Related papers: Learning Flexible Forward Trajectories for Masked …

Masked Diffusion Models (MDMs) have emerged as a promising approach for generative modeling in discrete spaces. By generating sequences in any order and allowing for parallel decoding, they enable fast inference and strong performance on…

Anomaly detection aims to identify samples that deviate from the nominal data distribution and is central to many safety-critical applications. However, developing effective anomaly detection methods for categorical, mixed-type, and…

Large Language Models (LLMs) have significantly advanced molecular discovery, but existing multimodal molecular architectures fundamentally rely on autoregressive (AR) backbones. This strict left-to-right inductive bias is sub-optimal for…

Pre-trained diffusion models have emerged as powerful generative priors for both unconditional and conditional sample generation, yet their outputs often deviate from the characteristics of user-specific target data. Such mismatches are…

Speaker verification systems are increasingly deployed in security-sensitive applications but remain highly vulnerable to adversarial perturbations. In this work, we propose the Mask Diffusion Detector (MDD), a novel adversarial detection…

While Diffusion Language Models (DLMs) are theoretically well-suited for iterative refinement due to their non-causal structure, they often fail to reliably revise incorrect tokens in practice. The key challenge lies in the model's…

Part of the success of diffusion models stems from their ability to perform iterative refinement, i.e., repeatedly correcting outputs during generation. However, modern masked discrete diffusion lacks this capability: when a token is…

Recently proposed generative models for discrete data, such as Masked Diffusion Models (MDMs), exploit conditional independence approximations to reduce the computational cost of popular Auto-Regressive Models (ARMs), at the price of some…

Diffusion-based generative models (DBGMs) perturb data to a target noise distribution and reverse this process to generate samples. The choice of noising process, or inference diffusion process, affects both likelihoods and sample quality.…

Scientific machine learning (SciML) increasingly requires models that capture multimodal conditional uncertainty arising from ill-posed inverse problems, multistability, and chaotic dynamics. While recent work has favored highly expressive…

Federated learning provides a privacy-preserving manner to collaboratively train models on data distributed over multiple local clients via the coordination of a global server. In this paper, we focus on label distribution skew in federated…

Three-dimensional molecular generators based on diffusion models can now reach near-crystallographic accuracy, yet they remain fragmented across tasks. SMILES-only inputs, two-stage pretrain-finetune pipelines, and one-task-one-model…

Inverse protein folding generates valid amino acid sequences that can fold into a desired protein structure, with recent deep-learning advances showing strong potential and competitive performance. However, challenges remain, such as…

Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…

Discrete diffusion models offer global context awareness and flexible parallel generation. However, uniform random noise schedulers in standard DLLM training overlook the highly non-uniform information density inherent in real-world…

Masked diffusion models (MDMs), which leverage bidirectional attention and a denoising process, are narrowing the performance gap with autoregressive models (ARMs). However, their internal attention mechanisms remain under-explored. This…

Multimodal learning enhances the performance of various machine learning tasks by leveraging complementary information across different modalities. However, existing methods often learn multimodal representations that retain substantial…

Recent studies on deepfake detection have achieved promising results when training and testing faces are from the same dataset. However, their results severely degrade when confronted with forged samples that the model has not yet seen…

Masked diffusion models (MDMs) for text offer a compelling alternative to traditional autoregressive language models. Parallel generation makes them efficient, but their computational capabilities and the limitations inherent in their…

Semantic segmentation is essential in computer vision for various applications, yet traditional approaches face significant challenges, including the high cost of annotation and extensive training for supervised learning. Additionally, due…