From the 2 of 12 linked papers with an AI index.
12 papers
Sample Is Feature: Beyond Item-Level, Toward Sample-Level Tokens for Unified Large Recommender Models
Shuli Wang, Junwei Yin, Changhao Li +6
The paper introduces SIF, a method that converts each historical user interaction sample into a token using hierarchical group-adaptive quantization and then mixes these tokens wit…
Not Only NTP: Extending Training Signal Coverage for Generative Recommendation
Changhao Li, Shuli Wang, Junwei Yin +6
The paper introduces NONTP, a method that augments next‑token prediction for recommendation models with temporal contrastive learning and trans‑domain learning to capture longer‑ra…
DynamicPO: Dynamic Preference Optimization for Recommendation
Xingyu Hu, Kai Zhang, Jiancan Wu +7
In large language model (LLM)-based recommendation systems, direct preference optimization (DPO) effectively aligns recommendations with user preferences, requiring multi-negative…
Discrimination Is Generation: Unifying Ranking and Retrieval from a Tokenizer Perspective
Shuli Wang
Semantic IDs (SIDs) define the generation space of generative recommendation and directly determine its personalization ceiling. However, existing tokenizers are trained independen…
Generative Bid Shading in Real-Time Bidding Advertising
Yinqiu Huang, Hao Ma, Wenshuai Chen +7
Bid shading plays a crucial role in Real-Time Bidding (RTB) by adaptively adjusting the bid to avoid advertisers overspending. Existing mainstream two-stage methods, which first mo…
Deep Situation-Aware Interaction Network for Click-Through Rate Prediction
Yimin Lv, Shuli Wang, Beihong Jin +6
User behavior sequence modeling plays a significant role in Click-Through Rate (CTR) prediction on e-commerce platforms. Except for the interacted items, user behaviors contain ric…