hanzla/STEM_Reasoning
Viewer • Updated • 23.5k • 10 • 1
hanzlajavaid PRO
hanzla
AI & ML interests
Direct Preference Optimization, Supervised Finetuning, Stable Diffusion
Recent Activity
posted an update 4 days ago
Reinforcement learning can sometimes lead to emergent behavior through much simpler training setups compared to large scale pre-training.
I explored this idea by running a small GRPO experiment on Qwen3.5 4B, and the results were pretty exciting.
Hypothesis: improving visual mathematical reasoning may also improve the model’s ability to transcribe LaTeX from images.
I wrote a short breakdown of the experiment here:
https://hanzlajavaid.github.io/blog/grpo-experiment-exploring-emergent-properties/ updated a model 12 days ago
hanzla/Qwen3.5-4B-mathvista-GRPO published a model 12 days ago
hanzla/Qwen3.5-4B-mathvista-GRPOOrganizations
