hanzla/STEM_Reasoning
Viewer • Updated • 23.5k • 6 • 1
hanzlajavaid PRO
hanzla
AI & ML interests
Direct Preference Optimization, Supervised Finetuning, Stable Diffusion
Recent Activity
posted an update about 16 hours 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 9 days ago
hanzla/Qwen3.5-4B-mathvista-GRPO published a model 9 days ago
hanzla/Qwen3.5-4B-mathvista-GRPOOrganizations
