Copertina

Beyond Intermediate States: Explaining Visual Redundancy through Language

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yang, Dingchen, Cao, Bowen, Zhang, Anran, Gu, Weibo, Hu, Winston, Chen, Guang
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Pensieve: Retrospect-then-Compare Mitigates Visual Hallucination
di: Yang, Dingchen, et al.
Pubblicazione: (2024)

Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction
di: Jian, Yiren, et al.
Pubblicazione: (2023)

FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers
di: Zhang, Renshan, et al.
Pubblicazione: (2025)

A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models
di: Li, Duo, et al.
Pubblicazione: (2025)

RedundancyLens: Revealing and Exploiting Visual Token Processing Redundancy for Efficient Decoder-Only MLLMs
di: Li, Hongliang, et al.
Pubblicazione: (2025)

Extracting Visual Facts from Intermediate Layers for Mitigating Hallucinations in Multimodal Large Language Models
di: Zhou, Haoran, et al.
Pubblicazione: (2025)

Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models
di: Dong, Yuhao, et al.
Pubblicazione: (2024)

Color-Oriented Redundancy Reduction in Dataset Distillation
di: Yuan, Bowen, et al.
Pubblicazione: (2024)

PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
di: Xing, Long, et al.
Pubblicazione: (2024)

Transfer Attack for Bad and Good: Explain and Boost Adversarial Transferability across Multimodal Large Language Models
di: Cheng, Hao, et al.
Pubblicazione: (2024)

ViC-Bench: Benchmarking Visual-Interleaved Chain-of-Thought Capability in MLLMs with Free-Style Intermediate State Representations
di: Wu, Xuecheng, et al.
Pubblicazione: (2025)

dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model
di: Li, Yumeng, et al.
Pubblicazione: (2025)

MFil-Mamba: Multi-Filter Scanning for Spatial Redundancy-Aware Visual State Space Models
di: Khadka, Puskal, et al.
Pubblicazione: (2026)

LWGANet: Addressing Spatial and Channel Redundancy in Remote Sensing Visual Tasks with Light-Weight Grouped Attention
di: Lu, Wei, et al.
Pubblicazione: (2025)

Beyond Visual Cues: Synchronously Exploring Target-Centric Semantics for Vision-Language Tracking
di: Ge, Jiawei, et al.
Pubblicazione: (2023)

Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy
di: Yang, Te, et al.
Pubblicazione: (2024)

Efficient Redundancy Reduction for Open-Vocabulary Semantic Segmentation
di: Chen, Lin, et al.
Pubblicazione: (2025)

AdaFV: Rethinking of Visual-Language alignment for VLM acceleration
di: Han, Jiayi, et al.
Pubblicazione: (2025)

Beyond the Visible: Disocclusion-Aware Editing via Proxy Dynamic Graphs
di: Qi, Anran, et al.
Pubblicazione: (2025)

Language Models Can See Better: Visual Contrastive Decoding For LLM Multimodal Reasoning
di: Pang, Yuqi, et al.
Pubblicazione: (2025)

BabyVision: Visual Reasoning Beyond Language
di: Chen, Liang, et al.
Pubblicazione: (2026)

Taming the Entropy Cliff: Variable Codebook Size Quantization for Autoregressive Visual Generation
di: Zheng, Bowen, et al.
Pubblicazione: (2026)

Rolling Shutter Correction with Intermediate Distortion Flow Estimation
di: Cao, Mingdeng, et al.
Pubblicazione: (2024)

Video-Language Alignment via Spatio-Temporal Graph Transformer
di: Zhang, Shi-Xue, et al.
Pubblicazione: (2024)

VIHD: Visual Intervention-based Hallucination Detection for Medical Visual Question Answering
di: Chen, Jiayi, et al.
Pubblicazione: (2026)

EmoSEM: Segment and Explain Emotion Stimuli in Visual Art
di: Zhang, Jing, et al.
Pubblicazione: (2025)

Beyond Degradation Redundancy: Contrastive Prompt Learning for All-in-One Image Restoration
di: Wu, Gang, et al.
Pubblicazione: (2025)

Seeing Beyond Redundancy: Task Complexity's Role in Vision Token Specialization in VLLMs
di: Hannan, Darryl, et al.
Pubblicazione: (2026)

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos
di: Yao, Linli, et al.
Pubblicazione: (2025)

Discovering Intrinsic Spatial-Temporal Logic Rules to Explain Human Actions
di: Cao, Chengzhi, et al.
Pubblicazione: (2023)

FontCLIP: A Semantic Typography Visual-Language Model for Multilingual Font Applications
di: Tatsukawa, Yuki, et al.
Pubblicazione: (2024)

VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies
di: Gao, Mingjian, et al.
Pubblicazione: (2026)

Investigating Redundancy in Multimodal Large Language Models with Multiple Vision Encoders
di: Wang, Yizhou, et al.
Pubblicazione: (2025)

Enhancing Targeted Adversarial Attacks on Large Vision-Language Models via Intermediate Projector
di: Cao, Yiming, et al.
Pubblicazione: (2025)

GAIS: Frame-Level Gated Audio-Visual Integration with Semantic Variance-Scaled Perturbation for Text-Video Retrieval
di: Yang, Bowen, et al.
Pubblicazione: (2025)

Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models
di: You, Zhiyuan, et al.
Pubblicazione: (2023)

Explaining Representation by Mutual Information
di: Gu, Lifeng
Pubblicazione: (2021)

VAEVQ: Enhancing Discrete Visual Tokenization through Variational Modeling
di: Yang, Sicheng, et al.
Pubblicazione: (2025)

Language Models Can Explain Visual Features via Steering
di: Ferrando, Javier, et al.
Pubblicazione: (2026)

Learning to Rank Patches for Unbiased Image Redundancy Reduction
di: Luo, Yang, et al.
Pubblicazione: (2024)