ePOWERAI
CoursesPhysical AI

Robotics

Physical AI & Vision-Language Models

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

14 lessons · runs in your browser · no account

Your progress00 / 14 · 0%

Course contents

  1. W01Week 1: Modern Vision Backbones
  2. W02Week 2: Self-Supervised Representation Learning for Vision
  3. W03Week 3: Contrastive Vision–Language Learning (CLIP)
  4. W04Week 4: Beyond CLIP — Captioning and Grounding
  5. W05Week 5: BLIP, BLIP-2, and Related Models
  6. W06Week 6: LLaVA and Multimodal Instruction Tuning
  7. W07Week 7: Alternative VLM Architectures
  8. W08Week 8: Fine-Tuning and Parameter-Efficient Methods
  9. W09Week 9: Evaluation and Robustness
  10. W10Week 10: ControlNet and Controlled Generation
  11. W11Week 11: Multimodal Agents and Tool Use
  12. W12Week 12: Vision-Language Models for Robotics
  13. W13Week 13: Bias, Fairness, and Safety in VLMs
  14. W14Week 14: Vision-Language Capstone