English
Related papers

Related papers: InstructDoc: A Dataset for Zero-Shot Generalizatio…

200 papers

Prior study shows that pre-training techniques can boost the performance of visual document understanding (VDU), which typically requires models to gain abilities to perceive and reason both document texts and layouts (e.g., locations of…

Computation and Language · Computer Science 2024-03-28 Zhiming Mao , Haoli Bai , Lu Hou , Jiansheng Wei , Xin Jiang , Qun Liu , Kam-Fai Wong

Video editing according to instructions is a highly challenging task due to the difficulty in collecting large-scale, high-quality edited video pair data. This scarcity not only limits the availability of training data but also hinders the…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Chi Zhang , Chengjian Feng , Feng Yan , Qiming Zhang , Mingjin Zhang , Yujie Zhong , Jing Zhang , Lin Ma

Text-rich document understanding (TDU) requires comprehensive analysis of documents containing substantial textual content and complex layouts. While Multimodal Large Language Models (MLLMs) have achieved fast progress in this domain,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Wenhui Liao , Jiapeng Wang , Hongliang Li , Chengyu Wang , Jun Huang , Lianwen Jin

With the rapid advancement of image generation, visual text editing using natural language instructions has received increasing attention. The main challenge of this task is to fully understand the instruction and reference image, and thus…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Lichen Ma , Xiaolong Fu , Gaojing Zhou , Zipeng Guo , Ting Zhu , Yichun Liu , Yu Shi , Jason Li , Junshi Huang

Visual document understanding (VDU) is a challenging task for large vision language models (LVLMs), requiring the integration of visual perception, text recognition, and reasoning over structured layouts. Although recent LVLMs have shown…

Computation and Language · Computer Science 2026-04-07 Haruka Kawasaki , Ryota Tanaka , Kyosuke Nishida

The ability to perform complex tasks from detailed instructions is a key to many remarkable achievements of our species. As humans, we are not only capable of performing a wide variety of tasks but also very complex ones that may entail…

Artificial Intelligence · Computer Science 2024-07-23 Xiaoxuan Lei , Lucas Gomez , Hao Yuan Bai , Pouya Bashivan

Visual Instruction Tuning (VisIT) data, commonly available as human-assistant conversations with images interleaved in the human turns, are currently the most widespread vehicle for aligning strong LLMs to understand visual inputs,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-26 Jacob Hansen , Wei Lin , Junmo Kang , Muhammad Jehanzeb Mirza , Hongyin Luo , Rogerio Feris , Alan Ritter , James Glass , Leonid Karlinsky

The proliferation of multimodal Large Language Models has significantly advanced the ability to analyze and understand complex data inputs from different modalities. However, the processing of long documents remains under-explored, largely…

Computer Vision and Pattern Recognition · Computer Science 2025-08-06 Goeric Huybrechts , Srikanth Ronanki , Sai Muralidhar Jayanthi , Jack Fitzgerald , Srinivasan Veeravanallur

We investigate a critical yet under-explored question in Large Vision-Language Models (LVLMs): Do LVLMs genuinely comprehend interleaved image-text in the document? Existing document understanding benchmarks often assess LVLMs using…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Haolong Yan , Kaijun Tan , Yeqing Shen , Xin Huang , Zheng Ge , Xiangyu Zhang , Si Li , Daxin Jiang

Instruction tuning, a new learning paradigm that fine-tunes pre-trained language models on tasks specified through instructions, has shown promising zero-shot performance on various natural language processing tasks. However, it has yet to…

Computation and Language · Computer Science 2023-06-13 Zhiyang Xu , Ying Shen , Lifu Huang

This paper presents a groundbreaking multimodal, multi-task, multi-teacher joint-grained knowledge distillation model for visually-rich form document understanding. The model is designed to leverage insights from both fine-grained and…

Computation and Language · Computer Science 2024-07-29 Yihao Ding , Lorenzo Vaiani , Caren Han , Jean Lee , Paolo Garza , Josiah Poon , Luca Cagliero

In large technology companies, the requirements for managing and organizing technical documents created by engineers and managers have increased dramatically in recent years, which has led to a higher demand for more scalable, accurate, and…

Machine Learning · Computer Science 2025-10-31 Shuo Jiang , Jie Hu , Christopher L. Magee , Jianxi Luo

Visually Rich Documents (VRDs) play a vital role in domains such as academia, finance, healthcare, and marketing, as they convey information through a combination of text, layout, and visual elements. Traditional approaches to extracting…

Computation and Language · Computer Science 2025-06-23 Yihao Ding , Soyeon Caren Han , Jean Lee , Eduard Hovy

The problem of document structure reconstruction refers to converting digital or scanned documents into corresponding semantic structures. Most existing works mainly focus on splitting the boundary of each element in a single document page,…

Computation and Language · Computer Science 2023-03-27 Jiefeng Ma , Jun Du , Pengfei Hu , Zhenrong Zhang , Jianshu Zhang , Huihui Zhu , Cong Liu

Recent advances in Large Multi-modal Models (LMMs) are primarily focused on offline video understanding. Instead, streaming video understanding poses great challenges to recent models due to its time-sensitive, omni-modal and interactive…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Shenghao Fu , Qize Yang , Yuan-Ming Li , Yi-Xing Peng , Kun-Yu Lin , Xihan Wei , Jian-Fang Hu , Xiaohua Xie , Wei-Shi Zheng

Visual Document Retrieval (VDR) typically operates as text-to-image retrieval using specialized bi-encoders trained to directly embed document images. We revisit a zero-shot generate-and-encode pipeline: a vision-language model first…

Information Retrieval · Computer Science 2025-09-22 Thong Nguyen , Yibin Lei , Jia-Huei Ju , Andrew Yates

Despite the advances in text-to-image synthesis, particularly with diffusion models, generating visual instructions that require consistent representation and smooth state transitions of objects across sequential steps remains a formidable…

Computer Vision and Pattern Recognition · Computer Science 2024-06-11 Quynh Phung , Songwei Ge , Jia-Bin Huang

Large language models (LLMs) have demonstrated that large-scale pretraining enables systems to adapt rapidly to new problems with little supervision in the language domain. This success, however, has not translated as effectively to the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Pablo Acuaviva , Aram Davtyan , Mariam Hassan , Sebastian Stapf , Ahmad Rahimi , Alexandre Alahi , Paolo Favaro

This paper presents instruct-imagen, a model that tackles heterogeneous image generation tasks and generalizes across unseen tasks. We introduce *multi-modal instruction* for image generation, a task representation articulating a range of…

Computer Vision and Pattern Recognition · Computer Science 2024-01-05 Hexiang Hu , Kelvin C. K. Chan , Yu-Chuan Su , Wenhu Chen , Yandong Li , Kihyuk Sohn , Yang Zhao , Xue Ben , Boqing Gong , William Cohen , Ming-Wei Chang , Xuhui Jia

The rapid evolution of artificial intelligence in drug discovery encounters challenges with generalization and extensive training, yet Large Language Models (LLMs) offer promise in reshaping interactions with complex molecular data. Our…

Biomolecules · Quantitative Biology 2024-12-20 He Cao , Zijing Liu , Xingyu Lu , Yuan Yao , Yu Li