collaborators

7 papers

cs.IR2026

From Trajectories to Evidence: Auditable Experimental Records for Industrial Research Agents

Zijie Zhuang, Changxin Lao, Pengbo Xu +13

Research agents increasingly conduct multi-round machine-learning experiments in industrial recommendation settings and retain the resulting trajectories to guide later decisions.…

cs.IR2026

Reward Guided Decoding for Generative Recommendation

Ruochen Yang, Yusheng Huang, Youfeng Zheng +11

Generative recommendation formulates recommendation task into an SID sequence autoregressive generation paradigm, but the decoding process is often dominated by generation likeliho…

cs.IR2026

Unifying Generative Recall and Multi-Objective Ranking in a Single Decoder-Only Sequence

Ruochen Yang, Shuang Wen, Pengbo Xu +6

Modern industrial recommendation systems typically separate recall and ranking into two independent stages. Although this cascade supports corpus-level retrieval and fine-grained m…

cs.IR2026

On the Equivalence Between Auto-Regressive Next Token Prediction and Full-Item-Vocabulary Maximum Likelihood Estimation in Generative Recommendation--A Short Note

Yusheng Huang, Shuang Yang, Zhaojie Liu +1

Generative recommendation (GR) has emerged as a widely adopted paradigm in industrial sequential recommendation. Current GR systems follow a similar pipeline: tokenization for item…

cs.IR2026

MaRI: Accelerating Ranking Model Inference via Structural Re-parameterization in Large Scale Recommendation System

Yusheng Huang, Pengbo Xu, Shen Wang +7

Ranking models, i.e., coarse-ranking and fine-ranking models, serve as core components in large-scale recommendation systems, responsible for scoring massive item candidates based…

cs.IR2026

OneLive: Dynamically Unified Generative Framework for Live-Streaming Recommendation

Shen Wang, Yusheng Huang, Ruochen Yang +15

Live-streaming recommender system serves as critical infrastructure that bridges the patterns of real-time interactions between users and authors. Similar to traditional industrial…