Related papers: Transition Models: Rethinking the Generative Learn…

The acquisition of annotated datasets with paired images and segmentation masks is a critical challenge in domains such as medical imaging, remote sensing, and computer vision. Manual annotation demands significant resources, faces ethical…

Diffusion models have demonstrated remarkable capabilities in generating high-quality samples and enhancing performance across diverse domains through Classifier-Free Guidance (CFG). However, the quality of generated samples is highly…

Recent advances in generative modeling -- particularly diffusion models and flow matching -- have achieved remarkable success in synthesizing discrete data such as images and videos. However, adapting these models to physical applications…

We introduce the Self-Evaluating Model (Self-E), a novel, from-scratch training approach for text-to-image generation that supports any-step inference. Self-E learns from data similarly to a Flow Matching model, while simultaneously…

Generative models have fundamentally reshaped the landscape of decision-making, reframing the problem from pure scalar reward maximization to high-fidelity trajectory generation and distribution matching. This paradigm shift addresses…

Diffusion models (DMs) are capable of generating remarkably high-quality samples by iteratively denoising a random vector, a process that corresponds to moving along the probability flow ordinary differential equation (PF ODE).…

Conditional diffusion models have achieved remarkable success in various generative tasks recently, but their training typically relies on large-scale datasets that inevitably contain imprecise information in conditional inputs. Such…

We introduce a new family of physics-inspired generative models termed PFGM++ that unifies diffusion models and Poisson Flow Generative Models (PFGM). These models realize generative trajectories for $N$ dimensional data by embedding paths…

Recent advances in diffusion and flow-based generative models have demonstrated remarkable success in image restoration tasks, achieving superior perceptual quality compared to traditional deep learning approaches. However, these methods…

Diffusion- and flow-based models have emerged as state-of-the-art generative modeling approaches, but they require many sampling steps. Consistency models can distill these models into efficient one-step generators; however, unlike flow-…

Generative models have demonstrated remarkable potential in time series analysis tasks, like synthesis, forecasting, imputation, etc. However, offering limited coverage for generative models, existing time series libraries are mainly…

The emergence of billion-parameter diffusion models such as Stable Diffusion XL, Imagen, and DALL-E 3 has significantly propelled the domain of generative AI. However, their large-scale architecture presents challenges in fine-tuning and…

Cognitive diagnosis (CD) models latent cognitive states of human learners by analyzing their response patterns on diagnostic tests, serving as a crucial machine learning technique for educational assessment and evaluation. Traditional…

As deep generative models proliferate across the AI landscape, industrial practitioners still face critical yet unanswered questions about which deep generative models best suit complex manufacturing design tasks. This work addresses this…

Shortcut models represent a promising, non-adversarial paradigm for generative modeling, uniquely supporting one-step, few-step, and multi-step sampling from a single trained network. However, their widespread adoption has been stymied by…

Transformer-based tabular foundation models (TFMs) dominate small to medium tabular predictive benchmark tasks, yet their inference mechanisms remain largely unexplored. We present the first large-scale mechanistic study of layerwise…

Denoising Probabilistic Models (DPMs) represent an emerging domain of generative models that excel in generating diverse and high-quality images. However, most current training methods for DPMs often neglect the correlation between…

Models obtained by decision tree induction techniques excel in being interpretable.However, they can be prone to overfitting, which results in a low predictive performance. Ensemble techniques are able to achieve a higher accuracy. However,…

Continuous-time Consistency Models (CMs) promise efficient few-step generation but face significant challenges with training instability. We argue this instability stems from a fundamental conflict: Training the network exclusively on a…

Text-to-image diffusion models are computationally intensive, often requiring dozens of forward passes through large transformer backbones. For instance, Stable Diffusion XL generates high-quality images with 50 evaluations of a…