Imagen de Portada

The Forgotten Shield: Safety Grafting in Parameter-Space for Medical MLLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhao, Jiale, Mou, Xing, Wu, Jinlin, Yu, Hongyuan, Sun, Mingrui, Shi, Yang, Yin, Xuanwu, Chen, Zhen, Lei, Zhen, Wang, Yaohua
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Graft: Integrating the Domain Knowledge via Efficient Parameter Synergy for MLLMs
por: Dai, Yang, et al.
Publicado: (2025)

AM$^3$Safety: Towards Data Efficient Alignment of Multi-modal Multi-turn Safety for MLLMs
por: Zhu, Han, et al.
Publicado: (2026)

SurgVisAgent: Multimodal Agentic Model for Versatile Surgical Visual Enhancement
por: Lei, Zeyu, et al.
Publicado: (2025)

Transforming Surgical Interventions with Embodied Intelligence for Ultrasound Robotics
por: Xu, Huan, et al.
Publicado: (2024)

Enhancing Surgical Robots with Embodied Intelligence for Autonomous Ultrasound Scanning
por: Xu, Huan, et al.
Publicado: (2024)

What Matters For Safety Alignment?
por: Li, Xing, et al.
Publicado: (2026)

Learning from Medical Entity Trees: An Entity-Centric Medical Data Engineering Framework for MLLMs
por: Lin, Jianghang, et al.
Publicado: (2026)

MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs
por: Shi, Baorong, et al.
Publicado: (2026)

ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors
por: Zhang, Zhexin, et al.
Publicado: (2024)

LoR2C : Low-Rank Residual Connection Adaptation for Parameter-Efficient Fine-Tuning
por: Zhao, Jiancheng, et al.
Publicado: (2025)

Do Images Speak Louder than Words? Investigating the Effect of Textual Misinformation in VLMs
por: Zhang, Chi, et al.
Publicado: (2026)

Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE
por: Chen, Zeren, et al.
Publicado: (2023)

Adaptive Shielding via Parametric Safety Proofs
por: Feng, Yao, et al.
Publicado: (2025)

Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning
por: Ma, Qinghe, et al.
Publicado: (2026)

Exploring the Design Space of Visual Context Representation in Video MLLMs
por: Du, Yifan, et al.
Publicado: (2024)

From Pruning to Grafting: Dynamic Knowledge Redistribution via Learnable Layer Fusion
por: Pei, Zehua, et al.
Publicado: (2024)

ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing
por: Zhao, Xuanle, et al.
Publicado: (2025)

UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Models
por: Qin, Zhanyue, et al.
Publicado: (2024)

Elucidating the Design Space of Decay in Linear Attention
por: Qin, Zhen, et al.
Publicado: (2025)

Span-level Detection of AI-generated Scientific Text via Contrastive Learning and Structural Calibration
por: Yin, Zhen, et al.
Publicado: (2025)

A Prompt-driven Task Planning Method for Multi-drones based on Large Language Model
por: Liu, Yaohua
Publicado: (2024)

Swift Parameter-free Attention Network for Efficient Super-Resolution
por: Wan, Cheng, et al.
Publicado: (2023)

Language, the Forgotten Content.
por: Kelly, Patricia P., Ed., et al.
Publicado: (1987)

InfiMed: Low-Resource Medical MLLMs with Advancing Understanding and Reasoning
por: Liu, Zeyu, et al.
Publicado: (2025)

Dual LoRA: Enhancing LoRA with Magnitude and Direction Updates
por: Xu, Yixing, et al.
Publicado: (2025)

A LongFormer-Based Framework for Accurate and Efficient Medical Text Summarization
por: Sun, Dan, et al.
Publicado: (2025)

From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities
por: Jiang, Shixin, et al.
Publicado: (2024)

SafeInt: Shielding Large Language Models from Jailbreak Attacks via Safety-Aware Representation Intervention
por: Wu, Jiaqi, et al.
Publicado: (2025)

UnlearnShield: Shielding Forgotten Privacy against Unlearning Inversion
por: Xue, Lulu, et al.
Publicado: (2026)

SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types
por: Mou, Yutao, et al.
Publicado: (2024)

Ethos: Rectifying Language Models in Orthogonal Parameter Space
por: Gao, Lei, et al.
Publicado: (2024)

Green Shielding: A User-Centric Approach Towards Trustworthy AI
por: Li, Aaron J., et al.
Publicado: (2026)

Right to be Forgotten in the Era of Large Language Models: Implications, Challenges, and Solutions
por: Zhang, Dawen, et al.
Publicado: (2023)

FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow
por: Sun, Haoyu, et al.
Publicado: (2025)

SafetyBench: Evaluating the Safety of Large Language Models
por: Zhang, Zhexin, et al.
Publicado: (2023)

MiSS: Revisiting the Trade-off in LoRA with an Efficient Shard-Sharing Structure
por: Kang, Jiale, et al.
Publicado: (2024)

Unhackable Temporal Rewarding for Scalable Video MLLMs
por: Yu, En, et al.
Publicado: (2025)

MSPLoRA: A Multi-Scale Pyramid Low-Rank Adaptation for Efficient Model Fine-Tuning
por: Zhao, Jiancheng, et al.
Publicado: (2025)

Affordance Benchmark for MLLMs
por: Wang, Junying, et al.
Publicado: (2025)

Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
por: Wu, Xiaoyu, et al.
Publicado: (2025)