Hugging Face's logo
Juan Carlos Piñeros's picture
76 7 73

Juan Carlos Piñeros

juancopi81
TuringRM's profile picture esselte974's profile picture clem's profile picture
·
https://www.komposair.com/

AI & ML interests

Music and AI

Recent Activity

reacted to Kseniase's post with ❤️ 1 day ago
13 New types of LoRA LoRA (Low-Rank Adaptation) is a popular lightweight method for fine-tuning AI models. It doesn't update the full model, it adds small trainable components, low-rank matrices, while keeping the original weights frozen. Only these adapters are trained. Recently, many interesting new LoRA variations came out, so it’s a great time to take a look at these 13 clever approaches: 1. T-LoRA → https://huggingface.co/papers/2507.05964 A timestep-dependent LoRA method for adapting diffusion models with a single image. It dynamically adjusts updates and uses orthogonal initialization to reduce overlap, achieving better fidelity–alignment balance than standard LoRA 2. SingLoRA → https://huggingface.co/papers/2507.05566 Simplifies LoRA by using only one small matrix instead of usual two, and multiplying it by its own transpose (like A × Aᵀ). It uses half the parameters of LoRA and avoids scale mismatch between different matrices 3. LiON-LoRA → https://huggingface.co/papers/2507.05678 Improves control and precision in video diffusion models when training data is limited. It builds on LoRA, adding 3 key principles: linear scalability, orthogonality, and norm consistency. A controllable token and modified self-attention enables smooth adjustment of motion 4. LoRA-Mixer → https://huggingface.co/papers/2507.00029 Combines LoRA and mixture-of-experts (MoE) to adapt LLMs for multiple tasks. It dynamically routes task-specific LoRA experts into linear projections of attention modules, supporting both joint training and frozen expert reuse 5. QR-LoRA → https://huggingface.co/papers/2507.04599 Separates content and style when combining multiple LoRA adapters. It implements QR decomposition to structure parameter updates, where the orthogonal Q matrix reduces interference between features, and the R matrix captures specific transformations Read further in the comments 👇 If you like it, also subscribe to the Turing Post: https://www.turingpost.com/subscribe
commented on an article 8 days ago
Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders
upvoted an article 8 days ago
Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders
View all activity

Organizations

DLAI - Chatbot's profile picture Gradio-Blocks-Party's profile picture JAX SAM ControlNet's profile picture Keras Dreambooth Event's profile picture Whispering GPT's profile picture Musika's profile picture Blog-explorers's profile picture 8Beats Demos's profile picture SketchPro Technologies, Inc.'s profile picture Ideas from Juan and Juan's profile picture BeatsOn's profile picture Hugging Face Discord Community's profile picture Hugging Face MCP Course's profile picture