Spending my time getting machines to understand the world a little better โand occasionally solve useful problems along the way.
- ๐ค VLA From Scratch โ Vision-Language-Action policy built and trained end-to-end from scratch on a single consumer GPU, with behavior cloning, DAgger-lite post-training, and a full evaluation harness.
- ๐จ Image Generation From Scratch โ Text-to-image diffusion model built end-to-end from scratch with DDPM noise scheduling, text conditioning, and a lightweight HTTP inference API.
- ๐ง LLM From Scratch โ Transformer-based language model built and trained end-to-end from scratch.
- ๐ Autonomous Driving with RL โ PPO/SAC/TD3 policy gradient agents for vehicle control in simulation.
- ๐๏ธ Stereo Visual Odometry โ Camera pose estimation from stereo imagery using classical CV techniques (research, Colorado School of Mines).
- ๐ญ Warehouse Automation โ Autonomous robot navigation and task planning for warehouse environments.
- ๐ Optical Flow Speed Estimation โ Vehicle speed estimation from dashcam footage using optical flow on comma.ai data.

