3 papers
cs.IR2026
AMES: Approximate Multi-modal Enterprise Search via Late Interaction Retrieval
Tony Joseph, Carlos Pareja, David Lopes Pegna +1
We present AMES (Approximate Multimodal Enterprise Search), a unified multimodal late interaction retrieval architecture which is backend agnostic. AMES demonstrates that fine-grai…
cs.LG2024
INDIC QA BENCHMARK: A Multilingual Benchmark to Evaluate Question Answering capability of LLMs for Indic Languages
Abhishek Kumar Singh, Vishwajeet kumar, Rudra Murthy +3
Large Language Models (LLMs) perform well on unseen tasks in English, but their abilities in non English languages are less explored due to limited benchmarks and training data. To…
cs.CV2023
EIGEN: Expert-Informed Joint Learning Aggregation for High-Fidelity Information Extraction from Document Images
Abhishek Singh, Venkatapathy Subramanian, Ayush Maheshwari +3
Information Extraction (IE) from document images is challenging due to the high variability of layout formats. Deep models such as LayoutLM and BROS have been proposed to address t…