Stars
PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722
Survey: A collection of AWESOME papers and resources on the latest research in Mixture of Experts.
A library for easily merging multiple LLM experts, and efficiently train the merged LLM.
Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
The official repository for the experiments included in the paper titled "Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks" [ICML, 2023]
A collection of AWESOME things about mixture-of-experts
Reference models and tools for Cloud TPUs.
unofficial implementation of CondConv: Conditionally Parameterized Convolutions for Efficient Inference in PyTorch.
Conditional convolution (Dynamic convolution) in tensorflow2
Representation Surgery for Multi-Task Model Merging. ICML, 2024.
SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection [ CVPR'24 Highlight🔥]
A curated list of Continual Learning papers and BibTeX entries
Project Page for "Multi-Task Dense Prediction via Mixture of Low-Rank Experts"
Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models
Code of paper, Person-in-WiFi: Fine-grained Person Perception using WiFi
Using of the WiFi signal in combination with deep learning architectures, commonly used in computer vision, to estimate dense human pose correspondence.
ICLR 2022 (Spolight): Continual Learning With Filter Atom Swapping
Pytorch implementation for Decomposed Convolutional Filters Network
JetBrains / swot
Forked from leereilly/swotIdentify email addresses or domains names that belong to colleges or universities. Help automate the process of approving or rejecting academic discounts.
The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"
Distribution-Aware Coordinate Representation for Human Pose Estimation
[NeurIPS 2019] Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss