Cover Image

MSQ: Memory-Efficient Bit Sparsification Quantization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Han, Seokho, Yoon, Seoyeon, Kim, Jinhee, Wang, Dongwei, Jeon, Kang Eun, Yang, Huanrui, Ko, Jong Hwan
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision
by: Kim, Jinhee, et al.
Published: (2025)

MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Any-Precision LLM
by: Wang, Dongwei, et al.
Published: (2026)

Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling
by: Kim, Jinhee, et al.
Published: (2025)

Column-wise Quantization of Weights and Partial Sums for Accurate and Efficient Compute-In-Memory Accelerators
by: Kim, Jiyoon, et al.
Published: (2025)

MEMHD: Memory-Efficient Multi-Centroid Hyperdimensional Computing for Fully-Utilized In-Memory Computing Architectures
by: Kang, Do Yeong, et al.
Published: (2025)

Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization
by: Wang, Dongwei, et al.
Published: (2024)

BitSnap: Checkpoint Sparsification and Quantization in LLM Training
by: Peng, Yanxin, et al.
Published: (2025)

Row-Column Hybrid Grouping for Fault-Resilient Multi-Bit Weight Representation on IMC Arrays
by: Jeon, Kang Eun, et al.
Published: (2025)

Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification
by: Huang, Hong, et al.
Published: (2026)

One-Bit Quantization and Sparsification for Multiclass Linear Classification with Strong Regularization
by: Ghane, Reza, et al.
Published: (2024)

GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs
by: Deng, Jianing, et al.
Published: (2026)

NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models
by: Chong, Hyochan, et al.
Published: (2026)

Efficient Asynchronous Federated Learning with Sparsification and Quantization
by: Jia, Juncheng, et al.
Published: (2023)

TESU-LLM: Training Speech-LLMs Without Speech via Unified Encoder Alignment
by: Kim, Taesoo, et al.
Published: (2025)

Efficient Distributed Training through Gradient Compression with Sparsification and Quantization Techniques
by: Singh, Shruti, et al.
Published: (2024)

DyBit: Dynamic Bit-Precision Numbers for Efficient Quantized Neural Network Inference
by: Zhou, Jiajun, et al.
Published: (2023)

Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models
by: Park, Jungwoo, et al.
Published: (2025)

LittleBit: Ultra Low-Bit Quantization via Latent Factorization
by: Lee, Banseok, et al.
Published: (2025)

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

BAQ: Efficient Bit Allocation Quantization for Large Language Models
by: Zhang, Chao, et al.
Published: (2025)

PaAno: Patch-Based Representation Learning for Time-Series Anomaly Detection
by: Park, Jinju, et al.
Published: (2026)

ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization
by: Yadav, Prateek, et al.
Published: (2023)

Task Vector Quantization for Memory-Efficient Model Merging
by: Kim, Youngeun, et al.
Published: (2025)

Preserve-Then-Quantize: Balancing Rank Budgets for Quantization Error Reconstruction in LLMs
by: Cho, Yoonjun, et al.
Published: (2026)

Q-Palette: Fractional-Bit Quantizers Toward Optimal Bit Allocation for Efficient LLM Deployment
by: Lee, Deokjae, et al.
Published: (2025)

Where and How to Enhance: Discovering Bit-Width Contribution for Mixed Precision Quantization
by: Kang, Haidong, et al.
Published: (2025)

MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity
by: Choi, Kanghyun, et al.
Published: (2024)

MOMEMTO: Patch-based Memory Gate Model in Time Series Foundation Model
by: Yoon, Samuel, et al.
Published: (2025)

Binary Weight Multi-Bit Activation Quantization for Compute-in-Memory CNN Accelerators
by: Zhou, Wenyong, et al.
Published: (2025)

L4Q: Parameter Efficient Quantization-Aware Fine-Tuning on Large Language Models
by: Jeon, Hyesung, et al.
Published: (2024)

RDIS: Random Drop Imputation with Self-Training for Incomplete Time Series Data
by: Choi, Tae-Min, et al.
Published: (2020)

Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control
by: Park, Seongmin, et al.
Published: (2024)

BitsMoE: Efficient Spectral Energy-Guided Bit Allocation for MoE LLM Quantization
by: Zhao, Jiayu, et al.
Published: (2026)

Efficient Unbiased Sparsification
by: Barnes, Leighton, et al.
Published: (2024)

LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model Finetuning
by: Guo, Han, et al.
Published: (2023)

Robust Ultra Low-Bit Post-Training Quantization via Stable Diagonal Curvature Estimate
by: Kim, Jaemin, et al.
Published: (2026)

SenDaL: An Effective and Efficient Calibration Framework of Low-Cost Sensors for Daily Life
by: Ahn, Seokho, et al.
Published: (2025)

One-Bit Quantization for Random Features Models
by: Akhtiamov, Danil, et al.
Published: (2025)

DecDEC: A Systems Approach to Advancing Low-Bit LLM Quantization
by: Park, Yeonhong, et al.
Published: (2024)

A Carbon Tracking Model for Federated Learning: Impact of Quantization and Sparsification
by: Barbieri, Luca, et al.
Published: (2023)