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

Anil Ramakrishna

ACL 2026×2ECCV 2026安全多模态长上下文与架构评测与基准对齐与偏好
新星分贡献者
55
一作贡献0
核心/参与22
方向广度13
合作网络9
0 一作 · 3 篇 · ACL 2026 / ECCV 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 #5/10ACL 2026Poster· Natural Language Processing

SWAN : Semantic Watermarking with A bstract M eaning R epresentation

Ziping Ye · Gourab Dey · Christos Christodoulopoulos · Charith Peris · Anil Ramakrishna · Weitong Ruan · Aram Galstyan · Kai-Wei Chang · Rahul Gupta · Ninareh Mehrabi

摘要

We introduce SWAN (Semantic Watermarking with Abstract Meaning Representation), a novel framework that embeds watermark signatures into the semantic structure of a sentence using Abstract Meaning Representation (AMR). In contrast to existing watermarking methods, which typically encode signatures...

评测与基准对齐与偏好安全OpenReview 项目页
作者位次 #2/8ACL 2026Poster· Natural Language Processing

From Narrow Unlearning to Emergent Misalignment in LLM s

Erum Mushtaq · Anil Ramakrishna · Satyapriya Krishna · Sattvik Sahai · Prasoon Goyal · Kai-Wei Chang · Tao Zhang · Rahul Gupta

摘要

Recent work has shown that fine-tuning on insecure code data can trigger an emergent misalignment (EMA) phenomenon, where models generate malicious responses even to prompts unrelated to the original insecure code-writing task. Such cross-domain generalization of harmful behavior underscores the...

安全社会与人本理论与学习动力学OpenReview 项目页

常见合作者