Victor Condino

un1tz3r0

https://un1tz3r0.github.io

AI & ML interests

Emergent misalignment, safety, future security. Alignment as a natural product of good datasets; dataset building (my background is in python and web scraping.)

Recent Activity

upvoted a collection 7 days ago

🧠 Abliteration

upvoted a paper 10 days ago

Farewell to Length Extrapolation, a Training-Free Infinite Context with Finite Attention Scope

View all activity

Organizations

un1tz3r0's activity

upvoted a collection 7 days ago

🧠 Abliteration

Collection

Uncensored models using abliteration. See this article for more information: huggingface.co/blog/mlabonne/abliteration • 15 items • Updated 18 days ago • 51

upvoted a paper 10 days ago

Farewell to Length Extrapolation, a Training-Free Infinite Context with Finite Attention Scope

Paper • 2407.15176 • Published Jul 21, 2024 • 3

upvoted a paper 18 days ago

Rolling Diffusion Models

Paper • 2402.09470 • Published Feb 12, 2024 • 14

upvoted 2 papers 12 months ago

ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback

Paper • 2404.07987 • Published Apr 11, 2024 • 47

HiDiffusion: Unlocking High-Resolution Creativity and Efficiency in Low-Resolution Trained Diffusion Models

Paper • 2311.17528 • Published Nov 29, 2023 • 4

upvoted a paper about 1 year ago

Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains

Paper • 2402.05140 • Published Feb 6, 2024 • 23