Deep Learning | Reinforcement Learning | Diffusion Modeling
Undergraduate student passionate about advancing generative AI through the intersection of reinforcement learning and diffusion models. I'm also interested in how representation learning can be improved through intelligent neural architecture design.
My interest includes but is not limited at:
- Diffusion Models: Interested in this architecture recently due to its inspiration from physics, specifically thermodynamics.
- Reinforcement Learning: Exploring exploration-exploitation trade-off and designing more approaches to leverage experience better for decision-making.
- Representation Learning: Designing novel architectures with advanced learning capabilities for high-dimensional data distributions.
Python, C++, German (Duolingo)
- Core: PyTorch, TensorFlow, transformers
- Specialization: diffusers, Ray RLlib, Stable Baselines3
- Mathematics and MlOps: NumPy, SciPy, Pandas, Scikit-learn, wandb
- deep-ml.com: Solving daily quests to avoid corruption from vibe coding
- German Language: Duolingo, learning basic vocabulary
- Diffusion modeling: How diffusion works, actually?
- Deep reinforcement learning: Reference Reinforcement Learning: An Introduction by Sutton & Barto
I love discussing deep learning stuff and its mysteries:
| Platform | URL |
|---|---|
| 🌐 Website | dzungphieuluuky |
| Work Email | |
| Dung Pham |