Cover Image

Vision Remember: Recovering Visual Information in Efficient LVLM with Vision Feature Resampling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Feng, Ze, Liu, Jiang-jiang, Yang, Sen, Xiao, Lingyu, Quan, Zhibin, Feng, Zhenhua, Yang, Wankou, Wang, Jingdong
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

EM-KD: Distilling Efficient Multimodal Large Language Model with Unbalanced Vision Tokens
by: Feng, Ze, et al.
Published: (2025)

Improving Generalized Visual Grounding with Instance-aware Joint Learning
by: Dai, Ming, et al.
Published: (2025)

PropVG: End-to-End Proposal-Driven Visual Grounding with Multi-Granularity Discrimination
by: Dai, Ming, et al.
Published: (2025)

Drone Referring Localization: An Efficient Heterogeneous Spatial Feature Interaction Method For UAV Self-Localization
by: Dai, Ming, et al.
Published: (2022)

Revisiting MLLMs: An In-Depth Analysis of Image Classification Abilities
by: Liu, Huan, et al.
Published: (2024)

SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion
by: Dai, Ming, et al.
Published: (2024)

MomentSeg: Moment-Centric Sampling for Enhanced Video Pixel Understanding
by: Dai, Ming, et al.
Published: (2025)

DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy
by: Dai, Ming, et al.
Published: (2025)

VALD: Multi-Stage Vision Attack Detection for Efficient LVLM Defense
by: Kadvil, Nadav, et al.
Published: (2026)

Resampling Benchmark for Efficient Comprehensive Evaluation of Large Vision-Language Models
by: Suzuki, Teppei, et al.
Published: (2025)

Vision-TTT: Efficient and Expressive Visual Representation Learning with Test-Time Training
by: Kong, Quan, et al.
Published: (2026)

Object-level Geometric Structure Preserving for Natural Image Stitching
by: Cai, Wenxiao, et al.
Published: (2024)

LVLM-Interpret: An Interpretability Tool for Large Vision-Language Models
by: Stan, Gabriela Ben Melech, et al.
Published: (2024)

VoxelSplat: Dynamic Gaussian Splatting as an Effective Loss for Occupancy and Flow Prediction
by: Zhu, Ziyue, et al.
Published: (2025)

SpatialBot: Precise Spatial Understanding with Vision Language Models
by: Cai, Wenxiao, et al.
Published: (2024)

DASViT: Differentiable Architecture Search for Vision Transformer
by: Wu, Pengjin, et al.
Published: (2025)

Beyond Visual Field of View: Perceiving 3D Environment with Echoes and Vision
by: Zhu, Lingyu, et al.
Published: (2022)

LVLM-Aided Alignment of Task-Specific Vision Models
by: Koebler, Alexander, et al.
Published: (2025)

Dynamic Embedding of Hierarchical Visual Features for Efficient Vision-Language Fine-Tuning
by: Wei, Xinyu, et al.
Published: (2025)

VIP: Visual-guided Prompt Evolution for Efficient Dense Vision-Language Inference
by: Zhu, Hao, et al.
Published: (2026)

LVLM_CSP: Accelerating Large Vision Language Models via Clustering, Scattering, and Pruning for Reasoning Segmentation
by: Chen, Hanning, et al.
Published: (2025)

Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-Text Matching
by: Liu, Yang, et al.
Published: (2025)

XDR-LVLM: An Explainable Vision-Language Large Model for Diabetic Retinopathy Diagnosis
by: Ito, Masato, et al.
Published: (2025)

Recov-Vision: Linking Street View Imagery and Vision-Language Models for Post-Disaster Recovery
by: Xiao, Yiming, et al.
Published: (2025)

Before Forgetting, Learn to Remember: Revisiting Foundational Learning Failures in LVLM Unlearning Benchmarks
by: Kwon, JuneHyoung, et al.
Published: (2026)

SFFR: Spatial-Frequency Feature Reconstruction for Multispectral Aerial Object Detection
by: Zuo, Xin, et al.
Published: (2025)

Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling
by: Wu, Tsung-Han, et al.
Published: (2025)

Fooling the LVLM Judges: Visual Biases in LVLM-Based Evaluation
by: Hwang, Yerin, et al.
Published: (2025)

Improving underwater semantic segmentation with underwater image quality attention and muti-scale aggregation attention
by: Zuo, Xin, et al.
Published: (2025)

TinyLVLM-eHub: Towards Comprehensive and Efficient Evaluation for Large Vision-Language Models
by: Shao, Wenqi, et al.
Published: (2023)

Short-LVLM: Compressing and Accelerating Large Vision-Language Models by Pruning Redundant Layers
by: Ma, Ji, et al.
Published: (2025)

PA-Attack: Guiding Gray-Box Attacks on LVLM Vision Encoders with Prototypes and Attention
by: Mei, Hefei, et al.
Published: (2026)

Quantized Prompt for Efficient Generalization of Vision-Language Models
by: Hao, Tianxiang, et al.
Published: (2024)

LVLM-COUNT: Enhancing the Counting Ability of Large Vision-Language Models
by: Qharabagh, Muhammad Fetrat, et al.
Published: (2024)

Hierarchical Cross-modal Prompt Learning for Vision-Language Models
by: Zheng, Hao, et al.
Published: (2025)

EVLM: An Efficient Vision-Language Model for Visual Understanding
by: Chen, Kaibing, et al.
Published: (2024)

Revisit What You See: Revealing Visual Semantics in Vision Tokens to Guide LVLM Decoding
by: Cho, Beomsik, et al.
Published: (2025)

Efficient Modulation for Vision Networks
by: Ma, Xu, et al.
Published: (2024)

Asymmetric Visual Semantic Embedding Framework for Efficient Vision-Language Alignment
by: Liu, Yang, et al.
Published: (2025)

ID-Selection: Importance-Diversity Based Visual Token Selection for Efficient LVLM Inference
by: Huang, Zhaohong, et al.
Published: (2026)