Search Results for author:
Found 74 papers, 21 papers with code
Enhanced Sentence Alignment Network for Efficient Short Text Matching
Cross-sentence attention has been widely applied in text matching, in which model learns the aligned information between two intermediate sequence representations to capture their semantic relationship.
ViralQC: A Tool for Assessing Completeness and Contamination of Predicted Viral Contigs
This highlights the urgent need for an accurate and efficient method to evaluate the quality of viral contigs.
Speedy MASt3R
Image matching is a key component of modern 3D vision algorithms, essential for accurate scene reconstruction and localization.
GiantHunter: Accurate detection of giant virus in metagenomic data using reinforcement-learning and Monte Carlo tree search
Results: In this work, we present GiantHunter, a reinforcement learning-based tool for identifying NCLDVs from metagenomic data.
An Immersive Multi-Elevation Multi-Seasonal Dataset for 3D Reconstruction and Visualization
Significant progress has been made in photo-realistic scene reconstruction over recent years.
GenEx: Generating an Explorable World
In this work, we take a step toward this goal by introducing GenEx, a system capable of planning complex embodied world exploration, guided by its generative imagination that forms priors (expectations) about the surrounding environments.
Geometry Field Splatting with Gaussian Surfels
We adapt Gaussian kernels or surfels to splat the geometry field rather than the volume, enabling precise reconstruction of opaque solids.
SPARS3R: Semantic Prior Alignment and Regularization for Sparse 3D Reconstruction
Recent efforts in Gaussian-Splat-based Novel View Synthesis can achieve photorealistic rendering; however, such capability is limited in sparse-view scenarios due to sparse initialization and over-fitting floaters.
DreamCraft3D++: Efficient Hierarchical 3D Generation with Multi-Plane Reconstruction Model
We introduce DreamCraft3D++, an extension of DreamCraft3D that enables efficient high-quality generation of complex 3D assets.
FusionRF: High-Fidelity Satellite Neural Radiance Fields from Multispectral and Panchromatic Acquisitions
Current work has demonstrated the increased accuracy of neural photogrammetry for surface reconstruction from optical satellite images compared to algorithmic methods.
OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs
This paper introduces a novel and efficient One-pass Generation and retrieval framework (OneGen), designed to improve LLMs' performance on tasks that require both generation and retrieval.
Drone-assisted Road Gaussian Splatting with Cross-view Uncertainty
Robust and realistic rendering for large-scale road scenes is essential in autonomous driving simulation.
PhaGO: Protein function annotation for bacteriophages by integrating the genomic context
Although a large number of new phages have been identified via metagenomic sequencing, many of them have limited protein function annotation.
UF-HOBI at "Discharge Me!": A Hybrid Solution for Discharge Summary Generation Through Prompt-based Tuning of GatorTronGPT Models
This paper presents a hybrid solution for generating discharge summary sections as part of our participation in the "Discharge Me!"
Rateless Stochastic Coding for Delay-Constrained Semantic Communication
Based on the proposed objective, we then propose a novel JSCC coding scheme called rateless stochastic coding (RSC) by introducing a generative decoder and dithered quantization.
LP-3DGS: Learning to Prune 3D Gaussian Splatting
Recently, 3D Gaussian Splatting (3DGS) has become one of the mainstream methodologies for novel view synthesis (NVS) due to its high quality and fast rendering speed.
Accurate and efficient protein embedding using multi-teacher distillation learning
Motivation: Protein embedding, which represents proteins as numerical vectors, is a crucial step in various learning-based protein annotation/classification problems, including gene ontology prediction, protein-protein interaction prediction, and protein structure prediction.
Automatic Summarization of Doctor-Patient Encounter Dialogues Using Large Language Model through Prompt Tuning
We examined the prompt-tuning strategies, the size of soft prompts, and the few-short learning ability of GatorTronGPT, a generative clinical LLM developed using 277 billion clinical and general English words with up to 20 billion parameters.
