Image credit: Sofia Crespo's "On the seabed gazing up" (2020).
Introduction
Generative machine learning and machine creativity have continued to grow and attract a wider audience to machine learning. Generative models enable new types of media creation across images, music, and text - including recent advances such as StyleGAN2, Jukebox and GPT-3. This one-day workshop broadly explores issues in the applications of machine learning to creativity and design. We will look at algorithms for generation and creation of new media, engaging researchers building the next generation of generative models (GANs, RL, etc). We investigate the social and cultural impact of these new models, engaging researchers from HCI/UX communities and those using machine learning to develop new creative tools. In addition to covering the technical advances, we also address the ethical concerns ranging from the use of biased datasets to replicating artistic work. Finally, we’ll hear from some of the artists and musicians who are adopting machine learning including deep learning and reinforcement learning as part of their own artistic process. We aim to balance the technical issues and challenges of applying the latest generative models to creativity and design with philosophical and cultural issues that surround this area of research.
The goal of this workshop is to bring together researchers interested in advancing art and music generation to present new work, foster collaborations and build networks with the aim of solving the most pressing problems in the field.
Invited Speakers
Sofia Crespo, Artist
Stephanie Dinkins, Artist and Professor at Stony Brook University
Scott Eaton, Artist
Jesse Engel, Magenta, Google Brain
Angela Fan, Facebook
Aaron Hertzmann, Adobe Research
Janelle Shane, AI Weirdness
Schedule
All times are EST (UTC -5).
You will find links to all the sessions on our NeurIPS workshop website (registered participants only).
| Time | Event |
|---|---|
| 8:15 AM | Introduction and Art Gallery Overiew Luba Elliott |
| 8:30 AM | Poster Session 1 Posters 1-32 apart from 29 |
| 9:30 AM | Farewell to Fart: Working with generated text in the age of huge neural nets Janelle Shane (AI Weirdness) |
| 9:56 AM | Artist+AI: Figures&Form Scott Eaton |
| 10:21 AM | Artificial biodiversity Sofia Crespo |
| 10:40 AM | Art Showcase 1 |
| 11:00 AM | Panel Discussion 1 Janelle Shane, Sofia Crespo, Scott Eaton and Angela Fan chaired by Adam Roberts and Luba Elliott |
| 11:30 AM | Social 1 |
| 12:15 PM | magenta: Empowering Creative Agency with Machine Learning Jesse Engel |
| 12:45 PM | Art Showcase 2 |
| 1:20 PM | Computation and the Human Visual Perception of Art Aaron Hertzmann (Adobe Research) |
| 1:47 PM | LIGHT: Language in Games with Humans and Text Angela Fan (Facebook) |
| 2:09 PM | Not the Only One Stephanie Dinkins (Stony Brook University) |
| 2:35 PM | Art Showcase 1 |
| 2:50 PM | Audio-reactive Latent Interpolations with StyleGAN Hans Brouwer |
| 3:00 PM | Towards realistic MIDI instrument synthesizers Rodrigo Castellon |
| 3:10 PM | Creative Sketch Generation Songwei Ge |
| 3:20 PM | Agence: an interactive film exploring multi-agent systems and human agency Dante Camarena |
| 3:30 PM | Art Showcase 2 |
| 3:45 PM | Poster Session 2 Posters 1-29 |
| 4:45 PM | Panel Discussion 2 Jesse Engel, Aaron Hertzmann and Stephanie Dinkins chaired by Holly Grimm and Tom White |
| 5:15 PM | Social 2 |
| 6:00 PM | End |
Accepted papers
- Audio-reactive Latent Interpolations with StyleGAN
- Hans Brouwer
- Creative Sketch Generation
- Songwei Ge, Vedanuj Goswami, C. Lawrence Zitnick, Devi Parikh
- Agence: an interactive film exploring multi-agent systems and human agency
- Dante Camarena, Pietro Gagliano, Alexander Bakogeorge, Nicholas Counter, Anuj Patel, Casey Ryan Blustein, Erin Ray, David Oppenheim, Laura Mingail, Kory W. Matthewson, Pablo S. Castro
