Wilson Zhao
@wilzh40fan of beep boop music + things in transit (transients) future author of "the art and zen of motorcycle crashing" opinions are my own
Similar User
@RLanceMartin
@DivGarg_
@abacaj
@conviction
@sjwhitmore
@willdepue
@minafahmi_
@GalactixyI
@AIDailyNewsNow
@asimdotshrestha
@walden_yan
@stef_r
@altryne
@gogoliansnake
@niraj
Somebody help us… please we cant stop
The next three grand challenges of @ISMIRConf proposed by @MasatakaGoto! Let's work on it! 🤘 - Ultimate Music Retrieval: Query-by-Brain 🧠 - Ultimate Music Creation: Music Drug 💊 - Ultimate Music Listening: Direct Digital Music 🎵
so i've spent a silly amount of time in this call booth selling software at @automat_ai's office. in the last 5 months, @sellsayed and I (in his words) have “built an absolute Go-to-Market machine" things are truly buzzing, we have more opportunities in the pipeline than we can…
Introducing Empathic Voice Interface 2 (EVI 2), our new voice-to-voice foundation model. EVI 2 merges language and voice into a single model trained specifically for emotional intelligence. You can try it and start building today.
🚀✨🎉 As of 11am today: Magic Circle is launched GLOBALLY on Discord! After 6 months of intense focus & collaboration with the awesome team at Discord, we're super proud to be among the very first game studios to ship a game on Discord's new game platform. Some thoughts &…
🔥llm.c update: Our single file of 2,000 ~clean lines of C/CUDA code now trains GPT-2 (124M) on GPU at speeds ~matching PyTorch (fp32, no flash attention) github.com/karpathy/llm.c… On my A100 I'm seeing 78ms/iter for llm.c and 80ms/iter for PyTorch. Keeping in mind this is fp32,…
It's amazing how real-time controls/synthesis can transform a music generative model into an actual instrument that you can get good at ! We are working on adding many features to this, stay tuned 🤘
I love music most when it’s live, in the moment, and expressing something personal. This is why I’m psyched about the new “DJ mode” we developed for MusicFX: aitestkitchen.withgoogle.com/tools/music-fx… It’s an infinite AI jam that you control 🎛️. Try mixing your unique 🌀 of instruments, genres,…
We've released the Song Describer Dataset, an evaluation set of ~1.1k human-written music captions collected through our open-source annotation platform, to be presented at the ML for Audio Workshop at #NeurIPS2023! Paper: arxiv.org/abs/2311.10057 Code: github.com/mulab-mir/song…
heading to #NeurIPS2023 soon! if you're interested in: - multimodal models (esp with nonconventional modalities, e.g. dance/emotion/touch) - eval/finetuning foundational models for x-modal retrieval - checking out some jazz bars feel free to reach out!
🎷🔥 Latent Diffusion Models Tutorial 🔥🎷 @RuiqiGao, @ArashVahdat and I will present the "Latent Diffusion Models: Is the Generative AI Revolution Happening in Latent Space?" tutorial @ NeurIPS'23 tomorrow! Tomorrow, Monday, 9:45am-12:15pm, Hall E2. neurips2023-ldm-tutorial.github.io
We're introducing new stereo models for MusicGen. By extending the delay codebook pattern to cover tokens from both left & right channels, these models can generate stereo output with no extra computational cost vs previous models. Try MusicGen on 🤗 ➡️ bit.ly/3uai3eC
We have just released a new ADCx SF23 Conference Video! #Ddsp-VST: Neural Synthesis for All - Nikhil Bhanu & @wilzh40 - ADCx SF youtube.com/watch?v=4-UgqS… #Coding #adcx
Lots of big announcements coming up this month, starting tomorrow :) My life is about to look completely different
cool stuff, been daydreaming about this for a while
no computer music project is complete without a musical interface, so here is **unloop**: a co-creative looper that uses vampnet to **not** repeat itself. unloop is open source: github.com/hugofloresgarc…, and is powered by a @huggingface space.
no computer music project is complete without a musical interface, so here is **unloop**: a co-creative looper that uses vampnet to **not** repeat itself. unloop is open source: github.com/hugofloresgarc…, and is powered by a @huggingface space.
"Music Production Behaviour Modelling" - PhD Thesis from @josephtcolonel qmro.qmul.ac.uk/xmlui/bitstrea…
any ideas on how this can be mapped into a latent space for physical lighting in conjunction with the audio component? i see a lot of potential here :)
Semantic exploration using real-time hand tracking, rave and msprior ! 🤚 The semantic space is much more structured than rave's latent space, and subtle movements can really make a difference 😁 github.com/caillonantoine…
Semantic exploration using real-time hand tracking, rave and msprior ! 🤚 The semantic space is much more structured than rave's latent space, and subtle movements can really make a difference 😁 github.com/caillonantoine…
Graphs & geometric deep learning are cool, but what's next? Our latest work leverages topology to model higher order relationships beyond graphs, covering domains like meshes, sets & their mixtures naturally. Learn more: arxiv.org/abs/2206.00606 #TopologicalDeepLearning #TDL
United States Trends
- 1. Hunter 1,05 Mn posts
- 2. $KIM N/A
- 3. Josh Allen 48,6 B posts
- 4. 49ers 54,9 B posts
- 5. 49ers 54,9 B posts
- 6. Niners 10,8 B posts
- 7. #BaddiesMidwest 18,4 B posts
- 8. Burisma 37,7 B posts
- 9. Montas 3.521 posts
- 10. Purdy 8.740 posts
- 11. Dolly 14,8 B posts
- 12. Manaea N/A
- 13. The Big Guy 55,6 B posts
- 14. #SFvsBUF 21,3 B posts
- 15. Hardy 13,8 B posts
- 16. Good for Joe 30,1 B posts
- 17. Achilles 6.027 posts
- 18. #Married2Med 4.456 posts
- 19. AFC East 9.209 posts
- 20. #RHOP 6.327 posts
Who to follow
-
Lance Martin
@RLanceMartin -
Div Garg
@DivGarg_ -
anton
@abacaj -
Conviction
@conviction -
Sam Whitmore
@sjwhitmore -
will depue
@willdepue -
Mina Fahmi
@minafahmi_ -
galactixy_illustrations
@GalactixyI -
AI Daily
@AIDailyNewsNow -
asim
@asimdotshrestha -
Walden
@walden_yan -
Stef Rouschop
@stef_r -
Alex Volkov (Thursd/AI)
@altryne -
Gogolian
@gogoliansnake -
Niraj
@niraj
Something went wrong.
Something went wrong.