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.
With the continual increase in model parameters, researchers have discovered emergent phenomena in LLMs, leading to new breakthroughs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.