8 papers
ChartAgent: A Multimodal Agent for Visually Grounded Reasoning in Complex Chart Question Answering
Rachneet Kaur, Nishan Srishankar, Zhen Zeng +2
Recent multimodal LLMs have shown promise in chart-based visual question answering, but their performance declines sharply on unannotated charts-those requiring precise visual inte…
SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document Understanding
Yiqiao Jin, Rachneet Kaur, Zhen Zeng +2
Multi-page visual documents such as manuals, brochures, presentations, and posters convey key information through layout, colors, icons, and cross-slide references. While multimoda…
MM-BizRAG: Rethinking Multimodal Retrieval-Augmented Generation for General Purpose Enterprise Q&A
Hanoz Bhathena, Parin Rajesh Jhaveri, Rohan Mittal +7
Recent advances in multimodal retrieval-augmented generation (MM-RAG) have shifted toward minimal parsing, relying on page-level images for producing retriever embeddings and for a…
Creating a Causally Grounded Rating Method for Assessing the Robustness of AI Models for Time-Series Forecasting
Kausik Lakkaraju, Rachneet Kaur, Parisa Zehtabi +5
AI models, including both time-series-specific and general-purpose Foundation Models (FMs), have demonstrated strong potential in time-series forecasting across sectors like financ…
AI Analyst: Framework and Comprehensive Evaluation of Large Language Models for Financial Time Series Report Generation
Elizabeth Fons, Elena Kochkina, Rachneet Kaur +5
This paper explores the potential of large language models (LLMs) to generate financial reports from time series data. We propose a framework encompassing prompt engineering, model…
LETS-C: Leveraging Text Embedding for Time Series Classification
Rachneet Kaur, Zhen Zeng, Tucker Balch +1
Recent advancements in language modeling have shown promising results when applied to time series data. In particular, fine-tuning pre-trained large language models (LLMs) for time…