Copertina

Outlier Smoothing with Closed-Form Rotations for W4A4 Large Language Model Quantization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xiao, Jinying, Ji, Bin, Li, Shasha, Liu, Xiaodong, Jun, Ma, Wang, Chao, Li, Wei, Zhong, Ye, Xie, Xuan, Tashi, Nyima, Yu, Jie
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

EMP: Enhance Memory in Data Pruning
di: Xiao, Jinying, et al.
Pubblicazione: (2024)

LSAQ: Layer-Specific Adaptive Quantization for Large Language Model Deployment
di: Zeng, Binrui, et al.
Pubblicazione: (2024)

SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization
di: Zhang, Jintao, et al.
Pubblicazione: (2024)

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

Model Editing for LLMs4Code: How Far are We?
di: Li, Xiaopeng, et al.
Pubblicazione: (2024)

Context-Aware Dynamic Chunking for Streaming Tibetan Speech Recognition
di: Wang, Chao, et al.
Pubblicazione: (2025)

RetrieveAll: A Multilingual Named Entity Recognition Framework with Large Language Models
di: Zhang, Jin, et al.
Pubblicazione: (2025)

TSCheater: Generating High-Quality Tibetan Adversarial Texts via Visual Similarity
di: Cao, Xi, et al.
Pubblicazione: (2024)

Human-in-the-Loop Generation of Adversarial Texts: A Case Study on Tibetan Script
di: Cao, Xi, et al.
Pubblicazione: (2024)

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

Rotate, Clip, and Partition: Towards W2A4KV4 Quantization by Integrating Rotation and Learnable Non-uniform Quantizer
di: Choi, Euntae, et al.
Pubblicazione: (2025)

QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
di: Ashkboos, Saleh, et al.
Pubblicazione: (2024)

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

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

TED: Accelerate Model Training by Internal Generalization
di: Xiao, Jinying, et al.
Pubblicazione: (2024)

TFD: A Comprehensive Structured Tibetan Foundation Dataset for Low-Resource Language Processing and Large-Scale Modeling
di: Huang, Cheng, et al.
Pubblicazione: (2025)

Identifying Knowledge Editing Types in Large Language Models
di: Li, Xiaopeng, et al.
Pubblicazione: (2024)

When Modalities Remember: Continual Learning for Multimodal Knowledge Graphs
di: Li, Linyu, et al.
Pubblicazione: (2026)

PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization
di: Chen, Mengzhao, et al.
Pubblicazione: (2024)

Listening, Imagining & Refining: A Heuristic Optimized ASR Correction Framework with LLMs
di: Liu, Yutong, et al.
Pubblicazione: (2025)

SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering
di: Li, Xiaopeng, et al.
Pubblicazione: (2024)

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
di: Xiao, Guangxuan, et al.
Pubblicazione: (2022)

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

MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models
di: Hu, Lulu, et al.
Pubblicazione: (2026)

Astro: Activation-guided Structured Regularization for Outlier-Robust LLM Post-Training Quantization
di: Chen, Xi, et al.
Pubblicazione: (2026)

MILLION: Mastering Long-Context LLM Inference Via Outlier-Immunized KV Product Quantization
di: Wang, Zongwu, et al.
Pubblicazione: (2025)

OptRot: Mitigating Weight Outliers via Data-Free Rotations for Post-Training Quantization
di: Gadhikar, Advait, et al.
Pubblicazione: (2025)

SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
di: Li, Muyang, et al.
Pubblicazione: (2024)

Accurate KV Cache Quantization with Outlier Tokens Tracing
di: Su, Yi, et al.
Pubblicazione: (2025)

DIM: Dynamic Integration of Multimodal Entity Linking with Large Language Model
di: Song, Shezheng, et al.
Pubblicazione: (2024)

SEVEN: Pruning Transformer Model by Reserving Sentinels
di: Xiao, Jinying, et al.
Pubblicazione: (2024)

LNPT: Label-free Network Pruning and Training
di: Xiao, Jinying, et al.
Pubblicazione: (2024)

QuantTune: Optimizing Model Quantization with Adaptive Outlier-Driven Fine Tuning
di: Chen, Jiun-Man, et al.
Pubblicazione: (2024)

Glucocorticoid‐Induced Tumor Necrosis Factor Receptor Ligand: Correlation and Therapeutic Potential for Cognitive Impairment in Temporal Lobe Epilepsy
di: Man Li, et al.
Pubblicazione: (2026)

Rethinking Residual Distribution in Locate-then-Edit Model Editing
di: Li, Xiaopeng, et al.
Pubblicazione: (2025)

TLUE: A Tibetan Language Understanding Evaluation Benchmark
di: Gao, Fan, et al.
Pubblicazione: (2025)

ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization
di: Zhao, Weibo, et al.
Pubblicazione: (2024)

EMSEdit: Efficient Multi-Step Meta-Learning-based Model Editing
di: Li, Xiaopeng, et al.
Pubblicazione: (2025)

RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization
di: Huang, Xijie, et al.
Pubblicazione: (2024)

Progressive Residual Extraction based Pre-training for Speech Representation Learning
di: Wang, Tianrui, et al.
Pubblicazione: (2024)