Related papers: Mirror: A Universal Framework for Various Informat…
We propose a unified cross-domain transfer learning framework that leverages knowledge from multiple heterogeneous medical imaging datasets to improve performance across segmentation, classification, and object detection tasks. Our approach…
Learning template based information extraction from documents is a crucial yet difficult task. Prior template-based IE approaches assume foreknowledge of the domain templates; however, real-world IE do not have pre-defined schemas and it is…
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…
Diffusion models have shown remarkable performance in generation problems over various domains including images, videos, text, and audio. A practical bottleneck of diffusion models is their sampling speed, due to the repeated evaluation of…
This paper proposes a new principled multi-task representation learning framework (InfoMTL) to extract noise-invariant sufficient representations for all tasks. It ensures sufficiency of shared representations for all tasks and mitigates…
Information seeking on mobile devices is often fragmented, trapping users in repetitive cycles of context switching and data re-entry, which increases cognitive load and disrupts workflow. Existing mobile agents provide limited cross-source…
The subgraph isomorphism finding problem is a well-studied problem in the field of computer science and graph theory, and it aims to enumerate all instances of a query graph in the respective data graph. In this paper, we propose an…
Information extraction (IE) is an important task in Natural Language Processing (NLP), involving the extraction of named entities and their relationships from unstructured text. In this paper, we propose a novel approach to this task by…
We provide a detailed overview of the various approaches that were proposed to date to solve the task of Open Information Extraction. We present the major challenges that such systems face, show the evolution of the suggested approaches…
Complex information extraction (IE) pipelines assembled by plumbing together off-the-shelf operators, specially customized operators, and operators re-used from other text processing pipelines are becoming an integral component of most text…
Current image retrieval systems often face domain specificity and generalization issues. This study aims to overcome these limitations by developing a computationally efficient training framework for a universal feature extractor that…
Meta-learning enables algorithms to quickly learn a newly encountered task with just a few labeled examples by transferring previously learned knowledge. However, the bottleneck of current meta-learning algorithms is the requirement of a…
End-to-end visual information extraction (VIE) aims at integrating the hierarchical subtasks of VIE, including text spotting, word grouping, and entity labeling, into a unified framework. Dealing with the gaps among the three subtasks plays…
We introduce an asymmetric distance in the space of learning tasks, and a framework to compute their complexity. These concepts are foundational for the practice of transfer learning, whereby a parametric model is pre-trained for a task,…
Multi-modal object Re-IDentification (ReID) aims to retrieve specific objects by utilizing complementary information from various modalities. However, existing methods focus on fusing heterogeneous visual features, neglecting the potential…
Existing Image Manipulation Localization (IML) methods mostly rely heavily on task-specific designs, making them perform well only on the target IML task, while joint training on multiple IML tasks causes significant performance…
This paper proposes OCR++, an open-source framework designed for a variety of information extraction tasks from scholarly articles including metadata (title, author names, affiliation and e-mail), structure (section headings and body text,…
Modern information retrieval (IR) models, trained exclusively on standard <query, passage> pairs, struggle to effectively interpret and follow explicit user instructions. We introduce InF-IR, a large-scale, high-quality training corpus…
Even as pre-trained language encoders such as BERT are shared across many tasks, the output layers of question answering, text classification, and regression models are significantly different. Span decoders are frequently used for question…
Efficiently merging several models fine-tuned for different tasks, but stemming from the same pretrained base model, is of great practical interest. Despite extensive prior work, most evaluations of model merging in computer vision are…