paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达
登录 DINQ
返回新星榜
YC

Yuan Chen

ACL 2026×2ECCV 2026×2CVPR 2026多模态推理评测与基准强化学习与后训练对齐与偏好
新星分新星
79
一作贡献30
核心/参与27
方向广度16
合作网络12
1 一作 · 5 篇 · ACL 2026 / ECCV 2026 / CVPR 2026

获取完整研究档案

首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。

联系方式

实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。

2026 顶会论文

5
作者位次 #4/8ACL 2026Poster· ACL Industry Track

SSR -A: Spatial- and Semantic-Aware Instructions and Curriculum Reinforcement for Advertisement Compliant Rectification

Cao Te · Mengge Xue · Zhenyu Hu · Yuan Chen · Liqun Liu · Peng Shu · Huan Yu · Jie Jiang

摘要

While advertising is a cornerstone of commercial growth, it is constrained by online violation detection systems that reject non-compliant content at a million-scale daily. Advertisers urgently require automated solutions to rectify these advertisements, especially visual ads, as manual fixing is...

强化学习与后训练多模态对齐与偏好OpenReview 项目页
一作ACL 2026Poster· ACL Industry Track

\mathcal{R}^3 : Advertisement Compliance \mathcal{R} ectification via Group- \mathcal{R} elative Experience Extractor and Curriculum \mathcal{R} einforcement

Yuan Chen · Zhenyu Hu · Mengge Xue · Cao Te · Liqun Liu · Peng Shu · Huan Yu · Jie Jiang

摘要

Rigorous content moderation is crucial for online advertising but leads to millions of daily rejections. This scale renders manual rectification infeasible, particularly for video advertisements.However, existing safety-driven methods often suffer from aggressive over-editing, which compromises t...

多模态安全推理OpenReview 项目页

常见合作者