PSD is a training-free framework that jointly optimizes spatial unmasking and temporal speculative decoding in diffusion LLMs to reach up to 5.5x tokens per forward pass while preserving accuracy comparable to greedy decoding.
Accelerating diffusion llm inference via local determinism propagation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CL 3years
2026 3representative citing papers
Introduces TSPD with a trajectory-feature controller and training-free CE to reduce denoising steps in dLLMs while aiming to preserve quality.
citing papers explorer
-
PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding
PSD is a training-free framework that jointly optimizes spatial unmasking and temporal speculative decoding in diffusion LLMs to reach up to 5.5x tokens per forward pass while preserving accuracy comparable to greedy decoding.
-
Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence Extrapolation
Introduces TSPD with a trajectory-feature controller and training-free CE to reduce denoising steps in dLLMs while aiming to preserve quality.
- $R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction