No article text was recorded for this version.
activation-dependent sparsity
Version 1 of 123 papers24 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Make LLM Inference Affordable to Everyone: Augmenting GPU Memory with NDP-DIMM
- Blog: Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsity
- Blog: The SkipSponge attack: Sponge weight poisoning of deep neural networks
- Blog: Learn To be Efficient: Build Structured Sparsity in Large Language Models
- Blog: Structured in Space, Randomized in Time: Leveraging Dropout in RNNs for Efficient Training
- Blog: MoEfication: Transformer Feed-forward Layers are Mixtures of Experts
- Blog: R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference
- Blog: Training-Free Activation Sparsity in Large Language Models
- Blog: MASR: A Modular Accelerator for Sparse RNNs
- Blog: HSR-Enhanced Sparse Attention Acceleration
- Blog: PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU
- Blog: Batch Normalization Tells You Which Filter is Important
- Blog: MBS: Macroblock Scaling for CNN Model Reduction
- Blog: Joint Regularization on Activations and Weights for Efficient Neural Network Pruning
- Blog: Exploring the Benefit of Activation Sparsity in Pre-training
- Blog: Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion
- Blog: ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models
- Blog: Compressing DMA Engine: Leveraging Activation Sparsity for Training Deep Neural Networks
- Blog: SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression
- Blog: CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification
- Blog: Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons
- Blog: Breaking ReLU Barrier: Generalized MoEfication for Dense Pretrained Models
- Blog: FIREPruning: Learning-based Filter Pruning for Convolutional Neural Network Compression
History & citation
Current · Permanent link
- This direction split from Activation Sparsity for Efficient Transformer Inference (87% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_activation_dependent_sparsity_4140300f,
title = {activation-dependent sparsity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/activation-dependent-sparsity/rdr_4140300f67c54b83ac5e65d8127d4cab},
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_activation_dependent_sparsity_4140300f_v1,
title = {activation-dependent sparsity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/activation-dependent-sparsity/rdr_4140300f67c54b83ac5e65d8127d4cab/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}