BARQ: Balanced Codebook Refinement for Low-Bit LLM Quantization

arXiv:2610.04490 · cs.LG · Submitted 2026-10-03 · Read on arXiv

cs.LG

Submitted: 2026-10-03

Updated: 2026-10-03

Code: https://github.com/chenhangcuisg-code/BARQ

Project page: https://dropbox.github.io/hqq_blog

Terminology

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

Sources

• QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment
• Transport and Merge: Cross-Architecture Merging for Large Language Models
• The Llama 3 Herd of Models
• VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models
• SpinQuant: LLM quantization with learned rotations
• PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression
• Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation
• TraceRouter: Robust Safety for Large Foundation Models via Path-Level Intervention
• GPTVQ: The Blessing of Dimensionality for LLM Quantization
• Qwen3 Technical Report
• Online Clustered Codebook

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