Uploaded June 2025 | Updated September 2026, 1 week ago
Get started now with open source & privacy focused password manager by Proton! proton.me/pass/bycloudai
In this video, we are going to dive into native MoE multimodal LLMs, the difference between early fusion and late fusion, and why a unified model is the way forward.
My Newsletter
mail.bycloud.ai
my project: find, discover & explain AI research semantically
findmypapers.ai
My Patreon
patreon.com/c/bycloud
paper sauces
Chameleon: Mixed-Modal Early-Fusion Foundation Models
[Paper] arxiv.org/abs/2405.09818
Scaling Laws for Native Multimodal Models
[Paper] arxiv.org/abs/2504.07951
Scaling Pre-training to One Hundred Billion Data for Vision Language Models
[Paper] arxiv.org/abs/2502.07617
Try out my new fav place to learn how to code scrimba.com/?via=bycloudAI
This video is supported by the kind Patrons & YouTube Members:
🙏Nous Research, Chris LeDoux, Ben Shaener, DX Research Group, Poof N' Inu, Andrew Lescelius, 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
[Discord] discord.gg/NhJZGtH
[Twitter] twitter.com/bycloudai
[Patreon] patreon.com/bycloud
[Business Inquiries] bycloud@smoothmedia.co
[Profile & Banner Art] twitter.com/pygm7
[Video Editor] @Booga04
[Bitcoin (BTC)] 3JFMJQVGXNA2HJE5V9qCwLiqy6wHY9Vhdx
[Ethereum (ETH)] 0x3d784F55E0bE5f35c1566B2E014598C0f354f190
[Litecoin (LTC)] MGHnqALjyU2W6NuJSSW9fTWV4dcHfwHZd7
[Bitcoin Cash (BCH)] 1LkyGfzHxnSfqMF8tN7ZGDwUTyBB6vcii9
[Solana (SOL)] 6XyMCEdVhtxJQRjMKgUJaySL8cGoBPzzA2NPDMPfVkKN
[Ko-fi] ko-fi.com/bycloudai
Get started now with open source & privacy focused password manager by Proton! proton.me/pass/bycloudai
In this video, we are going to dive into native MoE multimodal LLMs, the difference between early fusion and late fusion, and why a unified model is the way forward.
My Newsletter
mail.bycloud.ai
my project: find, discover & explain AI research semantically
findmypapers.ai
My Patreon
patreon.com/c/bycloud
paper sauces
Chameleon: Mixed-Modal Early-Fusion Foundation Models
[Paper] arxiv.org/abs/2405.09818
Scaling Laws for Native Multimodal Models
[Paper] arxiv.org/abs/2504.07951
Scaling Pre-training to One Hundred Billion Data for Vision Language Models
[Paper] arxiv.org/abs/2502.07617
Try out my new fav place to learn how to code scrimba.com/?via=bycloudAI
This video is supported by the kind Patrons & YouTube Members:
🙏Nous Research, Chris LeDoux, Ben Shaener, DX Research Group, Poof N' Inu, Andrew Lescelius, 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
[Discord] discord.gg/NhJZGtH
[Twitter] twitter.com/bycloudai
[Patreon] patreon.com/bycloud
[Business Inquiries] bycloud@smoothmedia.co
[Profile & Banner Art] twitter.com/pygm7
[Video Editor] @Booga04
[Bitcoin (BTC)] 3JFMJQVGXNA2HJE5V9qCwLiqy6wHY9Vhdx
[Ethereum (ETH)] 0x3d784F55E0bE5f35c1566B2E014598C0f354f190
[Litecoin (LTC)] MGHnqALjyU2W6NuJSSW9fTWV4dcHfwHZd7
[Bitcoin Cash (BCH)] 1LkyGfzHxnSfqMF8tN7ZGDwUTyBB6vcii9
[Solana (SOL)] 6XyMCEdVhtxJQRjMKgUJaySL8cGoBPzzA2NPDMPfVkKN
[Ko-fi] ko-fi.com/bycloudai
![AI Tech CEOs In A Cage Fight??? [The AI Timeline #6]](https://i.ytimg.com/vi/q4k3bQMNqtk/mqdefault.jpg "AI Tech CEOs In A Cage Fight??? [The AI Timeline #6]
Welcome to my 6th episode of the weekly AI news series The AI Timeline, where I go through the AI news in the past week with the most distilled information and memes!
