LEAP detects early-converging tokens in dLLMs via future context filtering and multi-sequence superposition, reducing average denoising steps by about 30% while maintaining accuracy.
Refusion: A diffu- sion large language model with parallel autoregressive decoding.arXiv preprint arXiv:2512.13586, 2025a
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
TEAM accelerates MoE dLLMs up to 2.2x by exploiting temporal-spatial consistency in expert routing to accept more tokens with fewer activations.
citing papers explorer
-
LEAP: Unlocking dLLM Parallelism via Lookahead Early-Convergence Token Detection
LEAP detects early-converging tokens in dLLMs via future context filtering and multi-sequence superposition, reducing average denoising steps by about 30% while maintaining accuracy.
-
TEAM: Temporal-Spatial Consistency Guided Expert Activation for MoE Diffusion Language Model Acceleration
TEAM accelerates MoE dLLMs up to 2.2x by exploiting temporal-spatial consistency in expert routing to accept more tokens with fewer activations.