GNMR is a gradient-norm-based controller that maps local stability signals to budgeted recovery actions to stabilize low-precision LLM training while preserving quality.
Efqat: An efficient framework for quantization-aware training
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
-
GNMR: Runtime Stability Control for Low-Precision Large Language Model Training
GNMR is a gradient-norm-based controller that maps local stability signals to budgeted recovery actions to stabilize low-precision LLM training while preserving quality.
-
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.