arXiv (All)
open access
Where Draft Trees Lose Target Mass: Exit-Guided Speculative Decoding
Tree-based speculative decoding verifies multiple draft continuations in one target-model pass, but finite trees built from draft scores face a fundamental draft-target mismatch. We ask whether better exact verification can increase acceptance on a fixed tree and how target feedback can improve the
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
- Rank-Aware Speculative Sampling for Diffusion Draft Trees#1186565
- Extremely randomized trees#7004
- SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models#16586
- Exact Feedback Is Not Control: Evaluating Text-based Closed-Loop Revision in LLMs#1064694
- Diversifying Long Prompt Image Generation through Structured Prompt Embedding Space Sampling#924480
Record · ID 1249030
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