arXiv (All)
open access
Next Token or Vector? Learning How Far to Decode
Standard autoregressive decoding advances one token at a time, even when several upcoming tokens can be predicted together. We propose CADENCE (Context-Adaptive DEcoding), a generation method that learns both what to draft and how far to draft. Gaussian prediction heads represent future spans as con
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
- To Copy or Not to Copy: Controlling Speculative Decoding via Intrinsic Model Signals#1033956
- HALO: Enhancing Time Series Generation via Hyperspherical Latents and Masked AutoregRessive Modeling#1131662
- AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters#1257979
- Reducing the Output-Mode Gap in Speech Language Models via Joint-Output On-Policy Distillation#1109343
- ChronoSSM: Training for Temporally Aware Representations in Autoregressive State Space Models#444599
Record · ID 1386757
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