Cover Image

Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Yiming, Zhao, Zhuokai, Chen, Zhaorun, Ding, Zenghui, Yang, Xianjun, Sun, Yining
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

RankCLIP: Ranking-Consistent Language-Image Pretraining
by: Zhang, Yiming, et al.
Published: (2024)

CircuitProbe: Tracing Visual Temporal Evidence Flow in Video Language Models
by: Zhang, Yiming, et al.
Published: (2025)

Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding
by: Fang, Yixiong, et al.
Published: (2024)

HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
by: Chen, Zhaorun, et al.
Published: (2024)

HyperTokens: Controlling Token Dynamics for Continual Video-Language Understanding
by: Nguyen, Toan, et al.
Published: (2026)

Video Token Merging for Long-form Video Understanding
by: Lee, Seon-Ho, et al.
Published: (2024)

Optimizing GPT for Video Understanding: Zero-Shot Performance and Prompt Engineering
by: Beliaev, Mark, et al.
Published: (2025)

Token Merging via Spatiotemporal Information Mining for Surgical Video Understanding
by: Jiang, Xixi, et al.
Published: (2025)

Zero-Shot Video Restoration and Enhancement Using Pre-Trained Image Diffusion Model
by: Cao, Cong, et al.
Published: (2024)

Let's Split Up: Zero-Shot Classifier Edits for Fine-Grained Video Understanding
by: Liu, Kaiting, et al.
Published: (2026)

SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations
by: Chen, Zhaorun, et al.
Published: (2024)

Efficient Visual Transformer by Learnable Token Merging
by: Wang, Yancheng, et al.
Published: (2024)

TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval
by: Shen, Leqi, et al.
Published: (2024)

Language-Driven Anchors for Zero-Shot Adversarial Robustness
by: Li, Xiao, et al.
Published: (2023)

T3: Test-Time Model Merging in VLMs for Zero-Shot Medical Imaging Analysis
by: Imam, Raza, et al.
Published: (2025)

Zero-Shot Video Translation via Token Warping
by: Zhu, Haiming, et al.
Published: (2024)

VideoOrion: Tokenizing Object Dynamics in Videos
by: Feng, Yicheng, et al.
Published: (2024)

DINORANKCLIP: DINOv3 Distillation and Injection for Vision-Language Pretraining with High-Order Ranking Consistency
by: Jiang, Shuyang, et al.
Published: (2026)

Navigate Beyond Shortcuts: Debiased Learning through the Lens of Neural Collapse
by: Wang, Yining, et al.
Published: (2024)

MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding
by: Fang, Xinyu, et al.
Published: (2024)

CubistMerge: Spatial-Preserving Token Merging For Diverse ViT Backbones
by: Gong, Wenyi, et al.
Published: (2025)

Zero-Shot Long-Form Video Understanding through Screenplay
by: Wu, Yongliang, et al.
Published: (2024)

VideoMerge: Towards Training-free Long Video Generation
by: Zhang, Siyang, et al.
Published: (2025)

Are Image-to-Video Models Good Zero-Shot Image Editors?
by: Zhang, Zechuan, et al.
Published: (2025)

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

Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers
by: Wang, Hongjie, et al.
Published: (2023)

FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging
by: Fan, Ziyang, et al.
Published: (2026)

Seeing Beyond Frames: Zero-Shot Pedestrian Intention Prediction with Raw Temporal Video and Multimodal Cues
by: Zambare, Pallavi, et al.
Published: (2025)

Unified Autoregressive Visual Generation and Understanding with Continuous Tokens
by: Fan, Lijie, et al.
Published: (2025)

Video, How Do Your Tokens Merge?
by: Pollard, Sam, et al.
Published: (2025)

D$^{3}$ToM: Decider-Guided Dynamic Token Merging for Accelerating Diffusion MLLMs
by: Chang, Shuochen, et al.
Published: (2025)

SUGAR: Subject-Driven Video Customization in a Zero-Shot Manner
by: Zhou, Yufan, et al.
Published: (2024)

DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
by: Tao, Keda, et al.
Published: (2024)

Beyond GSD-as-Token: Continuous Scale Conditioning for Remote Sensing VLMs
by: Zhang, Song, et al.
Published: (2026)

CETCAM: Camera-Controllable Video Generation via Consistent and Extensible Tokenization
by: Zhao, Zelin, et al.
Published: (2025)

Zero-Shot Dynamic Concept Personalization with Grid-Based LoRA
by: Abdal, Rameen, et al.
Published: (2025)

CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving
by: Yang, Huitong, et al.
Published: (2025)

Domain-Aware Continual Zero-Shot Learning
by: Yi, Kai, et al.
Published: (2021)

Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators
by: Zhang, Wentao, et al.
Published: (2024)

ShoulderShot: Generating Over-the-Shoulder Dialogue Videos
by: Zhang, Yuang, et al.
Published: (2025)