Welcome! I'm excited to start sharing my thoughts, research notes, and practical insights in this space.
This blog will primarily cover:
- Efficient deep learning and compression methods — pruning, quantization, distillation, and structured sparsity techniques that make neural networks smaller and faster without sacrificing performance.
- Practical lessons from industry ML deployment — real-world challenges and solutions from deploying models at companies like Zeiss, BMW, Huawei, and Intel.
- Research notes on LLM optimization and sparsity — deep dives into recent papers, including my own work on Bayesian sparsification published at NeurIPS.
I'll publish short, practical write-ups and research-oriented posts regularly. The goal is to bridge the gap between academic research and practical engineering — making efficient AI more accessible to everyone.
"The best model is not the biggest one — it's the one that solves the problem within your constraints."
Stay tuned for the first technical post. In the meantime, feel free to check out my projects or publications, and subscribe via RSS to get new posts as they land.
— Rayen