A new framework uses temporal-aware attention sink tokens between user behaviors to improve LM-based CTR prediction.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CTR-Sink: Attention Sink for Language Models in Click-Through Rate Prediction
A new framework uses temporal-aware attention sink tokens between user behaviors to improve LM-based CTR prediction.