Artificial Intelligence #diffusion llms#speculative decoding
New ASRD Method Boosts Diffusion LLM Accuracy by 6.4% and Inference Speed by 7.2×
Researchers propose ASRD (Anchor Supervised Revocable Decoding), a training-free framework that improves diffusion LLM accuracy by up to 6.4% and accelerates inference throughput by up to 7.2×. ASRD addresses error propagation and local error reinforcement in revocable decoding by introducing anchor tokens and two complementary mechanisms.
Jun 16, 2026 2 sources