arXiv (All)
open access
Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models
Speculative decoding accelerates generation without changing its output, yet on vision-language models (VLMs) it has been caught in a self-defeating cycle. The drafter stays autoregressive, so it must stay small. A small drafter cannot afford the image at every step, so vision is compressed, pruned,
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
- Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models#809811
- Resource-Efficient Speculative Decoding for Long-Context LLM Serving#1117896
- xPress: Parallel Refinement for Diffusion Drafters in Speculative Decoding#424016
- Reference-Guided Machine Unlearning#1141500
- Accelerating the Mitigation of LLM Inference Nondeterminism Across GPU Architectures#1061261
Record · ID 819807
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