paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

MV

Martin Vechev

NeurIPS 2026×5安全社会与人本评测与基准

新星分资深

13

一作贡献0

核心/参与5

方向广度6

合作网络3

0 一作 · 5 篇 · NeurIPS 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 #4/4NeurIPS 2026Poster· Social Aspects / Trustworthy Machine Learning

Making Open-Source Text LLM Watermarks Durable Against Merging

Luisa Scharff · Thibaud Gloaguen · Robin Staab · Martin Vechev

安全社会与人本OpenReview

作者位次 #3/4NeurIPS 2026Poster· Applications / Everything Else

End-to-End Neural Modeling of EM Response and Design Performance for Free-Form RFIC Passives

Yuhao Mao · Chenhao Chu · Martin Vechev · Hua Wang

作者位次 #9/9NeurIPS 2026Poster· Social Aspects / Trustworthy Machine Learning

Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots

Mark Vero · Fabian Kaczmarczyck · Ivan Petrov · I Shumailov · Niels Heinen · Jamie Hayes · Tianqi Fan · Luca Invernizzi · Martin Vechev

评测与基准社会与人本OpenReview

作者位次 #4/4NeurIPS 2026Poster

Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness

Ivo Petrov · Jasper Dekoninck · Dimitar I. Dimitrov · Martin Vechev

评测与基准OpenReview

作者位次 #4/4NeurIPS 2026Poster

Every Bit, Everywhere, All At Once: A Binomial Multibit LLM Watermark

Thibaud Gloaguen · Robin Staab · Mark Vero · Martin Vechev

安全OpenReview

常见合作者

TGThibaud Gloaguen×2 RSRobin Staab×2 MVMark Vero×2 LSLuisa Scharff YMYuhao Mao CCChenhao Chu HWHua Wang FKFabian Kaczmarczyck IPIvan Petrov ISI Shumailov NHNiels Heinen JHJamie Hayes