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

Denghui Zhang

ICLR 2026×3ACL 2026×2KDD 2026强化学习与后训练检索与知识推理安全对齐与偏好
新星分资深
47
一作贡献40
核心/参与15
方向广度16
合作网络12
1 一作 · 6 篇 · ICLR 2026 / ACL 2026 / KDD 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 #14/14ACL 2026Workshop· ACL System Demonstrations

Copyright Detective: A Forensic System to Evidence LLM s Flickering Copyright Leakage Risks

Guangwei Zhang · Jianing Zhu · Cheng Qian · Neil Zhenqiang Gong · Rada Mihalcea · Zhaozhuo Xu · Jingrui He · Jiaqi W. Ma · Chaowei Xiao · Bo Li · Ahmed Abbasi · Dongwon Lee · Heng Ji · Denghui Zhang

摘要

We present Copyright Detective , the first interactive forensic system for detecting, analyzing, and visualizing potential copyright risks in LLM outputs. The system treats copyright infringement versus compliance as an evidence discovery process rather than a static classification task due to th...

安全多模态可解释性OpenReview 项目页
作者位次 #6/6ACL 2026Findings· Findings of ACL

Accelerating LLM Fine-Tuning via Embedding Knowledge Transfer

Meishu Peng · Ziyue Zhang · Yi Zhang · Pengyang Wang · Zixuan Yuan · Denghui Zhang

摘要

Incorporating Large Language Models (LLMs) for downstream tasks has recently garnered considerable attention, where fine-tuning plays a key role in LLMs’ adaptation. These LLMs, often consisting of billions of parameters, require vast amounts of computational resources when customizing them for n...

强化学习与后训练检索与知识推理OpenReview 项目页
一作KDD 2026Oral· Knowledge Discovery & Data Mining

Evidencing LLM Misuse: A Hands-on Forensic Tutorial on Copyright Infringement and Plagiarism Detection

Denghui Zhang · Guangwei Zhang · Dongwon Lee

检索与知识OpenReview

常见合作者