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 progress0 / 14 · 0%

Lessons

Week 1: Modern Vision Backbones

Week 2: Self-Supervised Representation Learning for Vision

Week 3: Contrastive Vision–Language Learning (CLIP)

Week 4: Beyond CLIP — Captioning and Grounding

Week 5: BLIP, BLIP-2, and Related Models

Week 6: LLaVA and Multimodal Instruction Tuning

Week 7: Alternative VLM Architectures

Week 8: Fine-Tuning and Parameter-Efficient Methods

Week 9: Evaluation and Robustness

Week 10: ControlNet and Controlled Generation

Week 11: Multimodal Agents and Tool Use

Week 12: Vision-Language Models for Robotics

Week 13: Bias, Fairness, and Safety in VLMs

Week 14: Vision-Language Capstone