PrismQuant: Optimal Null-Space Rotations for Grouped Quantizers
cs.AI, cs.LG
Submitted: 2026-09-26
Updated: 2026-09-26
Code: https://github.com/ForeverBlue816/PrismQuant
Terminology
Sources
- Training Verifiers to Solve Math Word Problems
- The Llama 3 Herd of Models
- BASE-Q: Bias and Asymmetric Scaling Enhanced Rotational Quantization for Large Language Models
- OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting
- KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
- ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals
- Massive Activations in Large Language Models
- FlatQuant: Flatness Matters for LLM Quantization
- Demystifying Singular Defects in Large Language Models
- OffQ: Taming Structured Outliers in LLM Quantization by Offsetting
- DFRot: Achieving Outlier-Free and Massive Activation-Free for Rotated LLMs with Refined Rotation
- Qwen3 Technical Report
- RPTQ: Reorder-based Post-training Quantization 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