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

Junyu Lu

AAAI 2026ACL 2026SIGIR 2026推理智能体与工具多模态强化学习与后训练对齐与偏好
新星分新星
79
一作贡献40
核心/参与17
方向广度16
合作网络12
1 一作 · 3 篇 · AAAI 2026 / ACL 2026 / SIGIR 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

3
作者位次 #2/10ACL 2026Poster· ACL Industry Track

ARGUS : Policy-Adaptive Ad Governance via Evolving Reinforcement with Adversarial Umpiring

Deyi Ji · Junyu Lu · Xuanyi Liu · Liqun Liu · Hailong Zhang · Peng Shu · Huan Yu · Jie Jiang · Tianrun Chen · Lanyun Zhu

摘要

Online advertising governance faces significant challenges due to the non-stationary nature of regulatory policies, where emerging mandates (e.g., restrictions on education or aesthetic anxiety) create severe label inconsistencies and reasoning ambiguities in historical datasets. In this paper, w...

推理智能体与工具强化学习与后训练OpenReview 项目页
一作SIGIR 2026Oral· Information Retrieval (Full)

Decoding Multimodal Cues: Unveiling the Implicit Meaning Behind Hateful Videos

Junyu Lu · Deyi Ji · Liqun Liu · Xiaokun Zhang · Youlin Wu · Roy Ka-Wei Lee · Peng Shu · Huan Yu · Jie Jiang · Bo Xu · Liang Yang · Hongfei Lin

摘要

Hateful videos have become prevalent on online platforms, highlighting an urgent need for effective detection. However, existing studies primarily focus on binary classification and fail to provide contextual rationales that reveal the implicit meanings behind these judgments, significantly under...

推理多模态对齐与偏好OpenReview

常见合作者