CapsID uses probabilistic capsule routing and confidence-based termination to generate variable-length semantic IDs, improving recall by 9.6% over strong baselines with half the latency of dual-representation systems.
Learning vector-quantized item representation for transferable sequential recommenders
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.IR 2years
2026 2representative citing papers
citing papers explorer
-
CapsID: Soft-Routed Variable-Length Semantic IDs for Generative Recommendation
CapsID uses probabilistic capsule routing and confidence-based termination to generate variable-length semantic IDs, improving recall by 9.6% over strong baselines with half the latency of dual-representation systems.
- TriAlignGR: Triangular Multitask Alignment with Multimodal Deep Interest Mining for Generative Recommendation