Related papers: DisCo: Physics-Based Unsupervised Discovery of Coh…
The interaction of multiple fluids through a heterogeneous pore space leads to complex pore-scale flow dynamics, such as intermittent pathway flow. The non-local nature of these dynamics, and the size of the 4D datasets acquired to capture…
Recent advancements in neural combinatorial optimization (NCO) methods have shown promising results in generating near-optimal solutions without the need for expert-crafted heuristics. However, high performance of these approaches often…
We propose a novel architecture UniTransfer, which introduces both spatial and diffusion timestep decomposition in a progressive paradigm, achieving precise and controllable video concept transfer. Specifically, in terms of spatial…
Diffusion-based imitation learning has shown strong promise for robot manipulation. However, most existing policies condition only on the current observation or a short window of recent observations, limiting their ability to resolve…
Physics-Informed Neural Networks (PINNs) offer a powerful paradigm for flow reconstruction, seamlessly integrating sparse velocity measurements with the governing Navier-Stokes equations to recover complete velocity and latent pressure…
The permutational invariance of identical two-level systems allows for an exponential reduction in the computational resources required to study the Lindblad dynamics of coupled spin-boson ensembles evolving under the effect of both local…
Unsupervised disentanglement is a long-standing challenge in representation learning. Recently, self-supervised techniques achieved impressive results in the sequential setting, where data is time-dependent. However, the latter methods…
Time periodic patterns in a semiconductor superlattice, relevant to microwave generation, are obtained upon numerical integration of a known set of drift-diffusion equations. The associated spatio-temporal transport mechanisms are uncovered…
Large-scale well-annotated datasets are of great importance for training an effective object detector. However, obtaining accurate bounding box annotations is laborious and demanding. Unfortunately, the resultant noisy bounding boxes could…
Learning physical dynamics from data is a fundamental challenge in machine learning and scientific modeling. Real-world observational data are inherently incomplete and irregularly sampled, posing significant challenges for existing…
From the intuitive notion of disentanglement, the image variations corresponding to different factors should be distinct from each other, and the disentangled representation should reflect those variations with separate dimensions. To…
We aim to solve the problem of generating coarse-to-fine skills learning from demonstrations (LfD). To scale precision, traditional LfD approaches often rely on extensive fine-grained demonstrations with external interpolations or dynamics…
Climate models are essential to understand and project climate change, yet long-standing biases and uncertainties in their projections remain. This is largely associated with the representation of subgrid-scale processes, particularly…
Multivariate time series in domains such as finance, climate science, and healthcare often exhibit long-term trends, seasonal patterns, and short-term fluctuations, complicating causal inference under non-stationarity and autocorrelation.…
Recently, large-scale pre-trained language-image models like CLIP have shown extraordinary capabilities for understanding spatial contents, but naively transferring such models to video recognition still suffers from unsatisfactory temporal…
Modeling the dynamic behavior of deformable objects is crucial for creating realistic digital worlds. While conventional simulations produce high-quality motions, their computational costs are often prohibitive. Subspace simulation…
Conversational Search (CS) involves retrieving relevant documents from a corpus while considering the conversational context, integrating retrieval with context modeling. Recent advancements in Large Language Models (LLMs) have…
Deoccluding the hidden portions of objects in a scene is a formidable task, particularly when addressing real-world scenes. In this paper, we present a new self-supervised PArallel visible-to-COmplete diffusion framework, named PACO, a…
Dynamic mode decomposition has emerged as a leading technique to identify spatiotemporal coherent structures from high-dimensional data, benefiting from a strong connection to nonlinear dynamical systems via the Koopman operator. In this…
We propose a new scientific application of unsupervised learning techniques to boost our ability to search for new phenomena in data, by detecting discrepancies between two datasets. These could be, for example, a simulated standard-model…