Related papers: UMIE: Unified Multimodal Information Extraction wi…
In this paper, we introduce ILLUME, a unified multimodal large language model (MLLM) that seamlessly integrates multimodal understanding and generation capabilities within a single large language model through a unified next-token…
Artificial intelligence (AI) has achieved astonishing successes in many domains, especially with the recent breakthroughs in the development of foundational large models. These large models, leveraging their extensive training data, provide…
IMU-based gesture interfaces are being increasingly adopted as efficient, accessible, and intuitive alternatives to traditional input methods, such as touchscreens and voice. However, current gesture recognition algorithms are tailored to…
Learning representations that generalize well to unknown downstream tasks is a central challenge in representation learning. Existing approaches such as contrastive learning, self-supervised masking, and denoising auto-encoders address this…
Instruction-based image editing (IIE) aims to modify images according to textual instructions while preserving irrelevant content. Despite recent advances in diffusion transformers, existing methods often suffer from over-editing,…
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…
Significant development of communication technology over the past few years has motivated research in multi-modal summarization techniques. A majority of the previous works on multi-modal summarization focus on text and images. In this…
Underwater image enhancement (UIE) presents a significant challenge within computer vision research. Despite the development of numerous UIE algorithms, a thorough and systematic review is still absent. To foster future advancements, we…
Multimodal fusion leverages information across modalities to learn better feature representations with the goal of improving performance in fusion-based tasks. However, multimodal datasets, especially in medical settings, are typically…
Unified multimodal models (UMMs) aim to integrate understanding and generation within a single architecture. However, it remains underexplored how to effectively coordinate these two capabilities for more effective and efficient reasoning.…
Mixture-of-Experts (MoE) presents a naturally compatible and scalable framework for multimodal learning, demonstrating strong adaptability across diverse modalities and tasks. Despite its growing success, a comprehensive and systematic…
Visual-semantic embedding models have been recently proposed and shown to be effective for image classification and zero-shot learning, by mapping images into a continuous semantic label space. Although several approaches have been proposed…
Advanced driver assistance systems require a comprehensive understanding of the driver's mental/physical state and traffic context but existing works often neglect the potential benefits of joint learning between these tasks. This paper…
Recently, automatically extracting information from visually rich documents (e.g., tickets and resumes) has become a hot and vital research topic due to its widespread commercial value. Most existing methods divide this task into two…
Privacy preservation in AI is crucial, especially in healthcare, where models rely on sensitive patient data. In the emerging field of machine unlearning, existing methodologies struggle to remove patient data from trained multimodal…
The application of visual instruction tuning and other post-training techniques has significantly enhanced the capabilities of Large Language Models (LLMs) in visual understanding, enriching Vision-Language Models (VLMs) with more…
Modelling highly multi-modal data is a challenging problem in machine learning. Most algorithms are based on maximizing the likelihood, which corresponds to the M(oment)-projection of the data distribution to the model distribution. The…
In this work, we focus on unsupervised vision-language-action mapping in the area of robotic manipulation. Recently, multiple approaches employing pre-trained large language and vision models have been proposed for this task. However, they…
No existing dataset adequately tests how well language models can incrementally update entity summaries - a crucial ability as these models rapidly advance. The Incremental Entity Summarization (IES) task is vital for maintaining accurate,…
Universal information extraction (UIE) primarily employs an extractive generation approach with large language models (LLMs), typically outputting structured information based on predefined schemas such as JSON or tables. UIE suffers from a…