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

Angelo Zangari

ACL 2026×2KDD 2026推理安全评测与基准可解释性数据与预训练
新星分新星
75
一作贡献30
核心/参与21
方向广度13
合作网络12
1 一作 · 3 篇 · 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

3
作者位次 #8/15ACL 2026Poster· Natural Language Processing

Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safety

Wei-Chieh Huang · Henry Peng Zou · Yaozu Wu · Dongyuan Li · Yankai Chen · Weizhi Zhang · Yangning Li · Angelo Zangari · Jizhou Guo · Chunyu Miao · Liancheng Fang · Langzhou He · Yinghui Li · Renhe Jiang · Philip S. Yu

摘要

Deep research frameworks have shown promising capabilities in synthesizing comprehensive reports from web sources. While deep research possesses significant potential to address complex issues through planning and research cycles, existing frameworks are deficient in sufficient evaluation procedu...

安全评测与基准推理OpenReview 项目页
一作ACL 2026Findings· Findings of ACL

Colorful Talks with Graphs: Human-Interpretable Graph Encodings for Large Language Models

Angelo Zangari · Peyman Baghershahi · Sourav Medya

摘要

Graph problems are fundamentally challenging for large language models (LLMs). While LLMs excel at processing unstructured text, graph tasks require reasoning over explicit structure, permutation invariance, and computationally complex relationships, creating a mismatch with the representations o...

可解释性推理数据与预训练OpenReview 项目页

常见合作者