Activation Denoising: A Robustness View on Parallel vs Sequential LLM Quantization

arXiv:2610.07522 · cs.LG · Submitted 2026-10-05 · Read on arXiv

cs.LG

Submitted: 2026-10-05

Updated: 2026-10-05

Code: https://github.com/Intelligent-Computing-Lab-Panda/GPTAQ

Terminology

• Quantization — 1× in this paper · explained in 12 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• CoreQ: Learning-Free Mismatch Correction and Successive Rounding for Quantization
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• OptRot: Mitigating Weight Outliers via Data-Free Rotations for Post-Training Quantization
• KronQ: LLM Quantization via Kronecker-Factored Hessian
• The Llama 3 Herd of Models
• SocialIQA: Commonsense Reasoning about Social Interactions
• Low-Rank Correction for Quantized LLMs
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Model-Preserving Adaptive Rounding
• GPTVQ: The Blessing of Dimensionality for LLM Quantization
• Pyramid Vector Quantization for LLMs
• Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling
• Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantization

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks