The official repo for “Semantic-guided Semantic Scene Completion”

Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts

[TPAMI 2024] Awesome Resources of GNNs for Time Series Analysis (GNN4TS)

A framework for time series modeling using adaptive expertise.

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

Raw data and processing scripts of Weather Captioned Dataset in TGTSF

FITS: Frequency Interpolation Time Series Analysis Baseline

🌎 Verification of weather and climate forecasts 🌍

A simple pip-installable Python tool to generate your own HTML citation world map from your Google Scholar ID.

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

[NeurIPS 2024] Code release for "Segment Anything without Supervision"

[CVPR 2024] SAI3D: Segment Any Instance in 3D Scenes

Official code for "Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization"

Awesome list of Mixture-of-Experts (MoE)

Code for paper "Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters" CVPR2024

This is the offical repository for "Multi-modal Gated Mixture of Local-to-Global Experts for Dynamic Image Fusion" (ICCV 2023).

PyTorch implementation of AirFormer, AAAI-23

Code for "Is Mamba Effective for Time Series Forecasting?"

④[ECCV 2024 Oral, Comparison among Multiple Images!] A study on open-ended multi-image quality comparison: a dataset, a model and a benchmark.

Mamba SSM architecture

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

[NeurIPS 2024] PointMamba: A Simple State Space Model for Point Cloud Analysis

阿里云盘命令行客户端，支持JavaScript插件，支持同步备份功能。

[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"

HumanML3D: A large and diverse 3d human motion-language dataset.

EILeV: Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional Properties

a curated list of high-quality papers on resource-efficient LLMs 🌱