No article text was recorded for this version.
pruning granularity trade-off
Version 1 of 1241 papers263 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Self-Supervised GAN Compression
- Blog: Sparse Transfer Learning Accelerates and Enhances Certified Robustness: A Comprehensive Study
- Blog: CIMinus: Empowering Sparse DNN Workloads Modeling and Exploration on SRAM-Based CIM Architectures
- Blog: The Sparsity Roofline: Understanding the Hardware Limits of Sparse Neural Networks
- Blog: Shfl-BW: Accelerating Deep Neural Network Inference with Tensor-Core\n Aware Weight Pruning
- Blog: A Survey on Deep Neural Network Pruning: Taxonomy, Comparison, Analysis, and Recommendations
- Blog: A Compression-Compilation Co-Design Framework Towards Real-Time Object Detection on Mobile Devices
- Blog: GAP: a Global Adaptive Pruning Method for Large Language Models
- Blog: DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models
- Blog: Block-Sparse Recurrent Neural Networks
- Blog: One Less Reason for Filter Pruning: Gaining Free Adversarial Robustness with Structured Grouped Kernel Pruning
- Blog: Balanced Sparsity for Efficient DNN Inference on GPU
- Blog: Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning
- Blog: Dynamic Probabilistic Pruning: A general framework for hardware-constrained pruning at different granularities
- Blog: Pruning Blocks for CNN Compression and Acceleration via Online Ensemble Distillation
- Blog: A Comprehensive Survey of Compression Algorithms for Language Models
- Blog: Exploring the Regularity of Sparse Structure in Convolutional Neural Networks
- Blog: WRP: Weight Recover Prune for Structured Sparsity
- Blog: PopSparse: Accelerated block sparse matrix multiplication on IPU
- Blog: An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices
- Blog: HRBP: Hardware-friendly Regrouping towards Block-based Pruning for Sparse CNN Training
- Blog: FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN Accelerator
- Blog: A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations
- Blog: LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification
- Blog: TSENOR: Highly-Efficient Algorithm for Finding Transposable N:M Sparse Masks
- Blog: Task-Agnostic Structured Pruning of Speech Representation Models
- Blog: Enhancing Certifiable Semantic Robustness via Robust Pruning of Deep Neural Networks
- Blog: HEAPr: Hessian-based Efficient Atomic Expert Pruning in Output Space
- Blog: Adversarial Robustness vs. Model Compression, or Both?
- Blog: SBNet: Sparse Blocks Network for Fast Inference
- Blog: Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets
- Blog: AutoSculpt: A Pattern-based Model Auto-pruning Framework Using Reinforcement Learning and Graph Learning
- Blog: Dynamic Structure Pruning for Compressing CNNs
- Blog: Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy
- Blog: StructPrune: Structured Global Pruning asymptotics with $\mathcal{O}(\sqrt{N})$ GPU Memory
- Blog: Learning N: M Fine-grained Structured Sparse Neural Networks From Scratch
- Blog: SlimLLM: Accurate Structured Pruning for Large Language Models
- Blog: Scene Adaptive Sparse Transformer for Event-based Object Detection
- Blog: NPAS: A Compiler-Aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration
- Blog: Winning the Lottery Ahead of Time: Efficient Early Network Pruning
- Blog: Fluctuation-based Adaptive Structured Pruning for Large Language Models
- Blog: Efficient Winning Tickets Drawing over Fine-Grained Structured Sparsity
- Blog: Faster CNNs with Direct Sparse Convolutions and Guided Pruning
- Blog: Layer Collapse Can be Induced by Unstructured Pruning
- Blog: Progressive multi-level distillation learning for pruning network
- Blog: Dynamic Sparsity Is Channel-Level Sparsity Learner
- Blog: PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech Representations
- Blog: Exposing and Exploiting Fine-Grained Block Structures for Fast and Accurate Sparse Training
- Blog: Self-Supervised Generative Adversarial Compression
- Blog: Iterative Deep Model Compression and Acceleration in the Frequency Domain
- Blog: BlockPruner: Fine-grained Pruning for Large Language Models
- Blog: FineScope : Precision Pruning for Domain-Specialized Large Language Models Using SAE-Guided Self-Data Cultivation
- Blog: REPrune: Channel Pruning via Kernel Representative Selection
- Blog: UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs
- Blog: SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks at the Edge
- Blog: FlexHiNM-GP: Flexible Hierarchical Pruning via Region Allocation and Channel Permutation
- Blog: EGGS-PTP: An Expander-Graph Guided Structured Post-training Pruning Method for Large Language Models
- Blog: Accelerating Sparse Convolution with Column Vector-Wise Sparsity
- Blog: STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning
- Blog: Accelerating Sparse Deep Neural Networks
Showing 60 of 241 papers.
History & citation
Current · Permanent link
- Balancing Pruning Granularity for Accuracy and Speed merged into this direction (85% overlap)
- Semi-Structured Sparsity for Hardware-Efficient Neural Networks merged into this direction (59% overlap)
- Structured Pruning for Hardware Accelerated Inference merged into this direction (60% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_pruning_granularity_trade_off_952520a2,
title = {pruning granularity trade-off},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/pruning-granularity-trade-off/rdr_952520a29a8f48d598c2437274f61e3d},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_pruning_granularity_trade_off_952520a2_v1,
title = {pruning granularity trade-off},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/pruning-granularity-trade-off/rdr_952520a29a8f48d598c2437274f61e3d/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}