UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence
cs.AI, cs.IR, cs.LG
Submitted: 2026-05-09
Updated: 2026-10-09
Comments: Work in progress
Code: https://github.com/HonghuiBao2000/LETTER
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- OneMall: One Architecture, More Scenarios -- End-to-End Generative Recommender Family at Kuaishou E-Commerce
- PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations
- PIT: A Dynamic Personalized Item Tokenizer for End-to-End Generative Recommendation
- DOS: Dual-Flow Orthogonal Semantic IDs for Recommendation in Meituan
- QARM V2: Quantitative Alignment Multi-Modal Recommendation for Reasoning User Sequence Modeling
- Deep Session Interest Network for Click-Through Rate Prediction
- Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations
- End-to-End User Behavior Retrieval in Click-Through RatePrediction Model
- OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment
- Farewell to Item IDs: Unlocking the Scaling Potential of Large Ranking Models via Semantic Tokens
- Finite Scalar Quantization: VQ-VAE Made Simple
- OneRec-V2 Technical Report
- LLaMA: Open and Efficient Foundation Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems