CORP performs one-shot structured pruning of Transformers by modeling removed components as affine functions of retained ones and solving closed-form ridge regressions on calibration data to fold compensation into weights, retaining 83.27% Top-1 accuracy on DeiT-Huge after 50% pruning.
Preserving deep representations in one-shot pruning: A hessian-free second- order optimization framework
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
RQP reduces search cost up to 20.58x versus standard monotonic HGQ workflows on jet substructure classification while producing competitive Pareto frontiers for FPGA neural network accelerators.
STARFISH recovers accuracy in pruned neural networks by optimizing internal state alignment to the original model with a minimal unlabeled calibration set, outperforming prior recovery methods especially at high pruning ratios.
Marchenko-Pastur random-matrix pruning of DNNs yields theoretical certificates for accuracy preservation under small fine-tuning and empirical ImageNet results with 50-60% MAC reduction and sub-2pp accuracy drops on ViT and CNN models.
citing papers explorer
-
CORP: Closed-Form One-shot Representation-Preserving Structured Pruning for Transformers
CORP performs one-shot structured pruning of Transformers by modeling removed components as affine functions of retained ones and solving closed-form ridge regressions on calibration data to fold compensation into weights, retaining 83.27% Top-1 accuracy on DeiT-Huge after 50% pruning.
-
RQP: Resource-Oriented Quantiser Pruning for Neural Networks on FPGAs
RQP reduces search cost up to 20.58x versus standard monotonic HGQ workflows on jet substructure classification while producing competitive Pareto frontiers for FPGA neural network accelerators.
-
STARFISH: faST Accuracy Recovery in pruned networks From Internal State Healing
STARFISH recovers accuracy in pruned neural networks by optimizing internal state alignment to the original model with a minimal unlabeled calibration set, outperforming prior recovery methods especially at high pruning ratios.
-
Pruning Deep Neural Networks via the Marchenko--Pastur Distribution
Marchenko-Pastur random-matrix pruning of DNNs yields theoretical certificates for accuracy preservation under small fine-tuning and empirical ImageNet results with 50-60% MAC reduction and sub-2pp accuracy drops on ViT and CNN models.