[AUDITORY] Call for Submissions — 1st Workshop on Large Language Models for Music & Audio (LLM4MA @ ISMIR 2025)

Subject: [AUDITORY] Call for Submissions — 1st Workshop on Large Language Models for Music & Audio (LLM4MA @ ISMIR 2025)

From: Yinghao Ma <yinghao.ma@xxxxxxxxxx>

Date: Thu, 12 Jun 2025 10:41:48 +0000

Accept-language: en-GB, zh-CN, en-US

Approved-by: yinghao.ma@xxxxxxxxxx

Arc-authentication-results: i=1; mx.microsoft.com 1; spf=pass smtp.mailfrom=qmul.ac.uk; dmarc=pass action=none header.from=qmul.ac.uk; dkim=pass header.d=qmul.ac.uk; arc=none

Arc-message-signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector10001; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-AntiSpam-MessageData-ChunkCount:X-MS-Exchange-AntiSpam-MessageData-0:X-MS-Exchange-AntiSpam-MessageData-1; bh=cVBlomtAUuNvP6iA3GNAO0CPisJ68nWdP70XJ8yEggU=; b=OIEjrBVNwz+pZGdh0MdrwBT3UEXs1/bntj+zzBA59I3c69tOPGFIP0imIWIUZNe3G+cNaF2CmeRWjpXrhXFMtluf9gBLfBJGyJS7QlXiJZu6RJQ2ow+7wZrvgLeOOP5IC+gGnzK/i7SuT5l7Sm6w8Eq/rFg92FqntWpveIlWKJuHABWXWVdltFQgNAKtIvGCJ+dTtU+sbn1+uEo61zuezfaa6/D+Wrk8RnkE48CR1r9KmkszugUPLJ5IclNu3plDRaundO/ppKyQKOG5/lrrsAxvQlLM5qBJ2mPa0N0RFLklipUavoXS0uQ/3L94+gMcMAbsQ/1q1r7PTRKHceQYFA==

Arc-seal: i=1; a=rsa-sha256; s=arcselector10001; d=microsoft.com; cv=none; b=wqiTyXTbMie1puFfPaImodnhJufVbb3B8SrIemyj5FqGoD6YcGR8Uxy/12vZbFxoS2wBOYDRXO6HKtVnAUhaPBWjWSazSOAnmv8LbtirJF0yST182wLAnHt2P6ijDCWlFIQC0i8sTtAX2KAdvneV/4uFpsulWPKiezldHkAo+rH1dX0IEVDKiKmtKhaYy3pAzZwT+NVzBKw7LZFL3Swa19znv+3UtMhc/Kzc09s50VwrBajGUuzAcOS5Ss5UsnQyfnscv+/uA1MfyA37BdXeIgrxqKavhDYpHv4QsLZ1YNsNEDum10J8OB3ff2dTa9LN4oo10gVIVMbzEgTE9VwWTA==

Authentication-results: mx.google.com; dkim=pass header.i=@LISTS.MCGILL.CA header.s=SELECTOR1 header.b=ZZID8twi; arc=fail (signature failed); spf=pass (google.com: domain of owner-auditory@xxxxxxxxxxxxxxx designates 132.206.27.104 as permitted sender) smtp.mailfrom=owner-auditory@xxxxxxxxxxxxxxx; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=qmul.ac.uk

Delivered-to: dan.ellis@xxxxxxxxx

Dkim-signature: v=1; a=rsa-sha256; d=LISTS.MCGILL.CA; s=SELECTOR1; c=relaxed/relaxed; bh=cVBlomtAUuNvP6iA3GNAO0CPisJ68nWdP70XJ8yEggU=; i=@LISTS.MCGILL.CA; h=Approved-By:ARC-Seal:ARC-Message-Signature:ARC-Authentication-Results:Thread-Topic:Thread-Index:Accept-Language:Content-Language:msip_labels:Content-Type:MIME-Version:Message-ID:Date:Reply-To:Sender:From:Subject:To:List-Help:List-Unsubscribe:List-Subscribe:List-Owner:List-Archive; b=ZZID8twi7E2vjQ81JdK3A9rseNpLjM8uI4Ed6DeecB4AtBGdP2hErtQ8XHzF9Rhv/0iCG4vmi0YFWIJOXGq0U8QLBeLQtT6qCa0MTD1gsNsNkSCRmaE4F/6jJQoD78BfeR9+I/fKUoVUokLwru/hJxumsPJ7L8vT4N08HGzL8v8R0vW4jdITT0xURkizOM0rDYFaoXhOHO8iwoeyBiRz8xuUSoHwpZqmOs7No3+JUxHYHuzCZRU5trsOWWY7CdtIpzN3jZCete7faAsQG2/mJZyxfhu1Sf2Ypc1efLxsSIXuWJppi2O0BhRANyu84f8kL6oBzLtwiQoGuzQ/V3cGfA==

