Cover Image

Beyond Intermediate States: Explaining Visual Redundancy through Language

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Dingchen, Cao, Bowen, Zhang, Anran, Gu, Weibo, Hu, Winston, Chen, Guang
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

BabyVision: Visual Reasoning Beyond Language
by: Chen, Liang, et al.
Published: (2026)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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