OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

推荐/广告/搜索领域工业界经典以及最前沿论文集合。A collection of industry classics and cutting-edge papers in the field of recommendation/advertising/search.

Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning

Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, Auxiliary Tasks in Multi-task Learning

An educational operating system written in C#. A great stepping stone from high to low level development.

[ECCV 2024] InstructIR: High-Quality Image Restoration Following Human Instructions https://huggingface.co/spaces/marcosv/InstructIR

A unified multi-task time series model.

An up-to-date list of works on Multi-Task Learning

Official implementation of "Multi-Task Learning as a Bargaining Game" [ICML 2022]

Multi-Task (Joint Segmentation / Depth / Surface Normas) Real-Time Light-Weight RefineNet

🔥🔥MLVU: Multi-task Long Video Understanding Benchmark

Code for BMVC2021 "MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation"

[SIGIR'24] The official implementation code of MOELoRA.

A large-scale multi-modal pre-trained model

Multitask Optimization Platform (MToP): A MATLAB Optimization Platform for Evolutionary Multitasking

Modular, fast NLP framework, compatible with Pytorch and spaCy, offering tailored support for French clinical notes.

Multi-label classification based on timm.

MOE is an event-driven OS for 8/16/32-bit MCUs. MOE means "Minds Of Embedded system", It’s also the name of my lovely baby daughter 😎

Roof Classification, Segmentation, and Damage Completion using 3D Point Clouds

🤖📇 handling multiple nlp task in one pipeline