Large Foundation Model for Ads Recommendation

• URL: http://arxiv.org/abs/2508.14948v1
• Date: Wed, 20 Aug 2025 10:18:01 GMT
• Title: Large Foundation Model for Ads Recommendation
• Authors: Shangyu Zhang, Shijie Quan, Zhongren Wang, Junwei Pan, Tianqu Zhuang, Bo Fu, Yilong Sun, Jieying Lin, Jushuo Chen, Xiaotian Li, Zhixiang Feng, Xian Hu, Huiting Deng, Hua Lu, Jinpeng Wang, Boqi Dai, Xiaoyu Chen, Bin Hu, Lili Huang, Yanwen Wu, Yeshou Cai, Qi Zhou, Huang Tang, Chunfeng Yang, Chengguo Yin, Tingyu Jiang, Lifeng Wang, Shudong Huang, Dapeng Liu, Lei Xiao, Haijie Gu, Shu-Tao Xia, Jie Jiang,
• Abstract summary: We propose LFM4Ads, an All-Representation Multi-Granularity transfer framework for ads recommendation.<n>LFM4Ads has been successfully deployed in Tencent's industrial-scale advertising platform.
• Score: 50.71446552453167
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Online advertising relies on accurate recommendation models, with recent advances using pre-trained large-scale foundation models (LFMs) to capture users' general interests across multiple scenarios and tasks. However, existing methods have critical limitations: they extract and transfer only user representations (URs), ignoring valuable item representations (IRs) and user-item cross representations (CRs); and they simply use a UR as a feature in downstream applications, which fails to bridge upstream-downstream gaps and overlooks more transfer granularities. In this paper, we propose LFM4Ads, an All-Representation Multi-Granularity transfer framework for ads recommendation. It first comprehensively transfers URs, IRs, and CRs, i.e., all available representations in the pre-trained foundation model. To effectively utilize the CRs, it identifies the optimal extraction layer and aggregates them into transferable coarse-grained forms. Furthermore, we enhance the transferability via multi-granularity mechanisms: non-linear adapters for feature-level transfer, an Isomorphic Interaction Module for module-level transfer, and Standalone Retrieval for model-level transfer. LFM4Ads has been successfully deployed in Tencent's industrial-scale advertising platform, processing tens of billions of daily samples while maintaining terabyte-scale model parameters with billions of sparse embedding keys across approximately two thousand features. Since its production deployment in Q4 2024, LFM4Ads has achieved 10+ successful production launches across various advertising scenarios, including primary ones like Weixin Moments and Channels. These launches achieve an overall GMV lift of 2.45% across the entire platform, translating to estimated annual revenue increases in the hundreds of millions of dollars.

Related papers

• Transport and Merge: Cross-Architecture Merging for Large Language Models [59.53629883788284]
  Large language models (LLMs) achieve strong capabilities by scaling model capacity and training data.<n>Many real-world deployments rely on smaller models trained or adapted from low-resource data.<n>This gap motivates the need for mechanisms to transfer knowledge from large, high-resource models to smaller, low-resource targets.
  arXiv  Detail & Related papers  (2026-02-05T09:57:57Z)
• Factorized Transport Alignment for Multimodal and Multiview E-commerce Representation Learning [7.390207354371506]
  We propose a framework that unifies multimodal and multi-view learning through Factorized Transport embedding.<n>During training, the method emphasizes primary views while sampling auxiliary ones, reducing training cost from quadratic in the number of views to constant per item.
  arXiv  Detail & Related papers  (2025-12-19T22:50:49Z)
• Generative Large-Scale Pre-trained Models for Automated Ad Bidding Optimization [5.460538555236247]
  We propose GRAD (Generative Reward-driven Ad-bidding with Mixture-of-Experts), a scalable foundation model for auto-bidding.<n>We show that GRAD significantly enhances platform revenue, highlighting its effectiveness in addressing the evolving and diverse requirements of modern advertisers.
  arXiv  Detail & Related papers  (2025-08-04T02:46:18Z)
• MMAT-1M: A Large Reasoning Dataset for Multimodal Agent Tuning [4.963955559863751]
  MMAT-1M is the first million-scale multimodal agent tuning dataset designed to support CoT, reflection, and dynamic tool usage.<n>Our dataset is constructed through a novel four-stage data engine.<n>By fine-tuning open-source multimodal models on the MMAT-1M, we observe significant performance gains.
  arXiv  Detail & Related papers  (2025-07-29T15:39:14Z)
• MTGR: Industrial-Scale Generative Recommendation Framework in Meituan [28.92150571719811]
  We propose MTGR (Meituan Generative Recommendation) to address this issue.<n> MTGR achieves training and inference acceleration through user-level compression to ensure efficient scaling.<n>This breakthrough was successfully deployed on Meituan, the world's largest food delivery platform.
  arXiv  Detail & Related papers  (2025-05-24T11:47:28Z)
• Learning Item Representations Directly from Multimodal Features for Effective Recommendation [51.49251689107541]
  multimodal recommender systems predominantly leverage Bayesian Personalized Ranking (BPR) optimization to learn item representations.<n>We propose a novel model (i.e., LIRDRec) that learns item representations directly from multimodal features to augment recommendation performance.
  arXiv  Detail & Related papers  (2025-05-08T05:42:22Z)
• Cream of the Crop: Harvesting Rich, Scalable and Transferable Multi-Modal Data for Instruction Fine-Tuning [59.56171041796373]
  We harvest multi-modal instructional data in a robust and efficient manner.<n>We take interaction style as diversity indicator and use a multi-modal rich styler to identify data instruction patterns.<n>Across 10+ experimental settings, validated by 14 multi-modal benchmarks, we demonstrate consistent improvements over random sampling, baseline strategies and state-of-the-art selection methods.
  arXiv  Detail & Related papers  (2025-03-17T17:11:22Z)
• Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performance [78.48606021719206]
  Mini-InternVL is a series of MLLMs with parameters ranging from 1B to 4B, which achieves 90% of the performance with only 5% of the parameters. We develop a unified adaptation framework for Mini-InternVL, which enables our models to transfer and outperform specialized models in downstream tasks.
  arXiv  Detail & Related papers  (2024-10-21T17:58:20Z)
• TransRec: Learning Transferable Recommendation from Mixture-of-Modality Feedback [19.78472406958724]
  We present TransRec, a modification made on the popular ID-based recommender systems (RS) framework.<n>TransRec learns directly from the raw features of the MoM items in an end-to-end training manner.<n>Our results suggest that learning neural recommendation models from MoM feedback provides a promising way to realize universal RS.
  arXiv  Detail & Related papers  (2022-06-13T14:23:34Z)
• Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-modal Pretraining [108.86502855439774]
  We investigate a more realistic setting that aims to perform weakly-supervised multi-modal instance-level product retrieval. We contribute Product1M, one of the largest multi-modal cosmetic datasets for real-world instance-level retrieval. We propose a novel model named Cross-modal contrAstive Product Transformer for instance-level prodUct REtrieval (CAPTURE)
  arXiv  Detail & Related papers  (2021-07-30T12:11:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.