# Climber: Toward Efficient Scaling Laws for Large Recommendation Models

arXiv: https://arxiv.org/abs/2502.09888 · HTML: https://mlsanity.com/paper/2502.09888/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Feb 2025.

## Built on by (most cited first, 8 of 8)

- [Kunlun: Establishing Scaling Laws for Massive-Scale Recommendation Systems through Unified Architecture Design](https://mlsanity.com/paper/2602.10016/) (2026)
- [UniMixer: A Unified Architecture for Scaling Laws in Recommendation Systems](https://mlsanity.com/paper/2604.00590/) (2026)
- [RelayGR: Scaling Long-Sequence Generative Recommendation via Cross-Stage Relay-Race Inference](https://mlsanity.com/paper/2601.01712/) (2026)
- [Hi-SAM: A Hierarchical Structure-Aware Multi-modal Framework for Large-Scale Recommendation](https://mlsanity.com/paper/2602.11799/) (2026)
- [Closing the Auto-Research Loop: An AI Co-Scientist for Production Search Ranking](https://mlsanity.com/paper/2603.22376/) (2026)
- [NestPipe: Large-Scale Recommendation Training on 1,500+ Accelerators via Nested Pipelining](https://mlsanity.com/paper/2604.06956/) (2026)
- [The Pitfall of Scaling Up: Uncovering and Mitigating Popularity Bias Amplification in Scaling Transformer-based Recommenders](https://mlsanity.com/paper/2606.21911/) (2026)
- [Advancing Model Research in AgentX: Long-Horizon Autonomy for Industrial Recommender Systems](https://mlsanity.com/paper/2609.30001/) (2026)

## Abstract (arXiv)

Transformer-based generative models have achieved remarkable success across domains with various scaling law manifestations. However, our extensive experiments reveal persistent challenges when applying Transformer to recommendation systems: (1) Transformer scaling is not ideal with increased computational resources, due to structural incompatibilities with recommendation-specific features such as multi-source data heterogeneity; (2) critical online inference latency constraints (tens of milliseconds) that intensify with longer user behavior sequences and growing computational demands. We propose Climber, an efficient recommendation framework comprising two synergistic components: the model architecture for efficient scaling and the co-designed acceleration techniques. Our proposed model adopts two core innovations: (1) multi-scale sequence extraction that achieves a time complexity reduction by a constant factor, enabling more efficient scaling with sequence length; (2) dynamic temperature modulation adapting attention distributions to the multi-scenario and multi-behavior patterns. Complemented by acceleration techniques, Climber achieves a 5.15× throughput gain without performance degradation by adopting a "single user, multiple item" batched processing and memory-efficient Key-Value caching. Comprehensive offline experiments on multiple datasets validate that Climber exhibits a more ideal scaling curve. To our knowledge, this is the first publicly documented framework where controlled model scaling drives continuous online metric growth (12.19% overall lift) without prohibitive resource costs. Climber has been successfully deployed on Netease Cloud Music, one of China's largest music streaming platforms, serving tens of millions of users daily.