TAD improves the accuracy-parallelism trade-off in diffusion LLMs via temporal-aware self-distillation that applies hard labels to soon-to-be-decoded tokens and soft supervision to future tokens.
dparallel: Learnable parallel decoding for dllms.arXiv preprint arXiv:2509.26488
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
years
2026 8verdicts
UNVERDICTED 8representative citing papers
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.
DARE reuses up to 87% of attention activations in diffusion LLMs through KV caching and output reuse, delivering 1.2x per-layer latency gains with average performance drops of 1.2-2.0%.
R²-dLLM reduces dLLM decoding steps by up to 75% via spatio-temporal redundancy reduction while keeping generation quality competitive.
ECHO is a one-step block diffusion VLM for chest X-ray reports that improves RaTE and SemScore by over 60% while delivering 8x faster inference than autoregressive baselines.
DEMASK adds a lightweight pairwise-dependency predictor to dLLMs and uses greedy selection to enable parallel unmasking whose total-variation error is provably bounded under sub-additivity.
Orthrus unifies autoregressive and diffusion views on a shared KV cache to deliver lossless parallel token generation with up to 7.8x speedup and O(1) memory overhead.
DMax enables faster parallel decoding in diffusion language models by using on-policy training to recover from errors and soft embedding interpolations for iterative revision, boosting tokens per forward pass roughly 2-3x on benchmarks while preserving accuracy.
citing papers explorer
-
TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM
TAD improves the accuracy-parallelism trade-off in diffusion LLMs via temporal-aware self-distillation that applies hard labels to soon-to-be-decoded tokens and soft supervision to future tokens.
-
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.
-
DARE: Diffusion Language Model Activation Reuse for Efficient Inference
DARE reuses up to 87% of attention activations in diffusion LLMs through KV caching and output reuse, delivering 1.2x per-layer latency gains with average performance drops of 1.2-2.0%.
-
$R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction
R²-dLLM reduces dLLM decoding steps by up to 75% via spatio-temporal redundancy reduction while keeping generation quality competitive.
-
ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion
ECHO is a one-step block diffusion VLM for chest X-ray reports that improves RaTE and SemScore by over 60% while delivering 8x faster inference than autoregressive baselines.
-
Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models
DEMASK adds a lightweight pairwise-dependency predictor to dLLMs and uses greedy selection to enable parallel unmasking whose total-variation error is provably bounded under sub-additivity.
-
Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
Orthrus unifies autoregressive and diffusion views on a shared KV cache to deliver lossless parallel token generation with up to 7.8x speedup and O(1) memory overhead.
-
DMax: Aggressive Parallel Decoding for dLLMs
DMax enables faster parallel decoding in diffusion language models by using on-policy training to recover from errors and soft embedding interpolations for iterative revision, boosting tokens per forward pass roughly 2-3x on benchmarks while preserving accuracy.