Vision-Language Models Courses and Certifications

NPTEL-NOC IITM

Vision Language Models: Introduction and History

Explore the introduction and historical development of Vision Language Models in this concise NPTEL lecture.

• YouTube
• 15 minutes
• Self-Paced
• Free Video

Data Science Conference

Vision-Language Models for Fraud Detection

Explore how vision-language models can consolidate multiple fraud detection systems into a single unified solution, addressing growing complexities in ID document fraud attacks while improving efficiency and effectiveness.

• YouTube
• 23 minutes
• Self-Paced
• Free Video

Roboflow

Brand Analysis at Scale with Vision Language Models

Discover how vision language models transform social media images into structured brand insights for advertising strategies using Roboflow Workflows and prompt engineering techniques.

• YouTube
• 13 minutes
• Self-Paced
• Free Video

NPTEL-NOC IITM

Bias in Vision-Language Models

Explore bias issues in Vision-Language Models, examining how these AI systems can perpetuate unfair representations and learning mitigation strategies for more equitable outcomes.

• YouTube
• 26 minutes
• Self-Paced
• Free Video

Qdrant - Vector Database & Search Engine

Vision-Language Models - A New Architecture for Embedding Models

Explore Vision-Language Models as embedding architectures, covering VLM training insights, dense/multi-vector retrieval, image resolution, modality gaps, and quantization trade-offs.

• YouTube
• 19 minutes
• Self-Paced
• Free Video

Recursive Reasoning with LLMs and VLMs

Explore the ThReaD framework for enhancing large language models' reasoning capabilities through recursive task decomposition, with applications for both text and video processing.

• YouTube
• 14 minutes
• Self-Paced
• Free Video

PyCon US

Transformando Gafas en Asistentes Inteligentes: Open Source Vision Language Models

Aprende a convertir gafas comunes en asistentes inteligentes económicos utilizando Vision Language Models de código abierto. Descubre su arquitectura, crea prototipos funcionales y optimiza estos sistemas para funcionar con recursos limitados.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

AI Engineer

Moondream - How Does a Tiny Vision Model Slap So Hard?

Discover how to build a tiny open-source vision language model that outperforms models 4x its size, competing with Meta, Google, and OpenAI through innovative efficiency techniques.

• YouTube
• 19 minutes
• Self-Paced
• Free Video

Sam Witteveen

Mastering Google's PaliGemma VLM: Tips and Tricks for Success and Fine-Tuning

Explore Google's PaliGemma VLM: Learn implementation, fine-tuning techniques, and practical applications. Gain insights into model sizes, checkpoints, and datasets for enhanced visual language processing.

• YouTube
• 21 minutes
• Self-Paced
• Free Video

Discover AI

Fine-tuning SmolVLM Vision Language Model with QLoRA on Consumer GPU

Master fine-tuning techniques for SmolVLM vision language model using QLoRA optimization on consumer GPUs, with complete Python implementation and Jupyter notebooks for hands-on practice.

• YouTube
• 17 minutes
• Self-Paced
• Free Video

Roboflow

Gemini 2.5 Pro and Qwen 2.5 VL for Object Detection - Benchmarking LLMs for Vision Tasks with RF100-VL

Explore how vision-language models perform on object detection tasks through RF100-VL benchmark testing, comparing Gemini 2.5 Pro, Qwen 2.5 VL, and other VLMs with detailed evaluation methods and results.

• YouTube
• 41 minutes
• Self-Paced
• Free Video

Roboflow

How to Use Qwen 2.5 VL - Reading Nutrition Labels and Image Comprehension

Explore Qwen 2.5 VL's capabilities in building vision applications, from scanning nutrition labels to comprehending complex scenes and images through practical demonstrations.

• YouTube
• 33 minutes
• Self-Paced
• Free Video

sentdex

A Bigger Brain for the Unitree G1 - Dev with G1 Humanoid Part 4

Enhance your knowledge of integrating vision language models into the Unitree G1 humanoid robot for advanced AI capabilities and cognitive processing.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

Discover AI

How to Transform Vision Tokens to a Language Vector Space - Exploring Vision Language Model Failure Modes

Explore failure modes in Vision Language Models, focusing on connector modules between vision and text embeddings and their information loss patterns.

• YouTube
• 18 minutes
• Self-Paced
• Free Video

Discover AI

New NVIDIA MASTERS Distillation - Local 3B Vision AI

Discover NVIDIA's breakthrough MASTERS protocol that solves the capacity gap problem in model distillation by dynamically adjusting teacher complexity to match student learning capacity.

• YouTube
• 15 minutes
• Self-Paced
• Free Video