Copertina

Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Shaotian, Li, Shangze, Shi, Chuancheng, Wu, Wenhua, Wu, Yanqiu, Yu, Xiaohan, Shen, Fei, Chua, Tat-Seng
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

TraceRouter: Robust Safety for Large Foundation Models via Path-Level Intervention
di: Shi, Chuancheng, et al.
Pubblicazione: (2026)

DNA: Uncovering Universal Latent Forgery Knowledge
di: Dou, Jingtong, et al.
Pubblicazione: (2026)

Beyond Surface Artifacts: Capturing Shared Latent Forgery Knowledge Across Modalities
di: Dou, Jingtong, et al.
Pubblicazione: (2026)

Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation
di: Shi, Chuancheng, et al.
Pubblicazione: (2025)

OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure
di: Shi, Chuancheng, et al.
Pubblicazione: (2026)

HarmoniAD: Harmonizing Local Structures and Global Semantics for Anomaly Detection
di: Zhang, Naiqi, et al.
Pubblicazione: (2026)

Universal Scene Graph Generation
di: Wu, Shengqiong, et al.
Pubblicazione: (2025)

Precise Shield: Explaining and Aligning VLLM Safety via Neuron-Level Guidance
di: Shi, Enyi, et al.
Pubblicazione: (2026)

Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing
di: Fei, Hao, et al.
Pubblicazione: (2024)

DRAFT: Task Decoupled Latent Reasoning for Agent Safety
di: Wang, Lin, et al.
Pubblicazione: (2026)

Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks
di: Xu, Shicheng, et al.
Pubblicazione: (2023)

Lingua-SafetyBench: A Benchmark for Safety Evaluation of Multilingual Vision-Language Models
di: Shi, Enyi, et al.
Pubblicazione: (2026)

Controllable Value Alignment in Large Language Models through Neuron-Level Editing
di: Yang, Yonghui, et al.
Pubblicazione: (2026)

SafeNeuron: Neuron-Level Safety Alignment for Large Language Models
di: Wang, Zhaoxin, et al.
Pubblicazione: (2026)

Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment
di: Fei, Hao, et al.
Pubblicazione: (2024)

Compose Your Aesthetics: Empowering Text-to-Image Models with the Principles of Art
di: Jin, Zhe, et al.
Pubblicazione: (2025)

Understanding Long Videos via LLM-Powered Entity Relation Graphs
di: Chu, Meng, et al.
Pubblicazione: (2025)

Learning to Ask Critical Questions for Assisting Product Search
di: Li, Zixuan, et al.
Pubblicazione: (2024)

Modeling Cross-vision Synergy for Unified Large Vision Model
di: Wu, Shengqiong, et al.
Pubblicazione: (2026)

Active Zero: Self-Evolving Vision-Language Models through Active Environment Exploration
di: He, Jinghan, et al.
Pubblicazione: (2026)

NExT-GPT: Any-to-Any Multimodal LLM
di: Wu, Shengqiong, et al.
Pubblicazione: (2023)

Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs
di: Fei, Hao, et al.
Pubblicazione: (2023)

Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning
di: Qian, Long, et al.
Pubblicazione: (2024)

Can Large Language Models Derive New Knowledge? A Dynamic Benchmark for Biological Knowledge Discovery
di: Yang, Chaoqun, et al.
Pubblicazione: (2026)

Who Transfers Safety? Identifying and Targeting Cross-Lingual Shared Safety Neurons
di: Zhang, Xianhui, et al.
Pubblicazione: (2026)

G2S: A General-to-Specific Learning Framework for Temporal Knowledge Graph Forecasting with Large Language Models
di: Bai, Long, et al.
Pubblicazione: (2025)

Thinking with Blueprints: Assisting Vision-Language Models in Spatial Reasoning via Structured Object Representation
di: Ma, Weijian, et al.
Pubblicazione: (2026)

Reasoning-VLA: A Fast and General Vision-Language-Action Reasoning Model for Autonomous Driving
di: Zhang, Dapeng, et al.
Pubblicazione: (2025)

Integrate Temporal Graph Learning into LLM-based Temporal Knowledge Graph Model
di: Chang, He, et al.
Pubblicazione: (2025)

XNLP: An Interactive Demonstration System for Universal Structured NLP
di: Fei, Hao, et al.
Pubblicazione: (2023)

Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models
di: Liang, Xiao, et al.
Pubblicazione: (2025)

Knowledge Boundary of Large Language Models: A Survey
di: Li, Moxin, et al.
Pubblicazione: (2024)

Unveiling Latent Knowledge in Chemistry Language Models through Sparse Autoencoders
di: Cohen, Jaron, et al.
Pubblicazione: (2025)

Global Commander and Local Operative: A Dual-Agent Framework for Scene Navigation
di: Jin, Kaiming, et al.
Pubblicazione: (2026)

Large Language Models Empowered Personalized Web Agents
di: Cai, Hongru, et al.
Pubblicazione: (2024)

Decoding in Latent Spaces for Efficient Inference in LLM-based Recommendation
di: Wang, Chengbing, et al.
Pubblicazione: (2025)

InstructVid2Vid: Controllable Video Editing with Natural Language Instructions
di: Qin, Bosheng, et al.
Pubblicazione: (2023)

Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models
di: Wu, Jialin, et al.
Pubblicazione: (2026)

Towards Semantic Equivalence of Tokenization in Multimodal LLM
di: Wu, Shengqiong, et al.
Pubblicazione: (2024)

NextMem: Towards Latent Factual Memory for LLM-based Agents
di: Zhang, Zeyu, et al.
Pubblicazione: (2026)