JARQ: Joint Alternating Refinement for Quantization

arXiv:2609.38599 · cs.LG · Submitted 2026-09-29 · Read on arXiv

cs.LG

Submitted: 2026-09-29

Updated: 2026-10-02

Code: https://github.com/Euphoria040201/JARQ

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
• QuantEase: Optimization-based Quantization for Language Models
• CoreQ: Learning-Free Mismatch Correction and Successive Rounding for Quantization
• The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Training Verifiers to Solve Math Word Problems
• GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
• The Pile: An 800GB Dataset of Diverse Text for Language Modeling
• The Llama 3 Herd of Models
• Measuring Massive Multitask Language Understanding
• SpinQuant: LLM quantization with learned rotations
• OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• OJBKQ: Objective-Joint Babai-Klein Quantization
• Qwen2.5 Technical Report
• Qwen3 Technical Report

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