No article text was recorded for this version.
batch normalization folding
Version 2 of 2100 papers133 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Finet: Using Fine-grained Batch Normalization to Train Light-weight Neural Networks
- Blog: Fast and Incremental Loop Closure Detection Using Proximity Graphs
- Blog: SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization
- Blog: LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
- Blog: SSN: Learning Sparse Switchable Normalization via SparsestMax
- Blog: To Fold or Not to Fold: a Necessary and Sufficient Condition on Batch-Normalization Layers Folding
- Blog: Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks
- Blog: SpeedDETR: Speed-aware Transformers for End-to-end Object Detection
- Blog: Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization
- Blog: Lightweight Monocular Depth Estimation via Token-Sharing Transformer
- Blog: Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs
- Blog: Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution Heterogeneity
- Blog: BGGAN: Bokeh-Glass Generative Adversarial Network for Rendering Realistic Bokeh
- Blog: BlendNet: Design and Optimization of a Neural Network-Based Inference Engine Blending Binary and Fixed-Point Convolutions
- Blog: Unified Normalization for Accelerating and Stabilizing Transformers
- Blog: Research on Road Damage Recognition Based on VanillaNet Neural Network
- Blog: TabConv: Low-Computation CNN Inference via Table Lookups
- Blog: EfficientFormer: Vision Transformers at MobileNet Speed
- Blog: Bayesian Federated Neural Matching That Completes Full Information
- Blog: Powerformer: Efficient and High-Accuracy Privacy-Preserving Language Model with Homomorphic Encryption
- Blog: MA-BERT: Towards Matrix Arithmetic-only BERT Inference by Eliminating Complex Non-Linear Functions
- Blog: ModuloNET: Neural Networks Meet Modular Arithmetic for Efficient Hardware Masking
- Blog: EfficientFormer: Vision Transformers at MobileNet Speed
- Blog: LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
- Blog: HIRI-ViT: Scaling Vision Transformer with High Resolution Inputs
- Blog: Unified Normalization for Accelerating and Stabilizing Transformers
- Blog: LiteDepth: Digging into Fast and Accurate Depth Estimation on Mobile Devices
- Blog: CS-Rep: Making Speaker Verification Networks Embracing Re-parameterization
- Blog: HotBEV: Hardware-oriented Transformer-based Multi-View 3D Detector for BEV Perception
- Blog: Efficient Long-Range Attention Network for Image Super-resolution
- Blog: Unfolding Once is Enough: A Deployment-Friendly Transformer Unit for Super-Resolution
- Blog: Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios
- Blog: Binary Deep Neural Networks for Speech Recognition
- Blog: SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization
- Blog: PTMQ: Post-training Multi-Bit Quantization of Neural Networks
- Blog: DeepRebirth: Accelerating Deep Neural Network Execution on Mobile Devices
- Blog: Efficient Long-Range Attention Network for Image Super-Resolution
- Blog: Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
- Blog: Verification of Neural Networks: Enhancing Scalability through Pruning
- Blog: EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications
- Blog: RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers
- Blog: FLARE: A Dataflow-Aware and Scalable Hardware Architecture for Neural-Hybrid Scientific Lossy Compression
- Blog: An Open Source and Open Hardware Deep Learning-powered Visual Navigation Engine for Autonomous Nano-UAVs
- Blog: Pre-RMSNorm and Pre-CRMSNorm Transformers: Equivalent and Efficient Pre-LN Transformers
- Blog: ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks
- Blog: CoCo-FL: Communication- and Computation-Aware Federated Learning via Partial NN Freezing and Quantization
- Blog: HAWQ-V3: Dyadic Neural Network Quantization
- Blog: Your ViT is Secretly an Image Segmentation Model
- Blog: Overview of the Neural Network Compression and Representation (NNR) Standard
- Blog: Real-Time Monocular Depth Estimation on Embedded Systems
- Blog: Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization
- Blog: Linear Symmetric Quantization of Neural Networks for Low-precision Integer Hardware
- Blog: Reducing the Side-Effects of Oscillations in Training of Quantized YOLO Networks
- Blog: Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization
- Blog: AQD: Towards Accurate Quantized Object Detection
- Blog: Q-EEGNet: an Energy-Efficient 8-bit Quantized Parallel EEGNet Implementation for Edge Motor-Imagery Brain-Machine Interfaces
- Blog: You can remove GPT2's LayerNorm by fine-tuning
- Blog: H3AE: High Compression, High Speed, and High Quality AutoEncoder for Video Diffusion Models
- Blog: Fully Quantized Image Super-Resolution Networks
- Blog: PZnet: Efficient 3D ConvNet Inference on Manycore CPUs
Showing 60 of 100 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_batch_normalization_folding_336d307d,
title = {batch normalization folding},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/batch-normalization-folding/rdr_336d307d168b4bf6a85a67d144ef71ba},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_batch_normalization_folding_336d307d_v2,
title = {batch normalization folding},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/batch-normalization-folding/rdr_336d307d168b4bf6a85a67d144ef71ba/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}