Yu Wang

Music x ML | Research Scientist @Spotify. PhD @nyuMARL. prev @AdobeResearch @GoogleMagenta 🎶🎸🇹🇼

[Yu Wang @yuwang_tw]

For more information about the team: https://t.co/HVFUnaBnKK

[Yu Wang @yuwang_tw]

I'll be at #NeurIPS2025, excited to meet old and new friends!
My team, Artist-First AI Music Lab, has openings for research scientists/engineers/interns. If you're excited about creating new experiences for artists and fans and have strong relevant expertise, let's connect!

[Shih-Lun (Sean) Wu @slseanwu]

Thrilled to announce “MIDI-LLM: Adapting LLMs for Text-to-MIDI Music Generation” w/ @huangcza and Yoon Kim!

🎸 Live Demo https://t.co/6N6AqyrZuW
💻 https://t.co/Z1v82uool5
🤗 https://t.co/k9deMY82Vk

From a text prompt, it generates MIDIs you can edit directly in a DAW 🧵

[Yu Wang @yuwang_tw]

Call for research interns @Spotify! Apply by Feb. 6th to join the audio intelligence team this summer in our London, Stockholm, or NYC offices!
Links:
- https://t.co/wHGcmOKhZP (London/Stockholm)
- https://t.co/yIn8GpWNKy (NYC)
(please ignore the preferred graduation year)

[Peter Sobot @psobot]

🔊 Come join my team at Spotify!

We’re hiring a Senior Machine Learning Infrastructure Engineer, with a focus on music and audio. https://t.co/yH90ujyoy1

[Yu Wang @yuwang_tw]

@hermanhwdong @UMich @umichsmtd Huge congrats!! 🎉🎉

[Yu Wang @yuwang_tw]

@saurabhbajaj717 @Spotify Hi @saurabhbajaj717, thank you for your interest. Please feel free to apply directly via the job posting link!

[Yu Wang @yuwang_tw]

Call for research interns @Spotify in London is now open!
Apply by Mar. 15th, 9AM ET to join the audio intelligence team this summer! For more information and to apply: https://t.co/GEFJpiLjvK

[Josh G @jpgard]

🐣 🎶  Excited to share LLark: A Multimodal Foundation Model for Music!

LLark is a 12B parameter model that produces text responses from (text + audio) inputs.

📖 https://t.co/3MJMZWP1RZ
🔊 https://t.co/hjmm7WKCW5
💻 https://t.co/5taynwmDOg

🧵

[Rachel Bittner @r4b1tt]

I'm proud to share that our team's work at @SpotifyResearch on audio-lyric alignment by Simon Durand, Daniel Stoller, and @sebastian_ewert was awarded the best industry paper award at #ICASSP2023 . More details in 🧵

[Yu Wang @yuwang_tw]

A little delayed, but I am thrilled to share some exciting life updates!! I defended my PhD last month, and started as a Research Scientist @Spotify earlier this year!

Many thanks to everyone who has supported me throughout the journey. Super excited about the next adventure!

[Yu Wang @yuwang_tw]

The call for research interns @Spotify is out!

Apply https://t.co/7IsuZoT9l6 by Feb 21st to join the audio intelligence team this summer!

[Yu Wang @yuwang_tw]

Looking forward to talking about my dissertation work in the DSP seminar at CCRMA tomorrow at 4:30pm PST!
- Title: Adaptive and Interactive Machine Listening with Minimal Supervision
- Abstract and zoom link: https://t.co/xlQYkcaDUj

[Yu Wang @yuwang_tw]

Had a blast giving a tutorial on “Few-Shot and Zero-Shot Learning for MIR” with @hugggof @kunimi00 at #ISMIR2022!
Here are some resources we put together
- JupyterBook: https://t.co/fouJGVgpo9
- Repo with slides: https://t.co/snETWW69Mt
- Coding examples: https://t.co/MrHKaWW76o

[Yu Wang @yuwang_tw]

@SantoAndre_6 @hugggof @ISMIRConf Thank you for joining us!! :))

[Yu Wang @yuwang_tw]

@affige_yang Congrats!!!🎉🎉

[Yu Wang @yuwang_tw]

@ethanmanilow @GoogleMagenta Congrats, Ethan!!!🎉👏

[Vincent Lostanlen @lostanlen]

I am looking for a PhD student in MIR! 🎓
to work on self-supervised learning in multitrack music

You will be employed by @Deezer Research
co-advised by R. Hennequin + me
based in Paris 🪗 and visiting my lab in Nantes 🦀

Start: Dec. 2022☃️ or later
https://t.co/cvGIFCzq7q

[Yu Wang @yuwang_tw]

We will present this work at the AUD-1 session (5/8 8am EST). https://t.co/reoScReBt2

[Yu Wang @yuwang_tw]

Looking forward to presenting "Few-Shot Musical Source Separation" at #ICASSP2022! Separating an instrument from a mixture based on a few audio examples.

arXiv - https://t.co/Cm8d8qupf3
Demos - https://t.co/BDZN2pkBPQ

Joint work with Daniel Stoller, @r4b1tt, Juan P. Bello.

[Yu Wang @yuwang_tw]

We further explore different characteristics of the conditioning audio examples, including relaxing different constraints as well as providing additional negative conditioning for a wider variety of applications.