相关论文: BCAT: A Block Causal Transformer for PDE Foundatio…

Autoregressive and diffusion models have achieved remarkable progress in language models and visual generation, respectively. We present ACDiT, a novel Autoregressive blockwise Conditional Diffusion Transformer, that innovatively combines…

Block-causal video generation faces a stark speed-quality trade-off: small 1.3B models manage only 16 FPS while large 14B models crawl at 4.5 FPS, forcing users to choose between responsiveness and quality. Block Cascading significantly…

The lateral-line system that has evolved in many aquatic animals enables them to navigate murky fluid environments, locate and discriminate obstacles. Here, we present a data-driven model that uses artificial neural networks to process flow…

Video-generative world models are increasingly used as neural simulators for embodied planning and policy learning, yet their ability to predict physical risk and severe consequences is rarely evaluated.We find that these models often…

Diffusion Transformers (DiT) have emerged as a widely adopted backbone for high-fidelity image and video generation, yet their iterative denoising process incurs high computational costs. Existing training-free acceleration methods rely on…

Flow-based generative models provide strong unconditional priors for inverse problems, but guiding their dynamics for conditional generation remains challenging. Recent work casts training-free conditional generation in flow models as an…

Computational Fluid Dynamics (CFD) serves as a powerful tool for simulating fluid flow across diverse industries. High-resolution CFD simulations offer valuable insights into fluid behavior and flow patterns, aiding in optimizing design…

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).…

Causal Transformers are trained to predict the next token for a given context. While it is widely accepted that self-attention is crucial for encoding the causal structure of sequences, the precise underlying mechanism behind this…

This work aims to improve fuel chamber injectors' performance in turbofan engines, thus implying improved performance and reduction of pollutants. This requires the development of models that allow real-time prediction and improvement of…

Modern retrieval system often requires recomputing the representation of every piece of data in the gallery when updating to a better representation model. This process is known as backfilling and can be especially costly in the real world…

Diffusion models have demonstrated impressive generation capabilities, particularly with recent advancements leveraging transformer architectures to improve both visual and artistic quality. However, Diffusion Transformers (DiTs) continue…

This paper presents a scalable physics-based block preconditioner for mixed-dimensional models in beam-solid interaction and their application in engineering. In particular, it studies the linear systems arising from a regularized…

Spatiotemporal prediction is important in solving natural problems and processing video frames, especially in weather forecasting and human action recognition. Recent advances attempt to incorporate prior physical knowledge into the deep…

In this study, we present the development and application of the physics-informed convolutional decoder (PICD) framework for inverse modeling of heterogenous groundwater flow. PICD stands out as a direct inversion method, eliminating the…

We introduce Poseidon, a foundation model for learning the solution operators of PDEs. It is based on a multiscale operator transformer, with time-conditioned layer norms that enable continuous-in-time evaluations. A novel training strategy…

This dissertation attempts to drive innovation in the field of generative modeling for computer vision, by exploring novel formulations of conditional generative models, and innovative applications in images, 3D animations, and video. Our…

Randomised field experiments, such as A/B testing, have long been the gold standard for evaluating software changes. In the automotive domain, running randomised field experiments is not always desired, possible, or even ethical. In the…

Underwater image enhancement (UIE) has attracted much attention owing to its importance for underwater operation and marine engineering. Motivated by the recent advance in generative models, we propose a novel UIE method based on…

We present a combined numerical and data-driven workflow for efficient prediction of nonlinear, instationary convection-diffusion-reaction dynamics on a two-dimensional phenotypic domain, motivated by macroscopic modeling of cancer cell…