Related papers: Auto-Connect: Connectivity-Preserving RigFormer wi…
We present a neural network for predicting purchasing intent in an Ecommerce setting. Our main contribution is to address the significant investment in feature engineering that is usually associated with state-of-the-art methods such as…
Estimating the 3D position of human joints has become a widely researched topic in the last years. Special emphasis has gone into defining novel methods that extrapolate 2-dimensional data (keypoints) into 3D, namely predicting the…
Reconfigurable optical topologies are a promising new technology to improve datacenter network performance and cope with the explosive growth of traffic. In particular, these networks allow to directly and adaptively connect racks between…
Implicit neural networks have emerged as a crucial technology in 3D surface reconstruction. To reconstruct continuous surfaces from discrete point clouds, encoding the input points into regular grid features (plane or volume) has been…
Since wearable linkage mechanisms could control the moment transmission from actuator(s) to wearers, they can help ensure that even low-cost wearable systems provide advanced functionality tailored to users' needs. For example, if a hip…
In this paper, a mechanistic data-driven approach is proposed to accelerate structural topology optimization, employing an in-house developed finite element convolutional neural network (FE-CNN). Our approach can be divided into two stages:…
This paper presents a novel model-reference reinforcement learning algorithm for the intelligent tracking control of uncertain autonomous surface vehicles with collision avoidance. The proposed control algorithm combines a conventional…
Visual design is critical to product success, and the subject of intensive marketing research effort. Yet visual elements, due to their holistic and interactive nature, do not lend themselves well to optimization using extant…
Foundation models are commonly deployed as frozen feature extractors with a small trainable head to adapt to private, user-generated data in federated settings. The ``right to be forgotten'' requires removing the influence of specific…
One of the most elusive goals in myographic prosthesis control is the ability to reliably decode continuous positions simultaneously across multiple degrees-of-freedom. Goal: To demonstrate dexterous, natural, biomimetic finger and wrist…
Tendon-Driven Continuum Robots (TDCRs) pose significant control challenges due to their highly nonlinear, path-dependent dynamics and non-Markovian characteristics. Traditional Jacobian-based controllers often struggle with…
Automated Radiology report generation (RRG) aims at producing detailed descriptions of medical images, reducing radiologists' workload and improving access to high-quality diagnostic services. Existing encoder-decoder models only rely on…
Enforcing complex (e.g., nonconvex) operational constraints is a critical challenge in real-world learning and control systems. However, existing methods struggle to efficiently enforce general classes of constraints. To address this, we…
Fiducial markers have been playing an important role in augmented reality (AR), robot navigation, and general applications where the relative pose between a camera and an object is required. Here we introduce TopoTag, a robust and scalable…
We introduce a novel deep learning framework for data-driven motion retargeting between skeletons, which may have different structure, yet corresponding to homeomorphic graphs. Importantly, our approach learns how to retarget without…
Vision-based pose estimation of articulated robots with unknown joint angles has applications in collaborative robotics and human-robot interaction tasks. Current frameworks use neural network encoders to extract image features and…
Generative recommendation (GR) aligns with advances in generative AI by casting next-item prediction as token-level generation rather than score-based ranking. Most GR methods adopt a two-stage pipeline: (i) \textit{item tokenization},…
Learning-based 3D object reconstruction enables single- or few-shot estimation of 3D object models. For robotics, this holds the potential to allow model-based methods to rapidly adapt to novel objects and scenes. Existing 3D reconstruction…
Topology optimization facilitates the automated design of high-performance structures across various engineering fields but, if unconstrained, often produces designs that are complex and difficult to manufacture. A key attribute of the…
Adaptive optimizers are pivotal in guiding the weight updates of deep neural networks, yet they often face challenges such as poor generalization and oscillation issues. To counter these, we introduce sigSignGrad and tanhSignGrad, two novel…