Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
SpecOPD: Branch-Parallel On-Policy Distillation for Speculative Decoding
Tianyu Liu, Jun Zhang, Wenjie Huang +12
Speculative decoding (SD) accelerates large language model inference by reducing the sequential cost of token-by-token generation. Advanced SD methods reduce proposal cost with par…
cs.AI2026
TailSieve: Partial-Rollout-Guided Tail Routing for LLM Rollouts
Tianqi Xu, Lu Lv, Haoyang Huang +15
Large-scale rollouts have become a core component of modern LLM systems, spanning reinforcement learning (RL) post-training, on-policy distillation (OPD), and sampling-heavy evalua…