7 papers
Revisiting Generative vs. Dense Retrieval: A Static Value Prior Reverses the Gap
Renbo Tu, Yang Liu, Shuying Sun
Generative retrieval (GR) has emerged as a strong candidate generator for sequential recommendation as language models and semantic-item identifiers have improved. However, GR is n…
T-RoPE: Time-Aware Rotary Position Embedding for Sequential Recommendation
Yang Liu, Noel Loo, Ali Khanafer +4
Large-scale recommenders increasingly adopt the sequential generative recipe behind large language models, bringing the Transformer into recommendation along with design choices ma…
Token-Level Credit Assignment Optimization for Generative Document Retrieval
Xinpeng Zhao, Yang Liu, Ran Chen +6
Generative retrieval models perform document retrieval by autoregressively generating document identifiers (DocIDs). This process naturally forms a sequential decision problem, i.e…
Scalable Peptide Design via Memory-Efficient Equivariant Transformer
Rui Jiao, Xiangzhe Kong, Yinjun Jia +4
Target-specific peptide design requires sequence and structure co-design under full atom geometric constraints. Latent generative frameworks offer an effective route for this probl…
TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems
Qingyun Liu, Bo Yan, Yang Liu +16
User modeling in industrial recommender systems typically produces dense embeddings, which suffer from representational constraints due to fixed-dimensional vectors. As an emerging…
Latent Block-Diffusion Temporal Point Processes: A Semi-Autoregressive Framework for Asynchronous Event Sequence Generation
Shuai Zhang, Yancheng Chen, Chuan Zhou +5
Modeling and sampling from the underlying distribution of asynchronous event sequences are crucial in various real-world applications, including social networks, medical diagnosis,…
Xetrieval: Explaining Dense Retrieval through Feature Elicitation
Zhixin Cai, Jun Bai, Yang Liu +7
Dense retrieval enables effective semantic matching, yet the semantic factors underlying its relevance scores remain opaque. Sparse autoencoders (SAEs) support feature-level explan…