paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

TL

Trung Le

ICML 2026×5可解释性多模态强化学习与后训练安全对齐与偏好

新星分资深

26

一作贡献0

核心/参与10

方向广度10

合作网络12

0 一作 · 5 篇 · 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

5

作者位次 #6/6ICML 2026Poster· General Machine Learning / Representation Learning

HieRD: Hierarchical Relational Distillation for Vision-Language Embedding Models

Vinh Le · Nguyen Dang · Tu Vu · Linh Van · Duc Nguyen · Trung Le

可解释性多模态强化学习与后训练OpenReview

作者位次 #10/21ICML 2026Poster· Deep Learning / Robustness

Does a Hybrid Space-Aware Randomized Defense Improve Empirical and Certified Adversarial Robustness?

Joy Dhar · Manish Pandey · Behzad Bozorgtabar · Nayyar Zaidi · Wenyu Zhang · Weihong Li · Tingting Mu · Dwarikanath Mahapatra · Mahsa Baktashmotlagh · Trung Le · Chen Chen · Sajib Mistry · Camila Gonzalez · Samira Ebrahimi Kahou · Lina Yao · Piotr Koniusz · Robert Fisher · Dinh Phung · Bohyung Han · Nuno Vasconcelos · Pietro Lió

安全OpenReview

作者位次 #5/6ICML 2026Poster· General Machine Learning / Everything Else

Causal-aware Anomaly Detection for Tabular Data

Dang Nguyen · Tu Anh Hoang Nguyen · Thuc Le · Svetha Venkatesh · Trung Le · Sunil Gupta

作者位次 #6/6ICML 2026Poster· Deep Learning / Large Language Models

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching

Truong Nguyen · Tien-Phat Nguyen · Linh Van · Duy Nguyen · Khoa Doan · Trung Le

对齐与偏好OpenReview

作者位次 #7/7ICML 2026Poster· Deep Learning / Large Language Models

$f$-Divergence Self-Play for Tabular Anomaly Detection via Large Language Models

Hoang Vuong Tran · Linh Van · Dang Nguyen · Thin Nguyen · Phuoc Nguyen · Mehrtash Harandi · Trung Le

常见合作者

LVLinh Van×3 DNDang Nguyen×2 VLVinh Le NDNguyen Dang TVTu Vu DNDuc Nguyen JDJoy Dhar MPManish Pandey BBBehzad Bozorgtabar NZNayyar Zaidi WZWenyu Zhang WLWeihong Li