arXiv (All)
open access
D-REAL: Acceptance-Length Optimization with Unbiased Gradients for Speculative Decoding
Speculative decoding efficiency depends on the number of consecutively accepted draft tokens, yet token-level training objectives do not directly optimize this quantity. We introduce D-REAL (Drafter Reinforcement of Expected Acceptance Length), a post-training method that directly optimizes expected
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- DEdit: Iterative Draft Editing for Speculative Decoding#1143111
- Acceptance Is Not Speed: Length Inflation in Training-Free Lossy Speculative Decoding#1388186
- ForeSpark: Joint Draft and Verification Budget Scheduling for Parallel Speculative Decoding#1616860
- Beyond the Point Mass: Acceptance-Derived Weights and Distributional Losses for Speculative Decoding#1412323
- Beyond the Point Mass: Acceptance-Derived Weights and Distributional Losses for Speculative Decoding#1394261
Record · ID 1634173
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive