Cover Image

Towards Efficient Vision State Space Models via Token Merging

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Park, Jinyoung, Son, Minseok, Kim, Changick
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

Difficulty-aware Balancing Margin Loss for Long-tailed Recognition
by: Son, Minseok, et al.
Published: (2024)

VideoMamba: Spatio-Temporal Selective State Space Model
by: Park, Jinyoung, et al.
Published: (2024)

Efficient Test-Time Optimization for Depth Completion via Low-Rank Decoder Adaptation
by: Seo, Minseok, et al.
Published: (2026)

Station2Radar: query conditioned gaussian splatting for precipitation field
by: Kim, Doyi, et al.
Published: (2026)

Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling
by: Seo, Minseok, et al.
Published: (2025)

Detecting AI-Generated Images via Contextual Anomaly Estimation in Masked AutoEncoders
by: Jang, Minsuk, et al.
Published: (2025)

TCP-SSM: Efficient Vision State Space Models with Token-Conditioned Poles
by: Shoouri, Sara, et al.
Published: (2026)

Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers
by: Lee, Dong Hoon, et al.
Published: (2024)

Vision SmolMamba: Spike-Guided Token Pruning for Energy-Efficient Spiking State-Space Vision Models
by: Bai, Dewei, et al.
Published: (2026)

Doubly-Universal Adversarial Perturbations: Deceiving Vision-Language Models Across Both Images and Text with a Single Perturbation
by: Kim, Hee-Seon, et al.
Published: (2024)

MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
by: Zhang, Luyuan, et al.
Published: (2026)

Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models
by: Woo, Sangmin, et al.
Published: (2024)

HalLoc: Token-level Localization of Hallucinations for Vision Language Models
by: Park, Eunkyu, et al.
Published: (2025)

Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation
by: Park, Dogyun, et al.
Published: (2025)

MoE-GRPO: Optimizing Mixture-of-Experts via Reinforcement Learning in Vision-Language Models
by: Ko, Dohwan, et al.
Published: (2026)

Bridging Implicit and Explicit Geometric Transformation for Single-Image View Synthesis
by: Park, Byeongjun, et al.
Published: (2022)

Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection
by: Kim, Jongha, et al.
Published: (2024)

Sequential Token Merging: Revisiting Hidden States
by: Wen, Yan, et al.
Published: (2025)

Prompt Learning via Meta-Regularization
by: Park, Jinyoung, et al.
Published: (2024)

DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO
by: Park, Jinyoung, et al.
Published: (2025)

BEEP3D: Box-Supervised End-to-End Pseudo-Mask Generation for 3D Instance Segmentation
by: Yoo, Youngju, et al.
Published: (2025)

ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation with Plain Vision Transformers
by: Norouzi, Narges, et al.
Published: (2024)

Diffusion Model Patching via Mixture-of-Prompts
by: Ham, Seokil, et al.
Published: (2024)

Flow-Assisted Motion Learning Network for Weakly-Supervised Group Activity Recognition
by: Nugroho, Muhammad Adi, et al.
Published: (2024)

RITUAL: Random Image Transformations as a Universal Anti-hallucination Lever in Large Vision Language Models
by: Woo, Sangmin, et al.
Published: (2024)

Token-Space Mask Prediction for Efficient Vision Transformer Segmentation
by: Galagain, Calvin, et al.
Published: (2026)

SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis
by: Go, Hyojun, et al.
Published: (2024)

EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality
by: Lee, Sanghyeok, et al.
Published: (2024)

Lossless Token Merging Even Without Fine-Tuning in Vision Transformers
by: Lee, Jaeyeon, et al.
Published: (2025)

Long-tailed Adversarial Training with Self-Distillation
by: Cho, Seungju, et al.
Published: (2025)

DORA: Dynamic Online Reinforcement Agent for Token Merging in Vision Transformers
by: He, Kaixuan, et al.
Published: (2026)

Indirect Gradient Matching for Adversarial Robust Distillation
by: Lee, Hongsin, et al.
Published: (2023)

Enhancing Robustness in Incremental Learning with Adversarial Training
by: Cho, Seungju, et al.
Published: (2023)

RegFormer: Transferable Relational Grounding for Efficient Weakly-Supervised Human-Object Interaction Detection
by: Park, Jihwan, et al.
Published: (2026)

Index-Preserving Lightweight Token Pruning for Efficient Document Understanding in Vision-Language Models
by: Son, Jaemin, et al.
Published: (2025)

Spatio-Temporal Proximity-Aware Dual-Path Model for Panoramic Activity Recognition
by: Lee, Sumin, et al.
Published: (2024)

Denoising Task Routing for Diffusion Models
by: Park, Byeongjun, et al.
Published: (2023)

Importance-Based Token Merging for Efficient Image and Video Generation
by: Wu, Haoyu, et al.
Published: (2024)

FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization
by: Liu, Yicheng, et al.
Published: (2025)

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model
by: Liu, Ting, et al.
Published: (2024)