SGHS: Dynamic Hybrid Sparse Pruning via Fine-grained Sensitivity Allocation for LLMs — one-shot N:M semi-structured pruning with sub-block heterogeneous patterns
-
Updated
Sep 14, 2026 - Python
#
sparsity
Here are 136 public repositories matching this topic...
Iterative magnitude pruning in PyTorch for finding lottery tickets (Frankle & Carbin), with late rewinding, quantisation-aware training and resumable checkpoints. Started for my ML MSc.
python machine-learning sparsity deep-learning pytorch pruning quantization model-compression lottery-ticket-hypothesis winning-tickets quantization-aware-training neural-network-pruning torchao iterative-magnitude-pruning
-
Updated
Oct 6, 2026 - Python
Official Repository for CSRv2 - ICLR 2026
-
Updated
Feb 28, 2026 - Python
A feed-forward neural network that learns to prune itself during training using differentiable gate parameters
machine-learning sparsity deep-learning pytorch cifar10 model-compression l1-regularization neural-network-pruning self-pruning
-
Updated
Apr 24, 2026 - Python
Official Repository for SeqTopK
-
Updated
Nov 26, 2025 - Python
python machine-learning sparsity neural-network pytorch symbolic sympy elastic-net custom-layer bayesian-regularization
-
Updated
Oct 9, 2022 - Python
Molecular-property prediction with sparsity
sparsity computational-chemistry group-lasso elastic-net sparse-group-lasso molecular-property-prediction
-
Updated
May 25, 2022 - Python
A supervised autoencoder with structured sparsity for efficient and informed clinical prognosis.
sparsity feature-selection supervised-learning autoencoder metabolomics interpretability metabolomics-database prognostic-score
-
Updated
Jul 7, 2023 - Python
A pure implementation for sparse denoising autoencoder with adaptive evolutionary training using Scipy. The sparse implementation makes the algorithm scalable to high dimensional data and trainable on CPUs.
-
Updated
Feb 10, 2020 - Python
Efficient neural network compression through sparse weight pruning for NPU oriented inference.
-
Updated
Aug 28, 2026 - Python
Simple world models lead to good abstractions, Google Cerebra internship 2020/master thesis at EPFL LCN 2021 ⬛◼️▪️🔦
sparsity epfl thesis tensorflow pytorch causality primal-dual model-based-reinforcement-learning tf-agents causal-reinforcement-learning abstraction-learning consciousness-prior model-sparsity
-
Updated
Sep 26, 2024 - Python
Code to reproduce the experiments of ICLR2023-paper: How I Learned to Stop Worrying and Love Retraining
-
Updated
Feb 23, 2023 - Python
Minimal Reproducibility Study of (https://arxiv.org/abs/1911.05248). Experiments with Compression of Deep Neural Networks
deep-neural-networks sparsity deep-learning neural-network tensorflow pruning deeplearning celeba celeba-dataset tensorflow-lite tflite sparsity-optimization model-optimization neural-network-pruning tracker-misc
-
Updated
Jun 4, 2021 - Python
Deterministic search over per-layer bit-widths to fit a model into a fixed VRAM budget. An LLM agent proposing allocations lost to a plain greedy loop by 4,386x at the same memory envelope; 2:4 structured sparsity lost to dense by 3,307x at equal memory.
python sparsity reproducible-research pytorch quantization model-compression mixed-precision inference-optimization llm-inference
-
Updated
Sep 9, 2026 - Python
Public code of the ML course
-
Updated
Jun 7, 2017 - Python
[ECCV 2026] KATANA: Knowledge-Aligned Topology-Aware Neural Agents for RL-Driven Vision-Language Model Compression
sparsity reinforcement-learning pruning model-compression efficient-inference multimodal llm vision-language-models grpo eccv2026
-
Updated
Jul 11, 2026 - Python
Reproducible Apple M2 study of dynamic FFN block sparsity for LLM inference: quality vs. latency, packed vs. per-neuron kernels, with all raw data and validators
performance-engineering sparsity reproducible-research neon llama arm64 apple-silicon cpu-inference llm-inference activation-sparsity
-
Updated
Sep 30, 2026 - Python
SinkSLOT: Sinkhorn via Sparse Lifted Optimal Transport
-
Updated
Sep 30, 2026 - Python
Add this topic to your repo
To associate your repository with the sparsity topic, visit your repo's landing page and select "manage topics."