No article text was recorded for this version.
linear layer fusion
Version 2 of 273 papers101 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Layer Collapse Can be Induced by Unstructured Pruning
- Blog: Can Unstructured Pruning Reduce the Depth in Deep Neural Networks?
- Blog: NEPENTHE: Entropy-Based Pruning as a Neural Network Depth's Reducer
- Blog: ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks
- Blog: DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
- Blog: RepCNN: Micro-sized, Mighty Models for Wakeword Detection
- Blog: Towards an Effective Orthogonal Dictionary Convolution Strategy
- Blog: Sequential Convolution and Runge-Kutta Residual Architecture for Image Compressed Sensing
- Blog: Rethinking Depth Pruning for Vision Transformers: A Heterogeneity-Aware Perspective
- Blog: CoPriv: Network/Protocol Co-Optimization for Communication-Efficient Private Inference
- Blog: Attention-Based Neural Networks for Chroma Intra Prediction in Video Coding
- Blog: MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention
- Blog: Collapsible Linear Blocks for Super-Efficient Super Resolution
- Blog: Enhanced collapsible linear blocks for arbitrary sized image super-resolution
- Blog: Till the Layers Collapse: Compressing a Deep Neural Network Through the Lenses of Batch Normalization Layers
- Blog: Towards Transparent Application of Machine Learning in Video Processing
- Blog: The Simpler The Better: An Entropy-Based Importance Metric to Reduce Neural Networks' Depth
- Blog: Centripetal SGD for Pruning Very Deep Convolutional Networks With Complicated Structure
- Blog: Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers
- Blog: DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
- Blog: Restructurable Activation Networks
- Blog: Surround the Nonlinearity: Inserting Foldable Convolutional Autoencoders to Reduce Activation Footprint
- Blog: NetBooster: Empowering Tiny Deep Learning By Standing on the Shoulders of Deep Giants
- Blog: ConformalLayers: A non-linear sequential neural network with associative layers
- Blog: Accelerating the convergence speed of neural networks learning methods using least squares
- Blog: Implicit Rank-Minimizing Autoencoder
- Blog: A representer theorem for deep neural networks
- Blog: Deep Epitome for Unravelling Generalized Hamming Network
- Blog: Fine-tuning Pruned Networks with Linear Over-parameterization
- Blog: ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting
- Blog: An SMT-Based Approach for Verifying Binarized Neural Networks
- Blog: Nonlinear Advantage: Trained Networks Might Not Be As Complex as You Think
- Blog: A Layer Decomposition-Recomposition Framework for Neuron Pruning towards Accurate Lightweight Networks
- Blog: DeepReDuce: ReLU Reduction for Fast Private Inference
- Blog: Can Unstructured Pruning Reduce the Depth in Deep Neural Networks?
- Blog: Lowering PyTorch's Memory Consumption for Selective Differentiation
- Blog: ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization
- Blog: DelBugV: Delta-Debugging Neural Network Verifiers
- Blog: LayerCollapse: Adaptive compression of neural networks
- Blog: Diverse Branch Block: Building a Convolution as an Inception-Like Unit
- Blog: On transfer learning using a MAC model variant
- Blog: MSE-Optimal Neural Network Initialization via Layer Fusion
- Blog: An Efficient Transformer Decoder with Compressed Sub-layers
- Blog: Layer Sparsity in Neural Networks
- Blog: Online Filter Clustering and Pruning for Efficient Convnets
- Blog: Learning Aggregations of Binary Activated Neural Networks with Probabilities over Representations
- Blog: An Incremental Construction of Deep Neuro Fuzzy System for Continual Learning of Nonstationary Data Streams
- Blog: Utilizing Excess Resources in Training Neural Networks
- Blog: Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inference
- Blog: LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference
- Blog: Selective Network Linearization for Efficient Private Inference
- Blog: Till the Layers Collapse: Compressing a Deep Neural Network through the Lenses of Batch Normalization Layers
- Blog: DeepReDuce: ReLU Reduction for Fast Private Inference
- Blog: Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming
- Blog: Improved Projection Learning for Lower Dimensional Feature Maps
- Blog: ExpandNets: Exploiting Linear Redundancy to Train Small Networks
- Blog: You Need to Pay Better Attention
- Blog: The Simpler The Better: An Entropy-Based Importance Metric To Reduce Neural Networks' Depth
- Blog: SP³: Enhancing Structured Pruning via PCA Projection
- Blog: An SMT-Based Approach for Verifying Binarized Neural Networks
Showing 60 of 73 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_linear_layer_fusion_e6c2eef2,
title = {linear layer fusion},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/linear-layer-fusion/rdr_e6c2eef2bee245b985f402d3e0a4c338},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_linear_layer_fusion_e6c2eef2_v2,
title = {linear layer fusion},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/linear-layer-fusion/rdr_e6c2eef2bee245b985f402d3e0a4c338/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}