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 2verdicts
UNVERDICTED 2representative citing papers
TriAlignGR introduces cross-modal alignment, deep interest mining via CoT, and triangular multitask training to fix semantic degradation and opacity in SID-based generative recommendation.
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
TriAlignGR introduces cross-modal alignment, deep interest mining via CoT, and triangular multitask training to fix semantic degradation and opacity in SID-based generative recommendation.