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

Ziqiong Liu

AAAI 2026×2ICLR 2026×2ACL 2026效率与系统多模态长上下文与架构推理代码
新星分贡献者
57
一作贡献0
核心/参与25
方向广度16
合作网络6
0 一作 · 5 篇 · AAAI 2026 / ICLR 2026 / ACL 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 #3/5ICLR 2026Poster· Deep Learning / Generative Models and Autoencoders

PARD: Accelerating LLM Inference with Low‑Cost PARallel Draft Model Adaptation

Zihao An · Huajun Bai · Ziqiong Liu · Dong Li · Emad Barsoum

效率与系统OpenReview
作者位次 #4/7ACL 2026Poster· Natural Language Processing

M o EC : A Memory-Routed Mixture-of-Experts Controller for Adaptive M inecraft Control

Hui Wu · Chao Xu · Jianghui Wang · Ziqiong Liu · Dong Li · Yiwei Dai · Emad Barsoum

摘要

Embodied agents in open-ended environments such as Minecraft increasingly adopt planner–controller architectures, with large language models acting as high-level planners. While planning has advanced rapidly, control remains underexplored. Existing systems commonly rely on a monolithic policy to...

效率与系统长上下文与架构推理OpenReview 项目页

常见合作者