eAI
Courses/Physical AI

Physical AI & Vision-Language Models

From vision backbones to embodied agents — how language and perception fuse into systems that act in the physical world.

Advanced14 weeks · 14 lessons
Your progress00 / 14 · 0%
Lessons
W01Week 1: Modern Vision BackbonesGeneralW02Week 2: Self-Supervised Representation Learning for VisionGeneralW03Week 3: Contrastive Vision–Language Learning (CLIP)GeneralW04Week 4: Beyond CLIP — Captioning and GroundingGeneralW05Week 5: BLIP, BLIP-2, and Related ModelsGeneralW06Week 6: LLaVA and Multimodal Instruction TuningGeneralW07Week 7: Alternative VLM ArchitecturesGeneralW08Week 8: Fine-Tuning and Parameter-Efficient MethodsGeneralW09Week 9: Evaluation and RobustnessGeneralW10Week 10: ControlNet and Controlled GenerationGeneralW11Week 11: Multimodal Agents and Tool UseGeneralW12Week 12: Vision-Language Models for RoboticsGeneralW13Week 13: Bias, Fairness, and Safety in VLMsGeneralW14Week 14: Vision-Language CapstoneGeneral