Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training
Paper • 2609.07108 • Published • 23
한서연
GraniteEvan
AI & ML interests
None yet
Recent Activity
upvoted a paper about 5 hours ago
Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training liked a model about 8 hours ago
nex-agi/Nex-N2.5-Pro upvoted a paper about 8 hours ago
BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model InferenceOrganizations
None yet