GenCDSR: Hybrid Tokenization Accelerates Cross-Domain Generative Recommendation
_reachsumit · x · 2026-08-03
To address the lack of cross-domain collaborative correlations and low decoding efficiency in generative cross-domain sequential recommendation (CDSR), researchers proposed the GenCDSR framework.
Technical Innovations:
- Cross-domain Hybrid Tokenization: Uses a multi-tower architecture with hierarchical shared-specific codebooks to jointly capture cross-domain commonalities and domain-specific distinctions.
- Serial-Parallel Decoding: Leverages the hierarchical Semantic ID (SID) structure to partially parallelize the generation process.
Results: On three public datasets, the framework achieved an average accuracy improvement of 1.5% while significantly reducing inference latency, solving the pain point of real-time deployment for generative recommendations.
More from Research
- LLM Safety Trilemma: Useful Capability, Reliable Safety, and Open Access Cannot Coexist — Pingyu Wu · 2026-08-03
- Replicating the Test: Can LLMs Spell Words Based on Audio? — theshawwn · 2026-08-03
- Analysis: Why AI Math Breakthroughs Lagged Behind Coding and What's Next — bookwormengr · 2026-08-03
- StatsMLlib: A Lean 4 Library Formally Verifying Probability, Statistics, and ML Theorems — ChengleiSi · 2026-08-03
- Don't build custom tools for agents: apply the Bitter Lesson — willccbb · 2026-08-03
- VOCA: Boosting Visual Odometry Performance Using Codec Information — rsasaki0109 · 2026-08-03