Researcher — paper.dinq.me

2026 顶会论文

一作ICML 2026Poster· Reinforcement Learning / Batch/Offline

Continuity-Regularized Flow Matching for Offline Reinforcement Learning

Xiaocong Chen · Siyu Wang · Lina Yao

强化学习与后训练OpenReview

作者位次 #2/6ICML 2026Poster· Reinforcement Learning / Batch/Offline

Reward-Preserving Counterfactual State Editing for Offline Reinforcement Learning

Siyu Wang · Xiaocong Chen · Mingming Gong · Yong Li · Quan Sheng · Lina Yao

强化学习与后训练检索与知识OpenReview

一作SIGIR 2026Oral· Information Retrieval (Full)

Advantage-Conditioned Flow Policy for Offline Reinforcement Learning in Recommendation

Xiaocong Chen · Siyu Wang · Lina Yao

摘要

Offline reinforcement learning (RL) is a useful approach for recommender systems because it can optimize long-term user feedback from logged interaction data without online exploration. A key challenge is the multi-modal nature of user preferences: a user may like several unrelated item types, so...

强化学习与后训练效率与系统对齐与偏好OpenReview

Xiaocong Chen

获取完整研究档案

联系方式

2026 顶会论文

Continuity-Regularized Flow Matching for Offline Reinforcement Learning

Reward-Preserving Counterfactual State Editing for Offline Reinforcement Learning

Advantage-Conditioned Flow Policy for Offline Reinforcement Learning in Recommendation

常见合作者