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

Zheng Gong

ACL 2026SIGIR 2026可解释性推理强化学习与后训练效率与系统检索与知识
新星分新星
80
一作贡献70
核心/参与0
方向广度13
合作网络6
2 一作 · 2 篇 · ACL 2026 / SIGIR 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
一作ACL 2026Poster· Natural Language Processing

Punctuation-Steered Representation Fine-Tuning

Zheng Gong · Ying Sun · Ping Li · Yi Zheng · Zhefeng Wang

摘要

Representation Fine-tuning (ReFT), a recently proposed parameter-efficient fine-tuning (PeFT) method, significantly improves parameter efficiency by modifying the representation space alone. However, directly applying ReFT, which alters a fixed number of representations at the beginning and end p...

推理可解释性强化学习与后训练OpenReview 项目页
一作SIGIR 2026Poster· Information Retrieval (Short)

TDHGNN: A Temporal Directed Hypergraph Neural Network for Bitcoin Fraud Detection

Zheng Gong · Shuheng Shen · Changhua Meng · Ying Sun

摘要

The rapid expansion of cryptocurrencies, especially Bitcoin, has heightened the need for efficient detection of illicit transactions, including ransomware payments and money laundering. To effectively address the unique challenges of Bitcoin fraud detection, such as handling heterogeneous, direct...

可解释性效率与系统检索与知识OpenReview

常见合作者