The paper introduces Uni-E, a unified energy for DLMs that accounts for model capacity, dependency and invariance, can be computed exactly, and corrects distribution shifts from dependency and invariance.
DAWN: dependency-aware fast inference for diffusion LLMs.CoRR, abs/2602.06953
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Continuous language diffusion works by entering high-margin decoder basins where frozen T5 embeddings recover 93-96% of native decisions and linear readouts reach 97.9% agreement, implying models should be evaluated as representation-decoder systems.
DepCap accelerates diffusion LM inference up to 5.63x by using last-block influence for adaptive block boundaries and conflict-free token selection for parallel decoding, with negligible quality loss.
AXON is a training-free module that selects supportive anchor tokens using attention, uncertainty, and confidence to improve the quality-latency trade-off in parallel decoding for diffusion language models.
citing papers explorer
-
Unified Energy for Invariant and Independent Decoding in Diffusion Language Models
The paper introduces Uni-E, a unified energy for DLMs that accounts for model capacity, dependency and invariance, can be computed exactly, and corrects distribution shifts from dependency and invariance.
-
Continuous Language Diffusion as a Decoder-Interface Problem
Continuous language diffusion works by entering high-margin decoder basins where frozen T5 embeddings recover 93-96% of native decisions and linear readouts reach 97.9% agreement, implying models should be evaluated as representation-decoder systems.
-
DepCap: Adaptive Block-Wise Parallel Decoding for Efficient Diffusion LM Inference
DepCap accelerates diffusion LM inference up to 5.63x by using last-block influence for adaptive block boundaries and conflict-free token selection for parallel decoding, with negligible quality loss.
-
Supportive Token Revealing for Fast Diffusion Language Model Decoding
AXON is a training-free module that selects supportive anchor tokens using attention, uncertainty, and confidence to improve the quality-latency trade-off in parallel decoding for diffusion language models.