Search Results for author:
Found 71 papers, 19 papers with code
Efficient Skill Discovery via Regret-Aware Optimization
As an implementation, we score the degree of strength convergence with regret, and guide the skill discovery with a learnable skill generator.
MolEditRL: Structure-Preserving Molecular Editing via Discrete Diffusion and Reinforcement Learning
Molecular editing aims to modify a given molecule to optimize desired chemical properties while preserving structural similarity.
Improving Recommendation Fairness without Sensitive Attributes Using Multi-Persona LLMs
Therefore, we aim to improve recommendation fairness without any access to sensitive attributes.
LLMs as Better Recommenders with Natural Language Collaborative Signals: A Self-Assessing Retrieval Approach
To address this, we propose expressing CI directly in natural language to better align with LLMs' semantic space.
FCPCA: Fuzzy clustering of high-dimensional time series based on common principal component analysis
Clustering multivariate time series data is a crucial task in many domains, as it enables the identification of meaningful patterns and groups in time-evolving data.
OThink-MR1: Stimulating multimodal generalized reasoning capabilities via dynamic reinforcement learning
Multimodal Large Language Models (MLLMs) have gained significant traction for their ability to process diverse input data types and generate coherent, contextually relevant outputs across various applications.
Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding
Understanding long video content is a complex endeavor that often relies on densely sampled frame captions or end-to-end feature selectors, yet these techniques commonly overlook the logical relationships between textual queries and visual elements.
Enhancing Job Salary Prediction with Disentangled Composition Effect Modeling: A Neural Prototyping Approach
Despite efforts on salary prediction based on job positions and talent demographics, there still lacks methods to effectively discern the set-structured skills' intricate composition effect on job salary.
A Survey of fMRI to Image Reconstruction
Functional magnetic resonance imaging (fMRI) based image reconstruction plays a pivotal role in decoding human perception, with applications in neuroscience and brain-computer interfaces.
Biogeochemistry-Informed Neural Network (BINN) for Improving Accuracy of Model Prediction and Scientific Understanding of Soil Organic Carbon
Big data and the rapid development of artificial intelligence (AI) provide unprecedented opportunities to enhance our understanding of the global carbon cycle and other biogeochemical processes.
Decentralized Inference for Spatial Data Using Low-Rank Models
This paper presents a decentralized framework tailored for parameter inference in spatial low-rank models to address these challenges.
A Comprehensive Survey on Self-Interpretable Neural Networks
Neural networks have achieved remarkable success across various fields.
Exploring the Magnitude-Shape Plot Framework for Anomaly Detection in Crowded Video Scenes
Using its capacity to evaluate the magnitude and shape of deviations, the MS-Plot offers a statistically principled and interpretable framework for anomaly detection.
Non-Convex Tensor Recovery from Local Measurements
To solve the problem, we first propose an alternating minimization algorithm, termed \textsf{Alt-PGD-Min}, that iteratively optimizes the two factors using a projected gradient descent and an exact minimization step, respectively.
LLMs Can Simulate Standardized Patients via Agent Coevolution
Training medical personnel using standardized patients (SPs) remains a complex challenge, requiring extensive domain expertise and role-specific practice.
Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs
To address these limitations, we propose a novel self-correcting adaptive planning paradigm for KG-augmented LLM named Plan-on-Graph (PoG), which first decomposes the question into several sub-objectives and then repeats the process of adaptively exploring reasoning paths, updating memory, and reflecting on the need to self-correct erroneous reasoning paths until arriving at the answer.
The Potential of LLMs in Medical Education: Generating Questions and Answers for Qualification Exams
Recent research on large language models (LLMs) has primarily focused on their adaptation and application in specialized domains.
Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees
Personalized federated learning (PFL) offers a flexible framework for aggregating information across distributed clients with heterogeneous data.
Applying Hybrid Graph Neural Networks to Strengthen Credit Risk Analysis
This paper presents a novel approach to credit risk prediction by employing Graph Convolutional Neural Networks (GCNNs) to assess the creditworthiness of borrowers.
FreqINR: Frequency Consistency for Implicit Neural Representation with Adaptive DCT Frequency Loss
Recent advancements in local Implicit Neural Representation (INR) demonstrate its exceptional capability in handling images at various resolutions.
