Jacob Mapel
Principal ML engineer and AI development leader at a major telecom company. I work on applied AI systems at the enterprise and run a small home lab for research on the side.
This site collects the longer-form things I write: research notes, project write-ups, and the occasional opinion piece. Everything here is my own work; nothing represents my employer.
Recent research
- Teaching an open model to say how sure it is We turned open Qwen models into typed decision models that return calibrated probabilities for yes/no, pick-one and rating questions in one forward pass, with no generated text. One LoRA epoch makes every model from 2B up accurate and well calibrated on familiar tasks. Calibration on task types it never saw is where size matters, and where the work is still unfinished.
- A JEPA world model that learns Mario by playing itself We trained a self-supervised JEPA world model on NES Super Mario Bros and ran a closed-loop flywheel — collect, retrain the world model, train a policy in imagination, repeat — for fifteen iterations. The headline iter looked like a breakthrough; a five-seed re-run revealed it was a draw from a much wider distribution than we'd been measuring. This is the project so far, and the redesign that comes next.
- Sport-transfer SSL — what scaling up actually changed After the first writeup, three follow-up questions kept nagging. With more compute we tested them all — and one downstream task we hadn't measured before flipped the story.
- Sport-transfer self-supervised learning — what we learned A one-week investigation into whether self-supervised pretraining on in-domain video improves transfer to new sports tasks — and what those experiments taught us about how to actually measure SSL progress.