Copertina

Causal Probing for Internal Visual Representations in Multimodal Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Deng, Zehao, Ju, Tianjie, Wu, Zheng, He, Liangbo, Lan, Jun, Zhu, Huijia, Wang, Weiqiang, Zhang, Zhuosheng
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Training High-Level Schedulers with Execution-Feedback Reinforcement Learning for Long-Horizon GUI Automation
di: Deng, Zehao, et al.
Pubblicazione: (2025)

Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
di: Wei, Lai, et al.
Pubblicazione: (2026)

HoneyTrap: Deceiving Large Language Model Attackers to Honeypot Traps with Resilient Multi-Agent Defense
di: Li, Siyuan, et al.
Pubblicazione: (2026)

Disagreements in Reasoning: How a Model's Thinking Process Dictates Persuasion in Multi-Agent Systems
di: Zhao, Haodong, et al.
Pubblicazione: (2025)

Smoothing Grounding and Reasoning for MLLM-Powered GUI Agents with Query-Oriented Pivot Tasks
di: Wu, Zongru, et al.
Pubblicazione: (2025)

InsightVision: A Comprehensive, Multi-Level Chinese-based Benchmark for Evaluating Implicit Visual Semantics in Large Vision Language Models
di: Yin, Xiaofei, et al.
Pubblicazione: (2025)

Dynamic Generation of Personalities with Large Language Models
di: Liu, Jianzhi, et al.
Pubblicazione: (2024)

See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles
di: Wu, Zongru, et al.
Pubblicazione: (2025)

Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models
di: Liu, Yanjiang, et al.
Pubblicazione: (2025)

Probing Multimodal Large Language Models for Global and Local Semantic Representations
di: Tao, Mingxu, et al.
Pubblicazione: (2024)

NSmark: Null Space Based Black-box Watermarking Defense Framework for Language Models
di: Zhao, Haodong, et al.
Pubblicazione: (2024)

Probing Causality Manipulation of Large Language Models
di: Zhang, Chenyang, et al.
Pubblicazione: (2024)

Causality for Large Language Models
di: Wu, Anpeng, et al.
Pubblicazione: (2024)

When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models
di: Liu, Ziyu, et al.
Pubblicazione: (2026)

Revealing Multimodal Causality with Large Language Models
di: Li, Jin, et al.
Pubblicazione: (2025)

CausalVLBench: Benchmarking Visual Causal Reasoning in Large Vision-Language Models
di: Komanduri, Aneesh, et al.
Pubblicazione: (2025)

Causal-LLaVA: Causal Disentanglement for Mitigating Hallucination in Multimodal Large Language Models
di: Hu, Xinmiao, et al.
Pubblicazione: (2025)

Unleashing the Intrinsic Visual Representation Capability of Multimodal Large Language Models
di: Li, Hengzhuang, et al.
Pubblicazione: (2025)

ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
di: Ni, Jingwei, et al.
Pubblicazione: (2025)

Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Models
di: Liu, Shuodi, et al.
Pubblicazione: (2025)

Interpretable and Reliable Detection of AI-Generated Images via Grounded Reasoning in MLLMs
di: Ji, Yikun, et al.
Pubblicazione: (2025)

Exploring the Transferability of Visual Prompting for Multimodal Large Language Models
di: Zhang, Yichi, et al.
Pubblicazione: (2024)

Taxonomy-Aware Representation Alignment for Hierarchical Visual Recognition with Large Multimodal Models
di: He, Hulingxiao, et al.
Pubblicazione: (2026)

Generalizable Chain-of-Thought Prompting in Mixed-task Scenarios with Large Language Models
di: Zou, Anni, et al.
Pubblicazione: (2023)

Self-Prompting Large Language Models for Zero-Shot Open-Domain QA
di: Li, Junlong, et al.
Pubblicazione: (2022)

OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models
di: Zheng, Hao, et al.
Pubblicazione: (2025)

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images
di: Ji, Yikun, et al.
Pubblicazione: (2025)

ChemVTS-Bench: Evaluating Visual-Textual-Symbolic Reasoning of Multimodal Large Language Models in Chemistry
di: Huang, Zhiyuan, et al.
Pubblicazione: (2025)

NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models
di: Zhang, Chuhan, et al.
Pubblicazione: (2025)

Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoning
di: Tan, Hao, et al.
Pubblicazione: (2025)

Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining
di: Wu, Zongru, et al.
Pubblicazione: (2024)

Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models
di: Li, Kunhao, et al.
Pubblicazione: (2025)

Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning
di: Chen, Junkai, et al.
Pubblicazione: (2026)

VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models
di: Zhu, Zihao, et al.
Pubblicazione: (2023)

Efficient Detection of Toxic Prompts in Large Language Models
di: Liu, Yi, et al.
Pubblicazione: (2024)

A Survey of Hallucination in Large Visual Language Models
di: Lan, Wei, et al.
Pubblicazione: (2024)

Internalized Self-Correction for Large Language Models
di: Upadhyaya, Nishanth, et al.
Pubblicazione: (2024)

Exploring Multimodal Prompt for Visualization Authoring with Large Language Models
di: Wen, Zhen, et al.
Pubblicazione: (2025)

Benchmarking the Thinking Mode of Multimodal Large Language Models in Clinical Tasks
di: Hong, Jindong, et al.
Pubblicazione: (2025)

MEGen: Generative Backdoor into Large Language Models via Model Editing
di: Qiu, Jiyang, et al.
Pubblicazione: (2024)