Copertina

Where Does Vision Meet Language? Understanding and Refining Visual Fusion in MLLMs via Contrastive Attention

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Song, Shezheng, Li, Shasha, Yu, Jie
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Multimedia
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Seeing Right but Saying Wrong: Inter- and Intra-Layer Refinement in MLLMs without Training
di: Song, Shezheng, et al.
Pubblicazione: (2026)

How to Bridge the Gap between Modalities: Survey on Multimodal Large Language Model
di: Song, Shezheng, et al.
Pubblicazione: (2023)

TextRefiner: Internal Visual Feature as Efficient Refiner for Vision-Language Models Prompt Tuning
di: Xie, Jingjing, et al.
Pubblicazione: (2024)

Visual Semantic Description Generation with MLLMs for Image-Text Matching
di: Chen, Junyu, et al.
Pubblicazione: (2025)

Hierarchical Refinement of Universal Multimodal Attacks on Vision-Language Models
di: Zhang, Peng-Fei, et al.
Pubblicazione: (2026)

TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning
di: Zeng, Xiangyu, et al.
Pubblicazione: (2024)

Cross-Attention Fusion of Visual and Geometric Features for Large Vocabulary Arabic Lipreading
di: Daou, Samar, et al.
Pubblicazione: (2024)

PixCLIP: Achieving Fine-grained Visual Language Understanding via Any-granularity Pixel-Text Alignment Learning
di: Xiao, Yicheng, et al.
Pubblicazione: (2025)

Bi-VLDoc: Bidirectional Vision-Language Modeling for Visually-Rich Document Understanding
di: Luo, Chuwei, et al.
Pubblicazione: (2022)

Segmentation-Based Attention Entropy: Detecting and Mitigating Object Hallucinations in Large Vision-Language Models
di: Song, Jiale, et al.
Pubblicazione: (2026)

X-Former: Unifying Contrastive and Reconstruction Learning for MLLMs
di: Swetha, Sirnam, et al.
Pubblicazione: (2024)

SMSP: A Plug-and-Play Strategy of Multi-Scale Perception for MLLMs to Perceive Visual Illusions
di: Tu, Jinzhe, et al.
Pubblicazione: (2026)

Joint Flow And Feature Refinement Using Attention For Video Restoration
di: Merugu, Ranjith, et al.
Pubblicazione: (2025)

Where to Focus: Query-Modulated Multimodal Keyframe Selection for Long Video Understanding
di: Wang, Shaoguang, et al.
Pubblicazione: (2026)

Enhancing Vision-Language Tracking by Effectively Converting Textual Cues into Visual Cues
di: Feng, X., et al.
Pubblicazione: (2024)

Spatial-Aware Efficient Projector for MLLMs via Multi-Layer Feature Aggregation
di: Qian, Shun, et al.
Pubblicazione: (2024)

Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration
di: Fazli, Mehrdad, et al.
Pubblicazione: (2025)

Spatio-Temporal Data Enhanced Vision-Language Model for Traffic Scene Understanding
di: Ma, Jingtian, et al.
Pubblicazione: (2025)

POINTS1.5: Building a Vision-Language Model towards Real World Applications
di: Liu, Yuan, et al.
Pubblicazione: (2024)

Instruction-Grounded Visual Projectors for Continual Learning of Generative Vision-Language Models
di: Jin, Hyundong, et al.
Pubblicazione: (2025)

Emotion-Qwen: A Unified Framework for Emotion and Vision Understanding
di: Huang, Dawei, et al.
Pubblicazione: (2025)

Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment
di: Shan, Ziyu, et al.
Pubblicazione: (2024)

VidCompress: Memory-Enhanced Temporal Compression for Video Understanding in Large Language Models
di: Lan, Xiaohan, et al.
Pubblicazione: (2024)

Learning Contrastive Self-Distillation for Ultra-Fine-Grained Visual Categorization Targeting Limited Samples
di: Fang, Ziye, et al.
Pubblicazione: (2023)

SynthDoc: Bilingual Documents Synthesis for Visual Document Understanding
di: Ding, Chuanghao, et al.
Pubblicazione: (2024)

Linguistics-Vision Monotonic Consistent Network for Sign Language Production
di: Wang, Xu, et al.
Pubblicazione: (2024)

MLANet: Multi-Level Attention Network with Sub-instruction for Continuous Vision-and-Language Navigation
di: He, Zongtao, et al.
Pubblicazione: (2023)

G-Refine: A General Quality Refiner for Text-to-Image Generation
di: Li, Chunyi, et al.
Pubblicazione: (2024)

Language-Guided Diffusion Model for Visual Grounding
di: Chen, Sijia, et al.
Pubblicazione: (2023)

When Video Coding Meets Multimodal Large Language Models: A Unified Paradigm for Video Coding
di: Zhang, Pingping, et al.
Pubblicazione: (2024)

Scaling up Multimodal Pre-training for Sign Language Understanding
di: Zhou, Wengang, et al.
Pubblicazione: (2024)

Hierarchical Action Recognition: A Contrastive Video-Language Approach with Hierarchical Interactions
di: Zhang, Rui, et al.
Pubblicazione: (2024)

Unveiling Encoder-Free Vision-Language Models
di: Diao, Haiwen, et al.
Pubblicazione: (2024)

VAAS: Vision-Attention Anomaly Scoring for Image Manipulation Detection in Digital Forensics
di: Bamigbade, Opeyemi, et al.
Pubblicazione: (2025)

VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification
di: Meng, Jiahao, et al.
Pubblicazione: (2026)

Mitigating Image Captioning Hallucinations in Vision-Language Models
di: Zhao, Fei, et al.
Pubblicazione: (2025)

CalliReader: Contextualizing Chinese Calligraphy via an Embedding-Aligned Vision-Language Model
di: Luo, Yuxuan, et al.
Pubblicazione: (2025)

Cross-modal Proxy Evolving for OOD Detection with Vision-Language Models
di: Tang, Hao, et al.
Pubblicazione: (2026)

CASR: Refining Action Segmentation via Marginalizing Frame-levle Causal Relationships
di: Du, Keqing, et al.
Pubblicazione: (2023)

Zero-Shot Character Identification and Speaker Prediction in Comics via Iterative Multimodal Fusion
di: Li, Yingxuan, et al.
Pubblicazione: (2024)