John Thickstun (@jwthickstun) / X

John Thickstun

349 posts

John Thickstun

@jwthickstun

Assistant Professor @Cornell_CS. Previously @StanfordCRFM @stanfordnlp @uwcse Controllable Generative Models. AI for Music.

Ithaca, NY

Joined February 2020

Pinned
John Thickstun
@jwthickstun
Jul 25, 2024
I'm joining @Cornell this fall as an Assistant Professor of Computer Science! Looking forward to work with students and colleagues @Cornell_CS, @cornellCIS on generative models, controllable generation, and creative applications like #musictechnology
41K
John Thickstun
@jwthickstun
Jun 16, 2023
We’re releasing the Anticipatory Music Transformer: a controllable generative model for symbolic music (like MIDI). Read about the model on the CRFM blog: crfm.stanford.edu/2023/06/16/ant… 🧵👇
82K
John Thickstun
@jwthickstun
Jan 14, 2021
I'd like to share my course on generative models that I taught in the fall. The course covers AR, VAE, GAN, Flow, and EBM, as well as relevant NN stuff: resnets, transformers, etc. I hope some people find this helpful! courses.cs.washington.edu/courses/cse599…
John Thickstun
@jwthickstun
Jun 20, 2023
Music generation is control theory! arxiv.org/abs/2306.08620
39K
John Thickstun
@jwthickstun
Jul 7, 2023
OpenAI plans to shut down access to older models in January 2024. The text-davinci-003 model in particular has been used extensively in the research community. Losing access to this model would be a blow to reproducible research.
Deprecations | OpenAI API
From developers.openai.com
54K
John Thickstun
@jwthickstun
Mar 18, 2024
We’re releasing an updated version of the Anticipatory Music Transformer! A 780M parameter model, trained on a larger corpus of music: Lakh + MetaMIDI + transcripts of audio. It's the blue curve at the bottom of this plot! 📉 huggingface.co/stanford-crfm/… 🧵👇 (1/3)
19K
John Thickstun
@jwthickstun
Jul 30, 2021
I defended my dissertation at UW this week. I'm moving down to Stanford next month to start a postdoc with @percyliang. I'll continue to work in the music and generative modeling space. Looking forward to collaborating with @chrisdonahuey and others!
John Thickstun
@jwthickstun
Aug 6, 2024
Musicians from the San Francisco Symphony premiered music that I co-composed with an Anticipatory Music Transformer! Here are some thoughts about the process of creating this music and the performance: crfm.stanford.edu/2024/08/06/co-…
00:00
12K
John Thickstun
@jwthickstun
Jun 28, 2023
Let's play with the Anticipatory Music Transformer: reharmonizing a MIDI arrangement of Levitating (Dua Lipa). Blog post describing this interactive creative process: crfm.stanford.edu/2023/06/16/ant… Colab notebook used to create this demo: colab.research.google.com/drive/1HCQDtGF…
00:00
16K
John Thickstun
@jwthickstun
Oct 12, 2023
@megha_byte and I wrote a blog post on the release of >1,000 dynamic interaction traces between humans and LMs! These traces were collected for HALIE, a Human-AI Language Interactive Evaluation framework recently published in TMLR. Blog: crfm.stanford.edu/2023/10/11/hal… 🧵👇
GIF
60K
John Thickstun
@jwthickstun
Jan 2, 2024
Happy New Year! I have some promising new results training generative audio models from scratch. I'm looking forward to share more soon as I integrate this audio work with my (symbolic) Anticipatory Music Transformers. crfm.stanford.edu/2023/06/16/ant…
00:00
9.2K
John Thickstun
@jwthickstun
Dec 7, 2023
Thanks @StanfordHAI for featuring my work on the Anticipatory Music Transformer! I'm so excited to continue pursuing this line of work: DAW integrations, multi-modal (audio+MIDI) models, longer context, richer conditioning, and more. Stay tuned!
Anticipatory Music Transformer: A Composer’s Helper
From youtube.com
9K
John Thickstun
@jwthickstun
Jun 23, 2023
The Anticipatory Music Transformer models an anticipative process (non-adapted, in the sense of stochastic calculus). This process is anticipative of the filtration generated by music evolving through time. arxiv.org/abs/2306.08620
12K
John Thickstun
@jwthickstun
May 19, 2021
This new paper extends last year's work on Source Separation with Deep Generative Priors. We got it working on audio! Here's a reminder of last year's results for images:
arxiv.org
Source Separation with Deep Generative Priors
Despite substantial progress in signal source separation, results for richly structured data continue to contain perceptible artifacts. In contrast, recent deep generative models can produce...