Improving Generalizability of Extracting Social Determinants of Health Using Large Language Models through Prompt-tuning
The progress in natural language processing (NLP) using large language models (LLMs) has greatly improved patient information extraction from clinical narratives.
BAGS: Blur Agnostic Gaussian Splatting through Multi-Scale Kernel Modeling
Recent efforts in using 3D Gaussians for scene reconstruction and novel view synthesis can achieve impressive results on curated benchmarks; however, images captured in real life are often blurry.
Me LLaMA: Foundation Large Language Models for Medical Applications
This work underscores the importance of domain-specific data in developing medical LLMs and addresses the high computational costs involved in training, highlighting a balance between pre-training and fine-tuning strategies.
Aria Everyday Activities Dataset
We present Aria Everyday Activities (AEA) Dataset, an egocentric multimodal open dataset recorded using Project Aria glasses.
CARAT: Contrastive Feature Reconstruction and Aggregation for Multi-Modal Multi-Label Emotion Recognition
The challenge of MMER is how to effectively capture discriminative features for multiple labels from heterogeneous data.
Generative Large Language Models Are All-purpose Text Analytics Engines: Text-to-text Learning Is All Your Need
Objective To solve major clinical natural language processing (NLP) tasks using a unified text-to-text learning architecture based on a generative large language model (LLM) via prompt tuning.
GaitContour: Efficient Gait Recognition based on a Contour-Pose Representation
Gait recognition holds the promise to robustly identify subjects based on walking patterns instead of appearance information.
VILLS -- Video-Image Learning to Learn Semantics for Person Re-Identification
Person Re-identification is a research area with significant real world applications.
On the Impact of Cross-Domain Data on German Language Models
Traditionally, large language models have been either trained on general web crawls or domain-specific data.
Model Tuning or Prompt Tuning? A Study of Large Language Models for Clinical Concept and Relation Extraction
We evaluated the transfer learning ability of the prompt-based learning algorithms in a cross-institution setting.
Project Aria: A New Tool for Egocentric Multi-Modal AI Research
Egocentric, multi-modal data as available on future augmented reality (AR) devices provides unique challenges and opportunities for machine perception.
Distillation-guided Representation Learning for Unconstrained Gait Recognition
Gait recognition holds the promise of robustly identifying subjects based on walking patterns instead of appearance information.
Divergence Based Quadrangle and Applications
This paper introduces a novel framework for assessing risk and decision-making in the presence of uncertainty, the \emph{$\varphi$-Divergence Quadrangle}.
Knowledge-enhanced Prompt-tuning for Stance Detection
However, conducting prompt-tuning methods for stance detection in real-world remains a challenge for several reasons: (1) The text form of stance detection is usually short and informal, which makes it difficult to design label words for the verbalizer.
Machine learning enabled experimental design and parameter estimation for ultrafast spin dynamics
Advanced experimental measurements are crucial for driving theoretical developments and unveiling novel phenomena in condensed matter and material physics, which often suffer from the scarcity of facility resources and increasing complexities.
Control4D: Efficient 4D Portrait Editing with Text
We introduce Control4D, an innovative framework for editing dynamic 4D portraits using text instructions.
A Study of Generative Large Language Model for Medical Research and Healthcare
This study provides insights on the opportunities and challenges of LLMs for medical research and healthcare.
Capturing dynamical correlations using implicit neural representations
The observation and description of collective excitations in solids is a fundamental issue when seeking to understand the physics of a many-body system.
PhaBOX: A web server for identifying and characterizing phage contigs in metagenomic data
Motivation: There is accumulating evidence showing the important roles of bacteriophages (phages) in regulating the structure and functions of the microbiome.
Clinical Concept and Relation Extraction Using Prompt-based Machine Reading Comprehension
GatorTron-MRC achieves the best strict and lenient F1-scores for concept extraction, outperforming previous deep learning models on the two datasets by 1%~3% and 0. 7%~1. 3%, respectively.
Clinical Concept Extraction
Machine Reading Comprehension
+3
PhaVIP: Phage VIrion Protein classification based on chaos game representation and Vision Transformer
Thus, there is a great demand to develop a computational method for fast and accurate phage virion protein classification.
