A Year Into Making LLMs, and now Topped Open Source SoTA?!

Name: A Year Into Making LLMs, and now Topped Open Source SoTA?!
Uploaded: 2026-06-17T13:33:19.437Z
Duration: 22 min 1 s
Channel: bycloud
Description: Video covering Xiaomi's MiMo models, a series of open-source LLMs that achieved state-of-the-art results within a year. Discusses research and training progress, including multimodal extensions and model optimizations.

bycloud17 June 2026Watch on YouTube

Description

Try Mammouth now for only €10/mo! https://mammouth.ai In today's video, let us find out how Xiaomi went from phones, appliances, and EVs to suddenly becoming one of the fastest-rising players in open-source AI. This video breaks down Xiaomi’s MiMo models, the research behind their insane progress, and how they caught up to frontier AI labs in just about a year since their first model release. my latest project: Intuitive AI Academy We just wrote a new piece on Optimizers! https://intuitiveai.academy/ limited time code "SUMMER" for 25% off yearly plan My Newsletter https://mail.bycloud.ai/ My Patreon https://www.patreon.com/c/bycloud [MiMo-Embodied] https://arxiv.org/pdf/2511.16518 [HySparse] https://arxiv.org/pdf/2602.03560 [MiMo] https://arxiv.org/pdf/2505.07608 [MiMo Audio] https://arxiv.org/abs/2512.23808 [MiMo VL] https://arxiv.org/abs/2506.03569 [MiMo V2 Flash] https://arxiv.org/abs/2601.02780 [MiMo V2.5 Pro] https://mimo.xiaomi.com/mimo-v2-5-pro/ [MiMo Huggingface Models] https://huggingface.co/XiaomiMiMo Try out my new fav place to learn how to code https://scrimba.com/?via=bycloudAI This video is supported by the kind Patrons & YouTube Members: 🙏Spam Maj, Alex, Chris LeDoux, DX Research Group, Poof N' Inu, Deagan, Robert Zawiasa, Ryszard Warzocha, Tobe2d, Louis Muk, Akkusativ, Kevin Tai, Mark Buckler, NO U, Tony Jimenez, Ângelo Fonseca, jiye, Anushka, Asad Dhamani, Binnie Yiu, Calvin Yan, Clayton Ford, Diego Silva, Etrotta, Gonzalo Fidalgo, Handenon, Hector, Jake Disco very, Michael Brenner, Nilly K, OlegWock, Daddy Wen, Shuhong Chen, Sid_Cipher, Stefan Lorenz, Sup, tantan assawade, Thipok Tham, Thomas Di Martino, Thomas Lin, Richárd Nagyfi, Paperboy, mika, Leo, Berhane-Meskel, Kadhai Pesalam, mayssam, Bill Mangrum, nyaa, Toru Mon, Lame Plane, Matej Macak, Len Mo, saylikhapekar, ZyanSheep, THEVIERAOS, Ricardo Raphael Corona-Moreno, superchordate [Discord] https://discord.gg/NhJZGtH [Twitter] https://twitter.com/bycloudai [Patreon] https://www.patreon.com/bycloud [Business Inquiries] bycloud@smoothmedia.co [Other Inquiries] bycloudai@gmail.com [Profile & Banner Art] https://twitter.com/pygm7 [Video Editor] @Booga04 Manim Animations created with Manimate https://www.manimate.ai/ [Ko-fi] https://ko-fi.com/bycloudai

What you'll learn

Xiaomi achieved state-of-the-art results in just one year with open-source LLMs, progressing from initial release to competing with frontier AI labs
MiMo models include multimodal extensions such as audio and vision capabilities, extending beyond text-only functionality
The video covers research and training progress that enabled Xiaomi's rapid advancement in open-source AI

Frequently asked questions

What are MiMo models and what made Xiaomi develop them?

MiMo models are a series of open-source LLMs from Xiaomi that achieved state-of-the-art results within one year. They include multimodal extensions for audio and vision alongside core functionality.

How did Xiaomi shift from phones and EVs to AI research?

The video explores how Xiaomi, known for phones and appliances, became one of the fastest-rising players in open-source AI through focused LLM research and optimization.

What types of AI models are included in the MiMo releases?

The MiMo series includes diverse releases such as embodied models, multimodal vision-language models, and audio models, alongside optimizations like HySparse and Flash versions.

Topics

llm models open source ai xiaomi mimo model research multimodal ai