No article text was recorded for this version.
global importance ranking
Version 1 of 171 papers99 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Numerical Pruning for Efficient Autoregressive Models
- Blog: HEAPr: Hessian-based Efficient Atomic Expert Pruning in Output Space
- Blog: Decomposable-Net: Scalable Low-Rank Compression for Neural Networks
- Blog: Exploring Federated Pruning for Large Language Models
- Blog: Spectral pruning of fully connected layers
- Blog: Accelerating Convolutional Networks via Global & Dynamic Filter Pruning
- Blog: COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning
- Blog: Attribution-guided Pruning for Compression, Circuit Discovery, and Targeted Correction in LLMs
- Blog: Fluctuation-Based Adaptive Structured Pruning for Large Language Models
- Blog: Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes
- Blog: A One-step Pruning-recovery Framework for Acceleration of Convolutional Neural Networks
- Blog: COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning
- Blog: Importance Estimation for Neural Network Pruning
- Blog: Exploring Gradient Flow Based Saliency for DNN Model Compression
- Blog: Probabilistic Connection Importance Inference and Lossless Compression of Deep Neural Networks
- Blog: Multi-Layer Pruning Framework for Compressing Single Shot MultiBox Detector
- Blog: Pruning Convolutional Neural Networks for Resource Efficient Inference
- Blog: Towards Efficient Model Compression via Learned Global Ranking
- Blog: Layer-compensated Pruning for Resource-constrained Convolutional Neural Networks
- Blog: Learning Efficient Convolutional Networks through Network Slimming
- Blog: OICSR: Out-In-Channel Sparsity Regularization for Compact Deep Neural Networks
- Blog: AIRE-Prune: Asymptotic Impulse-Response Energy for State Pruning in State Space Models
- Blog: Loss-Driven Channel Pruning of Convolutional Neural Networks
- Blog: Fine-Grained Neural Network Abstraction for Efficient Formal Verification
- Blog: FIREPruning: Learning-based Filter Pruning for Convolutional Neural Network Compression
- Blog: Efficient Neural Network Compression
- Blog: Pruning during training by network efficacy modeling
- Blog: Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models
- Blog: Neuron ranking - an informed way to condense convolutional neural networks architecture
- Blog: Pruning by explaining: A novel criterion for deep neural network pruning
- Blog: SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning
- Blog: Influence Function Based Second-Order Channel Pruning-Evaluating True Loss Changes For Pruning Is Possible Without Retraining
- Blog: Knowledge-preserving Pruning for Pre-trained Language Models without Retraining
- Blog: SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning
- Blog: (PASS) Visual Prompt Locates Good Structure Sparsity through a Recurrent HyperNetwork
- Blog: Constraint-Aware Importance Estimation for Global Filter Pruning under Multiple Resource Constraints
- Blog: CSTAR: Towards Compact and Structured Deep Neural Networks with Adversarial Robustness
- Blog: What is the State of Neural Network Pruning?
- Blog: Dynamic Low-rank Estimation for Transformer-based Language Models
- Blog: Rare Gems: Finding Lottery Tickets at Initialization
- Blog: Structured Pruning for Large Language Models Using Coupled Components Elimination and Minor Fine-tuning
- Blog: Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks
- Blog: DLP: Dynamic Layerwise Pruning in Large Language Models
- Blog: Importance Estimation for Neural Network Pruning
- Blog: A Greedy Hierarchical Approach to Whole-Network Filter-Pruning in CNNs
- Blog: Feature Statistics Guided Efficient Filter Pruning
- Blog: Gradual Channel Pruning while Training using Feature Relevance Scores for Convolutional Neural Networks
- Blog: Efficient Unstructured Pruning of Mamba State-Space Models for Resource-Constrained Environments
- Blog: Towards thinner convolutional neural networks through Gradually Global Pruning
- Blog: Efficient Adversarial Training with Robust Early-Bird Tickets
- Blog: Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks
- Blog: What Matters in Transformers? Not All Attention is Needed
- Blog: Target Aware Network Adaptation for Efficient Representation Learning
- Blog: Structured Sparsity Learning for Efficient Video Super-Resolution
- Blog: Physics Inspired Criterion for Pruning-Quantization Joint Learning
- Blog: Exploring Gradient Flow Based Saliency for DNN Model Compression
- Blog: Pruning at a Glance: Global Neural Pruning for Model Compression
- Blog: Adaptive Loss-Aware Quantization for Multi-Bit Networks
- Blog: Structured Probabilistic Pruning for Convolutional Neural Network Acceleration
- Blog: Towards Optimal Filter Pruning with Balanced Performance and Pruning Speed
Showing 60 of 71 papers.
History & citation
Current · Permanent link
- This direction split from Global Sparsity Allocation for Efficient Model Compression (62% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_global_importance_ranking_e7e5e482,
title = {global importance ranking},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/global-importance-ranking/rdr_e7e5e482130c4ae4aed71e480d13608b},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_global_importance_ranking_e7e5e482_v1,
title = {global importance ranking},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/global-importance-ranking/rdr_e7e5e482130c4ae4aed71e480d13608b/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}