arXiv (All)
open access
JuDi: Revisiting Judge Decoding from First Principles via Training-Free Distributional Divergence
Judge Decoding accelerates LLM inference by relaxing the strict verification of Speculative Decoding, yet it typically relies on expensive and noisy supervision. In this work, we revisit this paradigm from first principles, revealing that the ``criticality'' scores learned via costly supervision are
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
- Verification-Aware Training for Speculative Decoding#799360
- Verification-Aware Training for Speculative Decoding#797937
- Revisiting Lossy Verification in Speculative Decoding: Mechanisms, Trade-offs, and Failure Modes#927402
- Less Experts, Faster Decoding: Cost-Aware Speculative Decoding for Mixture-of-Experts#366224
- Uncheatable Eval: Dynamic Compression-Based Evaluation of Language Models#1064054
Record · ID 1117293
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