Samuel Lima Braz's picture

Samuel Lima Braz PRO

samuellimabraz

·

AI & ML interests

None yet

Recent Activity

liked a Space about 11 hours ago

samuellimabraz/cv-hangout

posted an update 3 days ago

I recently had the opportunity to present at a Computer Vision Hangout, sharing my journey from autonomous drone competition to fine-tuning Vision-Language Models. I built an interactive presentation app! Here's a glimpse of the topics: 🚁 Black Bee Drones: My first steps into CV with Latin America's first autonomous drone team. Covering classical CV techniques (filtering, edge detection), the IMAV 2023 mission (ArUco detection, line following with PID control), and links to demos for OpenCV basics and PID simulation. 🤖 Asimo Foundation: Using MediaPipe for gesture control of a robotic arm in an educational project. ☕ CafeDL: Building a small Deep Learning framework from scratch in Java (inspired by Keras, using ND4J) and training a CNN for a QuickDraw-like app. 🏢 Tech4Humans: Real-world applications, including open-source signature detection and efficient fine-tuning of VLMs for document extraction. Check out the interactive demos (also embedded in the main app): 1️⃣ CV Hangout App: The main presentation app showcasing my journey. https://huggingface.co/spaces/samuellimabraz/cv-hangout 2️⃣ OpenCV GUI: Real-time demo of CV techniques (filters, color filtering, ArUco) & AI models. https://huggingface.co/spaces/samuellimabraz/opencv-gui 3️⃣ Line Follow PID: Simulation of a PID controller for drone line-following. https://huggingface.co/spaces/samuellimabraz/line-follow-pid I hope these resources are helpful to someone on their CV learning journey!

updated a model 3 days ago

samuellimabraz/granite-3.3-2b-instruct-Q4_K_M-GGUF

View all activity

Organizations

samuellimabraz's activity

upvoted a paper 12 days ago

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published 13 days ago • 163

upvoted a collection 20 days ago

Portuguese LLM Leaderboard best models ❤️‍🔥

A daily uploaded list of models with best evaluations on the PT-LLM leaderboard: • 17 items • Updated 23 minutes ago • 30

upvoted a collection 29 days ago

H2OVL Mississippi

H2O Multimodal models • 9 items • Updated Feb 20 • 7

upvoted an article 29 days ago

Article

π0 and π0-FAST: Vision-Language-Action Models for General Robot Control

Feb 4

• 143

upvoted a paper about 1 month ago

GuardReasoner: Towards Reasoning-based LLM Safeguards

Paper • 2501.18492 • Published Jan 30 • 87

upvoted 2 articles 2 months ago

Article

Vision Language Models Explained

Apr 11, 2024

• 311

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.22k

upvoted a collection 3 months ago

ViTucano-v1

ViTucano is our first attempt at creating a vision assistant natively pretrained in Portuguese. ViTucano is built on top of the Tucano series. • 5 items • Updated 12 days ago • 1