Pure PyTorch Implementation of NVIDIA paper on Instant Training of Neural Graphics primitives: https://nvlabs.github.io/instant-ngp/

APOLLO: SGD-like Memory, AdamW-level Performance

1.5−3.0× lossless training or pre-training speedup. An off-the-shelf, easy-to-implement algorithm for the efficient training of foundation visual backbones.

SlamKit is an open source tool kit for efficient training of SpeechLMs. It was used for "Slamming: Training a Speech Language Model on One GPU in a Day"

Official code for our ECCV'22 paper "A Fast Knowledge Distillation Framework for Visual Recognition"

[arXiv:2309.16669] Code release for "Training a Large Video Model on a Single Machine in a Day"

Can We Find Strong Lottery Tickets in Generative Models? - Official Code (Pytorch)

PyTorch implementation of X3D models with Multigrid training.

[ICLR 2023] "Learning to Grow Pretrained Models for Efficient Transformer Training" by Peihao Wang, Rameswar Panda, Lucas Torroba Hennigen, Philip Greengard, Leonid Karlinsky, Rogerio Feris, David Cox, Zhangyang Wang, Yoon Kim

[ICLR 2023] MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization

Code for "OnlineAugment: Online Data Augmentation with Less Domain Knowledge" (ECCV 2020)

[CVPR 2020] L2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks

[ICLR 2021 Spotlight] "CPT: Efficient Deep Neural Network Training via Cyclic Precision" by Yonggan Fu, Han Guo, Meng Li, Xin Yang, Yining Ding, Vikas Chandra, and Yingyan (Celine) Lin.

✂️ Dataset Culling: Faster training of domain specific models with distillation ✂️ (IEEE ICIP 2019)

[ICLR 2023] Link Prediction with Non-Contrastive Learning

(CVPR 2022) Automated Progressive Learning for Efficient Training of Vision Transformers

Code for ACL 2025 Main paper "Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning".

This is the official repo for Densely-Anchored Sampling for Deep Metric Learning (ECCV 22).

[NeurIPS 2020] "FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training" by Yonggan Fu, Haoran You, Yang Zhao, Yue Wang, Chaojian Li, Kailash Gopalakrishnan, Zhangyang Wang, Yingyan Lin

Salient Video Frames Sampling Method Using the Mean of Deep Features for Efficient Model Training (KIBME 2021)