Mega stoked to attend Conference on Language Modeling this week and present our work, MixAssist, on Wednesday! Ana Marasović sadly can't make it 😭, but hit me up if you'd like to chat about audio language models, music mixing, or anything else regarding music and audio!

Honored 🎷🎸🥁 𝗠𝗶𝘅𝗔𝘀𝘀𝗶𝘀𝘁 🎷🎸🥁 was selected as the #COLM2025 oral spotlight. Go check out MClem's 𝐭𝐚𝐥𝐤 on 𝐖𝐞𝐝 (𝐎𝐜𝐭 𝟖) at 𝟑:𝟑𝟎𝐩𝐦 in 517BC and 𝐩𝐨𝐬𝐭𝐞𝐫 from 𝟒:𝟑𝟎-𝟓:𝟑𝟎 in 710!

Happening today! #COLM2025

Tomorrow @ #COLM2025: 1️⃣ Purbid's 𝐩𝐨𝐬𝐭𝐞𝐫 @ 𝐒𝐨𝐋𝐚𝐑 (𝟏𝟏:𝟏𝟓-𝟏:𝟎𝟎𝐩𝐦) on catching redundant preference pairs & how pruning them hurts accuracy 2️⃣ My 𝐭𝐚𝐥𝐤 @ 𝐗𝐋𝐋𝐌-𝐑𝐞𝐚𝐬𝐨𝐧-𝐏𝐥𝐚𝐧 (𝟏𝟐𝐩𝐦) on measuring CoT faithfulness by looking at internals 1/3

Purbid's paper: anamarasovic.com/publications/c… A new addition to my talk is Fateme Hashemi Chaleshtori's ongoing work on 𝑎𝑢𝑡𝑜𝑚𝑎𝑡𝑒𝑑 𝑑𝑖𝑠𝑐𝑜𝑣𝑒𝑟𝑦 𝑜𝑓 𝑠𝑝𝑎𝑟𝑠𝑒 𝑓𝑒𝑎𝑡𝑢𝑟𝑒 𝑐𝑖𝑟𝑐𝑢𝑖𝑡𝑠 with 𝐠𝐫𝐚𝐩𝐡 𝐬𝐤𝐞𝐥𝐞𝐭𝐨𝐧𝐢𝐳𝐚𝐭𝐢𝐨𝐧 2/3

Excited to be going to my first #WASPAA2025 this year to present Stable Audio Open Small! Will be around all week for those who want to chat about all things fast and interactive audio gen 🤘

Everyone talks about LLM as a judge. But what about LLM as a witness.

PhD apps season is here! 😱🥳 Apply to do a PhD UW–Madison Computer Sciences (as pictured) w/ me to research: - Societal impact of AI - NLP ←→ CSS and cultural analytics - Computational sociolinguistics - Human-AI interaction - Culturally competent and inclusive NLP lucy3.github.io/prospective-st…

18 months ago, Andrej Karpathy set a challenge: "Can you take my 2h13m tokenizer video and translate [into] a book chapter". We've done it! It includes prose, code & key images. It's a great way to learn this key piece of how LLMs work. fast.ai/posts/2025-10-…

are you curious about generative recommendations for music? me too.. and that's why SeungHeon Doh and i have been working on TalkPlay by talkpl.ai. giving a talk in a week, at RIT & online.

🎵Music Arena ⚔️ was accepted to the NeurIPS 2025 Creativity Track, and we've released a big update to celebrate! Includes new models from Sonauto AI and ElevenLabs. Also, Music Arena is now available as a 🤗 Hugging Face space and dataset!

Biggest takeaway from Elon’s propaganda machine's talk at the #ICCV2025 CV4A11y Workshop: There are a lot of turtles. But seriously, cool to see great arguments on how advancements on LLMs and VLMs alone don't solve a11y automatically. There are actually more cool work to do enabled by LMs.

1/2 We’re releasing an in-depth tutorial on neural audio codecs, the secret sauce that makes it possible for audio LLMs to not sound like a horror movie:

Call for Papers: NLP4MusA 2026 We welcome work at the intersection of language, music, and audio — from music understanding and recommendation to creative generation. Submission deadline: Dec 19, 2025 Details & submission: sites.google.com/view/nlp4musa-…

This year: 1) NLP4MusA is expanding ISMIR to EACL 2) the Conversational Music Recommendation Challenge has been newly established! - Challenge Dataset: arxiv.org/abs/2509.09685 - Baseline Code: github.com/nlp4musa/music… - Evaluation Code: github.com/nlp4musa/music…

Musetok by the titan Jingyue Huang is out!! If you’re interested in representation learning, especially for discrete modalities like symbolic music, this is for you! Some extra thoughts here 🧵

NLP4MUSA 2026 officially announced a new challenge on conversational music recommendation. this year's challenge is based on TalkPlayData-2! i'm so honored to have contributed to this timely challenge.

tomorrow (10/23 Thu), 4:30PM EST. my talk on TalkPlay representing talkpl.ai. at RIT (Rochester) / on Zoom rit.zoom.us/j/93666758694?…

Some more work we are doing here at Smule Labs this summer. Just by adopting a mean-var head on top of rectified flow matching, we can make it model a distribution of velocities at each step, making it capable for test-time search use cases (and generated cool playable

New VST3/AU plugin drop to kick off the week! 🚀 Stable Audio Open Small by Stability AI Demucs stem separation LoopGAN for generating audio loops Many more models to come All running locally on-device! Opensource SDK and free plugin, enjoy! github.com/Neutone/neuton…