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.
Discrete copula diffusion
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Diffusion and flow processes forget dependencies to define valid copulas then learn to remember them for density estimation and sampling, outperforming prior copula methods on complex datasets.
Fast-dLLM adds reusable KV cache blocks and selective parallel decoding to diffusion LLMs, closing most of the speed gap with autoregressive models without retraining.
Fast-dLLM++ generalizes Fast-dLLM decoding to heterogeneous confidence profiles via Fréchet profile selection, delivering up to 37% throughput gains on GSM8K, MATH, HumanEval, and MBPP with LLaDA-8B.
VADD augments masked diffusion models with an auxiliary recognition model and variational inference to implicitly model inter-dimensional correlations, yielding higher-quality samples than standard MDMs at low denoising step counts on toy data, images, and text.
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.
-
Diffusion and Flow-based Copulas: Forgetting and Remembering Dependencies
Diffusion and flow processes forget dependencies to define valid copulas then learn to remember them for density estimation and sampling, outperforming prior copula methods on complex datasets.
-
Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations Modeling
VADD augments masked diffusion models with an auxiliary recognition model and variational inference to implicitly model inter-dimensional correlations, yielding higher-quality samples than standard MDMs at low denoising step counts on toy data, images, and text.