SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models
Paper • 2610.04875 • Published • 7
佐藤 真綾
Orbit-Loom
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 8 hours ago
SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models liked a model 3 days ago
Cactus-Compute/whistle upvoted a paper 4 days ago
PluginRSI: Recursive Improvement of Agent Harnesses with Reusable PluginsOrganizations
None yet