paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

AH

Andi Han

ICML 2026×5AAAI 2026效率与系统理论与学习动力学数据与预训练检索与知识推理

新星分贡献者

61

一作贡献0

核心/参与27

方向广度13

合作网络12

0 一作 · 6 篇 · ICML 2026 / AAAI 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

6

作者位次 #3/7ICML 2026Poster· Deep Learning / Sequential Models, Time series

Expanding the Chaos: Neural Operator for Stochastic (Partial) Differential Equations

Dai Shi · Lequan Lin · Andi Han · Luke Thompson · Jose Miguel Hernandez-Lobato · Zhiyong Wang · Junbin Gao

作者位次 #3/4ICML 2026Poster· Deep Learning / Large Language Models

Memory-Efficient LLM Pretraining via Minimalist Optimizer Design

Athanasios Glentis · Jiaxiang Li · Andi Han · Mingyi Hong

效率与系统数据与预训练检索与知识OpenReview

作者位次 #5/5ICML 2026Poster· Deep Learning / Sequential Models, Time series

Learning Manifold and Itô Dynamics with Branched Neural Rough Differential Equations

Luke Thompson · Dai Shi · Lequan Lin · Junbin Gao · Andi Han

作者位次 #3/7ICML 2026Poster· Deep Learning / Theory

Provable Sample Efficiency of Curriculum Post-Training for Transformer Reasoning

Dake Bu · Wei Huang · Andi Han · Atsushi Nitanda · Hau-San Wong · Qingfu Zhang · Taiji Suzuki

理论与学习动力学推理强化学习与后训练OpenReview

作者位次 #5/7ICML 2026Spotlight· Deep Learning / Graph Neural Networks

S$^3$GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning

Dai Shi · Linhan Luo · Luke Thompson · Lequan Lin · Andi Han · Junbin Gao · Jose Miguel Hernandez-Lobato

效率与系统OpenReview

作者位次 #4/7AAAI 2026Poster· Artificial Intelligence

On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD

Tongcheng Zhang · Zhanpeng Zhou · Mingze Wang · Andi Han · Wei Huang · Taiji Suzuki · Junchi Yan

理论与学习动力学OpenReview

常见合作者

DSDai Shi×3 LLLequan Lin×3 LTLuke Thompson×3 JGJunbin Gao×3 JHJose Miguel Hernandez-Lobato×2 WHWei Huang×2 ZWZhiyong Wang AGAthanasios Glentis JLJiaxiang Li MHMingyi Hong DBDake Bu ANAtsushi Nitanda