arXiv (All)
open access
One Block Ahead: Promoting Sampler State in Diffusion Language Models
Block-diffusion language models denoise a whole block of token positions in parallel so each forward pass can emit many tokens. However, blocks are still denoised in strict sequence, a cost that within-block acceleration leaves untouched. Here, we investigate decoding blocks concurrently and propose
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
- PACE-dLLM: Elastic Block Decoding via Confidence Cliff Estimation for Diffusion Language Models#1062149
- Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models#800070
- Temporal Self-Distillation: Faster Inference in Discrete Diffusion Language Models#1109227
- Fork-dLLM: Avoiding the Flexibility Trap in Diffusion Language Models#1145026
- DP-LAC: Lightweight Adaptive Clipping for Differentially Private Federated Fine-tuning of Language Models#175131
Record · ID 1345333
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