No article text was recorded for this version.
activation-induced sparsity
Version 1 of 141 papers51 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Phonetic Context Embeddings for DNN-HMM Phone Recognition
- Blog: Sparse Subspace Clustering by Learning Approximation ℓ0 Codes
- Blog: Accelerating Transformer Inference and Training with 2:4 Activation Sparsity
- Blog: Sparsing Law: Towards Large Language Models with Greater Activation Sparsity
- Blog: Dynamic Mixture-of-Experts for Visual Autoregressive Model
- Blog: SQ-DM: Accelerating Diffusion Models with Aggressive Quantization and Temporal Sparsity
- Blog: Why Regularized Auto-Encoders learn Sparse Representation?
- Blog: Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time
- Blog: Resource Allocation in Uplink NOMA-IoT Networks: A Reinforcement-Learning Approach
- Blog: Sparse Subspace Clustering by Learning Approximation _0 Codes
- Blog: The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers
- Blog: Rectified linear neural networks with tied-scalar regularization for LVCSR
- Blog: AdaDrive: Self-Adaptive Slow-Fast System for Language-Grounded Autonomous Driving
- Blog: SplitFed resilience to packet loss: Where to split, that is the question
- Blog: Basis Pursuit Denoising via Recurrent Neural Network Applied to Super-Resolving SAR Tomography
- Blog: Mixture-of-Channels: Exploiting Sparse FFNs for Efficient LLMs Pre-Training and Inference
- Blog: Event-based optical flow on neuromorphic processor: ANN vs. SNN comparison based on activation sparsification
- Blog: MASR: A Modular Accelerator for Sparse RNNs
- Blog: Mixture of Experts Made Intrinsically Interpretable
- Blog: Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time
- Blog: Adam Induces Implicit Weight Sparsity in Rectifier Neural Networks
- Blog: PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU
- Blog: ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models
- Blog: Does Preprocessing Help Training Over-parameterized Neural Networks?
- Blog: On the Robustness and Training Dynamics of Raw Waveform Models
- Blog: The Utility of Sparse Representations for Control in Reinforcement Learning
- Blog: Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion
- Blog: Deep Sparse Rectifier Neural Networks
- Blog: Learning Graph Structure from Convolutional Mixtures
- Blog: On Network Science and Mutual Information for Explaining Deep Neural Networks
- Blog: ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models
- Blog: Transformation of Dense and Sparse Text Representations
- Blog: Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
- Blog: GLoMo: Unsupervised Learning of Transferable Relational Graphs
- Blog: Memorizing Documents with Guidance in Large Language Models
- Blog: A Probabilistic Framework for Deep Learning
- Blog: An Accelerated Alternating Partial Bregman Algorithm for ReLU-based Matrix Decomposition
- Blog: Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time
- Blog: Saturating Auto-Encoder
- Blog: Exploring ℓ0 Sparsification for Inference-free Sparse Retrievers
- Blog: Q-Sparse: All Large Language Models can be Fully Sparsely-Activated
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_activation_induced_sparsity_7ccf4be7,
title = {activation-induced sparsity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/activation-induced-sparsity/rdr_7ccf4be7ae8e4fdabce3278e8ff40157},
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_induced_sparsity_7ccf4be7_v1,
title = {activation-induced sparsity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/activation-induced-sparsity/rdr_7ccf4be7ae8e4fdabce3278e8ff40157/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}