Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment

[NeuIPS'24] FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction

[ACM CSUR 2025] Understanding World or Predicting Future? A Comprehensive Survey of World Models

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

You only need to configure one file to support model heterogeneity. Consistent GPU memory usage for single or multiple clients.

PyQt5 implementation of YOLOv5 GUI

CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks

Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

非常全的文言文（古文）-现代文平行语料

A PyTorch implementation of EfficientNet

Official repository for "AM-RADIO: Reduce All Domains Into One"

👀「大模型」2小时从0训练65M参数的视觉多模态VLM！Train a 65M-parameter VLM from scratch in just 2h!

✨✨Latest Advances on Multimodal Large Language Models

Mamba SSM architecture

Grok open release

MOCO v3 adaptation for MNIST dataset

PyTorch implementation of RCG https://arxiv.org/abs/2312.03701

Code for ICLR 2023 Paper Better Generative Replay for Continual Federated Learning

Python Socket.IO server and client

A python (PyTorch) implementation of federated multi-encoding U-Net (Fed-MENU) method for federated learning-based multi-organ segmentation with inconsistent labels.

Code for: Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification

This repository is an official PyTorch implementation of the paper "Boundary-Sensitive Loss Function With Location Constraint for Hard Region Segmentation"

Inference code for Llama models

Making large AI models cheaper, faster and more accessible

Handy PyTorch implementation of Federated Learning (for your painless research)

Linux kernel source tree

Continual learning baselines and strategies from popular papers, using Avalanche. We include EWC, SI, GEM, AGEM, LwF, iCarl, GDumb, and other strategies.