When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization
cs.AI, cs.LG, stat.ML
Submitted: 2026-10-08
Updated: 2026-10-08
Code: https://github.com/z-lab/paroquant
Terminology
Sources
- PIQA: Reasoning about Physical Commonsense in Natural Language
- CoreQ: Learning-Free Mismatch Correction and Successive Rounding for Quantization
- QuIP: 2-Bit Quantization of Large Language Models With Guarantees
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- The Llama 3 Herd of Models
- Measuring Massive Multitask Language Understanding
- GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance
- SpinQuant: LLM quantization with learned rotations
- WinoGrande: An Adversarial Winograd Schema Challenge at Scale
- Qwen3 Technical Report
- Saliency-Aware Regularized Quantization Calibration for Large Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection