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

Qingan Li

ACL 2026OSDI 2026效率与系统对齐与偏好评测与基准多模态可解释性
新星分资深
24
一作贡献0
核心/参与9
方向广度13
合作网络6
0 一作 · 2 篇 · ACL 2026 / OSDI 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 #3/5OSDI 2026Oral· Operating Systems & Distributed Systems

LifeLine: An Object-Page Lifetime Alignment GC Enabling Minimal Memory Copying for Mobile Devices

Jiacheng Huang · Yunmo Zhang · Qingan Li · Junqiao Qiu · Chun Jason Xue

摘要

LifeLine is a garbage collection (GC) framework for Android that tackles the fundamental object–page lifetime mismatch. Existing copying collectors move objects, while the OS manages pages; mixed lifetimes within a page force excessive object copying instead of efficient page remapping. LifeLine...

对齐与偏好效率与系统评测与基准OpenReview
作者位次 #4/4ACL 2026Findings· Findings of ACL

POP : Prefill-Only Pruning for Efficient Large Model Inference

Junhui He · Zhihui Fu · Jun Wang · Qingan Li

摘要

Large Language Models (LLMs) and Vision-Language Models (VLMs) have demonstrated remarkable capabilities.However, their deployment is hindered by significant computational costs. Existing structured pruning methods, while hardware-efficient, often suffer from significant accuracy degradation. In...

效率与系统多模态可解释性OpenReview 项目页

常见合作者