Unified Dual-Intent Translation for Joint Modeling of Search and Recommendation
It is therefore feasible to utilize the interaction data from both scenarios to reinforce the dual intents for joint intent-aware modeling.
Predicting Genetic Mutation from Whole Slide Images via Biomedical-Linguistic Knowledge Enhanced Multi-label Classification
(b) A knowledge association module that fuses linguistic and biomedical knowledge into gene priors by transformer-based graph representation learning, capturing the intrinsic relationships between different genes' mutations.
SpGesture: Source-Free Domain-adaptive sEMG-based Gesture Recognition with Jaccard Attentive Spiking Neural Network
This enables SpGesture to mitigate the accuracy degradation caused by distribution shifts.
Bridging the Intent Gap: Knowledge-Enhanced Visual Generation
To address these challenges, we propose a knowledge-enhanced iterative refinement framework for visual content generation.
Revisiting Noise Resilience Strategies in Gesture Recognition: Short-Term Enhancement in Surface Electromyographic Signal Analysis
We propose a Short Term Enhancement Module(STEM) which can be easily integrated with various models.
TransFusion: Covariate-Shift Robust Transfer Learning for High-Dimensional Regression
Nonasymptotic bound is provided for the estimation error of the target model, showing the robustness of the proposed method to covariate shifts.
The Effectiveness of Local Updates for Decentralized Learning under Data Heterogeneity
Specifically, for $\mu$-strongly convex and $L$-smooth loss functions, we proved that local DGT achieves communication complexity {}{$\tilde{\mathcal{O}} \Big(\frac{L}{\mu(K+1)} + \frac{\delta + {}{\mu}}{\mu (1 - \rho)} + \frac{\rho }{(1 - \rho)^2} \cdot \frac{L+ \delta}{\mu}\Big)$}, %\zhize{seems to be $\tilde{\mathcal{O}}$} {where $K$ is the number of additional local update}, $\rho$ measures the network connectivity and $\delta$ measures the second-order heterogeneity of the local losses.
AdaTrans: Feature-wise and Sample-wise Adaptive Transfer Learning for High-dimensional Regression
We consider the transfer learning problem in the high dimensional linear regression setting, where the feature dimension is larger than the sample size.
SGD with Partial Hessian for Deep Neural Networks Optimization
Compared with first-order optimizers, it adopts a certain amount of information from the Hessian matrix to assist optimization, while compared with the existing second-order optimizers, it keeps the good generalization performance of first-order optimizers.
Fuzzy clustering of circular time series based on a new dependence measure with applications to wind data
Time series clustering is an essential machine learning task with applications in many disciplines.
Team I2R-VI-FF Technical Report on EPIC-KITCHENS VISOR Hand Object Segmentation Challenge 2023
In this report, we present our approach to the EPIC-KITCHENS VISOR Hand Object Segmentation Challenge, which focuses on the estimation of the relation between the hands and the objects given a single frame as input.
Towards Faithful Neural Network Intrinsic Interpretation with Shapley Additive Self-Attribution
Self-interpreting neural networks have garnered significant interest in research.
Keyword-Aware Relative Spatio-Temporal Graph Networks for Video Question Answering
The main challenge in video question answering (VideoQA) is to capture and understand the complex spatial and temporal relations between objects based on given questions.
Bivariate DeepKriging for Large-scale Spatial Interpolation of Wind Fields
Large-scale spatial interpolation or downscaling of bivariate wind fields having velocity in two dimensions is a challenging task because wind data tend to be non-Gaussian with high spatial variability and heterogeneity.
A Study on Differentiable Logic and LLMs for EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2023
Our research focuses on the innovative application of a differentiable logic loss in the training to leverage the co-occurrence relations between verb and noun, as well as the pre-trained Large Language Models (LLMs) to generate the logic rules for the adaptation to unseen action labels.
A Comprehensive Survey of Artificial Intelligence Techniques for Talent Analytics
To this end, we present an up-to-date and comprehensive survey on AI technologies used for talent analytics in the field of human resource management.
