D-PACE derives per-position weights from a surrogate of expected accepted draft length to shift training focus toward currently limiting positions, yielding measured gains in wall-clock speedup and emitted length across benchmarks.
ShareGPT: GPT-4/ChatGPT conversations shared by users
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting
D-PACE derives per-position weights from a surrogate of expected accepted draft length to shift training focus toward currently limiting positions, yielding measured gains in wall-clock speedup and emitted length across benchmarks.