AIBullisharXiv – CS AI · 7h ago7/10
🧠
EPIC: Efficient and Parallel Inference under CFG Constraints for Diffusion Language Models
Researchers introduce EPIC, an efficient decoding framework for diffusion language models that operate under context-free grammar constraints. The method reduces inference time by up to 67.5% compared to existing CFG-constrained approaches while preserving the parallel decoding advantage that makes diffusion models competitive with autoregressive alternatives.