AI & ML New Capability

Integrates auction bids and monetization logic directly into generative recommender systems (like TIGER) via bid-aware decoding.

March 24, 2026

Original Paper

One Model, Two Markets: Bid-Aware Generative Recommendation

Yanchen Jiang, Zhe Feng, Christopher P. Mah, Aranyak Mehta, Di Wang

arXiv · 2603.22231

The Takeaway

Generative RecSys has struggled with industry adoption because it lacks clear mechanisms for ad placement and pricing. GEM-Rec enables real-time monetization without retraining, guaranteeing that higher bids increase an item's likelihood of being generated.

From the abstract

Generative Recommender Systems using semantic ids, such as TIGER (Rajput et al., 2023), have emerged as a widely adopted competitive paradigm in sequential recommendation. However, existing architectures are designed solely for semantic retrieval and do not address concerns such as monetization via ad revenue and incorporation of bids for commercial retrieval. We propose GEM-Rec, a unified framework that integrates commercial relevance and monetization objectives directly into the generative seq