PopPy: Opportunistically Exploiting Parallelism in Python Compound AI Applications Paper • 2605.18697 • Published May 18 • 1
When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models Paper • 2609.19671 • Published 8 days ago • 49
Temporal Preference Optimization for Unsupervised Retrieval Paper • 2606.17664 • Published Jun 16 • 2