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

Zechun Liu

ICLR 2026×2ACL 2026CVPR 2026推理多模态效率与系统长上下文与架构可解释性
新星分贡献者
56
一作贡献0
核心/参与20
方向广度16
合作网络9
0 一作 · 4 篇 · ICLR 2026 / ACL 2026 / CVPR 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

4
作者位次 #6/23CVPR 2026Poster· Computer Vision & Pattern Recognition

VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice

Shuming Liu · Mingchen Zhuge · Changsheng Zhao · Jun Chen · Lemeng Wu · Zechun Liu · Chenchen Zhu · zhipeng cai · Chong Zhou · Haozhe Liu · Ernie Chang · Saksham Suri · Hongyu Xu · Qi Qian · Wei Wen · Balakrishnan Varadarajan · Zhuang Liu · Hu Xu · Florian Bordes · Raghuraman Krishnamoorthi · Bernard Ghanem · Vikas Chandra · Yunyang Xiong

多模态推理OpenReview 项目页
作者位次 #12/17ACL 2026Poster· ACL Industry Track

M obile LLM -Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment

Hanxian Huang · Igor Fedorov · Andrey Gromov · Bernard Beckerman · Naveen Suda · David Eriksson · Maximilian Balandat · Rylan Conway · Patrick Huber · Chinnadhurai Sankar · Ayushi Dalmia · Zechun Liu · Lemeng Wu · Tarek Elgamal · Adithya Sagar · Vikas Chandra · Raghuraman Krishnamoorthi

摘要

Real-time AI experiences call for on-device large language models (OD-LLMs) optimized for efficient deployment on resource-constrained hardware. The most useful OD-LLMs produce near-real-time responses and exhibit broad hardware compatibility, maximizing user reach. We present a methodology for d...

效率与系统长上下文与架构可解释性OpenReview 项目页

常见合作者