Search papers, labs, and topics across Lattice.
Institute of Information Engineering,Chinese Academy of Sciences,Beijing,China, Institute of Information Engineering, Chinese Academy of Sciences
5
2
5
15
Forget one-size-fits-all recommendations: this model uses normalizing flows to capture the *multimodal* nature of individual user preferences, leading to better cold-start performance in cross-domain recommendation.
Fragmented retrieval in long-term conversational agents is solved by HyperMem, which uses hypergraphs to model high-order associations between memories, achieving state-of-the-art performance.
Forget scaling depth and width鈥擬OUE unlocks a new "virtual width" dimension for Mixture-of-Experts by cleverly reusing a single expert pool across layers.
Ditch the training data: S2CDR achieves state-of-the-art cross-domain recommendation by smoothing and sharpening user-item interactions with ODEs, all without any training.
Diffusion models can now generate user preferences for multi-behavior sequential recommendation, outperforming traditional methods by better capturing uncertainty and enabling more diverse recommendations.
