CS3 strengthens two-tower retrievers via cycle-adaptive feature denoising, cross-tower mutual awareness, and cascade knowledge reuse, delivering consistent gains on public datasets and up to 8.36% revenue lift in production advertising at millisecond latency.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CS3: Efficient Online Capability Synergy for Two-Tower Recommendation
CS3 strengthens two-tower retrievers via cycle-adaptive feature denoising, cross-tower mutual awareness, and cascade knowledge reuse, delivering consistent gains on public datasets and up to 8.36% revenue lift in production advertising at millisecond latency.