Fabien Herry's picture

1 2

Fabien Herry

Gahnos

·

AI & ML interests

Currently learning to become an IA Dev

Recent Activity

replied to etemiz's post 1 day ago

According to the paper below, when you fine tune a model with harmful code, it turns evil in other areas. https://arxiv.org/abs/2502.17424 This may be good news because now turning a model to be beneficial might be easier: https://x.com/ESYudkowsky/status/1894453376215388644 Does this mean evil and good are a single direction just like censorship is a single direction? So in theory one can make a model good doing an abliteration like operation?

reacted to JunhaoZhuang's post with ❤️ 2 days ago

We are excited to announce the release of our paper, "Cobra: Efficient Line Art COlorization with BRoAder References," along with the official code! Cobra is a novel efficient long-context fine-grained ID preservation framework for line art colorization, achieving high precision, efficiency, and flexible usability for comic colorization. By effectively integrating extensive contextual references, it transforms black-and-white line art into vibrant illustrations. We invite you to explore Cobra and share your feedback! You can access the paper and code via the following links: [PDF](https://arxiv.org/abs/2504.12240) and [Project page](https://zhuang2002.github.io/Cobra/). We eagerly anticipate your engagement and support! Thank you for your interest!

View all activity

Organizations

Gahnos's activity

liked a model 4 months ago

HuggingFaceTB/SmolVLM-Instruct

Image-Text-to-Text • Updated 16 days ago • 85.7k • 428

liked a model 5 months ago

nvidia/Hymba-1.5B-Instruct

Text Generation • Updated Jan 2 • 3.41k • 228