DEC 6th - DEC 14th

NeurIPS 2021

Training virtual robots in 3D environments. Discovering new catalysts for renewable energy storage. Training speech recognition without any labeled data. These are some of the topics that Meta AI researchers will present new work on at the virtual Conference on Neural Information Processing Systems (NeurIPS), one of the largest AI conferences of the year. Our researchers and technologists work closely with open-source communities, academia, and partners to build the future of AI together.

Zero-Shot Transfer to Formula 1 Race Tracks

This shows agents trained using our methods (PLR and REPAIRED) outperforming baseline agents in zero-shot transfer to the challenging task of driving a track in the shape of the Nürburging Grand Prix racetrack. This means they are able to drive this track without having ever trained on it.

See Demo

Building diverse MiniHack environments within just a few lines of code

MiniHack is a sandbox framework for easily designing rich and diverse environments for Reinforcement Learning. To this end, MiniHack leverages description files written using a human-readable domain-specific language. With just a few lines of code, people can generate a large variety of Gym environments, ranging from small rooms to complex, procedurally generated worlds.

See Demo

Habitat 2.0: Training Home Assistants to Rearrange their Habitat

The Habitat 2.0 simulation platform is for training virtual robots in interactive, physics-enabled, 3D environments. We present the new ReplicaCAD 3D dataset of apartments, the Habitat 2.0 simulator capable of simulating 850x faster than real-time, and the Home Assistant Benchmark, a suite of common

See Demo
Invited Talks
Spotlight Papers
CtrlGen: Controllable Generative Modeling in Language and Vision
Mon Dec 13, 8:00 AM - 5:00 PM PT - Jason Weston, Angela Fan

Machine Learning for Creativity and Design
Mon Dec 13, 8:15 AM - 6:00 PM PT - Devi Parikh

Efficient Natural Language and Speech Processing

Mon Dec 13, 2:00 PM - 2:40 PM PT - Luke Zettlemoyer

Out-of-distribution generalization and adaptation in natural and artificial intelligence
Tue Dec 14, 5:00 AM - 5:00 PM PT - Brenden Lake

Ecological Theory of RL Workshop
Tue Dec 14, 5:40 AM PT - Joelle Pineau
Tue Dec 14, 11:40 AM PT - Amy Zhang

4th Robot Learning Workshop: Self-Supervised and Lifelong Learning
Tue Dec 14, 7:00 AM - 7:00 PM PT - Roberto Calandra

Workshop on Human and Machine Decisions
Tue Dec 14, 8:00 AM - 9:00 AM PT - Alex Peysakhovich

Machine Learning for Creativity and Design
Mon Dec 13, 8:15 AM - 6:00 PM PT - Samaneh Azadi

Workshop on ML for Systems at NeurIPS
Mon Dec 13, 9:00 AM - 5:40 PM PT - Yuandong Tian, Benoit Steiner

Self-Supervised Learning - Theory and Practice
Tue Dec 14, 7:00 AM - 4:30 PM PT - Ishan Misra, Abdelrahman Mohamed

Cooperative AI Workshop
Tue Dec 14, 5:20 AM - 2:15 PM PT - Noam Brown

Privacy in Machine Learning
Tue Dec 14, 8:10 AM - 5:55 PM PT - Kristin Lauter, Kamalika Chaudhuri

Data-Centric AI Workshop
Tue Dec 14, 8:45 AM - 4:30 PM PT - Carole-Jean Wu

Lossy Compression for Lossless Prediction
Dec 7, Poster session 2

Yann Dubois, Benjamin Bloem-Reddy, Karen Ullrich, Chris Maddison

Multimodal and Multilingual Embeddings for Large-Scale Speech Mining
Dec 8, Poster session 3

Paul-Ambroise Duquenne, Hongyo Gong, Holger Schwenk

Habitat 2.0: Training Home Assistants to Rearrange their Habitat
Dec 9, Poster session 5

Andrew Szot, Alexander Clegg, Eric Undersander, Erik Wijmans, Yili Zhao, John Turner, Noah Maestre, Mustafa Mukadam, Devendra Singh Chaplot, Oleksandr Maksymets, Aaron Gokaslan, Vladimir Vondrus, Sameer Dharur, Franziska Meier, Wojciech Galuba, Angel Chang, Zsolt Kira, Vladlen Koltun, Jitendra Malik, Manolis Savva, Dhruv Batra

A Provably Efficient Sample Collection Strategy for Reinforcement Learning
Dec 9, Poster session 5

Jean Tarbouriech, Michal Valko, Matteo Pirotta, Alessandro Lazaric

Instance-Conditioned GAN

Dec 9, Poster session 6

Arantxa Cassanova Paga, Marlene Careil, Jakob Verbeek, Michal Drozdzal, Adriana Romero Soriano

Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret
Dec 9, Poster session 6

Jean Tarbouriech, Runlong Zhou, Simon Du, Matteo Pirotta, Michal Valko, Alessandro Lazaric

Hash Layers For Large Sparse Models
Dec 10, Poster session 8

Stephen Roller, Sainbayar Sukhbaatar, Arthur D Szlam, Jason Weston

Per-Pixel Classification is Not All You Need for Semantic Segmentation
Dec 10, Poster session 8

Bowen Cheng, Alex Schwing, Alexander Kirillov

Billion-Scale Approximate Nearest Neighbor Search Challenge

Matthijs Douze

IGLU: Interactive Grounded Language Understanding in a Collaborative Environment

Kavya Srinet, Arthur Szlam

Image Similarity Challenge

Cristian Canton Ferrer, Matthijs Douze, Zoe Papakipos

Open Catalyst Challenge

Larry Zitnick, Abhishek Das, Siddharth Goyal

NetHack Challenge

Eric Hambro, Minqi Jiang, Heinrich Kuttler, Vegard Mella, Tim Rocktäschel, Danielle Rothermel, Edward Grefenstette

Help Us Pioneer the Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.