arXiv CS
open access
Beyond the Point Mass: Acceptance-Derived Weights and Distributional Losses for Speculative Decoding
In speculative decoding, a lightweight draft model proposes tokens that the target model verifies in parallel, speeding up generation without changing the target distribution. D-PACE (Wu et al., 2026) trains such drafters with a loss that weights each position by its contribution to the expected acc
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
- Acceptance Is Not Speed: Length Inflation in Training-Free Lossy Speculative Decoding#1388186
- ReAnchor: Reusing Rejected Verifier States for Diffusion Drafting#1401695
- MineDraft: A Framework for Batch Parallel Speculative Decoding#821432
- SpecKV: Adaptive Speculative Decoding with Compression-Aware Gamma Selection#155233
- Approximate Speculative Decoding#799030
Record · ID 1394261
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