Haven Kim
@havenkim.bsky.social
1st-year CS PhD student at UCSD
I work on music and ML.
havenpersona.github.io
I work on music and ML.
havenpersona.github.io
Reposted by Haven Kim
Today we release Stable Audio Open Small 🫂
Based on adversarial post-training, it does not rely on distillation or CFG
Runtime is reduced to milliseconds with GPUs or seconds with CPUs
Weights huggingface.co/stabilityai/...
Blog stability.ai/news/stabili...
Paper arxiv.org/abs/2505.08175
Based on adversarial post-training, it does not rely on distillation or CFG
Runtime is reduced to milliseconds with GPUs or seconds with CPUs
Weights huggingface.co/stabilityai/...
Blog stability.ai/news/stabili...
Paper arxiv.org/abs/2505.08175
May 14, 2025 at 3:51 PM
Today we release Stable Audio Open Small 🫂
Based on adversarial post-training, it does not rely on distillation or CFG
Runtime is reduced to milliseconds with GPUs or seconds with CPUs
Weights huggingface.co/stabilityai/...
Blog stability.ai/news/stabili...
Paper arxiv.org/abs/2505.08175
Based on adversarial post-training, it does not rely on distillation or CFG
Runtime is reduced to milliseconds with GPUs or seconds with CPUs
Weights huggingface.co/stabilityai/...
Blog stability.ai/news/stabili...
Paper arxiv.org/abs/2505.08175
What are some interesting yet *easy-to-understand* papers in the field of music AI? I'm planning to introduce a good number of papers to undergrads, but I feel my list is becoming biased toward work by researchers around me. Happy to hear suggestions from others in the field!
February 13, 2025 at 5:43 AM
What are some interesting yet *easy-to-understand* papers in the field of music AI? I'm planning to introduce a good number of papers to undergrads, but I feel my list is becoming biased toward work by researchers around me. Happy to hear suggestions from others in the field!
Reposted by Haven Kim
🎉Super excited to share that our TeaserGen project led by Weihan Xu (wx83.github.io) has been accepted to #ICLR2025!
🔍We explored a new task of generating teasers for long documentaries.
🤩We presented a new dataset, new models, and new evaluation metrics for teaser generation.
🔍We explored a new task of generating teasers for long documentaries.
🤩We presented a new dataset, new models, and new evaluation metrics for teaser generation.
January 26, 2025 at 7:03 AM
🎉Super excited to share that our TeaserGen project led by Weihan Xu (wx83.github.io) has been accepted to #ICLR2025!
🔍We explored a new task of generating teasers for long documentaries.
🤩We presented a new dataset, new models, and new evaluation metrics for teaser generation.
🔍We explored a new task of generating teasers for long documentaries.
🤩We presented a new dataset, new models, and new evaluation metrics for teaser generation.
Reposted by Haven Kim
📢 Call to all #MIRCommunity!
Have you ever wondered what an open model means? Help us shape the definition of open models in generative AI for music by taking our survey — just 10 minutes!
👉 forms.gle/Z48t6HPBXwWC3r…
thank you 💫
Have you ever wondered what an open model means? Help us shape the definition of open models in generative AI for music by taking our survey — just 10 minutes!
👉 forms.gle/Z48t6HPBXwWC3r…
thank you 💫
https://forms.gle/Z48t6HPBXwWC3r…
December 3, 2024 at 12:36 PM
📢 Call to all #MIRCommunity!
Have you ever wondered what an open model means? Help us shape the definition of open models in generative AI for music by taking our survey — just 10 minutes!
👉 forms.gle/Z48t6HPBXwWC3r…
thank you 💫
Have you ever wondered what an open model means? Help us shape the definition of open models in generative AI for music by taking our survey — just 10 minutes!
👉 forms.gle/Z48t6HPBXwWC3r…
thank you 💫
Reposted by Haven Kim
We just created a Bluesky starter pack featuring people and groups working at the intersection of AI and music, covering both symbolic and audio approaches. Let us know if you'd like to be added or removed!
go.bsky.app/PBvFCxa
go.bsky.app/PBvFCxa
November 28, 2024 at 3:20 AM
We just created a Bluesky starter pack featuring people and groups working at the intersection of AI and music, covering both symbolic and audio approaches. Let us know if you'd like to be added or removed!
go.bsky.app/PBvFCxa
go.bsky.app/PBvFCxa