Copertina

Towards Superior Quantization Accuracy: A Layer-sensitive Approach

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Feng, Liu, Yanbin, Li, Weihua, Lv, Jie, Wang, Xiaodan, Bai, Quan
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Multiscale Dual-path Feature Aggregation Network for Remaining Useful Life Prediction of Lithium-Ion Batteries
di: Lv, Zihao, et al.
Pubblicazione: (2025)

LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation
di: Chen, Han, et al.
Pubblicazione: (2025)

Depth-Structured Music Recurrence: Budgeted Recurrent Attention for Full-Piece Symbolic Music Modeling
di: Yi, Yungang, et al.
Pubblicazione: (2026)

AMS-QUANT: Adaptive Mantissa Sharing for Floating-point Quantization
di: Lv, Mengtao, et al.
Pubblicazione: (2025)

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design
di: Duanmu, Haojie, et al.
Pubblicazione: (2025)

CALM: A CKA-Guided Adaptive Layer-Wise Modularization Framework for LLM Quantization
di: Zhang, Jinhao, et al.
Pubblicazione: (2025)

From Similarity to Superiority: Channel Clustering for Time Series Forecasting
di: Chen, Jialin, et al.
Pubblicazione: (2024)

Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds
di: Liang, Hao, et al.
Pubblicazione: (2022)

Optimizing Prompts for Large Language Models: A Causal Approach
di: Chen, Wei, et al.
Pubblicazione: (2026)

RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models
di: Wei, Quan, et al.
Pubblicazione: (2025)

Efficient Edge LLMs Deployment via HessianAware Quantization and CPU GPU Collaborative
di: Zhang, Tuo, et al.
Pubblicazione: (2025)

OSC: Hardware Efficient W4A4 Quantization via Outlier Separation in Channel Dimension
di: Zhang, Zhiyuan, et al.
Pubblicazione: (2026)

CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compression
di: Liu, Wenyuan, et al.
Pubblicazione: (2024)

AsymKV: Enabling 1-Bit Quantization of KV Cache with Layer-Wise Asymmetric Quantization Configurations
di: Tao, Qian, et al.
Pubblicazione: (2024)

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

HESTIA: A Hessian-Guided Differentiable Quantization-Aware Training Framework for Extremely Low-Bit LLMs
di: Wang, Guoan, et al.
Pubblicazione: (2026)

Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models
di: Chen, Kejia, et al.
Pubblicazione: (2025)

Kelp: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection
di: Li, Xiaodan, et al.
Pubblicazione: (2025)

TempoGPT: Enhancing Time Series Reasoning via Quantizing Embedding
di: Zhang, Haochuan, et al.
Pubblicazione: (2025)

FAQ: Mitigating Quantization Error via Regenerating Calibration Data with Family-Aware Quantization
di: Xiao, Haiyang, et al.
Pubblicazione: (2026)

Global Stress Generation and Spatiotemporal Super-Resolution Physics-Informed Operator under Dynamic Loading for Two-Phase Random Materials
di: Xing, Tengfei, et al.
Pubblicazione: (2025)

Predicting Stress in Two-phase Random Materials and Super-Resolution Method for Stress Images by Embedding Physical Information
di: Xing, Tengfei, et al.
Pubblicazione: (2025)

SplitQuant: Layer Splitting for Low-Bit Neural Network Quantization
di: Song, Jaewoo, et al.
Pubblicazione: (2025)

Theory-optimal Quantization Based on Flatness
di: Huang, Xiusheng, et al.
Pubblicazione: (2026)

PatternKV: Flattening KV Representation Expands Quantization Headroom
di: Zhang, Ji, et al.
Pubblicazione: (2025)

"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization
di: Kurtic, Eldar, et al.
Pubblicazione: (2024)

Data Distribution as a Lever for Guiding Optimizers Toward Superior Generalization in LLMs
di: Gangavarapu, Tushaar, et al.
Pubblicazione: (2026)

Universality of Layer-Level Entropy-Weighted Quantization Beyond Model Architecture and Size
di: Behtash, Alireza, et al.
Pubblicazione: (2025)

Towards Minimizing Feature Drift in Model Merging: Layer-wise Task Vector Fusion for Adaptive Knowledge Integration
di: Sun, Wenju, et al.
Pubblicazione: (2025)

INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats
di: Chen, Mengzhao, et al.
Pubblicazione: (2025)

Towards Data-Centric AI: A Comprehensive Survey of Traditional, Reinforcement, and Generative Approaches for Tabular Data Transformation
di: Wang, Dongjie, et al.
Pubblicazione: (2025)

DAQ: Delta-Aware Quantization for Post-Training LLM Weight Compression
di: Yu, Xiaoming, et al.
Pubblicazione: (2026)

What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study
di: Lv, Keyu, et al.
Pubblicazione: (2026)

Low-bit Model Quantization for Deep Neural Networks: A Survey
di: Liu, Kai, et al.
Pubblicazione: (2025)

TTVS: Boosting Self-Exploring Reinforcement Learning via Test-time Variational Synthesis
di: Bai, Sikai, et al.
Pubblicazione: (2026)

CodeGEMM: A Codebook-Centric Approach to Efficient GEMM in Quantized LLMs
di: Park, Gunho, et al.
Pubblicazione: (2025)

Enhancing Model Privacy in Federated Learning with Random Masking and Quantization
di: Xu, Zhibo, et al.
Pubblicazione: (2025)

RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracy
di: Lee, Geonho, et al.
Pubblicazione: (2024)

DNN Memory Footprint Reduction via Post-Training Intra-Layer Multi-Precision Quantization
di: Ghavami, Behnam, et al.
Pubblicazione: (2024)

ADAPTive Input Training for Many-to-One Pre-Training on Time-Series Classification
di: Quinlan, Paul, et al.
Pubblicazione: (2026)