NUS-HPC-AI-Lab/InfoGrowth

Stars
19
Rank 1,163,249 (Top 23 %)
Language
Python
Created 5 months ago
Updated 3 months ago

NUS-HPC-AI-Lab/InfoGrowth

NUS-HPC-AI-Lab

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Efficient and Online Dataset Growth Algorithm (with cleanness and diversity awareness) to deal with growing web data

VideoSys

VideoSys: An easy and efficient system for video generation

Neural-Network-Parameter-Diffusion

We introduce a novel approach for parameter generation, named neural network parameter diffusion (p-diff), which employs a standard latent diffusion model to synthesize a new set of parameters

InfoBatch

Lossless Training Speed Up by Unbiased Dynamic Data Pruning

DATM

ICLR 2024, Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching

LARS-ImageNet-PyTorch

Accuracy 77%. Large batch deep learning optimizer LARS for ImageNet with PyTorch and ResNet, using Horovod for distribution. Optional accumulated gradient and NVIDIA DALI dataloader.

Dynamic-Tuning

The official implementation of "2024NeurIPS Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation"

oh-my-server

GEOM

Pytorch implementation of ICML-2024 "Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching"

PAD

Prioritize Alignment in Dataset Distillation

pytorch-lamb

PyTorch implementation of LAMB for ImageNet/ResNet-50 training

Helen

The official implementation of "Helen: Optimizing CTR Prediction Models with Frequency-wise Hessian Eigenvalue Regularization"

CTRL

Pytorch implementation of "Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matching"

Dynamic-Diffusion-Transformer