A family of System One-style models fine-tuned from Qwen3.5, designed for one-pass typed decisions with calibrated probabilities.
Mark Marosi
Mapika
AI & ML interests
NLP, Drug Discovery
Recent Activity
submitted a paper 2 days ago
General progress substitutes for specific training data in language models authored a paper 2 days ago
New upper and lower bounds on covering codes K_q(n,R) for alphabets of size 5 <= q <= 21 authored a paper 2 days ago
General progress substitutes for specific training data in language models