Nicholas J. Bryan

Head of Music AI / Principal Scientist, Adobe Research (personal account)

[Nicholas J. Bryan @NicholasJBryan]

Adobe Firefly's Generate Music Wins TIME Best Invention 2026 Special Mention! 🎵👏

It's been a wonderful journey building studio-quality commercially-safe music AI for any use.

@j_p_caceres @__gzhu__, @zhepeiw03, @gimdong58085414 @slseanwu

https://t.co/WdpMMSeiCg

[Nicholas J. Bryan @NicholasJBryan]

Congrats @yblin98 and #team on the @NeurIPSConf 2026 Accept!

SOTA synchronized video-to-music generation without using any paired video-music training data! 👏👏👏

[Yan-Bo Lin @yblin98]

🎵🎵What if we could generate video soundtracks without paired video–music data? Introducing V2M-Zero, a method that generates music synchronized with video events. https://t.co/pwksqKrQTa w. @CasebeerJonah @mtlong_88 @aniruddha26398 @gberta227 @NicholasJBryan

[Nicholas J. Bryan @NicholasJBryan]

Excited for "Beats" is released in @Adobe #PremiereMobile on iOS!

We detect musically meaningful markers within your music to sync, snap, and cut to your video. Three visualization options corresponding to less → more markers.

w/@JojoGiltsoff, Eric Brandt, @j_p_caceres ++!

[Nicholas J. Bryan @NicholasJBryan]

Introducing #AIStudio via #AdobeStock — edit stock assets before licensing https://t.co/1JmhRsRP9M

AI Studio features #AudioMatch -- create custom soundtracks for video before licensing.

Proud of the #team 🥂👇 + Adobe Stock's new economic models to blend #GenAI w/licensing.

[Nicholas J. Bryan @NicholasJBryan]

@AiquestAcademy Check out https://t.co/qmFNPXG0zg

[Yan-Bo Lin @yblin98]

🎵🎵What if we could generate video soundtracks without paired video–music data? Introducing V2M-Zero, a method that generates music synchronized with video events. https://t.co/pwksqKrQTa w. @CasebeerJonah @mtlong_88 @aniruddha26398 @gberta227 @NicholasJBryan

[Nicholas J. Bryan @NicholasJBryan]

@ArxivSound Check out https://t.co/qmFNPXG0zg

[Yan-Bo Lin @yblin98]

🎵🎵What if we could generate video soundtracks without paired video–music data? Introducing V2M-Zero, a method that generates music synchronized with video events. https://t.co/pwksqKrQTa w. @CasebeerJonah @mtlong_88 @aniruddha26398 @gberta227 @NicholasJBryan

[Nicholas J. Bryan @NicholasJBryan]

🎶 V2M-Zero: SOTA time-sync'd video-to-music! 🎶

* Music sync'd to dance, scene cuts,
* Easily adapt existing TTM models,
* No paired video-music data,
* SOTA objective + human preference.

Exceptional work @yblin98 + @casebeer! w/@mtlong_88 @aniruddha26398 @gberta227, me

[Yan-Bo Lin @yblin98]

🎵🎵What if we could generate video soundtracks without paired video–music data? Introducing V2M-Zero, a method that generates music synchronized with video events. https://t.co/pwksqKrQTa w. @CasebeerJonah @mtlong_88 @aniruddha26398 @gberta227 @NicholasJBryan

[Nicholas J. Bryan @NicholasJBryan]

Audio VAEs + VQ-VAEs designed for #GenAI!

* Ultra-fast encoding for on-the-fly training pipelines,
* ~2x more compression (13Hz) w/frontier quality,
* Any format (mono, stereo LR, MS, mel, raw),
* Cont. or discrete latents.

👏 @CasebeerJonah! w/@__gzhu__ @zhepeiw03, me

[Jonah Casebeer @CasebeerJonah]

GenAE: An audio autoencoder engineered for generative modeling.
To appear at ICASSP 2026.
w/ @__gzhu__ @zhepeiw03 @NicholasJBryan
arXiv: https://t.co/akXYENgCZG
Video: https://t.co/udshifZ7tY

[Nicholas J. Bryan @NicholasJBryan]

TAC: Timestamped Audio Captioning 👇

[Justin Salamon @justin_salamon]

This is big. SOTA audio reasoning. SOTA video reasoning. SOTA audio captioning. SOTA sound event detection. Better than Gemini. Better than Qwen.

