Cover Image

MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Siyuan, Zhang, Luyuan, Wang, Zedong, Tian, Juanxi, Tan, Cheng, Liu, Zicheng, Yu, Chang, Xie, Qingsong, Lu, Haonan, Wang, Haoqian, Lei, Zhen
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
by: Li, Siyuan, et al.
Published: (2024)

OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning
by: Li, Siyuan, et al.
Published: (2022)

LongVQ: Long Sequence Modeling with Vector Quantization on Structured Memory
by: Liu, Zicheng, et al.
Published: (2024)

MergeDNA: Context-aware Genome Modeling with Dynamic Tokenization through Token Merging
by: Li, Siyuan, et al.
Published: (2025)

Taming LLMs by Scaling Learning Rates with Gradient Grouping
by: Li, Siyuan, et al.
Published: (2025)

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

MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding
by: Jin, Xin, et al.
Published: (2025)

A Survey on Mixup Augmentations and Beyond
by: Jin, Xin, et al.
Published: (2024)

VQ-Style: Disentangling Style and Content in Motion with Residual Quantized Representations
by: Zargarbashi, Fatemeh, et al.
Published: (2026)

VQ‐Style: Disentangling Style and Content in Motion with Residual Quantized Representations
by: Fatemeh Zargarbashi, et al.
Published: (2026)

Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights
by: Tian, Juanxi, et al.
Published: (2025)

E-PMQ: Expert-Guided Post-Merge Quantization with Merged-Weight Anchoring
by: Wang, Wenjun, et al.
Published: (2026)

QuickMerge++: Fast Token Merging with Autoregressive Prior
by: Liu, Dong, et al.
Published: (2025)

Masked Modeling for Self-supervised Representation Learning on Vision and Beyond
by: Li, Siyuan, et al.
Published: (2023)

Merging and Disentangling Views in Visual Reinforcement Learning for Robotic Manipulation
by: Almuzairee, Abdulaziz, et al.
Published: (2025)

1bit-Merging: Dynamic Quantized Merging for Large Language Models
by: Liu, Shuqi, et al.
Published: (2025)

Merge and Guide: Unifying Model Merging and Guided Decoding for Controllable Multi-Objective Generation
by: Xie, Guofu, et al.
Published: (2025)

Batching BPE Tokenization Merges
by: Morgan, Alexander P.
Published: (2024)

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

VQDNA: Unleashing the Power of Vector Quantization for Multi-Species Genomic Sequence Modeling
by: Li, Siyuan, et al.
Published: (2024)

VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation
by: Yang, Sicheng, et al.
Published: (2026)

Learning Unified User Quantized Tokenizers for User Representation
by: He, Chuan, et al.
Published: (2025)

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer
by: Chen, Hao, et al.
Published: (2024)

Switch EMA: A Free Lunch for Better Flatness and Sharpness
by: Li, Siyuan, et al.
Published: (2024)

Accelerating Transformers with Spectrum-Preserving Token Merging
by: Tran, Hoai-Chau, et al.
Published: (2024)

ToMA: Token Merge with Attention for Diffusion Models
by: Lu, Wenbo, et al.
Published: (2025)

CORE: Compact Object-centric REpresentations as a New Paradigm for Token Merging in LVLMs
by: Lei, Jingyu, et al.
Published: (2025)

Model Merging in the Essential Subspace
by: Li, Longhua, et al.
Published: (2026)

TMCIR: Token Merge Benefits Composed Image Retrieval
by: Wang, Chaoyang, et al.
Published: (2025)

Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers
by: Chen, Yutian, et al.
Published: (2025)

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

Multi-Task Model Merging via Adaptive Weight Disentanglement
by: Xiong, Feng, et al.
Published: (2024)

Representation Surgery for Multi-Task Model Merging
by: Yang, Enneng, et al.
Published: (2024)

Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning
by: Wang, Zedong, et al.
Published: (2025)

AutoMerge: Search-Based Model Merging Framework for Effective Model Reuse
by: Lu, You, et al.
Published: (2026)

VQ-SGen: A Vector Quantized Stroke Representation for Creative Sketch Generation
by: Wang, Jiawei, et al.
Published: (2024)

FREE-Merging: Fourier Transform for Efficient Model Merging
by: Zheng, Shenghe, et al.
Published: (2024)

InfoMerge: Information-aware Token Compression for Efficient Video Large Language Models
by: Liu, Xinxin, et al.
Published: (2026)

OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging
by: Wei, Yongxian, et al.
Published: (2025)