 of their papers we have counts for

collaborators

10 papers

cs.AI2026

AUTOPILOT VQA: Benchmarking Vision-Language Models for Incident-Centric Dashcam Understanding

Siddharth Damodharan, Radhika Gupta, Ali Alshami +2

Recent advances in Vision-Language Models, Large Language Models, and Multimodal Large Language Models have improved autonomous driving tasks such as scene understanding, decision…

cs.CL20262 cited

Explainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models

Melkamu Abay Mersha, Jugal Kalita

Transformer models achieve state-of-the-art performance across domains and tasks, yet their deeply layered representations make their predictions difficult to interpret. Existing e…

cs.CL2026

Semantic-Driven Topic Modeling for Analyzing Creativity in Virtual Brainstorming

Melkamu Abay Mersha, Jugal Kalita

Virtual brainstorming sessions have become a central component of collaborative problem solving, yet the large volume and uneven distribution of ideas often make it difficult to ex…

cs.SE2025

Analyzing Code Injection Attacks on LLM-based Multi-Agent Systems in Software Development

Brian Bowers, Smita Khapre, Jugal Kalita

Agentic AI and Multi-Agent Systems are poised to dominate industry and society imminently. Powered by goal-driven autonomy, they represent a powerful form of generative AI, marking…

cs.CY2025

Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directions

Smita Khapre, Melkamu Abay Mersha, Hassan Shakil +2

The evolution of digital communication systems and the designs of online platforms have inadvertently facilitated the subconscious propagation of toxic behavior. Giving rise to rea…

cs.LG2025

Drug Repurposing Using Deep Embedded Clustering and Graph Neural Networks

Luke Delzer, Robert Kroleski, Ali K. AlShami +1

Drug repurposing has historically been an economically infeasible process for identifying novel uses for abandoned drugs. Modern machine learning has enabled the identification of…