Related papers: The Evolution of Multimodal Model Architectures
Transfer learning has recently become the dominant paradigm of machine learning. Pre-trained models fine-tuned for downstream tasks achieve better performance with fewer labelled examples. Nonetheless, it remains unclear how to develop…
Unified image understanding and generation has emerged as a promising paradigm in multimodal artificial intelligence. Despite recent progress, the optimal architectural design for such unified models remains an open challenge. In this work,…
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…
Since many real world networks are evolving over time, such as social networks and user-item networks, there are increasing research efforts on dynamic network embedding in recent years. They learn node representations from a sequence of…
Deep neural networks (DNNs) have shown superior performances on various multimodal learning problems. However, it often requires huge efforts to adapt DNNs to individual multimodal tasks by manually engineering unimodal features and…
Multimodal models have been proven to outperform text-based models on learning semantic word representations. Almost all previous multimodal models typically treat the representations from different modalities equally. However, it is…
In this paper we propose a novel approach to model compression termed Architecture Compression. Instead of operating on the weight or filter space of the network like classical model compression methods, our approach operates on the…
The rapid advancement of AI technology has led to widespread applications of agent systems across various domains. However, the need for detailed architecture design poses significant challenges in designing and operating these systems.…
Connecting text and visual modalities plays an essential role in generative intelligence. For this reason, inspired by the success of large language models, significant research efforts are being devoted to the development of Multimodal…
This paper presents a novel model for multimodal learning based on gated neural networks. The Gated Multimodal Unit (GMU) model is intended to be used as an internal unit in a neural network architecture whose purpose is to find an…
This paper updates the cognitive model, firstly by creating two systems and then unifying them over the same structure. It represents information at the semantic level only, where labelled patterns are aggregated into a 'type-set-match'…
With the exponential surge in diverse multi-modal data, traditional uni-modal retrieval methods struggle to meet the needs of users seeking access to data across various modalities. To address this, cross-modal retrieval has emerged,…
This study proposes a novel perspective on multimodal deep learning for biomedical signal classification, systematically analyzing how complementary feature domains impact model performance. While fusing multiple domains often presumes…
The growing interest in both the automation of machine learning and deep learning has inevitably led to the development of a wide variety of automated methods for neural architecture search. The choice of the network architecture has proven…
Recently, it has become progressively more evident that classic diagnostic labels are unable to reliably describe the complexity and variability of several clinical phenotypes. This is particularly true for a broad range of neuropsychiatric…
Time series forecasting is a critical task that provides key information for decision-making. After traditional statistical and machine learning approaches, various fundamental deep learning architectures such as MLPs, CNNs, RNNs, and GNNs…
Many adaptations of transformers have emerged to address the single-modal vision tasks, where self-attention modules are stacked to handle input sources like images. Intuitively, feeding multiple modalities of data to vision transformers…
Multimodal learning typically relies on the assumption that all modalities are fully available during both the training and inference phases. However, in real-world scenarios, consistently acquiring complete multimodal data presents…
Deep learning yields great results across many fields, from speech recognition, image classification, to translation. But for each problem, getting a deep model to work well involves research into the architecture and a long period of…
More information leads to better decisions and predictions, right? Confirming this hypothesis, several studies concluded that the simultaneous use of optical and thermal images leads to better predictions in crowd counting. However, the way…