Marco Lopez — ML Engineer
NLP and applied machine learning. Current work: controllable summarization (salient-information extraction + LLM steering), efficient local inference on Apple Silicon (MLX), gesture recognition from skeletal time series.
- GitHub: LookUpMark
- Site: lookupmark.github.io
Featured work:
- SM-SIP — salient-information extractors for LLM-steered summarization (English + Italian, Longformer-based)
- Ornith-1.5 · MLX Quantizations — 4/6/8-bit MTP quants for Apple Silicon (oMLX)
- DYLEM-GRID — dynamic hand-gesture dataset (Leap Motion, 400 recordings)