Rafael Valle

@RafaelValleArt

Chief Science Officer at RIME ex-META, ex-NVIDIA, UC Berkeley alumn. Love, music, set and setting!

rafaelvalle.github.io

Joined June 2012

189 Following

1,335 Followers

Replies Reposts Media

Rafael Valle
@RafaelValleArt
Oct 20
Hoje, às 18h (Brasília), participo do Encontros ABM sobre composição musical em tempos de IA, com Jônatas Manzolli, Rodolfo Coelho de Souza e mediação de Liduino Pitombeira. Ao vivo no YouTube da Academia Brasileira de Música:
Rafael Valle
@RafaelValleArt
Jul 15
I am thrilled to join @rimelabs as Chief Science Officer. V-easy problems are falling fast. The path to audio superintelligence runs through the V-hard ones: there's no scoring function for how much one cares. Grateful to @LilyClifford & the RIME team.
Rime picks up $24M Series A to help enterprises field customer calls | TechCrunch
From techcrunch.com
6
Rafael Valle
@RafaelValleArt
Dec 2, 2025
Against all odds, I’ll be at NeurIPS 2025 in San Diego this Thursday. If you trip on multimodal general intelligence, let’s chat.
3
Rafael Valle
@RafaelValleArt
Oct 20, 2025
Superintelligence is nearer and multimodal! 🚀🙏💚 Great honor to be involved in OmniVinci! - SOTA AVLM - Audio understanding significantly enhances video comprehension - Audio signals improve omni-modal reinforcement learning - Understanding demands omni-modal context
Huck Yang
@huckiyang
Oct 20, 2025
@NVIDIAAI's 🎨 OmniVinci 9B is now open on @huggingface, topping 🎙️ audio, 🗣️ speech, 🖼️ image, 📽️video benchmarks with applications on 🤖 robot, 🏭semiconductor, 🥎 sport, and 🩺 medical. Paper (nvlabs.github.io/OmniVinci/), Model and Omni demo Video w/ @leoyerrrr @goelarushi27
1
Rafael Valle
@RafaelValleArt
Oct 16, 2025
When Jinchuan became a guest researcher with ADLR-AGI, I knew we'd push the Audio General Intelligence frontier beyond Fugatto and UniAudio. UALM is a milestone that unifies audio understanding, generation, and multimodal reasoning in a single model 💚🙏🚀
arxiv.org
UALM: Unified Audio Language Model for Understanding, Generation...
Recent advances in the audio language modeling (ALM) domain tackle audio understanding and text-to-audio generation as separate tasks. Very few studies attempt to unify these tasks -- an essential...

Rafael Valle

Rafael Valle’s posts