Predict-then-Diffuse predicts response length for diffusion LLMs before inference, cutting FLOPs with a data-driven safety buffer while preserving output quality.
Ground every sentence: Improving retrieval-augmented LLMs with interleaved reference-claim generation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Predict-then-Diffuse: Adaptive Response Length for Compute-Budgeted Inference in Diffusion LLMs
Predict-then-Diffuse predicts response length for diffusion LLMs before inference, cutting FLOPs with a data-driven safety buffer while preserving output quality.