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.
-
natolambert/rlhf-book
Wrote sections, derivations, and figures, restyled the site, and contributed the foundations of the code library.
-
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.