10 papers
BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving
Yuanjie Zhu, Liangwei Yang, Ke Xu +4
Efficient serving of diffusion large language models (dLLMs) is hindered by convergence heterogeneity: when batching multiple requests, different sequences converge at different ra…
LLM-MemCluster: Empowering Large Language Models with Dynamic Memory for Text Clustering
Yuanjie Zhu, Liangwei Yang, Ke Xu +4
Large Language Models (LLMs) are reshaping unsupervised learning by offering an unprecedented ability to perform text clustering based on their deep semantic understanding. However…
A Long-term Value Prediction Framework In Video Ranking
Huabin Chen, Xinao Wang, Huiping Chu +5
Accurately modeling long-term value (LTV) at the ranking stage of short-video recommendation remains challenging. While delayed feedback and extended engagement have been explored,…
LLMInit: A Free Lunch from Large Language Models for Selective Initialization of Recommendation
Weizhi Zhang, Liangwei Yang, Wooseong Yang +5
Collaborative filtering (CF) is widely adopted in industrial recommender systems (RecSys) for modeling user-item interactions across numerous applications, but often struggles with…
Shylock: Causal Discovery in Multivariate Time Series based on Hybrid Constraints
Shuo Li, Keqin Xu, Jie Liu +1
Causal relationship discovery has been drawing increasing attention due to its prevalent application. Existing methods rely on human experience, statistical methods, or graphical c…
DiffusionGS: Generative Search with Query Conditioned Diffusion in Kuaishou
Qinyao Li, Xiaoyang Zheng, Qihang Zhao +6
Personalized search ranking systems are critical for driving engagement and revenue in modern e-commerce and short-video platforms. While existing methods excel at estimating users…