@Haessun0213 Profile picture

Haesun Joung (Sunny)

@Haessun0213

Ph.D student @ Music and Audio Research Group (MARG), Seoul National University (SNU)

Similar User
Junghyun (Tony) Koo photo

@Junghyun_Koo

Seungryeol Paik photo

@PaikRyeol

Chang-Bin Jeon photo

@jeonchangbin49

Jin Woo Lee photo

@szin94

Eungbeom Kim photo

@eungbeomkim

yunkee chae photo

@ygch43

Dasaem Jeong photo

@DasaemJ

Seung-won Park photo

@veydpz_public

최형석 (Hyeong-Seok Choi) photo

@92HsChoi

Marco Martínez photo

@marcoamaram

SeungHeon Doh @ ISMIR2024 photo

@SeungHeon_Doh

Jongmin `sake` Jung photo

@sake_min

Jongho Choi photo

@_JonghoChoi

WOOSUNG CHOI photo

@WOOSUNGCHOI3

Gautham Mysore photo

@GauthamMysore

Haesun Joung (Sunny) Reposted

``Music Discovery Dialogue Generation Using Human Intent Analysis and Large Language Models,'' SeungHeon Doh, Keunwoo Choi, Daeyong Kwon, Taesu Kim, Juhan Nam, ift.tt/xqBuhgO


Haesun Joung (Sunny) Reposted

Introducing Copilot Arena - Interactive coding evaluation in the wild. Our extension lets you test top models for free, right in VSCode. Let's vote and build the Copilot leaderboard! Download here: marketplace.visualstudio.com/items?itemName… Led by @iamwaynechi and @valeriechen_ at CMU. 1/🧵


Haesun Joung (Sunny) Reposted

Excited to share our latest research, "Multidimensional Interpolants," now available on #arXiv! Exploring new dimensions in flow and diffusion, we're planning further experiments to enrich our insights. Check it out: arxiv.org/abs/2404.14161 #ML #AI #GenerativeAI #Flow #Diffusion

Tweet Image 1

Haesun Joung (Sunny) Reposted

``Musical Word Embedding for Music Tagging and Retrieval,'' SeungHeon Doh, Jongpil Lee, Dasaem Jeong, Juhan Nam, ift.tt/yRY1Mz9


Haesun Joung (Sunny) Reposted

SMITIN: Self-Monitored Inference-Time INtervention for Generative Music Transformers paper: arxiv.org/abs/2404.02252 demo: tinyurl.com/smitin code: coming soon w/ G. Wichern, @Francois6ermain, @sameer_khurana_, and @JonathanLeRoux 🧵


Haesun Joung (Sunny) Reposted

Nvidia releases Chat with RTX Personalize a custom chatbot connected to your content using the Chat with RTX demo app. Get fast and secure answers, all locally on your RTX-accelerated PC, using RAG and TensorRT-LLM.


Haesun Joung (Sunny) Reposted

Repeat After Me Transformers are Better than State Space Models at Copying paper page: huggingface.co/papers/2402.01… Transformers are the dominant architecture for sequence modeling, but there is growing interest in models that use a fixed-size latent state that does not depend on…

Tweet Image 1

Haesun Joung (Sunny) Reposted

As many of you know, over the past few months I have been sharing Prompt Engineering resources in different forms. I have now compiled them all into a cohesive publication and uploaded to arxiv: arxiv.org/abs/2401.14423

Tweet Image 1

Haesun Joung (Sunny) Reposted

How do you normalize your audio data before sending it into a neural net?


Haesun Joung (Sunny) Reposted

Music Structure Analyzer Released ✨ [Python Package] github.com/mir-aidj/all-i… [Paper] arxiv.org/abs/2307.16425 [Interactive Demo] taejun.kim/music-dissecto… [Hugging Face Space] huggingface.co/spaces/taejunk…


Haesun Joung (Sunny) Reposted

Can’t believe this is real. The Music De-limiter is now available!! Time to save music from the Loudness War! #WASPAA #WASPAA2023 Paper: arxiv.org/abs/2308.01187 Codes: github.com/jeonchangbin49… Try: huggingface.co/spaces/jeoncha… Sample: tinyurl.com/de-limiter-sam…


Haesun Joung (Sunny) Reposted

Thrilled to share that our paper "Towards a New Interface for Music Listening: A User Experience Study on YouTube" has been accepted to @ISMIRConf #ISMIR2023 paper: arxiv.org/abs/2307.14718 w. Ahyeon Choi, @Haessun0213, Joongseek Lee, K.Lee


Haesun Joung (Sunny) Reposted

Want to practice with a basic language model for melody generation? Here is my assignment notebook for the DL MIR course using torch. 1) RNN and Embedding from scratch 2) training pipeline (using PackedSequence) 3) inference part 4) decoding to MIDI colab.research.google.com/github/jdasam/…


Haesun Joung (Sunny) Reposted

AI doesn't stop 🤯 In the last 5 days: Meta's MusicGen Amazon Review AI StabilityAI Uncrop Runway Gen-2 For All Wordpress Jetpack AI Chinese LLM > GPT-3 ChatGPT for Enterprise Google Bard 30% Better Here's what you need to know:


Haesun Joung (Sunny) Reposted

🎤 Are you ready for a revolutionary breakthrough in audio technology? Say hello to AudioGPT!👋 This incredible tool allows LLMs to process complex audio information & conduct spoken conversations. Let's explore this game-changing innovation and try the official @Gradio demo.👇

Tweet Image 1

Haesun Joung (Sunny) Reposted

``M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval. (arXiv:2211.01180v2 [cs.CL] UPDATED),'' Layne Berry, Yi-Jen Shih, Hsuan-Fu Wang, Heng-Jui Chang, Hung-yi Lee, David Harwath, ift.tt/4M0O1pq


Haesun Joung (Sunny) Reposted

How to write math in a paper? Math allows you to convey your idea precisely and concisely. But how to write them clearly? 🤔 Check out some high-level tips (with examples). 🧵


Haesun Joung (Sunny) Reposted

🤩 HEADS UP • IMAGE-TO-MUSIC is back on @huggingface 🥹 — Update: now get text caption output from CLIP Interrogator + One more thing: you can use the magic of GPT to generate a more musical prompt from original caption 😇 — THX 🙏 @mubertapp team 🤗 huggingface.co/spaces/fffilon…

Tweet Image 1

Haesun Joung (Sunny) Reposted

I asked GPT-4 to create a new emotion. Then explain the emotion through sight, sound, and smell. It created "Meldoria", and it's absolutely incredible:

Tweet Image 1

Haesun Joung (Sunny) Reposted

"A goldendoodle playing in a park by a lake."


Loading...

Something went wrong.


Something went wrong.