15 papers
Large Models for Small Devices: Recent Advances and Empirical Analysis of Edge AI Deployment
Subhransu Das, Jiaming Cheng, Arnav Kumar +6
Running large AI models on resource-constrained edge devices requires model compression to reduce model size and computation. What compresses well, however, need not deploy well. W…
When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs
Jiaming Cheng, Subhransu Das, Rajiv Ramnath
Multi-agent LLM systems relay key--value caches instead of text and credit their gains to exchanged ``latent thoughts''. That credit is a claim about \emph{which} example's cache i…
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…
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…
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…
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…