XOR-Trellis: Ultra-Low-Complexity Dequantization and Curvature-Aware Hadamard-Free LLM Quantization

arXiv:2610.00432 · cs.LG, cs.AI · Submitted 2026-09-30 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-09-30

Updated: 2026-09-30

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

Terminology

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

Sources

• QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
• GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
• VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models
• QTIP: Quantization with Trellises and Incoherence Processing
• Model-Preserving Adaptive Rounding
• GPTVQ: The Blessing of Dimensionality for LLM Quantization
• Pyramid Vector Quantization for LLMs
• Leech Lattice Vector Quantization for Efficient LLM Compression

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