Training-free Object Counting with Prompts
However, the vanilla mask generation method of SAM lacks class-specific information in the masks, resulting in inferior counting accuracy.
Ranked #1 on
Object Counting
on PASCAL VOC
Efficient Large-scale Nonstationary Spatial Covariance Function Estimation Using Convolutional Neural Networks
Fitting a Gaussian process with a nonstationary Mat\'ern covariance is challenging.
Spatio-temporal DeepKriging for Interpolation and Probabilistic Forecasting
Gaussian processes (GP) and Kriging are widely used in traditional spatio-temporal mod-elling and prediction.
Meta Compositional Referring Expression Segmentation
Then, following a novel meta optimization scheme to optimize the model to obtain good testing performance on the virtual testing sets after training on the virtual training set, our framework can effectively drive the model to better capture semantics and visual representations of individual concepts, and thus obtain robust generalization performance even when handling novel compositions.
Domain-knowledge Inspired Pseudo Supervision (DIPS) for Unsupervised Image-to-Image Translation Models to Support Cross-Domain Classification
Cross-domain classification frameworks were developed to handle this data domain shift problem by utilizing unsupervised image-to-image translation models to translate an input image from the unlabeled domain to the labeled domain.
Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022
In this report, we present the technical details of our submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation (UDA) Challenge for Action Recognition 2022.
A General Regret Bound of Preconditioned Gradient Method for DNN Training
Though the full-matrix preconditioned gradient methods theoretically have a lower regret bound, they are impractical for use to train DNNs because of the high complexity.
A Framework for Generalizing Critical Heat Flux Detection Models Using Unsupervised Image-to-Image Translation
To deal with datasets from new domains a model needs to be trained from scratch.
Learning to Learn: How to Continuously Teach Humans and Machines
For example, when we learn mathematics at school, we build upon our knowledge of addition to learn multiplication.
Unveiling the Tapestry: the Interplay of Generalization and Forgetting in Continual Learning
In AI, generalization refers to a model's ability to perform well on out-of-distribution data related to the given task, beyond the data it was trained on.
Classifications of Single-input Lower Triangular Forms
It is verified that the type that a given lower triangular form belongs to is invariant under any lower triangular coordinate transformation.
Monitoring Vegetation From Space at Extremely Fine Resolutions via Coarsely-Supervised Smooth U-Net
This poses a challenging coarsely-supervised regression (or downscaling) task; at training time, we only have SIF labels at a coarse resolution (3km), but we want to predict SIF at much finer spatial resolutions (e. g. 30m, a 100x increase).
Tackling Data Heterogeneity: A New Unified Framework for Decentralized SGD with Sample-induced Topology
We develop a general framework unifying several gradient-based stochastic optimization methods for empirical risk minimization problems both in centralized and distributed scenarios.
Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2021
Based on an existing method for video domain adaptation, i. e., TA3N, we propose to learn hand-centric features by leveraging the hand bounding box information for UDA on fine-grained action recognition.
TAILOR: Teaching with Active and Incremental Learning for Object Registration
When deploying a robot to a new task, one often has to train it to detect novel objects, which is time-consuming and labor-intensive.
Three-Dimensional Segmentation of the Left Ventricle in Late Gadolinium Enhanced MR Images of Chronic Infarction Combining Long- and Short-Axis Information
We have also tested the robustness of the framework with respect to varied a priori segmentation in both practical and simulated settings.
A Comprehensive 3-D Framework for Automatic Quantification of Late Gadolinium Enhanced Cardiac Magnetic Resonance Images
To achieve accurate quantification, LGE CMR images need to be processed in two steps: segmentation of the myocardium followed by classification of infarcts within the segmented myocardium.
Myocardial Segmentation of Late Gadolinium Enhanced MR Images by Propagation of Contours from Cine MR Images
Automatic segmentation of myocardium in Late Gadolinium Enhanced (LGE) Cardiac MR (CMR) images is often difficult due to the intensity heterogeneity resulting from accumulation of contrast agent in infarcted areas.
Bone marrow sparing for cervical cancer radiotherapy on multimodality medical images
Experiments on patient dataset reveal that our proposed method can enhance the multimodal image registration accuracy and efficiency for medical practitioners in sparing BM of cervical cancer radiotherapy.
