No article text was recorded for this version.
compression-accuracy trade-off
Version 2 of 2873 papers916 conceptsfrozen 2026-10-04
Papers in this version
- Blog: A Proper Orthogonal Decomposition Approach for Parameters Reduction of Single Shot Detector Networks
- Blog: Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language Tasks
- Blog: Joint architecture and knowledge distillation in CNN for Chinese text recognition
- Blog: Accelerating Training using Tensor Decomposition
- Blog: Progressive Binarization with Semi-Structured Pruning for LLMs
- Blog: Nonparametric Compositional Stochastic Optimization for Risk-Sensitive Kernel Learning
- Blog: Channel Merging: Preserving Specialization for Merged Experts
- Blog: Compression of Fully-Connected Layer in Neural Network by Kronecker Product
- Blog: Learning Directly from Grammar Compressed Text
- Blog: Toward Democratized Generative AI in Next-Generation Mobile Edge Networks
- Blog: DepthNet Nano: A Highly Compact Self-Normalizing Neural Network for Monocular Depth Estimation
- Blog: PPC-GPT: Federated Task-Specific Compression of Large Language Models via Pruning and Chain-of-Thought Distillation
- Blog: Hallucination-aware Optimization for Large Language Model-empowered Communications
- Blog: Efficiency optimization of large-scale language models based on deep learning in natural language processing tasks
- Blog: Knowledge Distillation for Enhancing a Lightweight Magnet Tile Target Detection Model: Leveraging Spatial Attention and Multi-Scale Output Features
- Blog: Multi-stage Progressive Compression of Conformer Transducer for On-device Speech Recognition
- Blog: Correction to: A compression pipeline for one-stage object detection model
- Blog: Lightweight Hypercomplex MRI Reconstruction: A Generalized Kronecker-Parameterized Approach
- Blog: Lightweight Attribute Localizing Models for Pedestrian Attribute Recognition
- Blog: PATROL: Privacy-Oriented Pruning for Collaborative Inference Against Model Inversion Attacks
- Blog: Compressing Deep Neural Networks via Layer Fusion
- Blog: Improved JPEG Lossless Compression for Compression of Intermediate Layers in Neural Networks Based on Compute-In-Memory
- Blog: xCOMET-lite: Bridging the Gap Between Efficiency and Quality in Learned MT Evaluation Metrics
- Blog: Relationship between Model Compression and Adversarial Robustness: A Review of Current Evidence
- Blog: Deeply Tensor Compressed Transformers for End-to-End Object Detection
- Blog: Dense Vision Transformer Compression with Few Samples
- Blog: An Exploratory Study on Model Compression for Text-to-SQL
- Blog: Compressing Local Descriptor Models for Mobile Applications
- Blog: Low-Cost Representation for Restricted Boltzmann Machines
- Blog: DeepZip: Lossless Data Compression using Recurrent Neural Networks
- Blog: Dealing with Uncertainty in Fuzzy Inductive Reasoning Methodology
- Blog: COMPRESSIVE SENSING BASED CONVOLUTIONAL NEURAL NETWORK FOR OBJECT DETECTION
- Blog: On Error and Compression Rates for Prototype Rules
- Blog: LLMs on a Budget? Say HOLA
- Blog: Doping: A technique for efficient compression of LSTM models using sparse structured additive matrices
- Blog: OplixNet: Towards Area-Efficient Optical Split-Complex Networks with Real-to-Complex Data Assignment and Knowledge Distillation
- Blog: Doping: A technique for Extreme Compression of LSTM Models using Sparse Structured Additive Matrices
- Blog: ProFormer: Towards On-Device LSH Projection Based Transformers
- Blog: More is Less: A More Complicated Network with Less Inference Complexity
- Blog: EoRA: Training-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation
- Blog: Efficient Memory Management for GPU-based Deep Learning Systems
- Blog: TinyHD: Efficient Video Saliency Prediction with Heterogeneous Decoders using Hierarchical Maps Distillation
- Blog: MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution
- Blog: Online Hybrid Lightweight Representations Learning: Its Application to Visual Tracking
- Blog: Tiny SSD: A Tiny Single-shot Detection Deep Convolutional Neural Network for Real-time Embedded Object Detection
- Blog: Dense Vision Transformer Compression with Few Samples
- Blog: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices
- Blog: CTC-based Compression for Direct Speech Translation
- Blog: A Multi-Stage Duplex Fusion ConvNet for Aerial Scene Classification
- Blog: T-Net: Parametrizing Fully Convolutional Nets with a Single High-Order Tensor
- Blog: Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation
- Blog: Quantisation and Pruning for Neural Network Compression and Regularisation
- Blog: Knowledge Distillation for Anomaly Detection
- Blog: Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions
- Blog: CR-SFP: Learning Consistent Representation for Soft Filter Pruning
- Blog: Design and Implementation of a Lightweight Object Detection System for Resource-Constrained Edge Environments
- Blog: Multi-Precision Quantized Neural Networks via Encoding Decomposition of {-1, +1}
- Blog: SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training
- Blog: Composable Interventions for Language Models
- Blog: QUART-Online: Latency-Free Large Multimodal Language Model for Quadruped Robot Learning
Showing 60 of 873 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_compression_accuracy_trade_off_9924cd1f,
title = {compression-accuracy trade-off},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/compression-accuracy-trade-off/rdr_9924cd1f07b64d70a1338421cadce591},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_compression_accuracy_trade_off_9924cd1f_v2,
title = {compression-accuracy trade-off},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/compression-accuracy-trade-off/rdr_9924cd1f07b64d70a1338421cadce591/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}