5 papers
DREAM Technical Report
Bin Zhang, Bowen Zheng, Chao Yi +74
Industrial recommender systems commonly use cascaded retrieval, ranking, and re-ranking pipelines. Although efficient, these pipelines fragment information and objectives across mo…
Goal-Conditioned Supervised Learning for LLM Fine-Tuning
Shijun Li, Kaiwen Dong, Xiang Gao +1
Large language models often require fine-tuning to better align their behavior with user intent at deployment. Existing approaches are commonly divided into online and offline para…
Reinforce Lifelong Interaction Value of User-Author Pairs for Large-Scale Recommendation Systems
Yisha Li, Lexi Gao, Jingxin Liu +4
Recommendation systems (RS) help users find interested content and connect authors with their target audience. Most research in RS tends to focus either on predicting users' immedi…
TADT-CSA: Temporal Advantage Decision Transformer with Contrastive State Abstraction for Generative Recommendation
Xiang Gao, Tianyuan Liu, Yisha Li +5
With the rapid advancement of Transformer-based Large Language Models (LLMs), generative recommendation has shown great potential in enhancing both the accuracy and semantic unders…
Supervised Learning-enhanced Multi-Group Actor Critic for Live Stream Allocation in Feed
Jingxin Liu, Xiang Gao, Yisha Li +3
In the context of a short video & live stream mixed recommendation scenario, the live stream recommendation system (RS) decides whether to allocate at most one live stream into the…