arXiv AI

Tokens are All You Need: Dual-purpose Semantic IDs for Achieving LLM-Level I/O Efficiency in recommendation systems

arXiv:2607. 24865v1 Announce Type: cross Abstract: Large-scale recommendation systems face "Memory Wall" bottlenecks due to massive, dense embedding tables.

arXiv Machine Learning

Jun 25

TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems

arXiv:2606. 25147v1 Announce Type: cross Abstract: User modeling in industrial recommender systems typically produces dense embeddings, which suffer from representational constraints inherent to fixed-dimensional vectors.

By Qingyun Liu, Bo Yan, Yang Liu, Yuji Roh, Ekansh Sharma, Likang Yin, Emma Olowo, Min-hsuan Tsai, Yuxuan Li, Diego Uribe, Saksham Aggarwal, Siqi Wu, Yuan Hao, Vikas Kedigehalli, Lukasz Heldt, Lichan Hong, Li Wei, Xinyang Yi

llms rag nlp

arXiv AI

Jun 9

Beyond Item IDs: Scaling Short-Form-Video Recommendation via Semantic-Native Long Sequence Modeling

arXiv:2606. 07546v1 Announce Type: cross Abstract: Capturing user interests across extensive watch histories is critical for short-form video recommendation, yet scaling sequence length is limited by two bottlenecks: the semantic sparsity of atomic Video IDs and the quadratic computational complexity of Transformers.

By Ruixiao Sun, Diego Uribe Mora, Zhimeng Jiang, Yuanzhen Lin, Jiarui Wang, Yuening Li, Danfeng Guo, Zhizhong Chen, Chuan He, Liang Liu

llms rag efficiency

arXiv AI

Jun 26

The Best of the Two Worlds: Harmonizing Semantic and Hash IDs for Sequential Recommendation

arXiv:2512. 10388v3 Announce Type: replace-cross Abstract: Conventional Sequential Recommender Systems (SRS) typically assign unique hash IDs (HID) to construct item embeddings, which mainly capture collaborative signals from historical user-item interactions.

By Ziwei Liu, Yejing Wang, Wanyu Wang, Wang Zejian, Qidong Liu, Zijian Zhang, Chong Chen, Wei Huang, Xiangyu Zhao

rag efficiency benchmarks safety

arXiv AI

Jun 16

FOUNDv2: Learning Unified User Quantized Tokenizers for User Representation

arXiv:2508. 00956v3 Announce Type: replace-cross Abstract: User representation learning serves as a fundamental pillar for personalized services on large-scale web platforms.

By Chuan He, Yang Chen, Bin Dou, Wuliang Huang, Baokun Wang, Yongchao Liu, Xing Fu, Yu Cheng, Chuntao Hong, Weiqiang Wang, Zhongle Xie, Jiajun Zheng, Xin-Wei Yao

rag nlp efficiency benchmarks safety

arXiv AI

Jun 8

Understanding Generative Recommendation with Semantic IDs from a Model-scaling View

arXiv:2509. 25522v3 Announce Type: replace Abstract: Recent advancements in generative models have allowed the emergence of a promising paradigm for recommender systems (RS), known as Generative Recommendation (GR), which tries to unify rich item semantics and collaborative filtering signals.

By Jingzhe Liu, Liam Collins, Jiliang Tang, Tong Zhao, Neil Shah, Clark Mingxuan Ju

llms rag nlp efficiency

arXiv AI

Jul 29

TopoGR: Revealing and Preserving Latent Structure of Semantic ID in Generative Recommendation

arXiv:2607. 25216v1 Announce Type: cross Abstract: Semantic ID-based generative recommendation tokenizes each item into a sequence of discrete semantic IDs and predicts the next item by generating semantic IDs.

By Ziyu Zheng, Zhengshun Du, Yaming Yang, Bin Tong, Guan Wang, Meng Yan, Ziyu Guan, Wei Zhao

rag nlp benchmarks

arXiv AI

Jul 29

VaLiDRec: Variable-Length LLM-Aligned Semantic IDs for Generative Recommendation

arXiv:2607. 25209v1 Announce Type: cross Abstract: Generative recommendation commonly represents items using fixed-length semantic identifiers (SIDs) constructed through clustering and quantization.

By Shutong Qiao, Wei Yuan, Tong Chen, Hao Wang, Quoc Viet Hung Nguyen, Hongzhi Yin

llms efficiency

arXiv Machine Learning

Jul 14

Tokenizing Numerical and Embedding Features for LLM RecSys

arXiv:2607. 10016v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as backbone architectures for recommender systems because of their strong sequence modeling and representation learning capabilities.

By Zhe Xu, Ankit Peshin, Chiyu Zhang, Feng Qi, Johnson Lui, Anil Ramakrishna, Justin Johnson, Carl Hu, Kaushik Rangadurai, Luke Simon

llms rag benchmarks

arXiv Machine Learning

Aug 3

PaletteID: Prototype-Composed Semantic Identifiers for Multimodal CTR Prediction

arXiv:2607. 29000v1 Announce Type: cross Abstract: Multimodal information can improve the accuracy of click-through rate (CTR) prediction and effectively alleviate item cold-start and long-tail problems.

By Huanyu Liu, Baining Chen, Hui Liu, Zengyang Li, Ziyi Huang

rag multimodal

arXiv Machine Learning

Aug 11

Preserving Item Semantics for Free: Rethinking Token Initialization in LLM-Based Generative Recommendation

arXiv:2608. 07816v1 Announce Type: cross Abstract: Recent advances in generative recommendation (GR) leverage large language models (LLMs) as recommender backbones, enabling LLMs to directly generate recommendations conditioned on item-interaction histories.

By Donald Loveland, Liam Collins, Bhuvesh Kumar, Danai Koutra, Neil Shah

llms rag fine-tuning

arXiv AI

Jul 7

Scalable Semantic Steering of Embedding Projections

arXiv:2607. 03978v1 Announce Type: cross Abstract: Low-dimensional projections support interactive visual analysis of high-dimensional data embeddings, but their structure often does not align with analyst-defined semantic relationships.

By Wei Liu, Eric Krokos, Kirsten Whitley, Rebecca Faust, Chris North

llms rag multimodal safety

arXiv Machine Learning

Jun 15

Learning Variable-Length Tokenization for Generative Recommendation

arXiv:2605. 17779v2 Announce Type: replace Abstract: Generative recommendation reformulates recommendation as next-token prediction over discrete semantic identifiers (IDs).

By Minhao Wang, Bowen Wu, Wei Zhang

nlp efficiency benchmarks

Related stories