4 papers
MCLMR: A Model-Agnostic Causal Learning Framework for Multi-Behavior Recommendation
Ranxu Zhang, Junjie Meng, Ying Sun +5
Multi-Behavior Recommendation (MBR) leverages multiple user interaction types (e.g., views, clicks, purchases) to enrich preference modeling and alleviate data sparsity issues in t…
Rethinking Popularity Bias in Collaborative Filtering via Analytical Vector Decomposition
Lingfeng Liu, Yixin Song, Dazhong Shen +4
Popularity bias fundamentally undermines the personalization capabilities of collaborative filtering (CF) models, causing them to disproportionately recommend popular items while n…
Breaking Model Lock-in: Cost-Efficient Zero-Shot LLM Routing via a Universal Latent Space
Cheng Yan, Wuyang Zhang, Zhiyuan Ning +5
The rapid proliferation of Large Language Models (LLMs) has led to a fragmented and inefficient ecosystem, a state of ``model lock-in'' where seamlessly integrating novel models re…
TransLLM: A Unified Multi-Task Foundation Framework for Urban Transportation via Learnable Prompting
Jiaming Leng, Yunying Bi, Chuan Qin +3
Urban transportation systems encounter diverse challenges across multiple tasks, such as traffic forecasting, electric vehicle (EV) charging demand prediction, and taxi dispatch. E…