John Graham Reynolds's picture

In a Training Loop 🔄

1 7 68

John Graham Reynolds PRO

MarioBarbeque

·

johngrahamreynolds

AI & ML interests

Quantum Computing, Mathematics+Code Generation, Deep Reasoning, Deep RL 🐂UT Austin, NASA Johnson Space Center🚀

Recent Activity

authored a paper 21 days ago

Mitigating Catastrophic Forgetting in Mathematical Reasoning Finetuning through Mixed Training

upvoted a paper 21 days ago

Mitigating Catastrophic Forgetting in Mathematical Reasoning Finetuning through Mixed Training

updated a model 25 days ago

MarioBarbeque/flan-t5-base-math-only-catastrophic

View all activity

Organizations

MarioBarbeque 's datasets 10

MarioBarbeque/StringTheorySolutions

Updated Nov 5, 2025 • 13 • 1

MarioBarbeque/CyberSolve-LinAlg-1.2-correctness-benchmark

Viewer • Updated Jan 9, 2025 • 10k • 4 • 1

MarioBarbeque/CyberSolve-LinAlg-1.1-correctness-benchmark

Viewer • Updated Jan 9, 2025 • 10k • 7 • 1

MarioBarbeque/CyberSolve-DeepMind-LinAlg-1D-downsample-benchmark-v2

Viewer • Updated Dec 21, 2024 • 10k • 6 • 1

MarioBarbeque/CyberSolve-DeepMind-LinAlg-1D-downsample-benchmark

Viewer • Updated Dec 20, 2024 • 10k • 7 • 1

MarioBarbeque/FLAN-T5-DeepMind-LinAlg-1D-benchmark

Viewer • Updated Dec 18, 2024 • 10k • 7 • 1

MarioBarbeque/DeepMind-LinAlg-1D-eval

Viewer • Updated Dec 11, 2024 • 10k • 4 • 1

MarioBarbeque/DeepMind-LinAlg-1D-train

Viewer • Updated Dec 11, 2024 • 2M • 5 • 1

MarioBarbeque/hf-github-issues

Viewer • Updated Nov 4, 2024 • 4k • 16 • 1

MarioBarbeque/UCI_drug_reviews

Viewer • Updated Nov 3, 2024 • 204k • 17 • 1