8 papers
GRP v0.1 Technical Report
Wenfeng Zhuo, Vincent Xue, Charles Wei +19
Industrial recommendation systems rely on multi-stage cascades whose retrieval, ranking, and serving components are difficult to replace jointly. We present GRP, a generative recom…
ClockRoPE: Random Fourier Rotations for Temporal Routine Modeling
Yiwen Chen, Joshua Ainslie, Krzysztof Choromanski +4
Rotary Position Embedding (RoPE) has been widely adopted in transformer-based large language models. However, its log-linear frequency schedule, originally designed to produce long…
Route Before Retrieve: Activating Latent Routing Abilities of LLMs for RAG vs. Long-Context Selection
Yiwen Chen, Kuan Li, Fuzhen Zhuang +6
Recent advances in large language models (LLMs) have expanded the context window to beyond 128K tokens, enabling long-document understanding and multi-source reasoning. A key chall…
LASAR: Latent Adaptive Semantic Aligned Reasoning for Generative Recommendation
Yiwen Chen, Fuwei Zhang, Zehao Chen +7
Large Language Models (LLMs) have demonstrated powerful reasoning capabilities through Chain-of-Thought (CoT) in various tasks, yet the inefficiency of token-by-token generation hi…
Semantic IDs for Recommender Systems at Snapchat: Use Cases, Technical Challenges, and Design Choices
Clark Mingxuan Ju, Tong Zhao, Leonardo Neves +15
Effective item identifiers (IDs) are an important component for recommender systems (RecSys) in practice, and are commonly adopted in many use cases such as retrieval and ranking.…
TextBridgeGNN: Pre-training Graph Neural Network for Cross-Domain Recommendation via Text-Guided Transfer
Yiwen Chen, Yiqing Wu, Huishi Luo +3
Graph-based recommendation has achieved great success in recent years. The classical graph recommendation model utilizes ID embedding to store essential collaborative information.…
CDC: Causal Domain Clustering for Multi-Domain Recommendation
Huishi Luo, Yiqing Wu, Yiwen Chen +2
Multi-domain recommendation leverages domain-general knowledge to improve recommendations across several domains. However, as platforms expand to dozens or hundreds of scenarios, t…
One for Dozens: Adaptive REcommendation for All Domains with Counterfactual Augmentation
Huishi Luo, Yiwen Chen, Yiqing Wu +2
Multi-domain recommendation (MDR) aims to enhance recommendation performance across various domains. However, real-world recommender systems in online platforms often need to handl…