Item Representations Matter: Bridging Hard Semantic IDs and Soft Prototype Mixtures for Generative Retrieval
cs.IR, cs.LG
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/RUCAIBox/RecSysDatasets2https:
Project page: https://amazon-reviews-2023.github.io/13
Terminology
Sources
- UniGRec: Unified Generative Recommendation with Soft Identifiers for End-to-End Optimization
- Masked Diffusion for Generative Recommendation
- PIT: A Dynamic Personalized Item Tokenizer for End-to-End Generative Recommendation
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
- OneRec Technical Report
Related papers
- UniRank: Benchmarking Ranking Models for Unified Sequential Modeling and Feature Interaction
- Revisiting Text Ranking in Deep Research
- GateSID: One Gate to Balance Semantic and Collaborative Signals across the Item Lifecycle
- SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerce
- GINGER: Spicing Up Graph-Based Vector Search
- Subtraction Gets You More: Gap-Aware Retrieval for Multimodal Multi-Hop QA