TASA improves task-aware mixed-precision LLM quantization by searching calibration data mixtures via gradient-trace alignment and aggregating perplexity plus reasoning sensitivity signals, enabling 3.5-bit models to match or beat 4-bit baselines with over 20-point gains on GSM8K.
IMPQ: Interaction-aware layerwise mixed preci- sion quantization for LLMs.arXiv preprint arXiv:2509.15455
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3representative citing papers
The budget constraint in discrete model compression defines a Riemannian manifold allowing exact-constraint first-order optimization via Riemannian Constrained Optimization (RCO) without extra hyperparameters.
citing papers explorer
-
Beyond Activation Alignment:The Alignment-Diversity Tradeoff in Task-Aware LLM Quantization
TASA improves task-aware mixed-precision LLM quantization by searching calibration data mixtures via gradient-trace alignment and aggregating perplexity plus reasoning sensitivity signals, enabling 3.5-bit models to match or beat 4-bit baselines with over 20-point gains on GSM8K.
-
Model Compression with Exact Budget Constraints via Riemannian Manifolds
The budget constraint in discrete model compression defines a Riemannian manifold allowing exact-constraint first-order optimization via Riemannian Constrained Optimization (RCO) without extra hyperparameters.
- Statistically-Lossless Quantization of Large Language Models