Related papers: Towards Efficient Resume Understanding: A Multi-Gr…

Learning general representations of text is a fundamental problem for many natural language understanding (NLU) tasks. Previously, researchers have proposed to use language model pre-training and multi-task learning to learn robust…

Multimodal large language models (MLLMs) may memorize sensitive cross-modal information during pretraining, making machine unlearning (MU) crucial. Existing methods typically evaluate unlearning effectiveness based on output deviations,…

Pre-trained language models demonstrate general intelligence and common sense, but long inputs quickly become a bottleneck for memorizing information at inference time. We resurface a simple method, Memorizing Transformers (Wu et al.,…

Natural Language Understanding (NLU) is a branch of Natural Language Processing (NLP) that uses intelligent computer software to understand texts that encode human knowledge. Recent years have witnessed notable progress across various NLU…

Video-and-language understanding has a variety of applications in the industry, such as video question answering, text-video retrieval, and multi-label classification. Existing video-and-language understanding methods generally adopt heavy…

In the recent past, complex deep neural networks have received huge interest in various document understanding tasks such as document image classification and document retrieval. As many document types have a distinct visual style, learning…

We propose SelfDoc, a task-agnostic pre-training framework for document image understanding. Because documents are multimodal and are intended for sequential reading, our framework exploits the positional, textual, and visual information of…

Unified information extraction (UIE) aims to extract diverse structured information from unstructured text. While large language models (LLMs) have shown promise for UIE, they require significant computational resources and often struggle…

In recent years, the use of multi-modal pre-trained Transformers has led to significant advancements in visually-rich document understanding. However, existing models have mainly focused on features such as text and vision while neglecting…

This paper explores Machine Unlearning (MU), an emerging field that is gaining increased attention due to concerns about neural models unintentionally remembering personal or sensitive information. We present SeUL, a novel method that…

Sequential fine-tuning and multi-task learning are methods aiming to incorporate knowledge from multiple tasks; however, they suffer from catastrophic forgetting and difficulties in dataset balancing. To address these shortcomings, we…

We introduce Dessurt, a relatively simple document understanding transformer capable of being fine-tuned on a greater variety of document tasks than prior methods. It receives a document image and task string as input and generates…

The Outstanding performance and growing size of Large Language Models has led to increased attention in parameter efficient learning. The two predominant approaches are Adapters and Pruning. Adapters are to freeze the model and give it a…

Automatic radiology report generation has attracted enormous research interest due to its practical value in reducing the workload of radiologists. However, simultaneously establishing global correspondences between the image (e.g., Chest…

Transformers achieve promising performance in document understanding because of their high effectiveness and still suffer from quadratic computational complexity dependency on the sequence length. General efficient transformers are…

Retrieval augmentation has become an effective solution to empower large language models (LLMs) with external and verified knowledge sources from the database, which overcomes the limitations and hallucinations of LLMs in handling…

Understanding intricate and fast-paced movements of body parts is essential for the recognition and translation of sign language. The inclusion of additional information intended to identify and locate the moving body parts has been an…

Continual learning is essential for adapting models to new tasks while retaining previously acquired knowledge. While existing approaches predominantly focus on uni-modal data, multi-modal learning offers substantial benefits by utilizing…

With the growth of the academic engines, the mining and analysis acquisition of massive researcher data, such as collaborator recommendation and researcher retrieval, has become indispensable. It can improve the quality of services and…

Fine-tuning Large Language Models (LLMs) is now a common approach for text classification in a wide range of applications. When labeled documents are scarce, active learning helps save annotation efforts but requires retraining of massive…