A New Dual‑Tower Multi‑Objective Recall Framework (CSMF) Boosts Efficiency Without Extra Parameters

The paper introduces CSMF, a cascaded selective‑mask fine‑tuning framework for dual‑tower embedding‑based retrieval that sequentially optimizes exposure, click and conversion goals, incorporates cumulative percentile pruning and adaptive margin loss, and achieves measurable gains in ad revenue and CTR without increasing model size or latency.

cascaded selective maskdual-towerembedding-based retrieval

0 likes · 15 min read

A New Dual‑Tower Multi‑Objective Recall Framework (CSMF) Boosts Efficiency Without Extra Parameters