Imagen de Portada

HAS-VQ: Hessian-Adaptive Sparse Vector Quantization for High-Fidelity LLM Compression

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Khasia, Vladimer
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Beyond Attention: True Adaptive World Models via Spherical Kernel Operator
por: Khasia, Vladimer
Publicado: (2026)

The Adaptive Vekua Cascade: A Differentiable Spectral-Analytic Solver for Physics-Informed Representation
por: Khasia, Vladimer
Publicado: (2025)

Hybrid Dual-Path Linear Transformations for Efficient Transformer Architectures
por: Khasia, Vladimer
Publicado: (2026)

BASIS: Balanced Activation Sketching with Invariant Scalars for "Ghost Backpropagation"
por: Khasia, Vladimer
Publicado: (2026)

Spectral-Window Hybrid (SWH)
por: Khasia, Vladimer
Publicado: (2026)

HoloByte: Continuous Hyperspherical Distillation for Tokenizer-Free Modeling
por: Khasia, Vladimer
Publicado: (2026)

DeepVekua: Geometric-Spectral Representation Learning for Physics-Informed Fields
por: Khasia, Vladimer
Publicado: (2025)

Dynamic Subspace Composition: Efficient Adaptation via Contractive Basis Expansion
por: Khasia, Vladimer
Publicado: (2025)

The Vekua Layer: Exact Physical Priors for Implicit Neural Representations via Generalized Analytic Functions
por: Khasia, Vladimer
Publicado: (2025)

Primal: A Unified Deterministic Framework for Quasi-Orthogonal Hashing and Manifold Learning
por: Khasia, Vladimer
Publicado: (2025)

Sparse-VQ Transformer: An FFN-Free Framework with Vector Quantization for Enhanced Time Series Forecasting
por: Zhao, Yanjun, et al.
Publicado: (2024)

BandVQ: Band-Wise Vector-Quantized EEG Foundation Model
por: Sukhbaatar, Jamiyan, et al.
Publicado: (2026)

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

HyperVQ: MLR-based Vector Quantization in Hyperbolic Space
por: Goswami, Nabarun, et al.
Publicado: (2024)

VQ-SAD: Vector Quantized Structure Aware Diffusion For Molecule Generation
por: Noravesh, Farshad, et al.
Publicado: (2026)

Leech Lattice Vector Quantization for Efficient LLM Compression
por: van der Ouderaa, Tycho F. A., et al.
Publicado: (2026)

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

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

RAVQ-HoloNet: Rate-Adaptive Vector-Quantized Hologram Compression
por: Rafiei, Shima, et al.
Publicado: (2025)

VQ-DSC-R: Robust Vector Quantized-Enabled Digital Semantic Communication With OFDM Transmission
por: Chen, Jianqiao, et al.
Publicado: (2026)

BeamVQ: Beam Search with Vector Quantization to Mitigate Data Scarcity in Physical Spatiotemporal Forecasting
por: Wang, Weiyan, et al.
Publicado: (2025)

Calo-VQ: Vector-Quantized Two-Stage Generative Model in Calorimeter Simulation
por: Liu, Qibin, et al.
Publicado: (2024)

CARVQ: Corrective Adaptor with Group Residual Vector Quantization for LLM Embedding Compression
por: Gou, Dayin, et al.
Publicado: (2025)

Revisiting Adaptive Rounding with Vectorized Reparameterization for LLM Quantization
por: Zhou, Yuli, et al.
Publicado: (2026)

EdgeCodec: Onboard Lightweight High Fidelity Neural Compressor with Residual Vector Quantization
por: Hodo, Benjamin, et al.
Publicado: (2025)

Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compression
por: Zhang, Xi, et al.
Publicado: (2025)

Quantize-then-Rectify: Efficient VQ-VAE Training
por: Zhang, Borui, et al.
Publicado: (2025)

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

MGVQ: Synergizing Multi-dimensional Sensitivity-Aware and Gradient-Hessian Fusion for Vector Quantization
por: Wang, Zhong, et al.
Publicado: (2026)

Graph VQ-Transformer (GVT): Fast and Accurate Molecular Generation via High-Fidelity Discrete Latents
por: Zheng, Haozhuo, et al.
Publicado: (2025)

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

Efficient VQ-QAT and Mixed Vector/Linear quantized Neural Networks
por: Gou, Terry, et al.
Publicado: (2026)

Locally-Adaptive Quantization for Streaming Vector Search
por: Aguerrebere, Cecilia, et al.
Publicado: (2024)

SqueezeLLM: Dense-and-Sparse Quantization
por: Kim, Sehoon, et al.
Publicado: (2023)

CRVQ: Channel-Relaxed Vector Quantization for Extreme Compression of LLMs
por: Xu, Yuzhuang, et al.
Publicado: (2024)

VP-VAE: Rethinking Vector Quantization via Adaptive Vector Perturbation
por: Zhai, Linwei, et al.
Publicado: (2026)

SBVR: Summation of BitVector Representation for Efficient LLM Quantization
por: Bang, Wonjun, et al.
Publicado: (2025)

SparseForge: Efficient Semi-Structured LLM Sparsification via Annealing of Hessian-Guided Soft-Mask
por: Hanzuo, Liu, et al.
Publicado: (2026)

SDQ: Sparse Decomposed Quantization for LLM Inference
por: Jeong, Geonhwa, 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)