Personalized recommendation systems often suffer from various biases in data-driven paradigms, which can significantly degrade their fairness and generalization. Existing debiasing approaches typically rely on strong assumptions about bias types or purely statistical corrections, limiting their adaptability to unknown...
Zhen-Zhen Hu, Yang Wang, Wen-Hao Qian et al.· IEEE Transactions on Computa...· 0 citations
A geometry-adaptive Riemannian framework for molecular representation learning, which explicitly models motifs as the basic units and learns their embeddings across multiple constant-curvature spaces, offering a general and scalable framework for scientific molecular modeling.
Fei Liu, Wen-Kai Lu, Fei-Long Wang et al.· Proceedings of the 32nd ACM...· 0 citations
LLM-ASAR is proposed, a Large Language Model-driven framework for Aspect-based Semantic Alignment in Review-based Recommendation that explicitly aligns aspect-level review semantics with user–item interaction patterns and achieves significant accuracy improvements over state-of-the-art baselines.
Huilin Chen, Zhi-Yong Cheng, Fan Liu et al.· ACM Transactions on Recommen...· 0 citations
Open-Vocabulary Multi-Label Image Classification (OV-MLIC) is an emerging task in computer vision aimed at recognizing unseen categories in real-world scenarios, leveraging Vision and Language Pre-training (VLP) models like CLIP. However, existing methods overlook the impact of category coupling and scale variation on...
Bei-Yan Liu, Sheng Huang, Bo Liu et al.· IEEE Transactions on Image P...· 0 citations
Molecular properties are often governed by a small number of local substructures, or motifs, whose topologies can vary drastically across molecules. Existing molecular representation learning approaches typically embed all motifs into a single Euclidean or fixed-curvature space, which fails to capture the motif-level t...
Fei Liu, Wen-Kai Lu, Feilong Wang et al.· Proceedings of the 32nd ACM...· 0 citations
Uni-AdaVD is presented, a universal inference-time concept erasure framework for visual generation that treats the value space of multimodal attention as a unified intervention space and introduces encoder-aware target representation construction to localize target semantics across heterogeneous text encoders.
A rationale-guided knowledge distillation framework for cross-lingual stance detection using Chain-of-Thought prompting to guide Large Language Models in generating informative rationales, and distill the resulting reasoning knowledge into a compact student model.
