Cover Image

Quantize-then-Rectify: Efficient VQ-VAE Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Borui, Rao, Qihang, Zheng, Wenzhao, Zhou, Jie, Lu, Jiwen
Format:	Preprint
Published:	2025
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

SFTok: Bridging the Performance Gap in Discrete Tokenizers
by: Rao, Qihang, et al.
Published: (2025)

Preventing Local Pitfalls in Vector Quantization via Optimal Transport
by: Zhang, Borui, et al.
Published: (2024)

Path Choice Matters for Clear Attribution in Path Methods
by: Zhang, Borui, et al.
Published: (2024)

Fast Shapley Value Estimation: A Unified Approach
by: Zhang, Borui, et al.
Published: (2023)

Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory
by: Wu, Yuqi, et al.
Published: (2025)

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

GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction
by: Zuo, Sicheng, et al.
Published: (2024)

DriveTok: 3D Driving Scene Tokenization for Unified Multi-View Reconstruction and Understanding
by: Zhuo, Dong, et al.
Published: (2026)

ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin
by: Kim, Jaeyung, et al.
Published: (2026)

SpectralAR: Spectral Autoregressive Visual Generation
by: Huang, Yuanhui, et al.
Published: (2025)

Streaming 4D Visual Geometry Transformer
by: Zhuo, Dong, et al.
Published: (2025)

Doe-1: Closed-Loop Autonomous Driving with Large World Model
by: Zheng, Wenzhao, et al.
Published: (2024)

EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding
by: Wu, Yuqi, et al.
Published: (2024)

Hardness-Aware Scene Synthesis for Semi-Supervised 3D Object Detection
by: Zeng, Shuai, et al.
Published: (2024)

GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction
by: Huang, Yuanhui, et al.
Published: (2024)

Terra: Explorable Native 3D World Model with Point Latents
by: Huang, Yuanhui, et al.
Published: (2025)

PCA-VAE: Differentiable Subspace Quantization without Codebook Collapse
by: Lu, Hao, et al.
Published: (2026)

Owl-1: Omni World Model for Consistent Long Video Generation
by: Huang, Yuanhui, et al.
Published: (2024)

VQ-NeRF: Neural Reflectance Decomposition and Editing with Vector Quantization
by: Zhong, Hongliang, et al.
Published: (2023)

Generalization and Memorization in Rectified Flow
by: Rao, Mingxing, et al.
Published: (2026)

MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization
by: Jia, Mingkai, et al.
Published: (2025)

Transformer-VQ: Linear-Time Transformers via Vector Quantization
by: Lingle, Lucas D.
Published: (2023)

GPD-1: Generative Pre-training for Driving
by: Xie, Zixun, et al.
Published: (2024)

Astra: General Interactive World Model with Autoregressive Denoising
by: Zhu, Yixuan, et al.
Published: (2025)

GlobalMamba: Global Image Serialization for Vision Mamba
by: Wang, Chengkun, et al.
Published: (2024)

Learning Counterfactually Decoupled Attention for Open-World Model Attribution
by: Zheng, Yu, et al.
Published: (2025)

BAMI: Training-Free Bias Mitigation in GUI Grounding
by: Zhang, Borui, et al.
Published: (2026)

TSP3D: Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding
by: Guo, Wenxuan, et al.
Published: (2025)

WaterVIB: Learning Minimal Sufficient Watermark Representations via Variational Information Bottleneck
by: He, Haoyuan, et al.
Published: (2026)

VFM-VAE: Vision Foundation Models Can Be Good Tokenizers for Latent Diffusion Models
by: Bi, Tianci, et al.
Published: (2025)

Training-Free Vector Quantization via Gaussian VAEs
by: Xu, Tongda, et al.
Published: (2025)

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

FlowIE: Efficient Image Enhancement via Rectified Flow
by: Zhu, Yixuan, et al.
Published: (2024)

PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views
by: Fei, Xin, et al.
Published: (2024)

Driv3R: Learning Dense 4D Reconstruction for Autonomous Driving
by: Fei, Xin, et al.
Published: (2024)

HireVAE: An Online and Adaptive Factor Model Based on Hierarchical and Regime-Switch VAE
by: Wei, Zikai, et al.
Published: (2023)

Stag-1: Towards Realistic 4D Driving Simulation with Video Generation Model
by: Wang, Lening, et al.
Published: (2024)

OGGSplat: Open Gaussian Growing for Generalizable Reconstruction with Expanded Field-of-View
by: Wang, Yanbo, et al.
Published: (2025)

V2M: Visual 2-Dimensional Mamba for Image Representation Learning
by: Wang, Chengkun, et al.
Published: (2024)

Improving the Training of Rectified Flows
by: Lee, Sangyun, et al.
Published: (2024)