List-archive: <https://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY>

List-help: <https://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY>, <mailto:LISTSERV@LISTS.MCGILL.CA?body=INFO%20AUDITORY>

List-owner: <mailto:AUDITORY-request@LISTS.MCGILL.CA>

List-subscribe: <mailto:AUDITORY-subscribe-request@LISTS.MCGILL.CA>

List-unsubscribe: <mailto:AUDITORY-unsubscribe-request@LISTS.MCGILL.CA>

Msip_labels:

Reply-to: Yinghao Ma <yinghao.ma@xxxxxxxxxx>

Sender: AUDITORY - Research in Auditory Perception <AUDITORY@xxxxxxxxxxxxxxx>

Thread-index: AQHb24YhjL1nDRKXfkOYJIKSCGp3/w==

Thread-topic: Call for Submissions — 1st Workshop on Large Language Models for Music & Audio (LLM4MA @ ISMIR 2025)

Dear Auditory and Listening Community,

We are pleased to announce the 1st Workshop on Large Language Models for Music & Audio (LLM4MA), to be held on Friday, September 26th, 2025, as the satellite event of the 26^th conference of the International Society for Music Information Retrieval (ISMIR 2025) at KAIST, Daejeon, Korea.

LLM4Music is a new forum dedicated to the intersection of large language models (LLMs) and music/audio research. As LLMs increasingly influence how we compose, analyse, and interact with music across modalities—including text, audio, image, and video—this workshop aims to foster early-stage ideas and community dialogue around LLM-driven approaches in Music Information Retrieval (MIR), audio generation, and computational creativity.

We particularly welcome submissions that may not yet be suited to the ISMIR main conference track but contribute novel insights or applications.

🔍 Topics of Interest (include but are not limited to):

Tokenisation of Music & Audio
Long Sequence Modelling
Instruction/Reinforcement Fine-tuning
Artistic Music & Audio Generation & Evaluation
Industry Applications & Creative Tools
Diversity, Bias, and Cultural Representation
Scaling Laws & Emergent Capabilities
Dataset Design & Generalizability
Multimodal Extensions (text, audio, vision)
Chain-of-Thought & Reasoning on Music & Sound
Prompt Engineering & In-Context Learning
Autonomous Agents on Music & Audio
Deepfake Detection in Music & Audio Generation

🗓️ Important Dates (AoE Timezone)

Submission Opens: June 6, 2025
Submission Deadline: August 10, 2025
Author Notification: August 31, 2025
Camera-Ready Version: September 14, 2025
Workshop Date: September 26, 2025

📄 Submission Guidelines

We invite 2-page extended abstracts or 4-page short papers.
Accepted submissions will be presented as posters during the in-person workshop.

Submission format: (2+1) or (4+1) — content + optional references/acknowledgements
Review process: Double-blind
Proceedings: Submissions are not part of the official ISMIR 2025 proceedings

Please visit our website for submission instructions and updates:
🔗 https://m-a-p.ai/LLM4Music/

Please visit the OpenReview website for submission: 🔗 https://openreview.net/group?id=ISMIR.net/2025/Workshop/LLM4Music&referrer=%5BHomepage%5D(%2F)#tab-your-consoles

For inquiries, contact:
📧 yinghao.ma@xxxxxxxxxx | a43992899@xxxxxxxxx

We look forward to your contributions and to building a vibrant LLM4Music community together!

Sincerely,

The LLM4MA Organizers