SpectrumQuant: Spectrum Alignment for LLM Quantization

arXiv:2610.20303 · cs.LG, stat.ML · Submitted 2026-10-14 · Read on arXiv

cs.LG, stat.ML

Submitted: 2026-10-14

Updated: 2026-10-14

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Alignment — 1× in this paper
• Quantization — 1× in this paper · explained in 15 episodes

Sources

• WUSH: Near-Optimal Adaptive Transforms for LLM Quantization
• Dissecting Quantization Error: A Concentration-Alignment Perspective
• GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
• Distilling the Knowledge in a Neural Network
• OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting
• Mistral 7B
• Pointer Sentinel Mixture Models
• LLaMA: Open and Efficient Foundation Language Models
• ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms

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