Imagen de Portada

MGVQ: Synergizing Multi-dimensional Sensitivity-Aware and Gradient-Hessian Fusion for Vector Quantization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Zhong, Xu, Zukang, Hu, Xing, Yang, Dawei
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models
por: Xu, Zukang, et al.
Publicado: (2025)

Background Invariance Testing According to Semantic Proximity
por: Liao, Zukang, et al.
Publicado: (2022)

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

Technical Report: Activation Residual Hessian Quantization (ARHQ) for Low-Bit LLM Quantization
por: Wang, YiFeng, et al.
Publicado: (2026)

Vector Quantization Prompting for Continual Learning
por: Jiao, Li, et al.
Publicado: (2024)

Masked Vector Quantization
por: Nguyen, David D., et al.
Publicado: (2023)

Modality-Aware Infrared and Visible Image Fusion with Target-Aware Supervision
por: Sun, Tianyao, et al.
Publicado: (2025)

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

Visualizing high-dimensional loss landscapes with Hessian directions
por: Böttcher, Lucas, et al.
Publicado: (2022)

EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise Optimization
por: Gordon, Ofir, et al.
Publicado: (2023)

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

Restructuring Vector Quantization with the Rotation Trick
por: Fifty, Christopher, et al.
Publicado: (2024)

Does Vector Quantization Fail in Spatio-Temporal Forecasting? Exploring a Differentiable Sparse Soft-Vector Quantization Approach
por: Chen, Chao, et al.
Publicado: (2023)

Concept-Centric Token Interpretation for Vector-Quantized Generative Models
por: Yang, Tianze, et al.
Publicado: (2025)

Enhancing Vector Quantization with Distributional Matching: A Theoretical and Empirical Study
por: Fang, Xianghong, et al.
Publicado: (2025)

Balance of Number of Embedding and their Dimensions in Vector Quantization
por: Chen, Hang, et al.
Publicado: (2024)

Scene-Aware Vectorized Memory Multi-Agent Framework with Cross-Modal Differentiated Quantization VLMs for Visually Impaired Assistance
por: Wang, Xiangxiang, et al.
Publicado: (2025)

Compressing 3D Gaussian Splatting by Noise-Substituted Vector Quantization
por: Wang, Haishan, et al.
Publicado: (2025)

Transformer-Based Autonomous Driving Models and Deployment-Oriented Compression: A Survey
por: Zhong, Juan, et al.
Publicado: (2023)

Multi-View Incremental Learning with Structured Hebbian Plasticity for Enhanced Fusion Efficiency
por: Chen, Yuhong, et al.
Publicado: (2024)

Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion
por: Cho, Minkyoung, et al.
Publicado: (2024)

FusionSF: Fuse Heterogeneous Modalities in a Vector Quantized Framework for Robust Solar Power Forecasting
por: Ma, Ziqing, et al.
Publicado: (2024)

Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation
por: Vepa, Arvind Murari, et al.
Publicado: (2024)

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

Hessian Surgery: Class-Targeted Post-Hoc Rebalancing via Hessian Spike Perturbation
por: Vigna, Hugo, et al.
Publicado: (2026)

CAMP-HiVe: Cyclic Pair Merging based Efficient DNN Pruning with Hessian-Vector Approximation for Resource-Constrained Systems
por: Uddin, Mohammad Helal, et al.
Publicado: (2025)

Flatness and Gradient Alignment Are Both Necessary: Spectral-Aware Gradient-Aligned Exploration for Multi-Distribution Learning
por: Ballas, Aristotelis, et al.
Publicado: (2026)

Image Similarity using An Ensemble of Context-Sensitive Models
por: Liao, Zukang, et al.
Publicado: (2024)

Progressive Element-wise Gradient Estimation for Neural Network Quantization
por: Zhao, Kaiqi
Publicado: (2025)

Gradient-Aligned Calibration for Post-Training Quantization of Diffusion Models
por: Hoang, Dung Anh, et al.
Publicado: (2026)

DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation
por: Hu, Jiaming, et al.
Publicado: (2025)

On-the-Fly Data Augmentation via Gradient-Guided and Sample-Aware Influence Estimation
por: Yang, Suorong, et al.
Publicado: (2025)

Instance-Aware Group Quantization for Vision Transformers
por: Moon, Jaehyeon, et al.
Publicado: (2024)

QGen: On the Ability to Generalize in Quantization Aware Training
por: AskariHemmat, MohammadHossein, et al.
Publicado: (2024)

Data-Augmented Quantization-Aware Knowledge Distillation
por: Kur, Justin, et al.
Publicado: (2025)

Adversarial Defenses via Vector Quantization
por: Dong, Zhiyi, et al.
Publicado: (2023)

Multi-view Deep Subspace Clustering Networks
por: Zhu, Pengfei, et al.
Publicado: (2019)

The effects of Hessian eigenvalue spectral density type on the applicability of Hessian analysis to generalization capability assessment of neural networks
por: Gabdullin, Nikita
Publicado: (2025)

Enhancing Quantization-Aware Training on Edge Devices via Relative Entropy Coreset Selection and Cascaded Layer Correction
por: Tong, Yujia, et al.
Publicado: (2025)

SVGFusion: A VAE-Diffusion Transformer for Vector Graphic Generation
por: Xing, Ximing, et al.
Publicado: (2024)