Related papers: Exploring Relational Context for Multi-Task Dense …

In sparse recommender settings, users' context and item attributes play a crucial role in deciding which items to recommend next. Despite that, recent works in sequential and time-aware recommendations usually either ignore both aspects or…

Recently recurrent neural networks (RNNs) have demonstrated the ability to improve scene labeling through capturing long-range dependencies among image units. In this paper, we propose dense RNNs for scene labeling by exploring various…

Learning to rank has been intensively studied and widely applied in information retrieval. Typically, a global ranking function is learned from a set of labeled data, which can achieve good performance on average but may be suboptimal for…

Referring expression comprehension (REC) and segmentation (RES) are two highly-related tasks, which both aim at identifying the referent according to a natural language expression. In this paper, we propose a novel Multi-task Collaborative…

Retrieval-Augmented Generation (RAG) systems have recently shown remarkable advancements by integrating retrieval mechanisms into language models, enhancing their ability to produce more accurate and contextually relevant responses.…

Relational understanding is critical for a number of visually-rich documents (VRDs) understanding tasks. Through multi-modal pre-training, recent studies provide comprehensive contextual representations and exploit them as prior knowledge…

Top-down attention allows neural networks, both artificial and biological, to focus on the information most relevant for a given task. This is known to enhance performance in visual perception. But it remains unclear how attention brings…

Visual saliency patterns are the result of a variety of factors aside from the image being parsed, however existing approaches have ignored these. To address this limitation, we propose a novel saliency estimation model which leverages the…

Learning an effective speaker representation is crucial for achieving reliable performance in speaker verification tasks. Speech signals are high-dimensional, long, and variable-length sequences containing diverse information at each…

Selecting an appropriate pre-trained source model is a critical, yet computationally expensive, task in transfer learning. Model Transferability Estimation (MTE) methods address this by providing efficient proxy metrics to rank models…

Recent works attempt to improve scene parsing performance by exploring different levels of contexts, and typically train a well-designed convolutional network to exploit useful contexts across all pixels equally. However, in this paper, we…

Knowledge tracing (KT) refers to the problem of predicting future learner performance given their past performance in educational applications. Recent developments in KT using flexible deep neural network-based models excel at this task.…

Objects, in the real world, rarely occur in isolation and exhibit typical arrangements governed by their independent utility, and their expected interaction with humans and other objects in the context. For example, a chair is expected near…

Successfully addressing a wide variety of tasks is a core ability of autonomous agents, requiring flexibly adapting the underlying decision-making strategies and, as we argue in this work, also adapting the perception modules. An analogical…

In recent years, several studies on neural machine translation (NMT) have attempted to use document-level context by using a multi-encoder and two attention mechanisms to read the current and previous sentences to incorporate the context of…

This paper presents a general scheme for enhancing the convergence and performance of DETR (DEtection TRansformer). We investigate the slow convergence problem in transformers from a new perspective, suggesting that it arises from the…

Test-Time Compute (TTC) has emerged as a powerful paradigm for enhancing the performance of Large Language Models (LLMs) at inference, leveraging strategies such as Test-Time Training (TTT) and Retrieval-Augmented Generation (RAG). However,…

Aspect-Target Sentiment Classification (ATSC) is a subtask of Aspect-Based Sentiment Analysis (ABSA), which has many applications e.g. in e-commerce, where data and insights from reviews can be leveraged to create value for businesses and…

Modern sequential recommender systems commonly use transformer-based models for next-item prediction. While these models demonstrate a strong balance between efficiency and quality, integrating interleaving features - such as the query…

Recent advancements in deep neural networks have markedly enhanced the performance of computer vision tasks, yet the specialized nature of these networks often necessitates extensive data and high computational power. Addressing these…