# Building a User Foundation Model for the Open Web

arXiv: https://arxiv.org/abs/2607.28019 · HTML: https://mlsanity.com/paper/2607.28019/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 30 Jul 2026.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [Deep Interest Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1706.06978/) (2017)
- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization](https://mlsanity.com/paper/2008.07873/) (2020)
- [Random Search and Reproducibility for Neural Architecture Search](https://mlsanity.com/paper/1902.07638/) (2019)
- [Time2Vec: Learning a Vector Representation of Time](https://mlsanity.com/paper/1907.05321/) (2019)
- [Behavior Sequence Transformer for E-commerce Recommendation in Alibaba](https://mlsanity.com/paper/1905.06874/) (2019)
- [Language Model Crossover: Variation through Few-Shot Prompting](https://mlsanity.com/paper/2302.12170/) (2023)
- [Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation](https://mlsanity.com/paper/2110.05730/) (2021)
- [HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling](https://mlsanity.com/paper/2409.12740/) (2024)
- [PinnerFormer: Sequence Modeling for User Representation at Pinterest](https://mlsanity.com/paper/2205.04507/) (2022)
- [Towards Deeper, Lighter and Interpretable Cross Network for CTR Prediction](https://mlsanity.com/paper/2311.04635/) (2023)
- [External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation](https://mlsanity.com/paper/2502.17494/) (2025)
- [PinFM: Foundation Model for User Activity Sequences at a Billion-scale Visual Discovery Platform](https://mlsanity.com/paper/2507.12704/) (2025)
- [Empowering General-purpose User Representation with Full-life Cycle Behavior Modeling](https://mlsanity.com/paper/2110.11337/) (2021)
- [Abacus: Self-Supervised Event Counting-Aligned Distributional Pretraining for Sequential User Modeling](https://mlsanity.com/paper/2512.16581/) (2025)
- [MTFM: A Scalable and Alignment-free Foundation Model for Industrial Recommendation in Meituan](https://mlsanity.com/paper/2602.11235/) (2026)

## Abstract (arXiv)

User foundation models have demonstrated strong results in e-commerce and social recommendation, but most industrial deployments assume environments where user identity is stable and persistent. Open-web real-time bidding (RTB) operates on a structurally different data distribution: user identity is fragmented and non-persistent across browsing sessions, and the availability of browsing history depends on user privacy choices. Consequently, a significant portion of traffic carries no historical data, and available records often consist of relatively short, disjointed sessions. As a result, historical signals in this domain are typically represented as aggregated counters and recency buckets, leaving the sequential structure unexploited. To address this limitation, we present a user foundation model that applies self-supervised learning on user browsing histories and show that the learned representation improves multiple downstream production tasks, demonstrating the viability of this approach on the open web. We pre-train a Transformer encoder with masked language modeling and a sequence-level contrastive objective, then fine-tune it on the click prediction task. We optimize the encoder's pre-training pipeline with an LLM-in-the-loop search over a curated catalog of reviewable, code-level edits (lifters), instantiating the LLM-as-optimizer paradigm in an industrial setting. The same encoder representation yields +1.197% RIG on the production bid win-rate model and +1.354% RIG on the production CTR ranker; a 7-day live A/B test confirms +2.13% CTR, -1.13% eCPC (80% CI excluding zero on both metrics).