- Latent Space for Chemometrics: What Spectra Are Really Telling YouPCA, PLS, and latent variables for spectral data — how to compress thousands of collinear wavelengths into a handful of meaningful directions.
- LLM Inference on a Budget: What Actually Moves the NeedleKV-cache, quantization, batching, and speculative decoding — the practitioner shortlist for serving LLMs fast without a GPU cluster.
- Faster Vision Inference: From Detector to Deployed PipelineONNX, quantization, resolution trade-offs, and tracking tricks — how I squeeze real-time perception out of Jetson and CPU edge boxes.
- Training Detection Models That Survive the FieldData curation, augmentation for ugly conditions, and evaluation beyond mAP — a field manual for training detectors that hold up on deployment.