No article text was recorded for this version.
high-sparsity performance degradation
Version 2 of 2494 papers573 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Adaptive Pruning of Deep Neural Networks for Resource-Aware Embedded Intrusion Detection on the Edge
- Blog: Low-Rank Winograd Transformation for 3D Convolutional Neural Networks
- Blog: The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter
- Blog: Pruning Before Training May Improve Generalization, Provably
- Blog: Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!
- Blog: One Shot vs. Iterative: Rethinking Pruning Strategies for Model Compression
- Blog: Beware of Calibration Data for Pruning Large Language Models
- Blog: Pruning Convolutional Neural Networks for Image Instance Retrieval
- Blog: The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation
- Blog: Compression Laws for Large Language Models
- Blog: Dynamic Low-Rank Sparse Adaptation for Large Language Models
- Blog: Effective Model Pruning
- Blog: QUICKSAL: A small and sparse visual saliency model for efficient inference in resource constrained hardware
- Blog: A Length Adaptive Algorithm-Hardware Co-design of Transformer on FPGA Through Sparse Attention and Dynamic Pipelining
- Blog: Bayesian sparse learning with preconditioned stochastic gradient MCMC and its applications
- Blog: Exploring the Relative Value of Collaborative Optimisation Pathways (Student Abstract)
- Blog: Pruning Sparse Tensor Neural Networks Enables Deep Learning for 3D Ultrasound Localization Microscopy
- Blog: Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward
- Blog: Less Token, More Signal: MoE Expert Pruning via Critical Token Selection
- Blog: Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!
- Blog: Beware of Calibration Data for Pruning Large Language Models
- Blog: OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization
- Blog: ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models
- Blog: Reprogramming under constraints: Revisiting efficient and reliable transferability of lottery tickets
- Blog: Olica: Efficient Structured Pruning of Large Language Models without Retraining
- Blog: Data-Free Backbone Fine-Tuning for Pruned Neural Networks
- Blog: Prune and Tune: Improving Efficient Pruning Techniques for Massive Language Models
- Blog: SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models
- Blog: DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization
- Blog: Partitioning Large Scale Deep Belief Networks Using Dropout
- Blog: Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon
- Blog: The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks
- Blog: Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large Language Models
- Blog: Coarse-Grained Pruning of Neural Network Models Based on Blocky Sparse Structure
- Blog: The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMM
- Blog: EcoVLA: Environment-Aware Adaptive Pruning with Interleaved Inference Orchestration for Vision-Language-Action Models
- Blog: Non-transferable Pruning
- Blog: SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models
- Blog: Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models
- Blog: Pruning Artificial Neural Networks: A Way to Find Well-Generalizing, High-Entropy Sharp Minima
- Blog: Parameter-Efficient Sparsity for Large Language Models Fine-Tuning
- Blog: Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiency
- Blog: Optimizing Small Language Models for In-Vehicle Function-Calling
- Blog: How can representation dimension dominate structurally pruned LLMs?
- Blog: Neuron-based Pruning of Deep Neural Networks with Better Generalization using Kronecker Factored Curvature Approximation
- Blog: Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiency
- Blog: The Cost of Compression: Investigating the Impact of Compression on Parametric Knowledge in Language Models
- Blog: Sparsified Model Zoo Twins: Investigating Populations of Sparsified Neural Network Models
- Blog: Reconstruction Task Finds Universal Winning Tickets
- Blog: Pruning Deep Neural Networks from a Sparsity Perspective
- Blog: Comb, Prune, Distill: Towards Unified Pruning for Vision Model Compression
- Blog: Pruning Deep Neural Networks from a Sparsity Perspective
- Blog: Efficient Pruning of Text-to-Image Models: Insights from Pruning Stable Diffusion
- Blog: GradPruner: Gradient-guided Layer Pruning Enabling Efficient Fine-Tuning and Inference for LLMs
- Blog: MINI-LLM: Memory-Efficient Structured Pruning for Large Language Models
- Blog: CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification
- Blog: Gradient-Free Adaptive Global Pruning for Pre-trained Language Models
- Blog: Adapt-Pruner: Adaptive Structural Pruning for Efficient Small Language Model Training
- Blog: Fine-tune Before Structured Pruning: Towards Compact and Accurate Self-Supervised Models for Speaker Diarization
- Blog: Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment
Showing 60 of 494 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_high_sparsity_performance_degradation_e130fa03,
title = {high-sparsity performance degradation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/high-sparsity-performance-degradation/rdr_e130fa035a304684aa9ad88163397fad},
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_high_sparsity_performance_degradation_e130fa03_v2,
title = {high-sparsity performance degradation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/high-sparsity-performance-degradation/rdr_e130fa035a304684aa9ad88163397fad/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}