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

Mete Ozay

ACL 2026×2ECCV 2026×2效率与系统对齐与偏好多模态长上下文与架构可解释性
新星分资深
23
一作贡献0
核心/参与10
方向广度13
合作网络3
0 一作 · 4 篇 · ACL 2026 / ECCV 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 #4/6ACL 2026Poster· Natural Language Processing

K-Merge: Online Continual Merging of Adapters for On-device Large Language Models

Donald Shenaj · Ondrej Bohdal · Taha Ceritli · Mete Ozay · Pietro Zanuttigh · Umberto Michieli

摘要

On-device deployment of Large Language Models (LLMs) frequently leverages Low-Rank Adapters (LoRAs) to support diverse downstream tasks under tight resource constraints. To address the limited storage capacity of mobile devices, recent works have explored model merging techniques to fuse multiple...

效率与系统OpenReview 项目页
作者位次 #5/5ACL 2026Poster· ACL Industry Track

Decoding Text Spans for Efficient and Accurate Named-Entity Recognition

Andrea Maracani · Savas Ozkan · Junyi Zhu · Sinan Mutlu · Mete Ozay

摘要

Named Entity Recognition (NER) is a key component in industrial information extraction pipelines, where systems must satisfy strict latency and throughput constraints in addition to strong accuracy. State-of-the-art NER accuracy is often achieved by span-based frameworks, which construct span rep...

效率与系统可解释性评测与基准OpenReview 项目页

常见合作者