Researcher — paper.dinq.me

2026 顶会论文

作者位次 #5/7ECCV 2026Poster

Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning

Zhen Zeng · Leijiang Gu · Zhangling Duan · Feng Li · Zenglin Shi · Cees Snoek · Meng Wang

多模态安全检索与知识Video Understanding, Generation and Multimodal LearningOpenReview

作者位次 #5/7CVPR 2026Poster· Computer Vision & Pattern Recognition

Harmonious Parameter Adaptation in Continual Visual Instruction Tuning for Safety-Aligned MLLMs

Ziqi Wang · Chang Che · Cheems Wang · Hui Ma · Zenglin Shi · Cees G. M. Snoek · Meng Wang

对齐与偏好安全多模态OpenReview 项目页

作者位次 #6/7CVPR 2026Poster· Computer Vision & Pattern Recognition

Layer Consistency Matters: Elegant Latent Transition Discrepancy for Generalizable Synthetic Image Detection

Yawen Yang · Feng Li · Shuqi Kong · Yunfeng Diao · Xinjian Gao · Zenglin Shi · Meng Wang

多模态理论与学习动力学OpenReview 项目页

作者位次 #7/8ACL 2026Findings· Findings of ACL

W eb U ncertainty: Dual-Level Uncertainty Driven Planning and Reasoning For Autonomous Web Agent

Lingfeng Zhang · Yongan Sun · Jinpeng Hu · Hui Ma · Ying Yang · Kuien Liu · Zenglin Shi · Meng Wang

摘要

Recent advancements in large language models (LLMs) have empowered autonomous web agents to execute natural language instructions directly on real-world webpages. However, existing agents often struggle with complex tasks involving dynamic interactions and long-horizon execution due to rigid plan...

推理智能体与工具安全OpenReview 项目页

作者位次 #6/6AAAI 2026Poster· Artificial Intelligence

LoRA in LoRA: Towards Parameter-Efficient Architecture Expansion for Continual Visual Instruction Tuning

Chang Che · Ziqi Wang · Pengwan Yang · Cheems Wang · Hui Ma · Zenglin Shi

效率与系统对齐与偏好多模态OpenReview

Zenglin Shi

获取完整研究档案

联系方式