- GANterpretations
- Pablo Samuel Castro
- Neural Style Transfer for Casual Creation
- Simon Colton
- Network Bending Neural Vocoders
- Louis McCallum, Matthew Yee-King
- Colorization Transformer
- Manoj Kumar, Dirk Weissenborn, Nal Kalchbrenner
- White-box Audio VST Effect Programming
- Christopher Mitcheltree, Hideki Koike
- TräumerAI: Dreaming Music with StyleGAN
- Dasaem Jeong, Seungheon Doh, Taegyun Kwon
- A Note on Data Biases in Generative Models
- Patrick Esser, Robin Rombach, Björn Ommer
- Randomized Overdrive Neural Networks
- Christian J. Steinmetz, Joshua D. Reiss
- Latent Space Oddity: Exploring Latent Spaces to Design Guitar Timbres
- Jason Taylor
- Resolution Dependant GAN Interpolation for Controllable Image Synthesis Between Domains
- Justin N. M. Pinkney, Doron Adler
- Image Generation With Neural Cellular Automatas
- Mingxiang Chen, Zhecheng Wang
- Behaviour Aesthetics of Reinforcement Learning in a Robotic Art Installation
- Sofian Audry, Rosalie Dumont Gagné, Hugo Scurto
- LiveGAN
- Cameron Smith
- Mask-Guided Discovery of Semantic Manifolds in Generative Models
- Mengyu Yang, David Rokeby, Xavier Snelgrove
- A Speech-Based Music Composition Tool with Transformer
- Jason d’Eon, Sri Harsha Dumpala, Daniel Oore, Sageev Oore
- Transformer-GAN: Symbolic music generation using a learned loss
- Aashiq Muhamed, Liang Li, Xingjian Shi, Suri Yaddanapudi, Wayne Chi, Dylan Jackson, Rahul Suresh, Zachary Lipton, Alexander J. Smola
- Latent Compass
- Sarah Schwettmann, Hendrik Strobelt, Mauro Martino
- Choreo-Graph: Learning Latent Graph Representations of the Dancing Body
- Mariel Pettee, Santiago Miret, Somdeb Majumdar, Marcel Nassar
- Painting from Music using Neural Visual StyleTransfer
- Ingrid Odlen, Prateek Verma, Constantin Basica, Pamela Davis Kivelson
- Horses With Blue Jeans - Creating New Worlds by Rewriting a GAN
- David Bau, Steven Liu, Tongzhou Wang, Jun-Yan Zhu, Antonio Torralba
- Spatial Assembly:Generative Architecture With Reinforcement Learning, Self Play and Tree Search
- Panagiotis Tigas, Tyson Hosmer
- Text to Dialog: Using Semantic Similarity to Extend Narrative Immersion in Virtual Worlds
- Sherol Chen, Ben Pietrzak, Kory W. Matthewson, Dan Cary, Anna Kipnis, Erin Hoffman-John
- Towards realistic MIDI instrument synthesizers
- Rodrigo Castellon, Chris Donahue, Percy Liang
- Musical Diary - AI Application for Music Making and Journaling
- Suyash Joshi, Devin Lane, Stephen Haney
- Copyspace: Where to Write on Images
- Jessica M. Lundin, Michael Sollami, Brian Lonsdorf, Alan Ross, Owen Schoppe, David Woodward, Sönke Rohde
- Weird AI Yankovic: Generating Parody Lyrics
- Mark O. Riedl
- Generating Novel Glyph without Human Data by Learning to Communicate
- Seung-won Park
- Diptychs of human and machine perceptions
- Vivien Cabannes, Thomas Kerdreux, Louis Thiry
- A Framework and Dataset for Abstract Art Generation via CalligraphyGAN
- Jinggang Zhuo, Ling Fan, Harry Jiannan Wang
Contact
If you have any questions, please contact us at neurips2020creativity@gmail.com
Workshop website: https://neurips2020creativity.github.io
Previous years:
- 2019 workshop (Vancouver, Canada)
- 2018 workshop (Montreal, Canada)
- 2017 workshop (Long Beach, CA, USA)
The art submissions from previous years can be viewed here
How to attend
You should purchase a ticket on neurips.cc. This will allow you to access our website on NeurIPS with links to the livestream, poster session and socials.
Organisers
Luba Elliott, AI Curator
Sander Dieleman, DeepMind
Adam Roberts, Magenta, Google Brain
Tom White, Victoria University of Wellington
Holly Grimm, Artist and freelance creative technologist
Mattie Tesfaldet, McGill University / MILA
Samaneh Azadi, UC Berkeley
Daphne Ippolito, University of Pennsylvania / Google Brain