Related papers: A Pretraining-Finetuning Computational Framework f…

With the ever-increasing number of pretrained models, machine learning practitioners are continuously faced with which pretrained model to use, and how to finetune it for a new dataset. In this paper, we propose a methodology that jointly…

This paper presents volumetric homogenization, a spatially varying homogenization scheme for knitwear simulation. We are motivated by the observation that macro-scale fabric dynamics is strongly correlated with its underlying knitting…

We propose a Newton-based scheme, initialized by neural operator predictions, to accelerate the parametric solution of nonlinear problems in computational solid mechanics. First, a physics informed conditional neural field is trained to…

Visual localization on standard-definition (SD) maps has emerged as a promising low-cost and scalable solution for autonomous driving. However, existing regression-based approaches often overlook inherent geometric priors, resulting in…

Monocular 4D human-object interaction (HOI) reconstruction - recovering a moving human and a manipulated object from a single RGB video - remains challenging due to depth ambiguity and frequent occlusions. Existing methods often rely on…

Generative modeling of human motion has broad applications in computer animation, virtual reality, and robotics. Conventional approaches develop separate models for different motion synthesis tasks, and typically use a model of a small size…

Human-object interactions (HOI) recognition and pose estimation are two closely related tasks. Human pose is an essential cue for recognizing actions and localizing the interacted objects. Meanwhile, human action and their interacted…

Modeling 4D human-object interaction (HOI) is a compelling challenge in computer vision and an essential technology powering virtual and mixed-reality applications. While existing works have achieved promising results on specific HOI…

Quantized training of Large Language Models (LLMs) remains an open challenge, as maintaining accuracy while performing all matrix multiplications in low precision has proven difficult. This is particularly the case when fine-tuning…

Multimodal deep learning harnesses diverse imaging modalities, such as MRI sequences, to enhance diagnostic accuracy in medical imaging. A key challenge is determining the optimal timing for integrating these modalities-specifically,…

Recent hardware acceleration advances have enabled powerful specialized accelerators for finite element computations, spiking neural network inference, and sparse tensor operations. However, existing approaches face fundamental limitations:…

Human motion prediction is an essential component for enabling closer human-robot collaboration. The task of accurately predicting human motion is non-trivial. It is compounded by the variability of human motion, both at a skeletal level…

Additive manufacturing methods together with topology optimization have enabled the creation of multiscale structures with controlled spatially-varying material microstructure. However, topology optimization or inverse design of such…

Microstructures are attracting academic and industrial interests with the rapid development of additive manufacturing. The numerical homogenization method has been well studied for analyzing mechanical behaviors of microstructures; however,…

Deep learning-based medical image segmentation and surface mesh generation typically involve a sequential pipeline from image to segmentation to meshes, often requiring large training datasets while making limited use of prior geometric…

Fully resolving dynamics of materials with rapidly-varying features involves expensive fine-scale computations which need to be conducted on macroscopic scales. The theory of homogenization provides an approach to derive effective…

In this paper, we propose a systematic approach for accelerating finite element-type methods by machine learning for the numerical solution of partial differential equations (PDEs). The main idea is to use a neural network to learn the…

We present deep neural network methodology to reconstruct the 3d pose and shape of people, given an input RGB image. We rely on a recently introduced, expressivefull body statistical 3d human model, GHUM, trained end-to-end, and learn to…

With the extensive applications of machine learning models, automatic hyperparameter optimization (HPO) has become increasingly important. Motivated by the tuning behaviors of human experts, it is intuitive to leverage auxiliary knowledge…

Pretraining methods gain increasing attraction recently for solving PDEs with neural operators. It alleviates the data scarcity problem encountered by neural operator learning when solving single PDE via training on large-scale datasets…