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

Tran Van Nhiem

ACL 2026ICML 2026效率与系统多模态评测与基准数据与预训练
新星分贡献者
39
一作贡献0
核心/参与10
方向广度11
合作网络6
0 一作 · 2 篇 · ACL 2026 / ICML 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
作者位次 #8/23ICML 2026Poster· Applications / Robotics

FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation

Duc Nguyen · Nghiem Diep · Binh Nguyen Gia · Trong-Bao Ho · Doanh Le Thien · Quang Nguyen · Thien-Loc Ha · Tran Van Nhiem · Bao Thach · Tran Nhat · Tuan Tran · Artur Habuda · Philip Lund Møller · Tran Nguyen Le · Daniel Sonntag · Mathias Niepert · Khoa Doan · Vu Duong · Hung Ngo · Minh VU · Duy Nguyen · An Thai Le · Vien Ngo

多模态效率与系统OpenReview
作者位次 #3/5ACL 2026Workshop· ACL System Demonstrations

Expert Calibration Lens for Pruning Mixture of Experts

Luis Frentzen Salim · Chia-Chun Wu · Tran Van Nhiem · Lun-Wei Ku · Yung-Hui Li

摘要

Expert pruning is a practical deployment technique for Mixture-of-Experts (MoE) models. It reduces resource usage and mitigates expert redundancy, but its success depends strongly on the calibration set used for pruning. In domain-general settings, it is unclear which properties of the calibratio...

效率与系统评测与基准数据与预训练OpenReview 项目页

常见合作者