A Geometric-Relational Deep Learning Framework for BIM Object Classification
It can be supplemented using deep learning.
DA-VSR: Domain Adaptable Volumetric Super-Resolution For Medical Images
Medical image super-resolution (SR) is an active research area that has many potential applications, including reducing scan time, bettering visual understanding, increasing robustness in downstream tasks, etc.
Multi-Modal Human Authentication Using Silhouettes, Gait and RGB
In this work, we propose Dual-Modal Ensemble (DME), which combines both RGB and silhouette data to achieve more robust performances for indoor and outdoor whole-body based recognition.
Phage family classification under Caudoviricetes: a review of current tools using the latest ICTV classification framework
Therefore, a comprehensive review and comparison of taxonomic classification tools under the new standard are needed to establish the state-of-the-art.
REGAS: REspiratory-GAted Synthesis of Views for Multi-Phase CBCT Reconstruction from a single 3D CBCT Acquisition
It is a long-standing challenge to reconstruct Cone Beam Computed Tomography (CBCT) of the lung under respiratory motion.
PDRF: Progressively Deblurring Radiance Field for Fast and Robust Scene Reconstruction from Blurry Images
We present Progressively Deblurring Radiance Field (PDRF), a novel approach to efficiently reconstruct high quality radiance fields from blurry images.
Towards performant and reliable undersampled MR reconstruction via diffusion model sampling
Magnetic Resonance (MR) image reconstruction from under-sampled acquisition promises faster scanning time.
Undersampled MRI Reconstruction with Side Information-Guided Normalisation
In this paper, we investigate the use of such side information as normalisation parameters in a convolutional neural network (CNN) to improve undersampled MRI reconstruction.
HyperSegNAS: Bridging One-Shot Neural Architecture Search with 3D Medical Image Segmentation using HyperNet
Given the recent success of deep learning in medical image segmentation, Neural Architecture Search (NAS) has been introduced to find high-performance 3D segmentation network architectures.
RSBNet: One-Shot Neural Architecture Search for A Backbone Network in Remote Sensing Image Recognition
Recently, a massive number of deep learning based approaches have been successfully applied to various remote sensing image (RSI) recognition tasks.
GAN-based disentanglement learning for chest X-ray rib suppression
Clinical evidence has shown that rib-suppressed chest X-rays (CXRs) can improve the reliability of pulmonary disease diagnosis.
Inverse Aerodynamic Design of Gas Turbine Blades using Probabilistic Machine Learning
One of the critical components in Industrial Gas Turbines (IGT) is the turbine blade.
U-DuDoNet: Unpaired dual-domain network for CT metal artifact reduction
Recently, both supervised and unsupervised deep learning methods have been widely applied on the CT metal artifact reduction (MAR) task.
XraySyn: Realistic View Synthesis From a Single Radiograph Through CT Priors
A radiograph visualizes the internal anatomy of a patient through the use of X-ray, which projects 3D information onto a 2D plane.
A Multi-Task Incremental Learning Framework with Category Name Embedding for Aspect-Category Sentiment Analysis
In this paper, to make multi-task learning feasible for incremental learning, we proposed Category Name Embedding network (CNE-net).
Portfolio Optimization on Multivariate Regime Switching GARCH Model with Normal Tempered Stable Innovation
Out-of-sample tests show that the optimal portfolios with tail measures outperform the optimal portfolio with standard deviation measure and the equally weighted portfolio in various performance measures.
SAINT: Spatially Aware Interpolation NeTwork for Medical Slice Synthesis
Deep learning-based single image super-resolution (SISR) methods face various challenges when applied to 3D medical volumetric data (i. e., CT and MR images) due to the high memory cost and anisotropic resolution, which adversely affect their performance.
Ellipse R-CNN: Learning to Infer Elliptical Object from Clustering and Occlusion
We first propose a robust and compact ellipse regression based on the Mask R-CNN architecture for elliptical object detection.
