When AI Sees and Speaks — The Rise of Vision-Language Models
Intermediate GenAI Systems 22 min
A high level view on how modern vision-language models connect pixels and prose, from CLIP and BLIP to Flamingo, MiniGPT-4, Kosmos, and Gemini.
← Back to Home
GenAI & LLM Systems
The System Design Round
Production systems for generative AI—scaling, optimization, and serving large language models at scale.
Learning Path
- → Start with **Transformers** to understand the architecture
- → Move to **Diffusion Models** for image and video generation
- → Explore **Vision-Language Models** for multimodal systems
- → Finish with **Video Diffusion** for temporal generation
All Posts in This Track
8 articles covering genai systems
-
-
Diffusion — From Molecules to Machines
Intermediate GenAI Systems 28 minA clear introduction to diffusion and guided diffusion — how a simple physical process became a foundation for modern generative AI, from Stable Diffusion to robotics and protein design.
-
Image Diffusion Models: From U-Net to DiT
Advanced GenAI Systems 15 minThe evolution of image diffusion models from U-Net architectures to Diffusion Transformers (DiT). Covers latent diffusion, the DiT revolution, and the complete image generation pipeline.
-
Modern Video Models & Motion: Sora, Veo 3, Open-Sora, and Motion Modeling
Advanced GenAI Systems 22 minDeep dive into state-of-the-art video generation models: Sora, Veo 3, and Open-Sora. Plus motion modeling techniques using optical flow, geometry, and diffusion fields.
-
Pre-Training & Post-Training: Building and Aligning Video Diffusion Models
Advanced GenAI Systems 20 minHow video diffusion models are built through pre-training and aligned through post-training. Covers the billion-frame training problem, DPO, RLHF, and the complete training pipeline.
-
Sampling & Guidance: The Dialects of Noise
Advanced GenAI Systems 18 minHow to accelerate diffusion sampling and control output quality. Covers DDIM, DPM-Solver, Classifier-Free Guidance (CFG), negative prompting, and inference optimization techniques.
-
Video Diffusion Fundamentals: The Temporal Challenge
Advanced GenAI Systems 18 minWhy video is harder than images, the DiT revolution for video, and how diffusion models learn temporal consistency. Covers V-DiT, AsymmDiT, and the mathematical foundations of video generation.
-
Physics-Aware Video Diffusion Models: From Intuition to Research Frontier
Advanced GenAI Systems 35 minA deep dive into physics-aware video diffusion models: how researchers inject physical constraints into generative models, the three leading technical approaches, and their practical impact on robotics and scientific simulation.