
AIcrowd
AIcrowd enables data science experts and enthusiasts to collaboratively solve real-world problems, through challenges.
HackAPrompt 2023
Trick Large Language Models
Scene Understanding for Autonomous Drone Delivery (SUADD'23)
Understand semantic segmentation and monocular depth estimation from downward-facing drone images
Visual Product Recognition Challenge 2023
Identify user photos in the marketplace
NeurIPS 2022: CityLearn Challenge
Using AI For Buildingβs Energy Management
NeurIPS 2022 IGLU Challenge
Interactive embodied agents for Human-AI collaboration
NeurIPS 2022 - The Neural MMO Challenge
Specialize and Bargain in Brave New Worlds
Multi Agent Behavior Challenge 2022
Behavioral Representation Learning from Animal Poses.
NeurIPS 2021 - The NetHack Challenge
ASCII-rendered single-player dungeon crawl game
Flatland 3
Multi-Agent RL for Trains
NeurIPS 2021 AWS DeepRacer AI Driving Olympics Challenge
Self-driving RL on DeepRacer cars - From simulation to real world
MABe Task 1: Classical Classification
Detect Multi-Animal Behaviors from a large, hand-labeled dataset.
MABe Task 2: Annotation Style Transfer
Adapt Behavior Detectors to capture individuals' annotation style.
MABe Task 3: Learning New Behavior
Learn to Recognise New Behaviors from limited training examples.
Lingua Franca Translation
Translate Crowd Talk (our new language) to English using Machine Translation
NeurIPS 2022 IGLU Challenge - RL Task
Use an RL agent to build a structure with natural language inputs
Semantic Segmentation
Perform semantic segmentation on aerial images from monocular downward-facing drone
Music Demixing Track - MDX'23
Music source separation of an audio signal into separate tracks for vocals, bass, drums, and other
Cinematic Sound Demixing Track - CDX'23
Source separation of a cinematic audio track into dialogue, sound-effects and misc.