Zafir Stojanovski

I am an engineer at Loka, applying ML to healthcare and life sciences.
Before that, I studied Machine Learning at the University of Tübingen.
My interests span post-training, continual learning, and fair benchmarking.

Publications

Reasoning Gym: Reasoning Environments for Reinforcement Learning with Verifiable Rewards

Zafir Stojanovski*, Oliver Stanley*, Joe Sharratt*, Richard Jones*, Abdulhakeem Adefioye, Jean Kaddour, Andreas Köpf

Neural Information Processing Systems (NeurIPS) 2025 Spotlight

Momentum-based Weight Interpolation of Strong Zero-Shot Models for Continual Learning

Zafir Stojanovski*, Karsten Roth*, Zeynep Akata

INTERPOLATE Workshop, Neural Information Processing Systems (NeurIPS) 2022 Best Paper Award

Open Source

open-thought/reasoning-gym

Built procedural RL environments that can generate infinite data from diverse domains. Core Contributor
natolambert/rlhf-book

Wrote sections, restyled the site, and contributed the foundations of the code library. Core Contributor
EleutherAI/lm-evaluation-harness

Contributed the Lambada Translations, Paloma, and LegalBench datasets.
zafstojano/ml-interview-questions-and-answers

Answered Chip Huyen's ML interview questions.