AI RESEARCH
P-Guide: Parameter-Efficient Prior Steering for Single-Pass CFG Inference
arXiv CS.AI
•
ArXi:2605.06124v1 Announce Type: new Classifier-Free Guidance (CFG) is essential for high-fidelity conditional generation in flow matching, yet it imposes significant computational overhead by requiring dual forward passes at each sampling step. In this work, we address this bottleneck by