Chelsi Jain
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chelsi Jain has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Heather Knight
Oregon State University
2 shared publications - Huazheng Wang
Oregon State University
2 shared publications - Jiale Liu
Pennsylvania State University
2 shared publications - Qingyun Wu
Pennsylvania State University
2 shared publications Yifan Zeng
Oregon State University
2 shared publications- Yiran Wu
Pennsylvania State University
2 shared publications
Latest Publications
- 2 January 2026
- Published by Springer Nature
- p. 370-386
Act-it-Out Method for Developing Robot Arm Actions and Semantic Commands
- 2 January 2026
- Published by Springer Nature
- p. 370-386
Act-it-Out Method for Developing Robot Arm Actions and Semantic Commands
- Open Access
SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement
Document Visual Question Answering (DocVQA) is a practical yet challenging task, which is to ask questions based on documents while referring to multiple pages and different modalities of information, e.g, images and tables. To handle multi-modality, recent methods follow a similar Retrieval Augmented Generation (RAG) pipeline, but utilize Visual Language Models (VLMs) based embedding model to embed and retrieve relevant pages as images, and generate answers with VLMs that can accept an image as input. In this paper, we introduce SimpleDoc, a lightweight yet powerful retrieval - augmented framework for DocVQA. It boosts evidence page gathering by first retrieving candidates through embedding similarity and then filtering and re-ranking these candidates based on page summaries. A single VLM-based reasoner agent repeatedly invokes this dual-cue retriever, iteratively pulling fresh pages into a working memory until the question is confidently answered. SimpleDoc outperforms previous baselines by 3.2% on average on 4 DocVQA datasets with much fewer pages retrieved. Our code is available at https://github.com/ag2ai/SimpleDoc.
Open AccessSimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement
Document Visual Question Answering (DocVQA) is a practical yet challenging task, which is to ask questions based on documents while referring to multiple pages and different modalities of information, e.g, images and tables. To handle multi-modality, recent methods follow a similar Retrieval Augmented Generation (RAG) pipeline, but utilize Visual Language Models (VLMs) based embedding model to embed and retrieve relevant pages as images, and generate answers with VLMs that can accept an image as input. In this paper, we introduce SimpleDoc, a lightweight yet powerful retrieval - augmented framework for DocVQA. It boosts evidence page gathering by first retrieving candidates through embedding similarity and then filtering and re-ranking these candidates based on page summaries. A single VLM-based reasoner agent repeatedly invokes this dual-cue retriever, iteratively pulling fresh pages into a working memory until the question is confidently answered. SimpleDoc outperforms previous baselines by 3.2% on average on 4 DocVQA datasets with much fewer pages retrieved. Our code is available at https://github.com/ag2ai/SimpleDoc.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 28398-28415
SimpleDoc: Multi‐Modal Document Understanding with Dual‐Cue Page Retrieval and Iterative Refinement
Chelsi Jain, Yiran Wu, Yifan Zeng, Jiale Liu, Shengyu Dai, Zhenwen Shao, Qingyun Wu, Huazheng Wang. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 28398-28415
Open AccessSimpleDoc: Multi‐Modal Document Understanding with Dual‐Cue Page Retrieval and Iterative Refinement
Chelsi Jain, Yiran Wu, Yifan Zeng, Jiale Liu, Shengyu Dai, Zhenwen Shao, Qingyun Wu, Huazheng Wang. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- Open Access
- 11 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 554-558
DRAWBOT: Making Everyday Objects Interactive
In various public settings, such as coffee shops, individuals often experience boredom while waiting in lines, a problem exacerbated by the lack of engaging and interactive experiences. This paper introduces DRAWBOT: Drawing Robotic Assistant for the Withering of Boredom or Tediousness. The project aims to address the challenge of uneventful waiting times by deploying a roboticized furniture system that encourages artistic expression in people.
- 11 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 554-558
Open AccessDRAWBOT: Making Everyday Objects Interactive
In various public settings, such as coffee shops, individuals often experience boredom while waiting in lines, a problem exacerbated by the lack of engaging and interactive experiences. This paper introduces DRAWBOT: Drawing Robotic Assistant for the Withering of Boredom or Tediousness. The project aims to address the challenge of uneventful waiting times by deploying a roboticized furniture system that encourages artistic expression in people.