# CORA-Diff: Confidence-Oriented Residual Acceptance for Efficient Diffusion Language Model Inference

arXiv: https://arxiv.org/abs/2608.11235 · HTML: https://mlsanity.com/paper/2608.11235/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Discrete and text diffusion, one of 14 directions in Diffusion models.
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Placed in

- Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/)

## Builds on (most cited first, 24 of 24)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution](https://mlsanity.com/paper/2310.16834/) (2023)
- [Simplified and Generalized Masked Diffusion for Discrete Data](https://mlsanity.com/paper/2406.04329/) (2024)
- [A Continuous Time Framework for Discrete Denoising Models](https://mlsanity.com/paper/2205.14987/) (2022)
- [Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding](https://mlsanity.com/paper/2505.22618/) (2025)
- [Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data](https://mlsanity.com/paper/2406.03736/) (2024)
- [LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding](https://mlsanity.com/paper/2404.16710/) (2024)
- [Scaling Diffusion Language Models via Adaptation from Autoregressive Models](https://mlsanity.com/paper/2410.17891/) (2024)
- [DynaBERT: Dynamic BERT with Adaptive Width and Depth](https://mlsanity.com/paper/2004.04037/) (2020)
- [FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion](https://mlsanity.com/paper/2505.21467/) (2025)
- [dParallel: Learnable Parallel Decoding for dLLMs](https://mlsanity.com/paper/2509.26488/) (2025)
- [KLASS: KL-Guided Fast Inference in Masked Diffusion Models](https://mlsanity.com/paper/2511.05664/) (2025)
- [Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Principles](https://mlsanity.com/paper/2506.10848/) (2025)
- [WeDLM: Reconciling Diffusion Language Models with Standard Causal Attention for Fast Inference](https://mlsanity.com/paper/2512.22737/) (2025)
- [AdaBlock-dLLM: Semantic-Aware Diffusion LLM Inference via Adaptive Block Size](https://mlsanity.com/paper/2509.26432/) (2025)
- [Learning to Parallel: Accelerating Diffusion Large Language Models via Learnable Parallel Decoding](https://mlsanity.com/paper/2509.25188/) (2025)
- [DMax: Aggressive Parallel Decoding for dLLMs](https://mlsanity.com/paper/2604.08302/) (2026)
- [DAPD: Dependency-Aware Parallel Decoding via Attention for Diffusion LLMs](https://mlsanity.com/paper/2603.12996/) (2026)
- [DAWN: Dependency-Aware Fast Inference for Diffusion LLMs](https://mlsanity.com/paper/2602.06953/) (2026)
- [FOCUS: DLLMs Know How to Tame Their Compute Bound](https://mlsanity.com/paper/2601.23278/) (2026)
- [TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload](https://mlsanity.com/paper/2605.20179/) (2026)
- [Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models](https://mlsanity.com/paper/2606.10829/) (2026)
- [Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence Extrapolation](https://mlsanity.com/paper/2605.30753/) (2026)

## Abstract (arXiv)

Diffusion language models (DLMs) update many tokens in parallel, yet practical decoders often use a fixed denoising horizon. Many predictions stabilize early, but blockwise decoding continues until all positions are resolved, causing repeated dense forward passes. Existing accelerators often rely on learned filters, modified scores, dependency models, or cache-specific mechanisms. We ask whether native trajectory signals can identify residual positions likely to match the deterministic dense endpoint. We propose CORA-Diff, a training-free method that preserves the original transfer rule and applies confidence-and-persistence gating only to positions that rule leaves unresolved. Accepted tokens remain visible as context, and the block terminates once all positions are resolved. This requires no backbone change, learned acceptance model, or logit modification. Our theory explains why high-confidence, persistent predictions are more likely to match the fixed-horizon dense endpoint, and paired post-intervention trajectories provide direct empirical support. We select one operating point on a separate GSM8K calibration subset and freeze it for all evaluations. Under a matched Learn2PD-style LLaDA protocol, CORA-Diff has the lowest measured runtime in all eight task-length settings. Task scores match or exceed dense decoding in five settings, and the largest observed drop is 1.22 points. Its incremental speedups over EOS-aware dense decoding are 2.70x and 3.32x on GSM8K and HumanEval. It also reaches 13.14x under the fixed-horizon 1024/1024 mechanism-isolation protocol and transfers to Dream without retuning at 3.18x-3.53x. These results show that native confidence and persistence enable reliable residual acceptance, reducing repeated denoising computation while preserving task quality.