SOTAVerified

Neural Network Compression

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 193 papers

TitleStatusHype
Linearity-based neural network compression—0
MUC-G4: Minimal Unsat Core-Guided Incremental Verification for Deep Neural Network Compression—0
Is Quantum Optimization Ready? An Effort Towards Neural Network Compression using Adiabatic Quantum Computing—0
Certified Neural Approximations of Nonlinear DynamicsCode0
Low-Rank Matrix Approximation for Neural Network Compression—0
GranQ: Granular Zero-Shot Quantization with Channel-Wise Activation Scaling in QAT—0
Stabilizing Quantization-Aware Training by Implicit-Regularization on Hessian Matrix—0
Compression of Site-Specific Deep Neural Networks for Massive MIMO Precoding—0
A Novel Structure-Agnostic Multi-Objective Approach for Weight-Sharing Compression in Deep Neural Networks—0
What is Left After Distillation? How Knowledge Transfer Impacts Fairness and Bias—0
Efficient and Robust Knowledge Distillation from A Stronger Teacher Based on Correlation Matching—0
Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior ModelsCode0
Adaptive Error-Bounded Hierarchical Matrices for Efficient Neural Network Compression—0
TropNNC: Structured Neural Network Compression Using Tropical Geometry—0
Unified Framework for Neural Network Compression via Decomposition and Optimal Rank Selection—0
Convolutional Neural Network Compression Based on Low-Rank Decomposition—0
Condensed Sample-Guided Model Inversion for Knowledge Distillation—0
An Efficient Real-Time Object Detection Framework on Resource-Constricted Hardware Devices via Software and Hardware Co-design—0
Tiled Bit Networks: Sub-Bit Neural Network Compression Through Reuse of Learnable Binary Vectors—0
The Impact of Quantization and Pruning on Deep Reinforcement Learning Models—0
Neural Network Compression for Reinforcement Learning Tasks—0
Torch2Chip: An End-to-end Customizable Deep Neural Network Compression and Deployment Toolkit for Prototype Hardware Accelerator DesignCode2
Towards Explaining Deep Neural Network Compression Through a Probabilistic Latent Space—0
SPC-NeRF: Spatial Predictive Compression for Voxel Based Radiance Field—0
Towards Meta-Pruning via Optimal TransportCode1
EPSD: Early Pruning with Self-Distillation for Efficient Model Compression—0
Convolutional Neural Network Compression via Dynamic Parameter Rank Pruning—0
Balanced and Deterministic Weight-sharing Helps Network Performance—0
ABKD: Graph Neural Network Compression with Attention-Based Knowledge Distillation—0
Grokking as Compression: A Nonlinear Complexity Perspective—0
Causal-DFQ: Causality Guided Data-free Network QuantizationCode0
A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and RecommendationsCode2
Quantization Aware Factorization for Deep Neural Network Compression—0
Survey on Computer Vision Techniques for Internet-of-Things Devices—0
Model Compression Methods for YOLOv5: A Review—0
Lightweight Attribute Localizing Models for Pedestrian Attribute Recognition—0
Neural Network Compression using Binarization and Few Full-Precision Weights—0
Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGDCode0
Understanding the Effect of the Long Tail on Neural Network Compression—0
End-to-End Neural Network Compression via _1_2 Regularized Latency Surrogates—0
Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference—0
Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network CompressionCode0
Evaluation Metrics for DNNs Compression—0
How Informative is the Approximation Error from Tensor Decomposition for Neural Network Compression?—0
Guaranteed Quantization Error Computation for Neural Network Model Compression—0
SwiftTron: An Efficient Hardware Accelerator for Quantized TransformersCode1
WHC: Weighted Hybrid Criterion for Filter Pruning on Convolutional Neural NetworksCode0
DepGraph: Towards Any Structural PruningCode4
Magnitude and Similarity based Variable Rate Filter Pruning for Efficient Convolution Neural NetworksCode0
PD-Quant: Post-Training Quantization based on Prediction Difference MetricCode1
Show:102550
← PrevPage 1 of 4Next →

No leaderboard results yet.