Cover Image

Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liao, Chenfei, Wang, Wensong, Wen, Zichen, Zheng, Xu, Wang, Yiyu, He, Haocong, Lyu, Yuanhuiyi, Jiang, Lutao, Zou, Xin, Fu, Yuqian, Ren, Bin, Zhang, Linfeng, Hu, Xuming
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

AI for Service: Proactive Assistance with AI Glasses
by: Wen, Zichen, et al.
Published: (2025)

Understanding-in-Generation: Reinforcing Generative Capability of Unified Model via Infusing Understanding into Generation
by: Lyu, Yuanhuiyi, et al.
Published: (2025)

Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention
by: Zou, Xin, et al.
Published: (2025)

RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning
by: Lyu, Yuanhuiyi, et al.
Published: (2025)

Accelerating Streaming Video Large Language Models via Hierarchical Token Compression
by: Wang, Yiyu, et al.
Published: (2025)

Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?
by: Wen, Zichen, et al.
Published: (2025)

MAGIC++: Efficient and Resilient Modality-Agnostic Semantic Segmentation via Hierarchical Modality Selection
by: Zheng, Xu, et al.
Published: (2024)

OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation
by: Zhong, Ding, et al.
Published: (2025)

Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks
by: Zheng, Xu, et al.
Published: (2025)

PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era
by: Zheng, Xu, et al.
Published: (2025)

MLLMs are Deeply Affected by Modality Bias
by: Zheng, Xu, et al.
Published: (2025)

Shifting AI Efficiency From Model-Centric to Data-Centric Compression
by: Liu, Xuyang, et al.
Published: (2025)

MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation
by: Liao, Chenfei, et al.
Published: (2025)

Learning Robust Anymodal Segmentor with Unimodal and Cross-modal Distillation
by: Zheng, Xu, et al.
Published: (2024)

Reducing Unimodal Bias in Multi-Modal Semantic Segmentation with Multi-Scale Functional Entropy Regularization
by: Zheng, Xu, et al.
Published: (2025)

BrightDreamer: Generic 3D Gaussian Generative Framework for Fast Text-to-3D Synthesis
by: Jiang, Lutao, et al.
Published: (2024)

A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges
by: Yan, Yibo, et al.
Published: (2024)

EgoIntent: An Egocentric Step-level Benchmark for Understanding What, Why, and Next
by: Pan, Ye, et al.
Published: (2026)

StruVis: Enhancing Reasoning-based Text-to-Image Generation via Thinking with Structured Vision
by: Lyu, Yuanhuiyi, et al.
Published: (2026)

Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlook
by: Zheng, Xu, et al.
Published: (2025)

SpeCa: Accelerating Diffusion Transformers with Speculative Feature Caching
by: Liu, Jiacheng, et al.
Published: (2025)

From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers
by: Liu, Jiacheng, et al.
Published: (2025)

T-Rex-Omni: Integrating Negative Visual Prompt in Generic Object Detection
by: Zhou, Jiazhou, et al.
Published: (2025)

SAVEn-Vid: Synergistic Audio-Visual Integration for Enhanced Understanding in Long Video Context
by: Li, Jungang, et al.
Published: (2024)

EvoStreaming: Your Offline Video Model Is a Natively Streaming Assistant
by: Wen, Zichen, et al.
Published: (2026)

CompoNeRF: Text-guided Multi-object Compositional NeRF with Editable 3D Scene Layout
by: Bai, Haotian, et al.
Published: (2023)

Variation-aware Vision Token Dropping for Faster Large Vision-Language Models
by: Chen, Junjie, et al.
Published: (2025)

VideoCompressa: Data-Efficient Video Understanding via Joint Temporal Compression and Spatial Reconstruction
by: Wang, Shaobo, et al.
Published: (2025)

StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding
by: Wang, Junxi, et al.
Published: (2026)

Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models
by: Liu, Xuyang, et al.
Published: (2025)

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders
by: Li, Teng, et al.
Published: (2026)

EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models
by: Yang, Yantai, et al.
Published: (2025)

PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs
by: Zhang, Zixin, et al.
Published: (2025)

Flash-Unified: A Training-Free and Task-Aware Acceleration Framework for Native Unified Models
by: Ke, Junlong, et al.
Published: (2026)

MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models
by: Huo, Jiahao, et al.
Published: (2025)

Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models
by: Han, Yuhang, et al.
Published: (2026)

Token Coordinated Prompt Attention is Needed for Visual Prompting
by: Liu, Zichen, et al.
Published: (2025)

Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalities
by: Zheng, Xu, et al.
Published: (2024)

Image Anything: Towards Reasoning-coherent and Training-free Multi-modal Image Generation
by: Lyu, Yuanhuiyi, et al.
Published: (2024)

IPCV: Information-Preserving Compression for MLLM Visual Encoders
by: Chen, Yuan, et al.
Published: (2025)