Image de couverture de livre

TokenFLEX: Unified VLM Training for Flexible Visual Tokens Inference

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hu, Junshan, Mao, Jialiang, Liu, Zhikang, Xia, Zhongpu, Jia, Peng, Lang, Xianpeng
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference
par: Singh, Aditya Kumar, et autres
Publié: (2026)

Efficient Token Pruning for LLaDA-V
par: Wan, Zhewen, et autres
Publié: (2026)

OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning
par: Li, Geng, et autres
Publié: (2026)

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
par: Zhang, Yuan, et autres
Publié: (2024)

UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking
par: Wu, Hao, et autres
Publié: (2026)

Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM
par: Wang, Han, et autres
Publié: (2024)

Efficient Video Sampling: Pruning Temporally Redundant Tokens for Faster VLM Inference
par: Bagrov, Natan, et autres
Publié: (2025)

MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
par: Zhang, Luyuan, et autres
Publié: (2026)

NativeTok: Native Visual Tokenization for Improved Image Generation
par: Wu, Bin, et autres
Publié: (2026)

DriveAgent-R1: Advancing VLM-based Autonomous Driving with Active Perception and Hybrid Thinking
par: Zheng, Weicheng, et autres
Publié: (2025)

DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
par: Tian, Xiaoyu, et autres
Publié: (2024)

FlashVLM: Text-Guided Visual Token Selection for Large Multimodal Models
par: Cai, Kaitong, et autres
Publié: (2025)

Training-Free Efficient Video Generation via Dynamic Token Carving
par: Zhang, Yuechen, et autres
Publié: (2025)

2D Gaussians Meet Visual Tokenizer
par: Shi, Yiang, et autres
Publié: (2025)

RedVTP: Training-Free Acceleration of Diffusion Vision-Language Models Inference via Masked Token-Guided Visual Token Pruning
par: Xu, Jingqi, et autres
Publié: (2025)

Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration
par: Zeng, Fanhu, et autres
Publié: (2025)

Similarity-Aware Token Pruning: Your VLM but Faster
par: Jeddi, Ahmadreza, et autres
Publié: (2025)

The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruning
par: Jiang, Titong, et autres
Publié: (2025)

HybridToken-VLM: Hybrid Token Compression for Vision-Language Models
par: Zhang, Jusheng, et autres
Publié: (2025)

OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation
par: Wang, Junke, et autres
Publié: (2024)

Video Token Merging for Long-form Video Understanding
par: Lee, Seon-Ho, et autres
Publié: (2024)

TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
par: Qu, Liao, et autres
Publié: (2024)

Unified Pix Token And Word Token Generative Language Model
par: Leung, Haun, et autres
Publié: (2026)

Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
par: Jin, Yang, et autres
Publié: (2023)

UniTok: A Unified Tokenizer for Visual Generation and Understanding
par: Ma, Chuofan, et autres
Publié: (2025)

OmniVLM: A Token-Compressed, Sub-Billion-Parameter Vision-Language Model for Efficient On-Device Inference
par: Chen, Wei, et autres
Publié: (2024)

TransDiffuser: Diverse Trajectory Generation with Decorrelated Multi-modal Representation for End-to-end Autonomous Driving
par: Jiang, Xuefeng, et autres
Publié: (2025)

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression
par: Hu, Lianyu, et autres
Publié: (2025)

ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement
par: Huang, Runhui, et autres
Publié: (2025)

TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models
par: Tan, Xudong, et autres
Publié: (2025)

Other Vehicle Trajectories Are Also Needed: A Driving World Model Unifies Ego-Other Vehicle Trajectories in Video Latent Space
par: Zhu, Jian, et autres
Publié: (2025)

ID-Selection: Importance-Diversity Based Visual Token Selection for Efficient LVLM Inference
par: Huang, Zhaohong, et autres
Publié: (2026)

SwiftVLM: Efficient Vision-Language Model Inference via Cross-Layer Token Bypass
par: Qian, Chen, et autres
Publié: (2026)

DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies
par: Song, Wei, et autres
Publié: (2025)

TokenAR: Multiple Subject Generation via Autoregressive Token-level enhancement
par: Sun, Haiyue, et autres
Publié: (2025)

Unified Autoregressive Visual Generation and Understanding with Continuous Tokens
par: Fan, Lijie, et autres
Publié: (2025)

Improving Flexible Image Tokenizers for Autoregressive Image Generation
par: Fu, Zixuan, et autres
Publié: (2026)

When Token Pruning is Worse than Random: Understanding Visual Token Information in VLLMs
par: Wang, Yahong, et autres
Publié: (2025)

VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration
par: Yu, Hanxun, et autres
Publié: (2026)

UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation
par: Yue, Zhengrong, et autres
Publié: (2025)