Introduces TSPD with a trajectory-feature controller and training-free CE to reduce denoising steps in dLLMs while aiming to preserve quality.
Animesh Jain, Shunting Zhang, Edward Yang, et al
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Saber improves both speed and accuracy of diffusion language models on code generation by dynamically adjusting unmasking steps and reverting low-confidence tokens via backtracking.
citing papers explorer
-
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.
-
Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model
Saber improves both speed and accuracy of diffusion language models on code generation by dynamically adjusting unmasking steps and reverting low-confidence tokens via backtracking.
- CreditDecoding: Accelerating Parallel Decoding in Diffusion Large Language Models with Trace Credit