Related papers: Dynamic Caustics by Ultrasonically Modulated Liqui…
Diffusion Models represent a significant advancement in generative modeling, employing a dual-phase process that first degrades domain-specific information via Gaussian noise and restores it through a trainable model. This framework enables…
Deep, high-resolution imaging is essential for unraveling biological complexity and advancing medical diagnostics, yet scattering fundamentally limits optical methods. Among the most promising approaches, photoacoustic imaging achieves…
Multimodal generative models that can understand and generate across multiple modalities are dominated by autoregressive (AR) approaches, which process tokens sequentially from left to right, or top to bottom. These models jointly handle…
Elastic metasurfaces offer precise control over elastic waves for applications such as vibration isolation, sensing, and imaging. However, achieving high-efficiency and scattering-free performance with complex functionalities remains a…
Topological photonics and acoustics have recently garnered wide research interests for their topological ability to manipulate the light and sound at surfaces. Conventionally, the supercell technique is the standard approach to calculating…
Computer-generated holograms with their animated, three-dimensional appearance have long appealed to our imagination as the path towards truly immersive displays with bi-directional natural parallax. Impressive progress in updateable 3-D…
We demonstrate theoretically that acoustic forces acting on inhomogeneous fluids can be used to pattern and manipulate solute concentration fields into spatio-temporally controllable configurations stabilized against gravity. A theoretical…
Modern computational science and engineering applications are being improved by the advances in scientific machine learning. Data-driven methods such as Dynamic Mode Decomposition (DMD) can extract coherent structures from spatio-temporal…
Diffusion models have gained attention for their ability to represent complex distributions and incorporate uncertainty, making them ideal for robust predictions in the presence of noisy or incomplete data. In this study, we develop and…
Diffusion models (DMs) excel in photo-realistic image synthesis, but their adaptation to LiDAR scene generation poses a substantial hurdle. This is primarily because DMs operating in the point space struggle to preserve the curve-like…
Spatial gradients of diffusible signalling molecules play crucial roles in controlling diverse cellular behaviour such as cell differentiation, tissue patterning and chemotaxis. In this paper, we report the design and testing of a…
Talking head synthesis with arbitrary speech audio is a crucial challenge in the field of digital humans. Recently, methods based on radiance fields have received increasing attention due to their ability to synthesize high-fidelity and…
Fast and programmable transport of liquid droplets on a solid substrate is desirable in microfluidic, thermal, biomedical, and energy devices. Past research has focused on designing substrates with asymmetric structures or gradient…
Holographic light potentials generated by phase-modulating liquid-crystal spatial light modulators (SLMs) are widely used in quantum technology applications. Accurate calibration of the wavefront and intensity profile of the laser beam at…
We present Surf-D, a novel method for generating high-quality 3D shapes as Surfaces with arbitrary topologies using Diffusion models. Previous methods explored shape generation with different representations and they suffer from limited…
The creation of whole 3D objects in one shot is an ultimate goal for rapid prototyping, most notably biofabrication, where conventional methods are typically slow and apply mechanical or chemical stress on biological cells. Here, we…
Previous surface reconstruction methods either suffer from low geometric accuracy or lengthy training times when dealing with real-world complex dynamic scenes involving multi-person activities, and human-object interactions. To tackle the…
Two-dimensional photonic crystal membranes provide a versatile planar architecture for integrated photonics to control the propagation of light on a chip employing high quality optical cavities, waveguides, beamsplitters or dispersive…
Modern electronic systems operate in complex electromagnetic environments and must handle noise and unwanted coupling. The capability to isolate or reject unwanted signals for mitigating vulnerabilities is critical in any practical…
As deep learning models grow in complexity and the volume of training data increases, reducing storage and computational costs becomes increasingly important. Dataset distillation addresses this challenge by synthesizing a compact set of…