TAC: Timestamped Audio Captioning

📑 paper: https://t.co/3IVuI6qn4S
🌐 website with more demos: https://t.co/FhoFqqTYQo

[Nicholas J. Bryan @NicholasJBryan]

@ArxivSound Check out https://t.co/eZRj4pcOTn

[Shih-Lun (Sean) Wu @slseanwu]

Excited to announce our ICASSP 2026 paper "Stemphonic: All-at-once Flexible Multi-stem Music Generation" !

w/ @__gzhu__, @j_p_caceres, @huangcza, and @NicholasJBryan

🔊Demo https://t.co/9TPzisBQLW
📰Paper https://t.co/SNWLNzyUAC

More details in🧵

[Nicholas J. Bryan @NicholasJBryan]

Thrilled about Stemphonic!

All-at-once Flexible Multi-stem Music Generation!

w/@slseanwu @__gzhu__ @j_p_caceres @huangcza and myself

[Shih-Lun (Sean) Wu @slseanwu]

Excited to announce our ICASSP 2026 paper "Stemphonic: All-at-once Flexible Multi-stem Music Generation" !

w/ @__gzhu__, @j_p_caceres, @huangcza, and @NicholasJBryan

🔊Demo https://t.co/9TPzisBQLW
📰Paper https://t.co/SNWLNzyUAC

More details in🧵

[Luiz Marques @stargliderbr]

@LudovicCreator I've been playing with Generate Soundtrack a lot today. It is pretty great, and really fast.
I've been collecting a bunch of alternate music options from my videos.

[Drashya Kuruwa @drashyakuruwa]

Why no one is talking about the new Meta AI - Image and Video generation which is partnered with Midjourney and Black Forest Labs??

The generations are fascinating.

Image and Video generated with @Meta @AIatMeta
Music - @Adobe Generate Soundtrack

@alexandr_wang #MetaAI

[Alexandra Aisling @AllaAisling]

@dreamina_ai Added sound in @AdobeFirefly , generate soundtrack feature

[Nicholas J. Bryan @NicholasJBryan]

🎵Hiring summer interns on AI music 2026! @AdobeResearch https://t.co/LgFIDo9guJ

Past intern papers:
https://t.co/biSceK5vgQ TMLR https://t.co/ugNVzGTynQ MLSP https://t.co/iHDsBfxNPt ICLR https://t.co/1FsqblMdjQ SPL https://t.co/pyZzfVEyJo ICML
https://t.co/q7F39jp47M TASLP

[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 🧵

[Nicholas J. Bryan @NicholasJBryan]

Congrats @JCJesseLai and Team!

[Chieh-Hsin (Jesse) Lai @JCJesseLai]

Tired to go back to the original papers again and again? Our monograph: a systematic and fundamental recipe you can rely on!

📘 We’re excited to release 《The Principles of Diffusion Models》— with @DrYangSong, @gimdong58085414, @mittu1204, and @StefanoErmon.

It traces the core ideas that shaped diffusion modeling and explains how today’s models work, why they work, and where they’re heading.

🧵You’ll find the link and a few highlights in the thread.
We’d love to hear your thoughts and join some discussions!

⚡ Stay tuned for our markdown version, where you can drop your comments!

[The Verge @verge]

Adobe’s new AI audio tools can add soundtracks and voice-overs to videos https://t.co/Y2SKL5YLh7

[Nicholas J. Bryan @NicholasJBryan]

Adobe's #GenerateSoundtrack is LIVE today! 🎉

Studio-quality music for storytellers🎵
* Trained on #Licensed data,
* Commercially safe, royalty-free, and cleared for any use, &
* Exported with #ContentCredentials for transparency and attribution.

Get started: https://t.co/ICe7jjt2HW

Powered by the #FireflyAudioModel, and built by an incredible R&D team: @j_p_caceres @CasebeerJonah @__gzhu__ @zhepeiw03 @ailiefraser @NicholasJBryan

Excited for the Team. Much more to come!

#Adobe #AdobeMAX #GenerateSoundtrack #FireflyAudioModel

[Nicholas J. Bryan @NicholasJBryan]

@wesroth More info below! https://t.co/lf82cnQvT0

[Nicholas J. Bryan @NicholasJBryan]

Introducing "DRAGON: Distributional Rewards Optimize Diffusion Generative Models"!

📖: https://t.co/biSceK5vgQ
🎹: https://t.co/6taiaC8SUZ

A new framework for fine-tuning gen models towards a target distribution.

By Yatong Bai w/@CasebeerJonah @somayeh_sojoudi @NicholasJBryan