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

Jiachen Qian

ACL 2026×2ICLR 2026KDD 2026多模态检索与知识安全对齐与偏好推理
新星分新星
96
一作贡献150
核心/参与0
方向广度16
合作网络6
4 一作 · 4 篇 · ACL 2026 / ICLR 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

4
一作ACL 2026Poster· Natural Language Processing

Visual Inception: Compromising Long-term Planning in Agentic Recommenders via Multimodal Memory Poisoning

Jiachen Qian

摘要

The evolution from static ranking models to Agentic Recommender Systems (Agentic RecSys) empowers AI agents to maintain long-term user profiles and autonomously plan service tasks. While this paradigm shift enhances personalization, it introduces a vulnerability: reliance on Long-term Memory (LTM...

多模态检索与知识推理OpenReview 项目页
一作ACL 2026Findings· Findings of ACL

"Penny Wise, Pixel Foolish": Bypassing Price Constraints in Multimodal Agents via Visual Adversarial Perturbations

Jiachen Qian · Zhaolu Kang

摘要

The rapid proliferation of Multimodal Large Language Models (MLLMs) has ushered in the era of the “Agentic Economy,” where Mobile Agents autonomously execute high-stakes financial transactions. While these agents demonstrate impressive operational capabilities, their adversarial robustness remain...

安全多模态评测与基准OpenReview 项目页
一作KDD 2026Oral· Knowledge Discovery & Data Mining

SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning

Jiachen Qian

检索与知识安全OpenReview

常见合作者