Rebar tying is a repetitive but critical task in reinforced concrete construction, typically performed manually at considerable ergonomic risk. Recent advances in robotic manipulation hold the potential to automate the tying process, yet face challen...
Recent 3D content generation pipelines commonly employ Variational Autoencoders (VAEs) to encode shapes into compact latent representations for diffusion-based generation. However, the widely adopted uniform point sampling strategy in Shape VAE train...
Mysteries in binary phase diagram are still in existence, e.g., the case in Cu-Ni which is mutual miscible system, the question addressed that "Indirect experimental evidence indicates the presence of a miscibility gap in the fcc phase at a temperatu...
We consider a reaction-diffusion system of densities of two types of particles, introduced by Edouard Hannezo et al. in the context of branching morphogenesis. It is a simple model for a growth process: active, branching particles form the growing bo...
Reliability is extremely important for large-scale cloud systems like Microsoft 365. Cloud failures such as disk failure, node failure, etc. threaten service reliability, resulting in online service interruptions and economic loss. Existing works foc...
Burton-Cabrera-Frank (BCF) theory has proven to be a versatile framework to relate surface morphology and dynamics during crystal growth to the underlying mechanisms of adatom diffusion and attachment at steps. For an important class of crystal surfa...
A complex process is often a balance between non-stationary and stationary components. We show how the non-extensive Tsallis q-entropy indicator may be interpreted as a measure of non-stationarity in time series. This is done by applying the non-ex...
We argue that a process of social interest is a balance of order and randomness, thereby producing a departure from a stationary diffusion process. The strength of this effect vanishes if the order to randomness intensity ratio vanishes, and this p...
In the absence of coalescence, coarsening of emulsions (and foams) is controlled by molecular diffusion of dispersed phase between droplets/bubbles. Studies of dilute emulsions have shown how the osmotic pressure of a trapped species within droplet...
Controllable generation, which enables fine-grained control over generated outputs, has emerged as a critical focus in visual generative models. Currently, there are two primary technical approaches in visual generation: diffusion models and autoregr...
Autoregressive video models are promising for world modeling via next-frame prediction, but they suffer from exposure bias: a mismatch between training on clean contexts and inference on self-generated frames, causing errors to compound and quality t...
Flow matching has emerged as a promising framework for training generative models, demonstrating impressive empirical performance while offering relative ease of training compared to diffusion-based models. However, this method still requires numerou...
Liouville Brownian motion (LBM) is the canonical diffusion process on a Liouville quantum gravity (LQG) surface. In this work, we establish upper and lower bounds for the heat kernel for LBM when $γ=\sqrt{8/3}$ in terms of the $\sqrt{8/3}$-LQG metri...
Content creators often draw inspiration from multiple visual sources, combining distinct elements to craft new compositions. Modern computational approaches now aim to emulate this fundamental creative process. Although recent diffusion models excel...
Large-scale generative models have achieved remarkable success in a number of domains. However, for sequential decision-making problems, such as robotics, action-labelled data is often scarce and therefore scaling-up foundation models for decision-ma...
This report presents an analysis of #hashtags used by Italian Cultural Heritage institutions to promote and communicate cultural content during the COVID-19 lock-down period in Italy. Several activities to support and engage users' have been proposed...
Mar 21, 2025 · A hybrid AI approach known as hybrid autoregressive transformer can generate realistic images with the same or better quality than state-of-the-art diffusion models, but that runs about nine â¦
2 days ago · AI algorithm enables tracking of vital white matter pathways Opening a new window on the brainstem, a new tool reliably and finely resolves distinct nerve bundles in live diffusion MRI scans, â¦
With the rise of Wikipedia as a first-stop source for scientific knowledge, it is important to compare its representation of that knowledge to that of the academic literature. Here we identify the 250 most heavily used journals in each of 26 research...
We have investigated the bleaching dynamics that occur in optofluidic dye lasers where the liquid laser dye in a microfluidic channel is locally bleached due to optical pumping. We find that for microfluidic devices, the dye bleaching may be compen...