Related papers: Compute Only Once: UG-Separation for Efficient Lar…

Transformer and its variants have been widely used for medical image segmentation. However, the large number of parameter and computational load of these models make them unsuitable for mobile health applications. To address this issue, we…

In this work, we study group recommendation in a particular scenario, namely Occasional Group Recommendation (OGR). Most existing works have addressed OGR by aggregating group members' personal preferences to learn the group representation.…

Traditional sequential recommendation methods assume that users' sequence data is clean enough to learn accurate sequence representations to reflect user preferences. In practice, users' sequences inevitably contain noise (e.g., accidental…

User feedback is critical for refining recommendation systems, yet explicit feedback (e.g., likes or dislikes) remains scarce in practice. As a more feasible alternative, inferring user preferences from massive implicit feedback has shown…

This paper proposes a user-centric split federated learning (UCSFL) framework for user-centric cell-free multiple-input multiple-output (CF-MIMO) networks to support split federated learning (SFL). In the proposed UCSFL framework, users…

Traditional Retrieval-Augmented Generation (RAG) approaches generally assume that retrieval and generation occur on powerful servers removed from the end user. While this reduces local hardware constraints, it introduces significant…

Recent interactive segmentation methods iteratively take source image, user guidance and previously predicted mask as the input without considering the invariant nature of the source image. As a result, extracting features from the source…

Side information fusion for sequential recommendation (SR) aims to effectively leverage various side information to enhance the performance of next-item prediction. Most state-of-the-art methods build on self-attention networks and focus on…

Latent reasoning has emerged as a promising paradigm for sequential recommendation, enabling models to capture complex user intent through multi-step deliberation. Yet existing approaches often rely on deterministic latent chains that…

Generative recommendation models often struggle with two key challenges: (1) the superficial integration of collaborative signals, and (2) the decoupled fusion of multimodal features. These limitations hinder the creation of a truly…

Nowadays, many platforms provide users with both search and recommendation services as important tools for accessing information. The phenomenon has led to a correlation between user search and recommendation behaviors, providing an…

Recommender Systems (RSs) are exploited by various business enterprises to suggest their products (items) to consumers (users). Collaborative filtering (CF) is a widely used variant of RSs which learns hidden patterns from user-item…

Most recommender systems research focuses on binary historical user-item interaction encodings to predict future interactions. User features, item features, and interaction strengths remain largely under-utilized in this space or only…

Large-scale diffusion models such as FLUX (12B parameters) and Stable Diffusion 3 (8B parameters) require multi-GPU parallelism for efficient inference. Unified Sequence Parallelism (USP), which combines Ulysses and Ring attention…

Characterizing users' interests accurately plays a significant role in an effective recommender system. The sequential recommender system can learn powerful hidden representations of users from successive user-item interactions and dynamic…

Deep learning recommendation models have grown to the terabyte scale. Traditional serving schemes--that load entire models to a single server--are unable to support this scale. One approach to support this scale is with distributed serving,…

There is significant interest in learning and optimizing a complex system composed of multiple sub-components, where these components may be agents or autonomous sensors. Among the rich literature on this topic, agent-based and…

Semi-supervised learning is increasingly popular in medical image segmentation due to its ability to leverage large amounts of unlabeled data to extract additional information. However, most existing semi-supervised segmentation methods…

Web sequential patterns are important for analyzing and understanding users behaviour to improve the quality of service offered by the World Wide Web. Web Prefetching is one such technique that utilizes prefetching rules derived through…

Recent progress on large language models (LLMs) has spurred interest in scaling up recommendation systems, yet two practical obstacles remain. First, training and serving cost on industrial Recommenders must respect strict latency bounds…