cortexelation's profile picture. → @dadabots ← Creative AI & Death Metal #DSP #MIR #NLP #ML #NeuralNetworks | @Harmonai_org

CJ Carr

@cortexelation

→ @dadabots ← Creative AI & Death Metal #DSP #MIR #NLP #ML #NeuralNetworks | @Harmonai_org

Pinned

Our paper "Generating Black Metal and Math Rock: Beyond Bach, Beethoven, and Beatles" got accepted by NIPS 2017 Workshop for Machine Learning for Creativity and Design! @zzuk_at_aol #dadabots


CJ Carr reposted

WizardCoder-15B is crushing it‼️🔥 Amazing progress in open-source code LLMs recently. I believe open-source may have progressed beyond closed-source models in this area. github.com/nlpxucan/Wizar…

hardmaru's tweet image. WizardCoder-15B is crushing it‼️🔥

Amazing progress in open-source code LLMs recently. I believe open-source may have progressed beyond closed-source models in this area.

github.com/nlpxucan/Wizar…

🔥🔥🔥 Introduce the newest WizardCoder model ! 1. Surpass Claude-Plus (+6.8), Bard (+15.3) and InstructCodeT5+ (+22.3) on HumanEval Benchmarks 2. Paper is coming, with brand-new Evol+ methods for code LLMs Github: github.com/nlpxucan/Wizar… HF Weight: huggingface.co/WizardLM/Wizar…

WizardLM_AI's tweet image. 🔥🔥🔥
Introduce the newest WizardCoder model !

1. Surpass Claude-Plus (+6.8), Bard (+15.3) and InstructCodeT5+ (+22.3) on HumanEval Benchmarks

2. Paper is coming, with brand-new Evol+ methods for code LLMs

Github:
github.com/nlpxucan/Wizar…

HF Weight:
huggingface.co/WizardLM/Wizar…
WizardLM_AI's tweet image. 🔥🔥🔥
Introduce the newest WizardCoder model !

1. Surpass Claude-Plus (+6.8), Bard (+15.3) and InstructCodeT5+ (+22.3) on HumanEval Benchmarks

2. Paper is coming, with brand-new Evol+ methods for code LLMs

Github:
github.com/nlpxucan/Wizar…

HF Weight:
huggingface.co/WizardLM/Wizar…


CJ Carr reposted

GPT-Engineer is BLOWING UP on GitHub right now 🔥 Prompt an AI agent to write an entire codebase 🤯 +2k stars today alone. I'll be experimenting with it this weekend to improve my workflow.

ehalm_'s tweet image. GPT-Engineer is BLOWING UP on GitHub right now 🔥

Prompt an AI agent to write an entire codebase 🤯

+2k stars today alone. I'll be experimenting with it this weekend to improve my workflow.

CJ Carr reposted

Absolutely fantastic work. Congrats! \m/

Darius's "Hyperbolic Audio Source Separation" paper has been recognized as one of the top 3% of all papers accepted at #ICASSP2023 @ieeeICASSP 👏🎉🍾 Paper: arxiv.org/abs/2212.05008 Code: github.com/merlresearch/h… Demo video: youtube.com/watch?v=RKsAMb…

JonathanLeRoux's tweet image. Darius's "Hyperbolic Audio Source Separation" paper has been recognized as one of the top 3% of all papers accepted at #ICASSP2023 @ieeeICASSP 👏🎉🍾
Paper: arxiv.org/abs/2212.05008
Code: github.com/merlresearch/h…
Demo video: youtube.com/watch?v=RKsAMb…


CJ Carr reposted

Interesting alternative derivation of diffusion models without differential equations or variational inference. Reminiscent of flow matching / rectified flow. Which of these perspectives is the simplest is subjective IMO, but more is better: new perspectives inspire new ideas!

When @_Laurent and I started learning about diffusion models, we were puzzled by the amount of jargon and concepts. So, we derived a model from scratch with our own graphics-people intuitions. Simple derivation, simple implementation, SOTA quality. ggx-research.github.io/publication/20…

eric_heitz's tweet image. When @_Laurent and I started learning about diffusion models, we were puzzled by the amount of jargon and concepts. 

So, we derived a model from scratch with our own graphics-people intuitions. Simple derivation, simple implementation, SOTA quality.

ggx-research.github.io/publication/20…


CJ Carr reposted

Phonetic palindrome Record yourself saying “Serbian neighbours” Reverse it (Sound on)


CJ Carr reposted

every moment you leave an A100 idle in the cloud the Basilisk adds another tally to your karmic record


CJ Carr reposted

3/ Volume control


CJ Carr reposted

the year is 2030. after ed sheeran lost his case, musicians exhausted every 4-bar chord progression. pop music now features 23-bar cycles. tutorial videos explain how to escape copyright infringement using arabic 17 tone equal temperament. noise music experiences a renaissance.