Entanglement and Confinement in Coupled Quantum Systems
We also consider the coupled gauged matrix model and vector model, and argue that the deconfinement is associated with the loss of the entanglement, similarly to the previous observation for the coupled SYK model.
High Energy Physics - Theory Strongly Correlated Electrons
Idle Time Optimization for Target Assignment and Path Finding in Sortation Centers
In this paper, we study the one-shot and lifelong versions of the Target Assignment and Path Finding problem in automated sortation centers, where each agent needs to constantly assign itself a sorting station, move to its assigned station without colliding with obstacles or other agents, wait in the queue of that station to obtain a parcel for delivery, and then deliver the parcel to a sorting bin.
Unsupervised Many-to-Many Image-to-Image Translation Across Multiple Domains
To improve the image quality, we propose an effective many-to-many mapping framework for unsupervised multi-domain image-to-image translation.
Potential Field: Interpretable and Unified Representation for Trajectory Prediction
From the generated potential fields, we further estimate future motion direction and speed, which are modeled as Gaussian distributions to account for the multi-modal nature of the problem.
DG-GAN: the GAN with the duality gap
Generative Adversarial Networks (GANs) are powerful, but difficult to understand and train because GANs is a min-max problem.
Map as The Hidden Sensor: Fast Odometry-Based Global Localization
The resulting map-corrected odometry localization is able to provide an accurate belief tensor of the robot state.
Deep Slice Interpolation via Marginal Super-Resolution, Fusion and Refinement
We propose a marginal super-resolution (MSR) approach based on 2D convolutional neural networks (CNNs) for interpolating an anisotropic brain magnetic resonance scan along the highly under-sampled direction, which is assumed to axial without loss of generality.
Towards multi-sequence MR image recovery from undersampled k-space data
Undersampled MR image recovery has been widely studied for accelerated MR acquisition.
DuDoNet: Dual Domain Network for CT Metal Artifact Reduction
The linkage between the sigogram and image domains is a novel Radon inversion layer that allows the gradients to back-propagate from the image domain to the sinogram domain during training.
Generative Tensor Network Classification Model for Supervised Machine Learning
By investigating the distances in the many-body Hilbert space, we find that (a) the samples are naturally clustering in such a space; and (b) bounding the bond dimensions of the TN's to finite values corresponds to removing redundant information in the image recognition.
Quantum simulation for thermodynamics of infinite-size many-body systems by O(10) sites
In this work we propose to simulate many-body thermodynamics of infinite-size quantum lattice models in one, two, and three dimensions, in terms of few-body models of only O(10) sites, which we coin as quantum entanglement simulators (QES's).
Strongly Correlated Electrons Computational Physics Quantum Physics
Adaptive View Planning for Aerial 3D Reconstruction
We then present (i)~a method that builds a view manifold for view selection, and (ii) an algorithm to select a sparse set of views.
Machine Learning by Two-Dimensional Hierarchical Tensor Networks: A Quantum Information Theoretic Perspective on Deep Architectures
The resemblance between the methods used in studying quantum-many body physics and in machine learning has drawn considerable attention.
Machine Learning by Unitary Tensor Network of Hierarchical Tree Structure
We study the quantum features of the TN states, including quantum entanglement and fidelity.
Review of Tensor Network Contraction Approaches
One goal is to provide a systematic introduction of TN contraction algorithms (motivations, implementations, relations, implications, etc.
Computational Physics Statistical Mechanics Strongly Correlated Electrons Applied Physics Quantum Physics
A Fast Integrated Planning and Control Framework for Autonomous Driving via Imitation Learning
For safe and efficient planning and control in autonomous driving, we need a driving policy which can achieve desirable driving quality in long-term horizon with guaranteed safety and feasibility.
View Selection with Geometric Uncertainty Modeling
Consider a world point $g \in \mathcal{G}$ and its worst case reconstruction uncertainty $\varepsilon(g,\mathcal{S})$ obtained by merging \emph{all} possible views of $g$ chosen from $\mathcal{S}$.