Seeing the World through Your Eyes
[Project Page] https://world-from-eyes.github.io/
Meta Voicebox
[Blog] https://about.fb.com/news/2023/06/introducing-voicebox-ai-for-speech-generation/
Acing MIT EECS Paper
[Paper] https://arxiv.org/abs/2306.08997
Acing MIT EECS Critical Analysis
[Notion] https://flower-nutria-41d.notion.site/No-GPT4-can-t-ace-MIT-b27e6796ab5a48368127a98216c76864?pvs=4
LIMA: Less Is More for Alignment
[Paper] https://arxiv.org/abs/2305.11206
Open LLaMa 13B
[Huggingface] https://huggingface.co/openlm-research/open_llama_13b
Google Try-on Diffusion
[TW] https://twitter.com/Google/status/1669431242889089029?s=20
[Paper] https://arxiv.org/pdf/2306.08276.pdf
Neuwigs
[Project Page] https://ziyanw1.github.io/neuwigs/
Rerender a Video
[Project Page] https://anonymous-31415926.github.io/
Adobe Firefly for Illustrator
[YT] https://youtu.be/6anR6nFUafU
Segment Anything to Remove IRL ads
[TW] https://twitter.com/localghost/status/1670884510261706752?s=20
ChatGPT Leak
[Rowan] https://twitter.com/rowancheung/status/1669750794659434496?s=20
Language to Rewards for Robotic Skill Synthesis
[Project Page] https://language-to-reward.github.io/
GLoRA
[Paper] https://arxiv.org/pdf/2306.07967.pdf
AniFaceDrawing
[Paper] https://arxiv.org/abs//2306.07476
[Demo] https://youtu.be/GcL67h8QEOY
TAPIR
[Project Page] https://deepmind-tapir.github.io/
BITE
[Project Page] https://bite.is.tue.mpg.de/
GAIA-1
[Project Page] https://wayve.ai/thinking/introducing-gaia1/
Vid2Avatar
[Project Page] https://moygcc.github.io/vid2avatar/
[Code] https://github.com/MoyGcc/vid2avatar
PS1 Graphics
[TW] https://twitter.com/Vajayjay_K
This video is supported by the kind Patrons & YouTube Members:
🙏Andrew Lescelius, alex j, Chris LeDoux, Alex Maurice, Deagan, Tony Jimenez, Panther Modern, Jake Disco, Demilson Quintao, Shuhong Chen, Hongbo Men, happi nyuu nyaa, Carol Lo, Mose Sakashita, Miguel, Bandera, Gennaro Schiano, gunwoo, Ravid Freedman, Mert Seftali, Mrityunjay, Richárd Nagyfi, Timo Steiner, Henrik G Sundt, projectAnthony, Brigham Hall, Kyle Hudson, Kalila, Jef Come, Jvari Williams, Tien Tien
[Discord] https://discord.gg/NhJZGtH
[Twitter] https://twitter.com/bycloudai
[Patreon] https://www.patreon.com/bycloud
[Profile & Banner Art] https://twitter.com/pygm7
0:00 Seeing the World through Your Eyes
0:30 Elon VS Zuck Cage Fight
0:48 Voicebox
1:05 GPT-4 Cant Ace MIT
2:01 LIMA
2:30 Open LLaMa 13B
2:39 Google Try-on Diffusion
3:24 Neuwigs
4:08 Rerender a Video
4:43 ChatGPT Windows Activation Key
4:52 Adobe Firefly + Illustrator
5:02 Removes IRL ads
5:09 ChatGPT leaks
5:20 Robot LLM
5:38 GLoRA
5:50 AniFaceDrawing
6:18 TAPIR
6:31 BITE
6:38 GAIA-1
6:55 Vid2Avatar
7:14 QR Code Art
7:25 PS1 Graphic Upgrade with SD
7:32 Video2Video
7:38 Wolfram + Cats
7:48 Outro")