CJ Carr reposted

One of the coolest uses I’ve seen of a NeRF so far


CJ Carr reposted

embodied experience as to what it is like to be a big bird

VRヘッドトラッキングを使ってドローンのパイロット気分を味わう youtu.be/N5cBKmFZ6Lo #FPV #POV #drone #OpenSource #HeadTracker #HMD #VR #VirtualReality #UX #experience



CJ Carr reposted

Announcing StableLM❗ We’re releasing the first of our large language models, starting with 3B and 7B param models, with 15-65B to follow. Our LLMs are released under CC BY-SA license. We’re also releasing RLHF-tuned models for research use. Read more→ stability.ai/blog/stability…

StabilityAI's tweet image. Announcing StableLM❗

We’re releasing the first of our large language models, starting with 3B and 7B param models, with 15-65B to follow. Our LLMs are released under CC BY-SA license.

We’re also releasing RLHF-tuned models for research use. Read more→ stability.ai/blog/stability…

CJ Carr reposted

Rather than sign some letter to delay AI progress, I signed @LAION_AI petition to democratize AI research by establishing an international, publicly funded supercomputing facility equipped with 100K SOTA accelerators to train open source foundation models. openpetition.eu/petition/onlin…


CJ Carr reposted

possibly one of the funniest model on the hub (the RLHF tutorial that was the reason of its creation is also awesome - check it out)

Thom_Wolf's tweet image. possibly one of the funniest model on the hub (the RLHF tutorial that was the reason of its creation is also awesome - check it out)

Excited to introduce: StackLlama🦙 An end-to-end tutorial for training Llama with RLHF on preference data such as the StackExchange questions! Blog: hf.co/blog/stackllama Demo: hf.co/spaces/trl-lib… Code: github.com/lvwerra/trl/tr… The resulting model is surprisingly fun!🧵

lvwerra's tweet image. Excited to introduce: StackLlama🦙

An end-to-end tutorial for training Llama with RLHF on preference data such as the StackExchange questions!

Blog: hf.co/blog/stackllama
Demo: hf.co/spaces/trl-lib…
Code: github.com/lvwerra/trl/tr…

The resulting model is surprisingly fun!🧵


CJ Carr reposted

The last couple of weeks on Twitter, aka GPT4 Twitter

sterlingcrispin's tweet image. The last couple of weeks on Twitter, aka GPT4 Twitter

CJ Carr reposted

Everyone's job description after GPT-5


CJ Carr reposted

Semi-realtime Stable Diffusion image-to-image (Van Gogh style), Unity plugin based on Apple's Core ML port. The latency is about 2 seconds on M1 Max MacBook Pro. github.com/keijiro/Stable…


CJ Carr reposted

You Had One Job 👋🏻 #StableDiffusion

hardmaru's tweet image. You Had One Job 👋🏻

#StableDiffusion

CJ Carr reposted

🎧🧠

🎵Introducing Diffusion Radio - A 24/7 Livestream of AI-Generated Music!🎵 📢The Harmonai team is excited to announce a New YouTube Live Stream which will run 24/7, showcasing amazing samples of AI-generated music from our latest models!📢 🎉Enjoy!🎉 youtube.com/watch?v=uGRLOM…

harmonai_org's tweet card. 🎵 Diffusion Radio - 24/7 AI music from Harmonai 🎵 [NEW LINK IN...

youtube.com

YouTube

🎵 Diffusion Radio - 24/7 AI music from Harmonai 🎵 [NEW LINK IN...



CJ Carr reposted

New paper from our research team: First true multimodal image synthesis. You can prompt any combination of texts and images. Also shows the power of our multimodal embedding. Check out the Catronaut in the paper.

M-VADER: A Model for Diffusion with Multimodal Context abs: arxiv.org/abs/2212.02936

_akhaliq's tweet image. M-VADER: A Model for Diffusion with Multimodal Context 
abs: arxiv.org/abs/2212.02936


CJ Carr reposted

You can now make stable diffusion music videos that interpolate to the beat of a song using stable_diffusion_videos==0.5.0! 🚀 I basically rewrote the codebase! Everything is in the pipeline class now, so you can load other models too. Anyway, here's how to use it...

_nateraw's tweet image. You can now make stable diffusion music videos that interpolate to the beat of a song using stable_diffusion_videos==0.5.0! 🚀

I basically rewrote the codebase! Everything is in the pipeline class now, so you can load other models too.

Anyway, here's how to use it...

Loading...

Something went wrong.


Something went wrong.