# Rec-Distill: An Industrial Distillation Pipeline for Large-Scale Recommendation Models

arXiv: https://arxiv.org/abs/2605.29755 · HTML: https://mlsanity.com/paper/2605.29755/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2026.

## Built on by (most cited first, 1 of 1)

- [QueryFormer: Winning Solution for KDD Cup 2026 Tencent UniRec Challenge](https://mlsanity.com/paper/2609.16548/) (2026)

## Abstract (arXiv)

Large recommendation models have demonstrated substantial potential gains under scaling laws, yet these gains are difficult to realize in industrial recommendation systems because real-world deployment requires lightweight models with strict serving efficiency and latency guarantees. This creates a fundamental gap between offline model scaling and online deployment. In this work, we present Rec-Distill, an industrial distillation pipeline that transfers the performance gains of large-scale recommendation modeling to efficient serving models. Rec-Distill combines large-teacher scaling with student-side transfer optimization through decoupled training, black-box distillation, debiasing mechanism, and a hybrid batch-streaming pipeline for dynamic recommendation environments. Across multiple recommendation and advertising scenarios on real-world platforms, our framework scales teacher models up to 24B dense parameters and 20K behavior sequence length, while enabling lightweight students to recover a substantial portion of teacher gains, with distillation transferability exceeding 60% in the best setting. Extensive offline and online experiments further show that these transferred gains consistently translate into measurable business improvements under industrial constraints. These results demonstrate that Rec-Distill provides a practical framework for distilling large-scale recommendation models into deployable, cost-efficient serving systems, while also establishing a reliable path toward scaling recommendation models to even larger regimes in the future.