We introduce PhysGaussian a new method that seamlessly integrates physically grounded
Newtonian dynamics within 3D Gaussians to achieve high-quality novel motion synthesis …

Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural
sciences. Today, AI has started to advance natural sciences by improving, accelerating, and …

The incorporation of physical information in machine learning frameworks is opening and
transforming many application domains. Here the learning process is augmented through …

Realistic object interactions are crucial for creating immersive virtual experiences, yet
synthesizing realistic 3D object dynamics in response to novel interactions remains a …

Data-driven models based on deep learning algorithms intend to overcome the limitations of
traditional constitutive modelling by directly learning from data. However, the need for …

Multiscale partial differential equations (PDEs) arise in various applications, and several
schemes have been developed to solve them efficiently. Homogenization theory is a …

We introduce DIFFTACTILE, a physics-based differentiable tactile simulation system
designed to enhance robotic manipulation with dense and physically accurate tactile …

Reconstructing and simulating elastic objects from visual observations is crucial for
applications in computer vision and robotics. Existing methods, such as 3D Gaussians …

The rapid growth of artificial intelligence is revolutionizing classical engineering society,
offering novel approaches to material and structural design and analysis. Among various …

Modeling unsteady, fast transient, and advection-dominated physics problems is a pressing
challenge for physics-aware deep learning (PADL). The physics of complex systems is …