337 989 11001

John Smith PRO

John6666

John6666cat

AI & ML interests

None yet

Recent Activity

updated a collection about 1 hour ago

Spaces for Image-to-Image / Video

liked a Space about 1 hour ago

innoai/TRELLIS

updated a collection about 1 hour ago

Spaces for Image Upscaler / Upsampler / Resizer

View all activity

Organizations

John6666's activity

updated a collection about 1 hour ago

Spaces for Image-to-Image / Video

Collection

313 items • Updated about 1 hour ago • 12

liked a Space about 1 hour ago

Running on Zero

🏢

TRELLIS

Scalable and Versatile 3D Generation from images

updated a collection about 1 hour ago

Spaces for Image Upscaler / Upsampler / Resizer

Collection

34 items • Updated about 1 hour ago • 4

liked a Space about 1 hour ago

Running

165

🏙️

Photo Upscaler

Ai Image Upscaler | Face Restoration | Image Enhancer

reacted to AlexBodner's post with 👀 about 2 hours ago

Post

🚀🤖𝐃𝐨 𝐀𝐧𝐝𝐫𝐨𝐢𝐝𝐬 𝐃𝐫𝐞𝐚𝐦 𝐨𝐟 𝐄𝐥𝐞𝐜𝐭𝐫𝐢𝐜 𝐌𝐚𝐫𝐢𝐨𝐬?

Discover how we replaced the classic game engine with DIAMOND, a Neural Network that predicts every frame based on actions, noise, and past states. From training on human and RL gameplay to generating surreal hallucinations, this project shows the potential of diffusion models in creating amazing simulations. 🎮

🧵 Dive into the full story in our Twitter thread:
👉 https://x.com/AlexBodner_/status/1871566560512643567
🌟 Don’t forget to follow and leave a star for more groundbreaking AI projects!

reacted to hba123's post with 🚀 about 2 hours ago

Post

190

Blindly applying algorithms without understanding the math behind them is not a good idea frmpv. So, I am on a quest to fix this!

I wrote my first hugging face article on how you would derive closed-form solutions for KL-regularised reinforcement learning problems - what is used for DPO.

Check it out: https://huggingface.co/blog/hba123/derivingdpo