Accelerating Diffusion LLMs via Adaptive Parallel Decoding Paper • 2506.00413 • Published May 31 • 9 • 4
Energy-Based Transformers are Scalable Learners and Thinkers Paper • 2507.02092 • Published Jul 2 • 69 • 26
OmniDraft: A Cross-vocabulary, Online Adaptive Drafter for On-device Speculative Decoding Paper • 2507.02659 • Published Jul 3 • 16 • 2