Decentralized Sparse Linear Regression via Gradient-Tracking: Linear Convergence and Statistical Guarantees
Our theory shows that, under standard notions of restricted strong convexity and smoothness of the loss functions, suitable conditions on the network connectivity and algorithm tuning, the distributed algorithm converges globally at a {\it linear} rate to an estimate that is within the centralized {\it statistical precision} of the model, $O(s\log d/N)$.
Self-Supervised Global-Local Structure Modeling for Point Cloud Domain Adaptation With Reliable Voted Pseudo Labels
In this paper, we propose an unsupervised domain adaptation method for deep point cloud representation learning.
Discerning Decision-Making Process of Deep Neural Networks with Hierarchical Voting Transformation
To this end, in this paper, we aim to discern the decision-making processes of neural networks through a hierarchical voting strategy by developing an explainable deep learning model, namely Voting Transformation-based Explainable Neural Network (VOTEN).
FashionSearchNet-v2: Learning Attribute Representations with Localization for Image Retrieval with Attribute Manipulation
A key challenge in e-commerce is that images have multiple attributes where users would like to manipulate and it is important to estimate discriminative feature representations for each of these attributes.
Distributed Sparse Regression via Penalization
First, we establish statistical consistency of the estimator: under a suitable choice of the penalty parameter, the optimal solution of the penalized problem achieves near optimal minimax rate $\mathcal{O}(s \log d/N)$ in $\ell_2$-loss, where $s$ is the sparsity value, $d$ is the ambient dimension, and $N$ is the total sample size in the network -- this matches centralized sample rates.
Hybrid Local SGD for Federated Learning with Heterogeneous Communications
Communication is a key bottleneck in federated learning where a large number of edge devices collaboratively learn a model under the orchestration of a central server without sharing their own training data.
Learning to Warm Up Cold Item Embeddings for Cold-start Recommendation with Meta Scaling and Shifting Networks
The cold item ID embedding has two main problems: (1) A gap is existing between the cold ID embedding and the deep model.
Using BART to Perform Pareto Optimization and Quantify its Uncertainties
This article proposes Pareto Front (PF) and Pareto Set (PS) estimation methods using Bayesian Additive Regression Trees (BART), which is a non-parametric model whose assumptions are typically less restrictive than popular alternatives, such as Gaussian Processes (GPs).
DeepKriging: Spatially Dependent Deep Neural Networks for Spatial Prediction
Kriging provides the best linear unbiased predictor using covariance functions and is often associated with Gaussian processes.
Accelerated Primal-Dual Algorithms for Distributed Smooth Convex Optimization over Networks
This paper proposes a novel family of primal-dual-based distributed algorithms for smooth, convex, multi-agent optimization over networks that uses only gradient information and gossip communications.
A Semi-Parametric Estimation Method for the Quantile Spectrum with an Application to Earthquake Classification Using Convolutional Neural Network
At each quantile level, we approximate the quantile spectrum by a function in the form of an ordinary AR spectrum.
Methodology Applications
6D Pose Estimation with Correlation Fusion
To our best knowledge, this is the first work to explore effective intra- and inter-modality fusion in 6D pose estimation.
Decentralized Dictionary Learning Over Time-Varying Digraphs
This paper studies Dictionary Learning problems wherein the learning task is distributed over a multi-agent network, modeled as a time-varying directed graph.
Likelihood Approximation With Hierarchical Matrices For Large Spatial Datasets
We use available measurements to estimate the unknown parameters (variance, smoothness parameter, and covariance length) of a covariance function by maximizing the joint Gaussian log-likelihood function.
Computation 62F99, 62P12, 62M30 G.3; G.4; J.2
Orthogonal Sparse PCA and Covariance Estimation via Procrustes Reformulation
In addition, we propose a method to improve the covariance estimation problem when its underlying eigenvectors are known to be sparse.
Robust Estimation of Structured Covariance Matrix for Heavy-Tailed Elliptical Distributions
This paper considers the problem of robustly estimating a structured covariance matrix with an elliptical underlying distribution with known mean.
