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

Siwei Wen

ACL 2026ECCV 2026多模态智能体与工具检索与知识推理强化学习与后训练
新星分新星
66
一作贡献30
核心/参与5
方向广度13
合作网络12
1 一作 · 2 篇 · ACL 2026 / ECCV 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

2
一作ECCV 2026Poster

EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use

Siwei Wen · Zhangcheng Wang · Xingjian Zhang · Lei Huang · wenjun wu

多模态智能体与工具检索与知识Video Understanding, Generation and Multimodal LearningOpenReview
作者位次 #3/7ACL 2026Poster· Natural Language Processing

Heterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token’s Nature

Zheng Liu · Mengjie Liu · Siwei Wen · Mengzhang Cai · Bin Cui · Conghui He · Wentao Zhang

摘要

Using entropy as a measure of heterogeneity to guide optimization has emerged as a crucial research direction in Reinforcement Learning for LLMs. However, existing methods typically treat it as a discrete filter or post-hoc regulator rather than a core optimization driver. To fully leverage the p...

推理强化学习与后训练评测与基准OpenReview 项目页

常见合作者