Related papers: CosmoFlow: Scale-Aware Representation Learning for…

Deep generative models such as flow matching and diffusion models have shown great potential in learning complex distributions and dynamical systems, but often act as black-boxes, neglecting underlying physics. In contrast, physics-based…

Autoregressive language models dominate modern text generation, yet their sequential nature introduces fundamental limitations: decoding is slow, and maintaining global coherence remains challenging. Diffusion models offer a promising…

Accurate and high-resolution Earth system model (ESM) simulations are essential to assess the ecological and socio-economic impacts of anthropogenic climate change, but are computationally too expensive to be run at sufficiently high…

Generative models have shown robust performance on speech enhancement and restoration tasks, but most prior approaches operate offline with high latency, making them unsuitable for streaming applications. In this work, we investigate the…

Generative models that can model and predict sequences of future events can, in principle, learn to capture complex real-world phenomena, such as physical interactions. However, a central challenge in video prediction is that the future is…

Urban wind flow modeling and simulation play an important role in air quality assessment and sustainable city planning. A key challenge for modeling and simulation is handling the complex geometries of the urban landscape. Low order models…

Generative modelling of entire CT volumes conditioned on clinical reports has the potential to accelerate research through data augmentation, privacy-preserving synthesis and reducing regulator-constraints on patient data while preserving…

Conditional Flow Matching (CFM), a simulation-free method for training continuous normalizing flows, provides an efficient alternative to diffusion models for key tasks like image and video generation. The performance of CFM in solving…

We propose a novel approach using neural networks (NNs) to differentiate between cosmological models, and implemented LIME as an interpretability approach to identify the key features influencing our model's decisions. We show the potential…

I present a large set of high resolution simulations, called CosmicGrowth Simulations, which were generated with either 8.6 billion or 29 billion particles. As the nominal cosmological model that can match nearly all observations on…

We use machine learning (ML) to infer stress and plastic flow rules using data from repre- sentative polycrystalline simulations. In particular, we use so-called deep (multilayer) neural networks (NN) to represent the two response…

Regional climate information at kilometer scales is essential for assessing the impacts of climate change, but generating it with global climate models is too expensive due to their high computational costs. Machine learning models offer a…

Symmetry is fundamental to understanding physical systems and can improve performance and sample efficiency in machine learning. Both pursuits require knowledge of the underlying symmetries in data, yet discovering these symmetries…

Sewing patterns define the structural foundation of garments and are essential for applications such as fashion design, fabrication, and physical simulation. Despite progress in automated pattern generation, accurately modeling sewing…

Generative models have proven effective at modeling 3D shapes and their statistical variations. In this paper we investigate their application to point clouds, a 3D shape representation widely used in computer vision for which, however,…

Knowledge distillation (KD) is an essential technique to compress large language models (LLMs) into smaller ones. However, despite the distinct roles of the student model and the teacher model in KD, most existing frameworks still use a…

Recent advances in generative models highlight the power of geometry-aware modeling in manifold-constrained settings. Yet, for natural images, the field remains confined to Euclidean assumptions, failing to exploit the potential of…

It is always demanding to learn robust visual representation for various learning problems; however, this learning and maintenance process usually suffers from noise, incompleteness or knowledge domain mismatch. Thus, robust representation…

We present a convolutional neural network to classify distinct cosmological scenarios based on the statistically similar weak-lensing maps they generate. Modified gravity (MG) models that include massive neutrinos can mimic the standard…

Feature representation plays a crucial role in visual correspondence, and recent methods for image matching resort to deeply stacked convolutional layers. These models, however, are both monolithic and static in the sense that they…