Related papers: Supporting Business Document Workflows via Collect…
We present Marco-MoE, a suite of fully open multilingual sparse Mixture-of-Experts (MoE) models. Marco-MoE features a highly sparse design in which only around 5\% of the total parameters are activated per input token. This extreme…
Document understanding aims to perform question answering and information extraction over document images, where the visual content is highly information-dense and most queries rely on only a few relevant layout regions. However, existing…
Despite the prevalence of pretrained language models in natural language understanding tasks, understanding lengthy text such as document is still challenging due to the data sparseness problem. Inspired by that humans develop their ability…
Understanding the contents of multimodal documents is essential to accurately extract relevant evidence and use it for reasoning. Existing document understanding models tend to generate answers with a single word or phrase directly,…
My research aims to design systems for complex sensemaking by remotely located non-expert collaborators (crowds), to solve computationally hard problems like crimes.
Large Language Models (LLMs) have become increasingly capable of interacting with external tools, granting access to specialized knowledge beyond their training data - critical in dynamic, knowledge-intensive domains such as Chemistry and…
We propose a novel end-to-end document understanding model called SeRum (SElective Region Understanding Model) for extracting meaningful information from document images, including document analysis, retrieval, and office automation. Unlike…
Recent research has explored using Large Language Models for recommendation tasks by transforming user interaction histories and item metadata into text prompts, then having the LLM produce rankings or recommendations. A promising approach…
As AI agents take on increasingly long-running tasks involving sophisticated planning and execution, there is a corresponding need for novel interaction designs that enable deeper human-agent collaboration. However, most prior works…
Large language models with long context windows can answer complex questions directly from full-length academic, technical, and policy documents, but passing entire documents is often costly, slow, and can degrade answer quality while…
We present MOSAIC, a multi-agent Large Language Model (LLM) framework for solving challenging scientific coding tasks. Unlike general-purpose coding, scientific workflows require algorithms that are rigorous, interconnected with deep domain…
The ability to understand and answer questions over documents can be useful in many business and practical applications. However, documents often contain lengthy and diverse multimodal contents such as texts, figures, and tables, which are…
We propose a new ensemble framework for supervised learning, called machine collaboration (MaC), using a collection of base machines for prediction tasks. Unlike bagging/stacking (a parallel & independent framework) and boosting (a…
In enterprise organizations, data-driven decision making processes include the use of business intelligence dashboards and collaborative deliberation on communication platforms such as Slack. However, apart from those in data analyst roles,…
Document management software are used widely for office paper management and related workflows. However, they have some differences from a flexibility perspective for the needs of workers. Moreover, they also differentiate in their…
This paper presents Lishu, a deployable web artifact for searching, monitoring, and interpreting literature from elite business and management journals. The system integrates the UTD-24 and Financial Times 50 (FT50) journal pools and…
Generalized text representations are the foundation of many natural language understanding tasks. To fully utilize the different corpus, it is inevitable that models need to understand the relevance among them. However, many methods ignore…
Recommender systems today have become an essential component of any commercial website. Collaborative filtering approaches, and Matrix Factorization (MF) techniques in particular, are widely used in recommender systems. However, the natural…
Graphs that capture relations between textual units have great benefits for detecting salient information from multiple documents and generating overall coherent summaries. In this paper, we develop a neural abstractive multi-document…
When people search for information about a new topic within large document collections, they implicitly construct a mental model of the unfamiliar information space to represent what they currently know and guide their exploration into the…