Modeling ultra-long user behavior sequences is crucial for industrial recommendation and online advertising, yet directly feeding thousands of historical actions into ranking models is computationally prohibitive, while truncation discards long-range signals. Existing lifelong-interest methods retrieve target-relevant...
Chengkai Huang, Yu-Bin Sheng, Liang Guo et al.· 0 citations
Cross-Domain Sequential Recommendation (CDSR) aims to improve next-item prediction by leveraging users’ sequential behaviors across multiple domains. Despite recent progress, existing CDSR models suffer from two fundamental limitations: (1) they often entangle transferable, domain-invariant interests with domain-specif...
Xiao-Xin Ye, Chengkai Huang, Hong-Tao Huang et al.· Proceedings of the 20th ACM...· 0 citations
Sequential recommenders are typically trained on long user histories to capture rich behavioral signals, yet serving with training-length sequences is often impractical due to real-time efficiency constraints. Directly using only recent behaviors leads to a severe performance drop. To bridge this gap, existing approach...
Ling-Feng Shi, Chengkai Huang, Lina Yao et al.· 0 citations
Causal Abstraction Learning for Multi-Modal Grounded Planning (CALM) is proposed, a framework that enhances planning agents with the ability to discover and exploit causal regularities across tasks.
Xin-Shu Li, Shiyi Yang, Ziqi Xu et al.· Proceedings of the 32nd ACM...· 0 citations
Offline reinforcement learning (RL) is a useful approach for recommender systems because it can optimize long-term user feedback from logged interaction data without online exploration. A key challenge is the multi-modal nature of user preferences: a user may like several unrelated item types, so a unimodal policy (for...
Self-supervised Causal Effects Estimation is proposed, a novel framework that integrates causal priors with self-supervised learning to construct balanced and predictive representations for causal effects estimation that consistently outperforms state-of-the-art methods.
Xin-Shu Li, Shiyi Yang, Venus Haghighi et al.· ACM Transactions on Intellig...· 0 citations
Recent advances in multimodal embodied agents have enabled long-horizon planning in visually rich environments via natural language. Yet, their generalization remains brittle when task instructions deviate from familiar examples, exposing a reliance on surface imitation rather than structural understanding. We propose...
Xinshu Li, Shiyi Yang, Ziqi Xu et al.· Proceedings of the 32nd ACM...· 0 citations
This work presents RegionSLM, a region-aware SLM designed to explicitly connect the question to its supporting regions, and curates ReDoc, a region-supervised corpus with 105k documents and 350k question-answer pairs obtained via a question-guided two-step filtering procedure.
Chao Wang, Hehe Fan, Huichen Yang et al.· Annual International ACM SIG...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
