Cover Image

Astro: Activation-guided Structured Regularization for Outlier-Robust LLM Post-Training Quantization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Xi, Li, Ming, Li, Junxi, Li, Changsheng, Wang, Peisong, Ding, Lizhong, Yuan, Ye, Wang, Guoren
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?
by: Chen, Xi, et al.
Published: (2024)

DeepFaith: A Domain-Free and Model-Agnostic Unified Framework for Highly Faithful Explanations
by: Guo, Yuhan, et al.
Published: (2025)

DREAM: Domain-agnostic Reverse Engineering Attributes of Black-box Model
by: Li, Rongqing, et al.
Published: (2024)

Macformer: Transformer with Random Maclaurin Feature Attention
by: Guo, Yuhan, et al.
Published: (2024)

DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization
by: Lee, Dongyeun, et al.
Published: (2025)

Outlier-Aware Training for Low-Bit Quantization of Structural Re-Parameterized Networks
by: Niu, Muqun, et al.
Published: (2024)

Robust Knowledge Adaptation for Dynamic Graph Neural Networks
by: Li, Hanjie, et al.
Published: (2022)

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

VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models
by: Liu, Yifei, et al.
Published: (2024)

InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization
by: Li, Ke, et al.
Published: (2026)

SliderQuant: Accurate Post-Training Quantization for LLMs
by: Wang, Shigeng, et al.
Published: (2026)

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

BiLLM: Pushing the Limit of Post-Training Quantization for LLMs
by: Huang, Wei, et al.
Published: (2024)

NestQuant: Post-Training Integer-Nesting Quantization for On-Device DNN
by: Xie, Jianhang, et al.
Published: (2025)

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

Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers
by: Chen, Lei, et al.
Published: (2024)

Activation Sensitivity as a Unifying Principle for Post-Training Quantization
by: Xu, Bruce Changlong
Published: (2026)

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

Dr. Post-Training: A Data Regularization Perspective on LLM Post-Training
by: Hu, Pingbang, et al.
Published: (2026)

Learning to Generate Parameters of ConvNets for Unseen Image Data
by: Wang, Shiye, et al.
Published: (2023)

Investigating the Impact of Quantization on Adversarial Robustness
by: Li, Qun, et al.
Published: (2024)

Activation Outliers in Transformer Quantization: Reproduction, Statistical Analysis, and Deployment Tradeoffs
by: Kaliaperumal, Pranav Kumar
Published: (2026)

MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization
by: Zhang, Aozhong, et al.
Published: (2024)

CardOOD: Robust Query-driven Cardinality Estimation under Out-of-Distribution
by: Li, Rui, et al.
Published: (2024)

Implicit Compression Regularization: Concise Reasoning via Internal Shorter Distributions in RL Post-Training
by: Wang, Chen, et al.
Published: (2026)

Widening the Gap: Exploiting LLM Quantization via Outlier Injection
by: Zhan, Xiaohua, et al.
Published: (2026)

Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization
by: Nrusimha, Aniruddha, et al.
Published: (2024)

Rethinking RoPE Scaling in Quantized LLM: Theory, Outlier, and Channel-Band Analysis with Weight Rescaling
by: Qiao, Ye, et al.
Published: (2025)

On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous Driving
by: Feng, Kaituo, et al.
Published: (2024)

DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training
by: Zhu, Dingwei, et al.
Published: (2025)

Outlier-Aware Post-Training Quantization for Image Super-Resolution
by: Wang, Hailing, et al.
Published: (2025)

Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models
by: Zhang, Tianao, et al.
Published: (2025)

Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity
by: Zhang, Sirui, et al.
Published: (2026)

ANAct: Adaptive Normalization for Activation Functions
by: Peiwen, Yuan, et al.
Published: (2022)

AstroReview: An LLM-driven Multi-Agent Framework for Telescope Proposal Peer Review and Refinement
by: Wang, Yutong, et al.
Published: (2025)

QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge
by: Shen, Xuan, et al.
Published: (2025)

Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis
by: Zhao, Jiaqi, et al.
Published: (2025)

Task-Stratified Knowledge Scaling Laws for Post-Training Quantized Large Language Models
by: Zhou, Chenxi, et al.
Published: (2025)

QuantMoE-Bench: Examining Post-Training Quantization for Mixture-of-Experts
by: Li, Pingzhi, et al.
Published: (2024)

Post-Training Quantization for Video Matting
by: Zhu, Tianrui, et al.
Published: (2025)