Label-free representation learning and decomposition for linear programs on bipartite graphs, using BiJEPA self-supervised pretraining and a differentiable KKT finetuning objective.
-
Updated
Apr 14, 2026 - Jupyter Notebook
Label-free representation learning and decomposition for linear programs on bipartite graphs, using BiJEPA self-supervised pretraining and a differentiable KKT finetuning objective.
📚 Explore a curated collection of research on Label-Free Reinforcement Learning with Verifiable Rewards for enhancing Large Language Models.
Add a description, image, and links to the label-free-learning topic page so that developers can more easily learn about it.
To associate your repository with the label-free-learning topic, visit your repo's landing page and select "manage topics."