Muninn accelerates diffusion trajectory planners up to 4.6x by spending an uncertainty budget to decide when to cache denoiser outputs, preserving performance and certifying bounded deviation from full computation.
DKV-Cache: The cache for diffusion language models
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
years
2026 9verdicts
UNVERDICTED 9representative citing papers
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.
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.
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.
CDLM trains denoisers to be path-invariant across stochastic posterior bridges in discrete diffusion, unifying prior methods and achieving new SOTA few-step text generation performance.
Stability-Weighted Decoding improves diffusion LLM accuracy by modulating token scores with temporal stability from KL divergence between prediction steps.
DualDiffusion combines a lightweight drafter using approximations with a full verifier to reduce generation steps in masked diffusion models while keeping accuracy on MMLU and GSM8K.
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
-
Muninn: Your Trajectory Diffusion Model But Faster
Muninn accelerates diffusion trajectory planners up to 4.6x by spending an uncertainty budget to decide when to cache denoiser outputs, preserving performance and certifying bounded deviation from full computation.
-
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.
-
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.
-
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.
-
Consistent Diffusion Language Models
CDLM trains denoisers to be path-invariant across stochastic posterior bridges in discrete diffusion, unifying prior methods and achieving new SOTA few-step text generation performance.
-
Stability-Weighted Decoding for Diffusion Language Models
Stability-Weighted Decoding improves diffusion LLM accuracy by modulating token scores with temporal stability from KL divergence between prediction steps.
-
DualDiffusion: A Speculative Decoding Strategy for Masked Diffusion Models
DualDiffusion combines a lightweight drafter using approximations with a full verifier to reduce generation steps in masked diffusion models while keeping accuracy on MMLU and GSM8K.
-
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.