Buchumschlag

Interpreting and Enhancing Emotional Circuits in Large Vision-Language Models via Cross-Modal Information Flow

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Zhang, Chengsheng, Sun, Chenghao, Xie, Zhining, Tian, Xinmei
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computer Vision and Pattern Recognition Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models
von: Zhang, Chengsheng, et al.
Veröffentlicht: (2026)

Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models
von: Che, Liwei, et al.
Veröffentlicht: (2026)

GLIMPSE: Holistic Cross-Modal Explainability for Large Vision-Language Models
von: Shen, Guanxi
Veröffentlicht: (2025)

Cross-Layer Vision Smoothing: Enhancing Visual Understanding via Sustained Focus on Key Objects in Large Vision-Language Models
von: Zhao, Jianfei, et al.
Veröffentlicht: (2025)

Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models
von: Kim, Jinyeong, et al.
Veröffentlicht: (2025)

GeoVLMath: Enhancing Geometry Reasoning in Vision-Language Models via Cross-Modal Reward for Auxiliary Line Creation
von: Guo, Shasha, et al.
Veröffentlicht: (2025)

AddressVLM: Cross-view Alignment Tuning for Image Address Localization using Large Vision-Language Models
von: Xu, Shixiong, et al.
Veröffentlicht: (2025)

Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language Models
von: Yan, Hanqi, et al.
Veröffentlicht: (2025)

Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models
von: Zhong, Yi, et al.
Veröffentlicht: (2026)

Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models
von: Xu, Shicheng, et al.
Veröffentlicht: (2024)

DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models
von: Zhang, Yudong, et al.
Veröffentlicht: (2024)

Large Vision-Language Models as Emotion Recognizers in Context Awareness
von: Lei, Yuxuan, et al.
Veröffentlicht: (2024)

MBQ: Modality-Balanced Quantization for Large Vision-Language Models
von: Li, Shiyao, et al.
Veröffentlicht: (2024)

Enhancing Interpretability for Vision Models via Shapley Value Optimization
von: Fan, Kanglong, et al.
Veröffentlicht: (2025)

SPARC: Concept-Aligned Sparse Autoencoders for Cross-Model and Cross-Modal Interpretability
von: Nasiri-Sarvi, Ali, et al.
Veröffentlicht: (2025)

Enhancing Medical Large Vision-Language Models via Alignment Distillation
von: Chang, Aofei, et al.
Veröffentlicht: (2025)

GPT-4 Enhanced Multimodal Grounding for Autonomous Driving: Leveraging Cross-Modal Attention with Large Language Models
von: Liao, Haicheng, et al.
Veröffentlicht: (2023)

Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model
von: Feng, Qianhan, et al.
Veröffentlicht: (2024)

Cross-modal Information Flow in Multimodal Large Language Models
von: Zhang, Zhi, et al.
Veröffentlicht: (2024)

PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questions
von: Zhang, Yudong, et al.
Veröffentlicht: (2024)

From Captions to Rewards (CAREVL): Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models
von: Dai, Muzhi, et al.
Veröffentlicht: (2025)

Cross-Modal Attention Analysis and Optimization in Vision-Language Models: A Study on Visual Reliability
von: Zhou, Lijie
Veröffentlicht: (2026)

CapRecover: A Cross-Modality Feature Inversion Attack Framework on Vision Language Models
von: Xiu, Kedong, et al.
Veröffentlicht: (2025)

QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models
von: Zhang, Yudong, et al.
Veröffentlicht: (2025)

Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement
von: Wang, Xiyao, et al.
Veröffentlicht: (2024)

V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization
von: Xie, Yuxi, et al.
Veröffentlicht: (2024)

Multimodal Emotion Recognition with Vision-language Prompting and Modality Dropout
von: QI, Anbin, et al.
Veröffentlicht: (2024)

FlowLearn: Evaluating Large Vision-Language Models on Flowchart Understanding
von: Pan, Huitong, et al.
Veröffentlicht: (2024)

Seeing is Believing: Robust Vision-Guided Cross-Modal Prompt Learning under Label Noise
von: Geng, Zibin, et al.
Veröffentlicht: (2026)

Cross-Modal Adapter for Vision-Language Retrieval
von: Jiang, Haojun, et al.
Veröffentlicht: (2022)

ViSA-Enhanced Aerial VLN: A Visual-Spatial Reasoning Enhanced Framework for Aerial Vision-Language Navigation
von: Tong, Haoyu, et al.
Veröffentlicht: (2026)

AnalogRetriever: Learning Cross-Modal Representations for Analog Circuit Retrieval
von: Wang, Yihan, et al.
Veröffentlicht: (2026)

FOCA: Frequency-Oriented Cross-Domain Forgery Detection, Localization and Explanation via Multi-Modal Large Language Model
von: Liu, Zhou, et al.
Veröffentlicht: (2026)

FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models
von: Tong, Jintao, et al.
Veröffentlicht: (2025)

CRFT: Consistent-Recurrent Feature Flow Transformer for Cross-Modal Image Registration
von: Liu, Xuecong, et al.
Veröffentlicht: (2026)

Interpretable Debiasing of Vision-Language Models for Social Fairness
von: An, Na Min, et al.
Veröffentlicht: (2026)

Large Vision-Language Models Get Lost in Attention
von: Xi, Gongli, et al.
Veröffentlicht: (2026)

XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models
von: Wang, Xingrui, et al.
Veröffentlicht: (2025)

How Do Vision-Language Models Process Conflicting Information Across Modalities?
von: Hua, Tianze, et al.
Veröffentlicht: (2025)

MM-MoralBench: A MultiModal Moral Evaluation Benchmark for Large Vision-Language Models
von: Yan, Bei, et al.
Veröffentlicht: (2024)