Related papers: EATXT: A textual concrete syntax for EAST-ADL

Structured document understanding has attracted considerable attention and made significant progress recently, owing to its crucial role in intelligent document processing. However, most existing related models can only deal with the…

Text-to-3D modelling has seen exciting progress by combining generative text-to-image models with image-to-3D methods like Neural Radiance Fields. DreamFusion recently achieved high-quality results but requires a lengthy, per-prompt…

We present DanceText, a training-free framework for multilingual text editing in images, designed to support complex geometric transformations and achieve seamless foreground-background integration. While diffusion-based generative models…

Multilingual large language models (LLMs) possess impressive multilingual understanding and generation capabilities. However, their performance and cross-lingual alignment often lag for non-dominant languages. A common solution is to…

Cross-entropy (CE) training provides dense and scalable supervision for language models, but it optimizes next-token prediction under teacher forcing rather than sequence-level behavior under model rollouts. We introduce a feature-matching…

In this paper, we elaborate upon recipes for building multilingual representation models that are not only competitive with existing state-of-the-art models but are also more parameter efficient, thereby promoting better adoption in…

Graphics design is important for various applications, including movie production and game design. To create a high-quality scene, designers usually need to spend hours in software like Blender, in which they might need to interleave and…

MatNexus is a specialized software for the automated collection, processing, and analysis of text from scientific articles. Through an integrated suite of modules, the MatNexus facilitates the retrieval of scientific articles, processes…

This research introduces the Multilevel Embedding Association Test (ML-EAT), a method designed for interpretable and transparent measurement of intrinsic bias in language technologies. The ML-EAT addresses issues of ambiguity and difficulty…

We introduce a Content-based Document Alignment approach (CDA), an efficient method to align multilingual web documents based on content in creating parallel training data for machine translation (MT) systems operating at the industrial…

Model editing aims to efficiently update a pre-trained model's knowledge without the need for time-consuming full retraining. While existing pioneering editing methods achieve promising results, they primarily focus on editing single-modal…

Converting different modalities into general text, serving as input prompts for large language models (LLMs), is a common method to align multimodal models when there is limited pairwise data. This text-centric approach leverages the unique…

Model editing aims to correct errors in large, pretrained models without altering unrelated behaviors. While some recent works have edited vision-language models (VLMs), no existing editors tackle reasoning-heavy tasks, which typically…

Language Models are the underpin of all modern Natural Language Processing (NLP) tasks. The introduction of the Transformers architecture has contributed significantly into making Language Modeling very effective across many NLP task,…

Explainable deep learning models are advantageous in many situations. Prior work mostly provide unimodal explanations through post-hoc approaches not part of the original system design. Explanation mechanisms also ignore useful textual…

Language Models (LMs) have greatly influenced diverse domains. However, their inherent limitation in comprehending 3D molecular structures has considerably constrained their potential in the biomolecular domain. To bridge this gap, we focus…

The static nature of knowledge within Large Language Models (LLMs) makes it difficult for them to adapt to evolving information, rendering knowledge editing a critical task. However, existing methods struggle with challenges of scalability…

Many recent works on Entity Resolution (ER) leverage Deep Learning techniques involving language models to improve effectiveness. This is applied to both main steps of ER, i.e., blocking and matching. Several pre-trained embeddings have…

Data engineering pipelines are essential - albeit costly - components of predictive analytics frameworks requiring significant engineering time and domain expertise for carrying out tasks such as data ingestion, preprocessing, feature…

There has been a growing interest in recent years in modelling multiple modalities (or views) of data to for example, understand the relationship between modalities or to generate missing data. Multi-view autoencoders have gained…