activity
20242026
collaborators

9 papers

cs.CV2026

DocVAL: Validated Chain-of-Thought Distillation for Grounded Document VQA

Pinaki Prasad Guha Neogi, Ahmad Mohammadshirazi, Ser-Nam Lim +1

Document visual question answering requires models not only to answer questions correctly, but also to precisely localize answers within complex document layouts. While large visio…

cs.CV2025

ARIAL: An Agentic Framework for Document VQA with Precise Answer Localization

Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Dheeraj Kulshrestha +1

Document Visual Question Answering (VQA) requires models to not only extract accurate textual answers but also precisely localize them within document images, a capability critical…

cs.LG2025

Exploiting the Experts: Unauthorized Compression in MoE-LLMs

Pinaki Prasad Guha Neogi, Ahmad Mohammadshirazi, Dheeraj Kulshrestha +1

Mixture-of-Experts (MoE) architectures are increasingly adopted in large language models (LLMs) for their scalability and efficiency. However, their modular structure introduces a…

cs.CV2025

MGA-VQA: Secure and Interpretable Graph-Augmented Visual Question Answering with Memory-Guided Protection Against Unauthorized Knowledge Use

Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Dheeraj Kulshrestha +1

Document Visual Question Answering (DocVQA) requires models to jointly understand textual semantics, spatial layout, and visual features. Current methods struggle with explicit spa…

cs.LG2025

InsightBuild: LLM-Powered Causal Reasoning in Smart Building Systems

Pinaki Prasad Guha Neogi, Ahmad Mohammadshirazi, Rajiv Ramnath

Smart buildings generate vast streams of sensor and control data, but facility managers often lack clear explanations for anomalous energy usage. We propose InsightBuild, a two-sta…

cs.LG2025

ALCo-FM: Adaptive Long-Context Foundation Model for Accident Prediction

Pinaki Prasad Guha Neogi, Ahmad Mohammadshirazi, Rajiv Ramnath

Traffic accidents are rare, yet high-impact events that require long-context multimodal reasoning for accurate risk forecasting. In this paper, we introduce ALCo-FM, a unified adap…