🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

I'll be at NIME showing token telephone, a sound installation where 4 neural networks play a game of telephone with each other, exposing the resonant properties of these complex soundmaking systems :) come say hi!!

Ultra-fast text-to-music generation w/o degrading quality? Introducing Presto! Distilling Steps and Layers for Accelerating Music Generation 🎹: buff.ly/4dC3rpl 📖: buff.ly/3TZBiBU w/Ge Zhu Jonah Casebeer Taylor Berg-Kirkpatrick McAuley Lab UCSD Nicholas J. Bryan 🧵

My first feature in Premiere Pro, from my time so far with Adobe Research, Justin Salamon, Oriol (Uri) Nieto. Taking interns for Summer 2025!

#ProjectSuperSonic at #AdobeMAX #Sneaks is pretty amazing!

What a thrill to present on the big stage! So excited to reveal our Sounds Effects GenAI tech in #ProjectSuperSonic #AdobeMAX Text-to-SFX and *VOICE*-to-SFX for expressive control! Huge kudos to Oriol (Uri) Nieto Prem Seetharaman hugo flores garcía 🌻 and our collaborators in design & prototyping!

Well, Jeff Winger talked about something I worked on (Project SuperSonic) - I'm happy. Thanks Joel McHale!

shameless self-promo; we're hiring pls help us get more stuff done New Lantern exciting news soon tba new-lantern.notion.site/Job-Board-584a…

Today, we're emerging from stealth with our $19M Series A fundraise led by Eric Vishria and Benchmark. We launched the first AI radiology resident. The round is accompanied by @Afore SV Angel @Neo Anthology Fund (Menlo Ventures + Anthropic) Jay Kreps Guillermo Rauch Amjad Masad

Super excited to announce our $19M Series A led by Eric Vishria / Benchmark!! Radiologists play Where's Waldo? with medical images on super-hard mode all day. We're building the first AI Radiology Resident so radiologists work faster and easier. techcrunch.com/2024/11/20/ben…

🎥 Introducing MultiFoley, a video-aware audio generation method with multimodal controls! 🔊 We can ⌨️Make a typewriter sound like a piano 🎹 🐱Make a cat meow like a lion roars! 🦁 ⏱️Perfectly time existing SFX 💥 to a video

New work from our group! Also, find this thread on the other place: bsky.app/profile/czyang… :)

📢 Audio AI Job opportunity at Adobe! The Sound Design AI Group (SODA) is looking for an exceptional research engineer to join us in building the future of AI-assisted audio and video creation. Strong ML background, GenAI experience a plus. Details: adobe.wd5.myworkdayjobs.com/external_exper…

I'm in Vancouver for NeurIPS until 12/13. Would love to chat about what’s coming in AI. Find me on Signal (dseetharaman.23) if you’d like to chat.

Cool work from our group at Adobe, led by our awesome intern hugo flores garcía 🌻! Turn your voice (or anything) into anything!

adobe is cooking a new method to generate sound from vocal imitations 👀

NEW story w/ Tom Dotan: chatter about o3 dominated X today. But it’s worth thinking abt OpenAI’s other big project: GPT-5 aka Orion, which has faced a slew of unexpected issues since mid-2023 that put it behind schedule. MSFT expected to see GPT-5 about 6 months ago…

🎵Hiring 1 scientist & 1 engineer for AI music gen Adobe Research!🎵 careers.adobe.com/us/en/job/R152… careers.adobe.com/us/en/job/R152… Build together. Licensed data. Papers: arxiv.org/abs/2410.05167 arxiv.org/abs/2405.20289 arxiv.org/abs/2403.10493 arxiv.org/abs/2401.12179 arxiv.org/abs/2311.07069

Generative Extend just released in Premiere Pro! Use GenAI to extend your video *and audio* clips for a perfectly timed edit. The audio model was built by our team, the Sound Design AI (SODA) group at Adobe Research w/ Prem Seetharaman and Oriol (Uri) Nieto 🙌 youtube.com/watch?v=_Bv5-Q…

``DRAGON: Distributional Rewards Optimize Diffusion Generative Models,'' Yatong Bai, Jonah Casebeer, Somayeh Sojoudi, Nicholas J. Bryan, ift.tt/0JpvRfW

Introducing "DRAGON: Distributional Rewards Optimize Diffusion Generative Models"! 📖: arxiv.org/abs/2504.15217 🎹: ml-dragon.github.io/web/ A new framework for fine-tuning gen models towards a target distribution. By Yatong Bai w/Jonah Casebeer Somayeh Sojoudi Nicholas J. Bryan