[CVPR 2023] Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs
-
Updated
Jun 18, 2024 - Python
[CVPR 2023] Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs
[CVPR 2024] Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis
[ICML'24 Oral] APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference
Official PyTorch implementation of "Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets" (ICLR 2021)
Official PyTorch implementation of "Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets" (ICLR 2023 notable top 25%)
[ICLR'24] "DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training" by Aochuan Chen*, Yimeng Zhang*, Jinghan Jia, James Diffenderfer, Jiancheng Liu, Konstantinos Parasyris, Yihua Zhang, Zheng Zhang, Bhavya Kailkhura, Sijia Liu
Denoising Diffusion Step-aware Models (ICLR2024)
[NeurIPS 2023] Structural Pruning for Diffusion Models
Code for "Language Model Knowledge Distillation for Efficient Question Answering in Spanish" (ICLR 2024 Tiny Papers)
[ICML 2023] Hierarchical Grammar-Induced Geometry for Data-Efficient Molecular Property Prediction
[ICML 2023] UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers.
Official PyTorch training code of Accelerating Deep Neural Networks via Semi-Structured Activation Sparsity (ICCV2023-RCV)
This repository is for reproducing the results shown in the NNCodec ICML Workshop paper. Additionally, it includes a demo, prepared for the Neural Compression Workshop (NCW).
[ICLR'23] Trainability Preserving Neural Pruning (PyTorch)
Frame Flexible Network (CVPR2023)
NeurIPS 2021, Official codes for "Efficient Training of Visual Transformers with Small Datasets".
Code and resources on scalable and efficient Graph Neural Networks
[NeurIPS2022] Official implementation of the paper 'Green Hierarchical Vision Transformer for Masked Image Modeling'.
This repository provides implementation of a baseline method and our proposed methods for efficient Skeleton-based Human Action Recognition.
A generic code base for neural network pruning, especially for pruning at initialization.
Add a description, image, and links to the efficient-deep-learning topic page so that developers can more easily learn about it.
To associate your repository with the efficient-deep-learning topic, visit your repo's landing page and select "manage topics."