arXiv:2606. 09623v1 Announce Type: new Abstract: When running marketing campaigns, retailers must decide which products to promote and which users to target.
UniPolicy is a multi-policy alignment framework for search advertising that jointly optimizes relevance, click propensity, and commercial value. It uses objective-specific prefix tokens, sparse MoE-LoRA routing, and residual FFNs to decouple parameters within a shared backbone, and builds pairwise preferences from multi-stage behavioral feedback to improve generation. In large-scale offline tests and a 7‑day online A/B test, UniPolicy achieved balanced gains across metrics, boosting CTR by 0.71%, RPS by 1.58%, and revenue by 1.32% while keeping latency stable.
UniPolicy is a unified objective‑specific policy framework for search advertising that jointly optimizes relevance, click propensity, and commercial value. It uses objective‑aware prefix tokens, sparse MoE‑LoRA routing, and residual FFNs to decouple parameters within a shared backbone, and constructs pairwise preferences from multi‑stage behavioral feedback to strengthen clicked candidates. In large‑scale offline tests and a 7‑day online A/B test, UniPolicy improves CTR by 0.71%, RPS by 1.58%, and advertising revenue by 1.32% while keeping serving latency stable.
arXiv:2004. 06321v2 Announce Type: replace Abstract: We study the sequential batch learning problem in linear contextual bandits with finite action sets, where the decision maker is constrained to split incoming individuals into (at most) a fixed number of batches and can only observe outcomes for the individuals within a batch at the batch's end.
arXiv:2610.34917v1 Announce Type: new Abstract: Diffusion models enable multiple advertisers to compete for exposure within a shared generated image. Yet existing approaches are computationally costl...
arXiv:2610.26380v2 Announce Type: replace-cross Abstract: This paper considers a decision-maker tasked with identifying the $k$ best items from a large pool of candidates, such as job applicants, LLM...
arXiv:2607. 11684v1 Announce Type: cross Abstract: Existing contextual multinomial logit (MNL) bandits model relevance-driven choice but ignore the potential benefits of within-assortment diversity, while submodular/combinatorial bandits encode diversity in rewards but lack structured choice probabilities.
DeGRe is a dense‑supervised generative reranking framework designed to improve multi‑stage recommender systems by addressing label bias and credit assignment issues. It uses an offline Lookahead Evaluator with beam search to generate dense supervision signals, which are distilled into a lightweight Online Generator that can perform efficient greedy decoding at inference time. Experiments show that DeGRe outperforms baselines on public benchmarks and industrial datasets, and it has been successfully deployed on Taobao Flash Shopping to enhance online recommendations.
Diffusion models enable multiple advertisers to compete for exposure within a shared generated image. Yet existing approaches are computationally costly when generating images under varying target-sha...
This paper considers a decision-maker tasked with identifying the $k$ best items from a large pool of candidates, such as job applicants, LLMs, award nominees, or new product ideas. The decision-maker...
The paper introduces Budget-Constrained Causal Bandits (BCCB), an online framework that learns individual treatment effects, explores uncertain users, and manages budget pacing simultaneously. It derives a per-arrival decision rule from a KKT condition of a Lagrangian relaxation, providing a principled algorithmic foundation. Experiments on the Criteo Uplift dataset show BCCB outperforms offline pipelines and other online baselines, especially when historical data is scarce (below 7,500 observations).
The paper introduces Latent Order Bandits (LOB), a new bandit framework that relaxes the strict assumptions of traditional latent bandits by only requiring a partial order of action preferences within each latent state. LOB allows instances sharing the same state to have different reward distributions as long as the action ranking remains consistent, making it suitable for scenarios like user groups on streaming services who agree on genre preferences but rate differently. The authors present an upper‑confidence bound algorithm for both total and partial latent orders, provide regret bounds, and propose a posterior‑sampling variant that empirically outperforms full‑prior latent bandits when reward scales vary across instances sharing the same latent state.