Related papers: KuaiFormer: Transformer-Based Retrieval at Kuaisho…

As large language models increasingly gain popularity in real-world applications, processing extremely long contexts, often exceeding the model's pre-trained context limits, has emerged as a critical challenge. While existing approaches to…

Transformer-based architectures have advanced medical image analysis by effectively modeling long-range dependencies, yet they often struggle in 3D settings due to substantial memory overhead and insufficient capture of fine-grained local…

Recommendation systems are essential tools in modern e-commerce, facilitating personalized user experiences by suggesting relevant products. Recent advancements in generative models have demonstrated potential in enhancing recommendation…

Multimodal recommendation systems utilize various types of information, including images and text, to enhance the effectiveness of recommendations. The key challenge is predicting user purchasing behavior from the available data. Current…

Sequential recommendation aims to model dynamic user behavior from historical interactions. Existing methods rely on either explicit item IDs or general textual features for sequence modeling to understand user preferences. While promising,…

We introduce the Evidential Transformer, an uncertainty-driven transformer model for improved and robust image retrieval. In this paper, we make several contributions to content-based image retrieval (CBIR). We incorporate probabilistic…

Recommender Systems (RS) aim to generate personalized ranked lists for each user and are evaluated using ranking metrics. Although personalized ranking is a fundamental aspect of RS, this critical property is often overlooked in the design…

Our objective is language-based search of large-scale image and video datasets. For this task, the approach that consists of independently mapping text and vision to a joint embedding space, a.k.a. dual encoders, is attractive as retrieval…

As the core building block of vision transformers, attention is a powerful tool to capture long-range dependency. However, such power comes at a cost: it incurs a huge computation burden and heavy memory footprint as pairwise token…

Transformers have shown outstanding results for natural language understanding and, more recently, for image classification. We here extend this work and propose a transformer-based approach for image retrieval: we adopt vision transformers…

Classification tasks in NLP are typically addressed by selecting a pre-trained language model (PLM) from a model hub, and fine-tuning it for the task at hand. However, given the very large number of PLMs that are currently available, a…

Recommender systems have become an essential component of many online platforms, providing personalized recommendations to users. A crucial aspect is embedding techniques that convert the high-dimensional discrete features, such as user and…

Instance-level image retrieval is the task of searching in a large database for images that match an object in a query image. To address this task, systems usually rely on a retrieval step that uses global image descriptors, and a…

Deep pretrained transformer networks are effective at various ranking tasks, such as question answering and ad-hoc document ranking. However, their computational expenses deem them cost-prohibitive in practice. Our proposed approach, called…

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…

Transformer-based methods have become the dominant approach for 3D instance segmentation. These methods predict instance masks via instance queries, ranking them by classification confidence and IoU scores to select the top prediction as…

In recent years, meta-reinforcement learning (meta-RL) algorithm has been proposed to improve sample efficiency in the field of decision-making and control, enabling agents to learn new knowledge from a small number of samples. However,…

Live streaming platforms have become a dominant form of online content consumption, offering dynamically evolving content, real-time interactions, and highly engaging user experiences. These unique characteristics introduce new challenges…

Blind face restoration is a challenging task due to the unknown and complex degradation. Although face prior-based methods and reference-based methods have recently demonstrated high-quality results, the restored images tend to contain…

Reinforcement learning (RL) recommender systems often rely on static datasets that fail to capture the fluid, ever changing nature of user preferences in real-world scenarios. Meanwhile, generative AI techniques have emerged as powerful…