activity
20222026
most citedA Review of Deep Learning Techniques for Speech Processing

22 citations · 44 across the 20 of their papers we have counts for

collaborators
Showing cs.IRShow all

2 papers · 1 filter

cs.IR2026

Constrained Dominant Sets for Multimodal Document Question Answering

Ambuj Mehrish, Sebastiano Vascon

Long multimodal document question answering is limited by which evidence reaches the reader, rather than by the quantity retrieved. In lengthy documents, findings often recur acros…

cs.IR2026

Min-Cost Flow Routing for Evidence Assembly in Long Multimodal Documents

Ambuj Mehrish, Sebastiano Vascon

Answering questions about long multimodal documents requires distributing a fixed evidence budget across relevant facets in text, tables, figures, and slides while avoiding near-du…