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

Zhiyu Chen

ACL 2026×2对齐与偏好多模态安全检索与知识理论与学习动力学
新星分资深
10
一作贡献0
核心/参与0
方向广度10
合作网络0
0 一作 · 2 篇 · 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

2
作者位次 #3/3ACL 2026Findings· Findings of ACL

Preference Learning Unlocks LLM s’ Psycho-Counseling Skills

Mian Zhang · Shaun M. Eack · Zhiyu Chen

摘要

Applying large language models (LLMs) to assist in psycho-counseling is an emerging and meaningful approach, driven by the significant gap between patient needs and the availability of mental health support. However, current LLMs struggle to consistently provide effective responses to client spee...

对齐与偏好多模态安全OpenReview 项目页
作者位次 #5/5ACL 2026Findings· Findings of ACL

Is Grokking Worthwhile? Functional Analysis and Transferability of Generalization Circuits in Transformers

Kaiyu He · Mian Zhang · Peilin Wu · Xinya Du · Zhiyu Chen

摘要

While Large Language Models (LLMs) excel at factual retrieval, they often struggle with the “curse of two-hop reasoning” in compositional tasks. Recent research suggests that parameter-sharing transformers can bridge this gap by forming a “Generalization Circuit” during a prolonged “grokking” pha...

检索与知识理论与学习动力学推理OpenReview 项目页

常见合作者