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

Michael Ng

ACL 2026×2NeurIPS 2026智能体与工具评测与基准强化学习与后训练数据与预训练检索与知识
新星分资深
23
一作贡献0
核心/参与5
方向广度13
合作网络9
0 一作 · 3 篇 · ACL 2026 / NeurIPS 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 #4/5ACL 2026Findings· Findings of ACL

A lpha E dit+: Model Editing in the Presence of Conflicting and Inconsistent Knowledge

qing liu · Jianhao Zhang · Ou Wu · Michael Ng · Yi Du

摘要

Knowledge editing is a crucial technique for daily updates in LLMs, requiring a balance between accurately modifying incorrect knowledge and preserving existing information. The recently proposed AlphaEdit method achieves competitive editing performance by updating parameters under null-space con...

评测与基准数据与预训练检索与知识OpenReview 项目页
作者位次 #6/6ACL 2026Findings· Findings of ACL

TVW orld: Foundations for Remote-Control TV Agents

Zhantao Ma · Quanfeng Lu · Shuai Zhong · Dahai Yu · Ping Luo · Michael Ng

摘要

Recent large vision–language models (LVLMs) have demonstrated strong potential for device control. However, existing research has primarily focused on point-and-click (PnC) interaction, while remote-control (RC) interaction commonly encountered in everyday TV usage remains largely underexplored....

评测与基准智能体与工具多模态OpenReview 项目页

常见合作者