Related papers: Scalable Spatio-Temporal SE(3) Diffusion for Long-…
Developing a theory of low-mass star formation ($\sim 0.1$ to 3~M$_{\odot}$) remains one of the most elusive and important goals of theoretical astrophysics. The star-formation process is the outcome of the complex dynamics of interstellar…
Self-supervised pretraining methods with masked prediction demonstrate remarkable within-dataset performance in skeleton-based action recognition. However, we show that, unlike contrastive learning approaches, they do not produce…
Video Question Answering (VideoQA) task serves as a critical playground for evaluating whether foundation models can effectively perceive, understand, and reason about dynamic real-world scenarios. However, existing Multimodal Large…
LiDAR-based 3D object detection presents significant challenges due to the inherent sparsity of LiDAR points. A common solution involves long-term temporal LiDAR data to densify the inputs. However, efficiently leveraging spatial-temporal…
Given the remarkable achievements in image generation through diffusion models, the research community has shown increasing interest in extending these models to video generation. Recent diffusion models for video generation have…
Image-based personalized medicine has the potential to transform healthcare, particularly for diseases that exhibit heterogeneous progression such as Multiple Sclerosis (MS). In this work, we introduce the first treatment-aware…
Developments in dynamical systems theory provides new support for the macroscale modelling of pdes and other microscale systems such as Lattice Boltzmann, Monte Carlo or Molecular Dynamics simulators. By systematically resolving subgrid…
Accurate imputation is essential for the reliability and success of downstream tasks. Recently, diffusion models have attracted great attention in this field. However, these models neglect the latent distribution in a lower-dimensional…
Diffusion models generate samples by denoising along the score of a perturbed target distribution. In practice, one trains a neural diffusion model, which is computationally expensive. Recent work suggests that score matching implicitly…
The chemical space of drug-like molecules is vast, motivating the development of generative models that must learn broad chemical distributions, enable conditional generation by capturing structure-property representations, and provide fast…
Simulating large proteins using traditional molecular dynamics (MD) is computationally demanding. To address this challenge, we propose a novel tree-structured coarse-grained model that efficiently captures protein dynamics. By leveraging a…
Massively parallel computer architectures create new opportunities for the performance of long-timescale molecular dynamics (MD) simulations. Here, we introduce the path-accelerated molecular dynamics (PAMD) method that takes advantage of…
Accurate prediction of energy and forces for 3D molecular systems is one of fundamental challenges at the core of AI for Science applications. Many powerful and data-efficient neural networks predict molecular energies and forces from…
We introduce STAR, a text-to-image model that employs a scale-wise auto-regressive paradigm. Unlike VAR, which is constrained to class-conditioned synthesis for images up to 256$\times$256, STAR enables text-driven image generation up to…
Generative models have shown great promise in generating 3D geometric systems, which is a fundamental problem in many natural science domains such as molecule and protein design. However, existing approaches only operate on static…
Protein structure prediction is pivotal for understanding the structure-function relationship of proteins, advancing biological research, and facilitating pharmaceutical development and experimental design. While deep learning methods and…
We propose enforcing constraints on Model-Based Diffusion by introducing emerging barrier functions inspired by interior point methods. We demonstrate that the standard Model-Based Diffusion algorithm can lead to catastrophic performance…
Molecular dynamics (MD) is a central computational tool in physics, chemistry, and biology, enabling quantitative prediction of experimental observables as expectations over high-dimensional molecular distributions such as Boltzmann…
Although continuous-time consistency models (e.g., sCM, MeanFlow) are theoretically principled and empirically powerful for fast academic-scale diffusion, its applicability to large-scale text-to-image and video tasks remains unclear due to…
Background: Current research suggests that a small set of "driver" mutations are responsible for tumorigenesis while a larger body of "passenger" mutations occurs in the tumor but does not progress the disease. Due to recent pharmacological…