Cover Image

Beyond Outliers: A Data-Free Layer-wise Mixed-Precision Quantization Approach Driven by Numerical and Structural Dual-Sensitivity

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Hengyuan, Chen, Xinrong, Su, Zunhai, Liang, Xiao, Xiong, Jing, Xu, Wendong, Xiao, He, Tao, Chaofan, Zhang, Wei, Xie, Ruobing, Jiang, Lei, So, Hayden Kwok-Hay, Wong, Ngai
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models
by: Xiao, He, et al.
Published: (2025)

Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation
by: Zhang, Hengyuan, et al.
Published: (2025)

GuiLoMo: Allocating Expert Number and Rank for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors
by: Zhang, Hengyuan, et al.
Published: (2025)

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

Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance
by: Chen, Xinrong, et al.
Published: (2026)

CktFormalizer: Autoformalization of Natural Language into Circuit Representations
by: Xiong, Jing, et al.
Published: (2026)

TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Review
by: Chang, Yuan, et al.
Published: (2025)

TATAA: Programmable Mixed-Precision Transformer Acceleration with a Transformable Arithmetic Architecture
by: Wu, Jiajun, et al.
Published: (2024)

A Composable Dynamic Sparse Dataflow Architecture for Efficient Event-based Vision Processing on FPGA
by: Gao, Yizhao, et al.
Published: (2024)

Co-designing a Sub-millisecond Latency Event-based Eye Tracking System with Submanifold Sparse CNN
by: Zhang, Baoheng, et al.
Published: (2024)

Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity
by: Ranjan, Navin, et al.
Published: (2025)

Layer-wise Quantization for Quantized Optimistic Dual Averaging
by: Nguyen, Anh Duc, et al.
Published: (2025)

LampQ: Towards Accurate Layer-wise Mixed Precision Quantization for Vision Transformers
by: Kim, Minjun, et al.
Published: (2025)

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
by: Zhang, Hengyuan, et al.
Published: (2026)

APTQ: Attention-aware Post-Training Mixed-Precision Quantization for Large Language Models
by: Guan, Ziyi, et al.
Published: (2024)

LRP-QViT: Mixed-Precision Vision Transformer Quantization via Layer-wise Relevance Propagation
by: Ranjan, Navin, et al.
Published: (2024)

AnchorTP: Resilient LLM Inference with State-Preserving Elastic Tensor Parallelism
by: Xu, Wendong, et al.
Published: (2025)

KVSink: Understanding and Enhancing the Preservation of Attention Sinks in KV Cache Quantization for LLMs
by: Su, Zunhai, et al.
Published: (2025)

SpikeMOT: Event-based Multi-Object Tracking with Sparse Motion Features
by: Wang, Song, et al.
Published: (2023)

PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models
by: Xiao, He, et al.
Published: (2025)

DoPE: Denoising Rotary Position Embedding
by: Xiong, Jing, et al.
Published: (2025)

RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations
by: Su, Zunhai, et al.
Published: (2025)

BATQuant: Outlier-resilient MXFP4 Quantization via Learnable Block-wise Optimization
by: Li, Ji-Fu, et al.
Published: (2026)

MUXQ: Mixed-to-Uniform Precision MatriX Quantization via Low-Rank Outlier Decomposition
by: Lee, Seoungsub, et al.
Published: (2026)

Fully Integrated Memristive Spiking Neural Network with Analog Neurons for High-Speed Event-Based Data Processing
by: Wang, Zhu, et al.
Published: (2025)

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
by: Su, Zunhai, et al.
Published: (2026)

Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networks
by: Motetti, Beatrice Alessandra, et al.
Published: (2024)

Mixed-Precision Graph Neural Quantization for Low Bit Large Language Models
by: Liu, Wanlong, et al.
Published: (2025)

KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference
by: Li, Xing, et al.
Published: (2025)

Beyond Outliers: A Study of Optimizers Under Quantization
by: Vlassis, Georgios, et al.
Published: (2025)

XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression
by: Su, Zunhai, et al.
Published: (2026)

XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression
by: Su, Zunhai, et al.
Published: (2026)

OMPQ: Orthogonal Mixed Precision Quantization
by: Ma, Yuexiao, et al.
Published: (2021)

Sensitivity-Aware Mixed-Precision Quantization for ReRAM-based Computing-in-Memory
by: Chen, Guan-Cheng, et al.
Published: (2025)

Lifecycle Cost-Effectiveness Modeling for Redundancy-Enhanced Multi-Chiplet Architectures
by: Liu, Zizhen, et al.
Published: (2026)

BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models
by: Chen, Junyu, et al.
Published: (2026)

LoaQ: Layer-wise Output Approximation Quantization
by: Lin, Li, et al.
Published: (2025)

Evaluating Numerical Accuracy in Mixed-Precision Computing by Dual-Delta Testing
by: Xie, Peichen
Published: (2026)

CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts
by: Yin, Xiangyang, et al.
Published: (2026)

Value-Driven Mixed-Precision Quantization for Patch-Based Inference on Microcontrollers
by: Tao, Wei, et al.
Published: (2024)