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

Yevgeniy Vorobeychik

AwardAAAI 2026×2ACL 2026×2ICML 2026推理安全智能体与工具可解释性强化学习与后训练
新星分资深
30
一作贡献0
核心/参与17
方向广度16
合作网络6
0 一作 · 5 篇 · AAAI 2026 / ACL 2026 / ICML 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

5
作者位次 #3/3ACL 2026OralOutstanding Paper· Natural Language Processing

Mind the ( DH ) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLM s

Luise Ge · Yongyan Zhang · Yevgeniy Vorobeychik

摘要

The use of large language models either as decision support systems, or in agentic workflows, is rapidly transforming the digital ecosystem. However, the understanding of LLM decision-making under uncertainty remains limited. We initiate a comparative study of LLM risky choices along two dimensio...

推理智能体与工具可解释性OpenReview 项目页
作者位次 #4/4ACL 2026Poster· Natural Language Processing

Protecting Language Models Against Unauthorized Distillation through Trace Rewriting

Xinhang Ma · William Yeoh · Ning Zhang · Yevgeniy Vorobeychik

摘要

Knowledge distillation is a widely adopted technique for transferring capabilities from LLMs to smaller, more efficient student models.However, unauthorized use of knowledge distillation takes unfair advantage of the considerable effort and cost put into developing frontier models.We investigate...

推理安全强化学习与后训练OpenReview 项目页
作者位次 #3/3AAAI 2026Poster· Artificial Intelligence

Optimized Distortion in Linear Social Choice

Luise Ge · Gregory Kehne · Yevgeniy Vorobeychik

社会与人本OpenReview

常见合作者