paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

SL

Shiwei Liu

ICML 2026×6效率与系统多模态检索与知识长上下文与架构

新星分资深

28

一作贡献0

核心/参与15

方向广度8

合作网络12

0 一作 · 6 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

6

作者位次 #5/5ICML 2026Poster· Deep Learning / Large Language Models

One LR Doesn’t Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs

Di He · Songjun Tu · Keyu Wang · Lu Yin · Shiwei Liu

作者位次 #13/13ICML 2026Poster· Optimization / Stochastic

GradientStabilizer: Fix the Norm, Not the Gradient

Tianjin Huang · Zhangyang “Atlas” Wang · Haotian Hu · Zhenyu Zhang · Gaojie Jin · Xiang Li · Li Shen · Jiaxing Shang · Tianlong Chen · Ke Li · Lu Liu · Qingsong Wen · Shiwei Liu

作者位次 #5/10ICML 2026Poster· Deep Learning / Generative Models and Autoencoders

Motion-Aware Caching for Efficient Autoregressive Video Generation

Jing Xu · Yuexiao Ma · Xuzhe Zheng · WANG · Shiwei Liu · Chenqian Yan · Xiawu Zheng · Rongrong Ji · Fei Chao · Songwei Liu

多模态效率与系统OpenReview

作者位次 #4/5ICML 2026Poster· Deep Learning / Large Language Models

Search or Accelerate: Confidence-Switched Position Beam Search for Diffusion Language Models

Mingyu Cao · Alvaro Correia · Christos Louizos · Shiwei Liu · Lu Yin

检索与知识长上下文与架构OpenReview

作者位次 #5/6ICML 2026Poster· Deep Learning / Large Language Models

Rewiring Experts on the Fly: Continuous Rerouting for Better Online Adaptation in Mixture-of-Expert Models

Guinan Su · Yanwu Yang · Li Shen · Lu Yin · Shiwei Liu · Jonas Geiping

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

When Does Sparsity Mitigate the Curse of Depth in LLMs

Yao Yao · Xinyuan Song · Sebastian Pokutta · Max Zimmer · Nico Pelleriti · Thomas Hofmann · Shiwei Liu

效率与系统OpenReview

常见合作者

LYLu Yin×3 LSLi Shen×2 DHDi He STSongjun Tu KWKeyu Wang THTianjin Huang ZWZhangyang “Atlas” Wang HHHaotian Hu ZZZhenyu Zhang GJGaojie Jin XLXiang Li JSJiaxing Shang