SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models
Paper • 2610.04875 • Published • 7
None defined yet.
SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models
TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization