Related papers: Learning Flexible Forward Trajectories for Masked …
Cell-level dense prediction is central to computational pathology, but remains challenging due to fine-grained histological structures, strong domain shifts, and costly dense annotations. Existing ViT-based pathology foundation models rely…
Understanding and accurately predicting hydrogen diffusion in materials is challenging due to the complex interactions between hydrogen defects and the crystal lattice. These interactions span large length and time scales, making them…
Post-training pretrained autoregressive models (ARMs) into masked diffusion models (MDMs) has emerged as a cost-effective way to overcome the limitations of sequential generation. Yet it remains unclear whether post-trained MDMs acquire…
Deep Metric Learning (DML) methods have been proven relevant for visual similarity learning. However, they sometimes lack generalization properties because they are trained often using an inappropriate sample selection strategy or due to…
Diffusion language models have recently emerged as a competitive alternative to autoregressive language models. Beyond next-token generation, they are more efficient and flexible by enabling parallel and any-order token generation. However,…
With the rapid progress of diffusion-based content generation, significant efforts are being made to unlearn harmful or copyrighted concepts from pretrained diffusion models (DMs) to prevent potential model misuse. However, it is observed…
Discrete diffusion models (DMs) have achieved strong performance in language and other discrete domains, offering a compelling alternative to autoregressive modeling. Yet this performance typically depends on large training datasets,…
The performance of pre-trained masked diffusion models is often constrained by their sampling procedure, which makes decisions irreversible and struggles in low-step generation regimes. We introduce a novel sampling algorithm that works…
Masked diffusion language models (MDLMs) enable parallel decoding by predicting all masked positions at each denoising step, yet existing training-free samplers usually decide which positions to commit at token-level granularity. We revisit…
Diffusion models are increasingly used as powerful conditional generators, yet real deployments often involve multiple target distributions arising from different tasks, e.g., diverse prompt domains in text-to-image generation, or multiple…
Latent space Energy-Based Models (EBMs), also known as energy-based priors, have drawn growing interests in generative modeling. Fueled by its flexibility in the formulation and strong modeling power of the latent space, recent works built…
The modern autoregressive Large Language Models (LLMs) have achieved outstanding performance on NLP benchmarks, and they are deployed in the real world. However, they still suffer from limitations of the autoregressive training paradigm.…
While state-of-the-art language models achieve impressive results through next-token prediction, they have inherent limitations such as the inability to revise already generated tokens. This has prompted exploration of alternative…
Molecular property prediction constitutes a cornerstone of drug discovery and materials science, necessitating models capable of disentangling complex structure-property relationships across diverse molecular modalities. Existing approaches…
Masked diffusion language models (MDMs) have recently gained traction as a viable generative framework for natural language. This can be attributed to its scalability and ease of training compared to other diffusion model paradigms for…
Generative data augmentation with latent diffusion models is a promising strategy for addressing class imbalance in medical imaging, yet current approaches focus on perceptual fidelity and domain-specific autoencoder fine-tuning while…
Molecule generation, especially generating 3D molecular geometries from scratch (i.e., 3D \textit{de novo} generation), has become a fundamental task in drug designs. Existing diffusion-based 3D molecule generation methods could suffer from…
Masked diffusion models (MDM) exhibit superior generalization when learned using a Partial masking scheme (Prime). This approach converts tokens into sub-tokens and models the diffusion process at the sub-token level. We identify two…
Learning complex distributions is a fundamental challenge in contemporary applications. Shen and Meinshausen (2024) introduced engression, a generative approach based on scoring rules that maps noise (and covariates, if available) directly…
Diffusion models (DMs) have achieved state-of-the-art results for image synthesis tasks as well as density estimation. Applied in the latent space of a powerful pretrained autoencoder (LDM), their immense computational requirements can be…