ProjQ constrains post-training quantization noise to a low-rank manifold through orthogonal subspace projection, enabling better compensation by LoRA adapters and preserving greater model plasticity than standard PTQ.
Available: https://arxiv.org/abs/2411.06084
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Thermodynamic lower bounds are approximated for exact and SGD linear regression, producing energy-aware scaling laws for optimal training dataset size given a target generalization error.
citing papers explorer
-
ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression
ProjQ constrains post-training quantization noise to a low-rank manifold through orthogonal subspace projection, enabling better compensation by LoRA adapters and preserving greater model plasticity than standard PTQ.
-
The Thermodynamic Costs of Simple Linear Regression
Thermodynamic lower bounds are approximated for exact and SGD linear regression, producing energy-aware scaling laws for optimal training dataset size given a target generalization error.