Related papers: VDL-Surrogate: A View-Dependent Latent-based Model…
Most visual recognition studies rely heavily on crowd-labelled data in deep neural networks (DNNs) training, and they usually train a DNN for each single visual recognition task, leading to a laborious and time-consuming visual recognition…
Vision language models (VLMs) typically pair a modestly sized vision encoder with a large language model (LLM), e.g., Llama-70B, making the decoder the primary computational burden during training. To reduce costs, a potential promising…
Accurate surrogate construction for PDE-driven high-dimensional rare-event simulation is challenging when performance evaluations are expensive. Since a globally accurate surrogate may require many high-fidelity evaluations, adaptive…
Innovations in digital intelligence are transforming robotic surgery with more informed decision-making. Real-time awareness of surgical instrument presence and actions (e.g., cutting tissue) is essential for such systems. Yet, despite…
In many-task optimization scenarios, surrogate models are valuable for mitigating the computational burden of repeated fitness evaluations across tasks. This study proposes a novel meta-surrogate framework to assist many-task optimization,…
Recent studies have shown great promise in unsupervised representation learning (URL) for multivariate time series, because URL has the capability in learning generalizable representation for many downstream tasks without using inaccessible…
Supervised dictionary learning (SDL) is a classical machine learning method that simultaneously seeks feature extraction and classification tasks, which are not necessarily a priori aligned objectives. The goal of SDL is to learn a…
In the last few years, energy efficiency has become a challenge. Not only mitigating environmental impact but reducing energy waste can lead to financial advantages. Buildings play an important role in this: they are among the biggest…
Vision-Language-Action (VLA) models built on pretrained Vision-Language Models (VLMs) show strong potential but are limited in practicality due to their large parameter counts. To mitigate this issue, using a lightweight VLM has been…
Virtual reality (VR) offers immersive visualization and intuitive interaction. We leverage VR to enable any biomedical professional to deploy a deep learning (DL) model for image classification. While DL models can be powerful tools for…
Variational quantum algorithms are a class of techniques intended to be used on near-term quantum computers. The goal of these algorithms is to perform large quantum computations by breaking the problem down into a large number of shallow…
Search engines enable the retrieval of unknown information with texts. However, traditional methods fall short when it comes to understanding unfamiliar visual content, such as identifying an object that the model has never seen before.…
This work presents a deep learning surrogate model for the fast simulation of high-dimensional frequency selective surfaces. We consider unit-cells which are built as multiple concatenated stacks of screens and their design requires the…
In many mechanistic medical, biological, physical and engineered spatiotemporal dynamic models the numerical solution of partial differential equations (PDEs) can make simulations impractically slow. Biological models require the…
The data-centric construction of inexpensive surrogates for fine-grained, physical models has been at the forefront of computational physics due to its significant utility in many-query tasks such as uncertainty quantification. Recent…
Surrogate strategies are used widely for uncertainty quantification of groundwater models in order to improve computational efficiency. However, their application to dynamic multiphase flow problems is hindered by the curse of…
Vision-Language Navigation in Continuous Environments (VLNCE), where an agent follows instructions and moves freely to reach a destination, is a key research problem in embodied AI. However, most existing approaches are sensitive to…
While traditional computer vision models have historically struggled to generalize to endoscopic domains, the emergence of foundation models has shown promising cross-domain performance. In this work, we present the first large-scale study…
Vision-language modeling (VLM) aims to bridge the information gap between images and natural language. Under the new paradigm of first pre-training on massive image-text pairs and then fine-tuning on task-specific data, VLM in the remote…
We propose a novel representation of virtual humans for highly realistic real-time animation and rendering in 3D applications. We learn pose dependent appearance and geometry from highly accurate dynamic mesh sequences obtained from…