Related papers: HiSAC: Hierarchical Sparse Activation Compression …
Long-context agentic workflows have emerged as a defining use case for large language models, making attention efficiency critical for both inference speed and serving cost. Sparse attention addresses this challenge effectively, and…
Modeling multi-interests has arisen as a core problem in real-world RS. Current multi-interest retrieval methods pose three major challenges: 1) Interests, typically extracted from predefined external knowledge, are invariant. Failed to…
Learning effective feature interactions is central to modern recommender systems, yet remains challenging in industrial settings due to sparse multi-field inputs and ultra-long user behavior sequences. While recent scaling efforts have…
Hypergraphs model complex, non-binary relationships like co-authorships, social group memberships, and recommendations. Like traditional graphs, hypergraphs can grow large, posing challenges for storage, transmission, and query performance.…
Although sophisticated sequence modeling paradigms have achieved remarkable success in recommender systems, the information capacity of hand-crafted sequential features constrains the performance upper bound. To better enhance user…
Recommendation model interpretation aims to reveal the relationships between inputs, model internal representations and outputs to enhance the transparency, interpretability, and trustworthiness of recommendation systems. However, the…
User interest modeling is critical for personalized news recommendation. Existing news recommendation methods usually learn a single user embedding for each user from their previous behaviors to represent their overall interest. However,…
Long-context language modeling is commonly framed as a scalability challenge of token-level attention, yet local-to-global information structuring remains largely implicit in existing approaches. Drawing on cognitive theories of discourse…
Recently, some span-based methods have achieved encouraging performances for joint aspect-sentiment analysis, which first extract aspects (aspect extraction) by detecting aspect boundaries and then classify the span-level sentiments…
Slate recommendation, which presents users with a ranked item list in a single display, is ubiquitous across mainstream online platforms. Recent advances in generative models have shown significant potential for this task via autoregressive…
Cross-Domain Sequential Recommendation (CDSR) predicts user behavior by leveraging historical interactions across multiple domains, focusing on modeling cross-domain preferences through intra- and inter-sequence item relationships. Inspired…
Modeling user interests is crucial in real-world recommender systems. In this paper, we present a new user interest representation model for personalized recommendation. Specifically, the key novelty behind our model is that it explicitly…
Click-Through Rate (CTR) prediction plays an important role in many industrial applications, and recently a lot of attention is paid to the deep interest models which use attention mechanism to capture user interests from historical…
DeepSeek Sparse Attention (DSA) sets the state of the art for fine-grained inference-time sparse attention by introducing a learned token-wise indexer that scores every prefix token and selects the most relevant ones for the main attention.…
In this era of information explosion, a personalized recommendation system is convenient for users to get information they are interested in. To deal with billions of users and items, large-scale online recommendation services usually…
The goal of sequential recommendation (SR) is to predict a user's potential interested items based on her/his historical interaction sequences. Most existing sequential recommenders are developed based on ID features, which, despite their…
Hierarchical Sparse Coding (HSC) is a powerful model to efficiently represent multi-dimensional, structured data such as images. The simplest solution to solve this computationally hard problem is to decompose it into independent layer-wise…
The rapid development of large climate models has created the requirement of storing and transferring massive atmospheric data worldwide. Therefore, data compression is essential for meteorological research, but an efficient compression…
Image based social networks are among the most popular social networking services in recent years. With tremendous images uploaded everyday, understanding users' preferences on user-generated images and making recommendations have become an…
Temporal Action Detection (TAD) is an essential and challenging topic in video understanding, aiming to localize the temporal segments containing human action instances and predict the action categories. The previous works greatly rely upon…