Nicholas J. Bryan

100 posts

Nicholas J. Bryan banner
Nicholas J. Bryan

Nicholas J. Bryan

@NicholasJBryan

Head of Music AI, Adobe Research (personal account)

เข้าร่วม Nisan 2010
488 กำลังติดตาม1.4K ผู้ติดตาม
ทวีตที่ปักหมุด
Nicholas J. Bryan
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. arxiv.org/abs/2603.11042 w. @CasebeerJonah @mtlong_88 @aniruddha26398 @gberta227 @NicholasJBryan

English
0
1
13
849
AIQUEST
AIQUEST@AiquestAcademy·
V2M-Zero: what if you could make music that perfectly matches your video's every move? this new AI makes it real, generating soundtracks that precisely align with events in your footage. it focuses on matching the *flow* and *changes* within your video and music separately, then brings them together, without needing tons of paired examples. teh results are super synced up. 🎶 demo available. links 👇
English
1
0
2
76
arXiv Sound
arXiv Sound@ArxivSound·
Yan-Bo Lin, Jonah Casebeer, Long Mai, Aniruddha Mahapatra, Gedas Bertasius, Nicholas J. Bryan, "V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation," arxiv.org/abs/2603.11042
Indonesia
1
0
4
467
Nicholas J. Bryan
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: arxiv.org/abs/2602.15749 Video: youtu.be/gDIIuLb0cf0

English
1
4
72
7.7K
arXiv Sound
arXiv Sound@ArxivSound·
Shih-Lun Wu, Ge Zhu, Juan-Pablo Caceres, Cheng-Zhi Anna Huang, Nicholas J. Bryan, "Stemphonic: All-at-once Flexible Multi-stem Music Generation," arxiv.org/abs/2602.09891
English
1
1
11
431
Nicholas J. Bryan รีทวีตแล้ว
Luiz Marques
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.
English
0
1
3
155
Nicholas J. Bryan รีทวีตแล้ว
Drashya Kuruwa
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
English
0
1
5
341
Nicholas J. Bryan
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!

English
1
0
4
617
Nicholas J. Bryan รีทวีตแล้ว
The Verge
The Verge@verge·
Adobe’s new AI audio tools can add soundtracks and voice-overs to videos theverge.com/news/807809/ad…
English
0
5
20
16.1K
Nicholas J. Bryan
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: firefly.adobe.com/generate/sound… 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
English
1
7
14
1.2K
Wes Roth
Wes Roth@WesRoth·
Adobe just dropped DRAGON on Hugging Face DRAGON (Distributional RewArds for Generative OptimizatioN) is a fine-tuning framework for media generation from images to text-to-music models. Unlike RLHF or DPO, DRAGON can optimize for individual samples and entire distributions of outputs giving it next-level flexibility for real-world creative tasks.
AK@_akhaliq

Adobe announced DRAGON on Hugging Face Distributional Rewards Optimize Diffusion Generative Models

English
1
0
13
1.6K
Nicholas J. Bryan รีทวีตแล้ว
AK
AK@_akhaliq·
Adobe announced DRAGON on Hugging Face Distributional Rewards Optimize Diffusion Generative Models
English
14
40
238
24.2K
arXiv Sound
arXiv Sound@ArxivSound·
``DRAGON: Distributional Rewards Optimize Diffusion Generative Models,'' Yatong Bai, Jonah Casebeer, Somayeh Sojoudi, Nicholas J. Bryan, ift.tt/0JpvRfW
English
1
2
10
1.5K
Nicholas J. Bryan
Nicholas J. Bryan@NicholasJBryan·
DRAGON introduces a new approach to designing and optimizing reward functions to enhance human-perceived quality.
English
0
0
0
200
Nicholas J. Bryan
Nicholas J. Bryan@NicholasJBryan·
With an appropriate exemplar set, DRAGON achieves a 60.95% human-voted music quality win rate without training on human preference annotations.
English
1
0
0
208

ค้นพบ

@AiquestAcademy @ArxivSound @CasebeerJonah @__gzhu__ @zhepeiw03 @slseanwu @j_p_caceres @huangcza