CAQ-ZO aligns ZO query stencils to compander grids, eliminating query-time residual error and improving NF4 fine-tuning performance on Qwen and Llama models compared to standard quantized baselines.
Quantization and training of neural networks for efficient integer-arithmetic-only inference
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Compander-Aligned Query Geometry for Quantized Zeroth-Order Optimization
CAQ-ZO aligns ZO query stencils to compander grids, eliminating query-time residual error and improving NF4 fine-tuning performance on Qwen and Llama models compared to standard quantized baselines.