🔥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

Excited for the "Generative Data Aug. for Real-World Signal Proc. Apps (GenDA 2025)" workshop at ICASSP 2025 w/Fabio Antonacci at Politecnico di Milano + Apoorv Vyas at Meta Research + organizers Minje Kim, John Hershey, Dinesh Manocha, and Trausti Kristjansson.

Ultra fast music generation via accelerating diffusion TTM without quality loss. Amazing work led by Zachary Novack! Summer research intern work at Adobe Research w/Ge Zhu, Jonah Casebeer, myself, and University collab w/ McAuley Lab UCSD Taylor Berg-Kirkpatrick at UCSD!

Ultra fast music generation via accelerating diffusion TTM without quality loss. Amazing work led by Zachary Novack! Summer research intern work at Adobe Research w/Ge Zhu, Jonah Casebeer, myself, and University collab w/ McAuley Lab UCSD Taylor Berg-Kirkpatrick at UCSD!

🎶Diffusion Inference-time T-Optimization (DITTO) for music gen gets faster w/DITTO2! Optimize diffusion initial noise latent via a 1-step sampler for powerful control. Decode w/few sampling steps for best quality. Led by Zachary Novack w/McAuley Lab UCSD Taylor Berg-Kirkpatrick, myself

Our paper "Presto! Distilling Steps and Layers for Accelerating Music Generation" has been accepted at #ICLR2025 ICLR 2026! Check out the demo video and links below, excited to see everyone in Singapore 🇸🇬!

🎵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

Hyped to be presenting Presto next week at #ICLR2025 as a Spotlight! Super excited to chat about all things generative music/audio, diffusion acceleration, and real-time audio systems, lmk if you want to meet (DMs open)!

Checkout more info at x.com/NicholasJBryan…

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