John Graham Reynolds's picture

In a Training Loop 🔄

John Graham Reynolds PRO

MarioBarbeque

·

johngrahamreynolds

AI & ML interests

Quantum Computing, Mathematics+Code Generation, Reasoning+RL+Agentic Systems @ 🐂UT Austin and NASA JSC🚀

Organizations

upvoted a paper 4 months ago

Mitigating Catastrophic Forgetting in Mathematical Reasoning Finetuning through Mixed Training

Paper • 2512.13706 • Published Dec 5, 2025 • 1

upvoted a collection 4 months ago

Catastrophic Forgetting in Mathematical Reasoning

7 items • Updated Dec 5, 2025 • 1

upvoted a collection 6 months ago

Flan-T5 release

The Flan-T5 covers 4 checkpoints of different sizes each time. It also includes upgrades versions trained using Universal sampling • 7 items • Updated 28 days ago • 35

upvoted 3 collections over 1 year ago

Code Generation

Models and datasets relevant to training code generation models in future projects • 5 items • Updated Nov 25, 2024 • 1

Finetuning

Models to fine-tune (and datasets to ft with) in future projects • 16 items • Updated Dec 2, 2025 • 1

Mathematics

Models and datasets related to mathematics generation • 13 items • Updated Nov 24, 2024 • 1