Search Results for author:
Found 58 papers, 17 papers with code
General-Purpose Aerial Intelligent Agents Empowered by Large Language Models
The emergence of large language models (LLMs) opens new frontiers for unmanned aerial vehicle (UAVs), yet existing systems remain confined to predefined tasks due to hardware-software co-design challenges.
Rapid morphology characterization of two-dimensional TMDs and lateral heterostructures based on deep learning
Two-dimensional (2D) materials and heterostructures exhibit unique physical properties, necessitating efficient and accurate characterization methods.
UIFace: Unleashing Inherent Model Capabilities to Enhance Intra-Class Diversity in Synthetic Face Recognition
While existing synthetic-based face recognition methods have made significant progress in generating identity-preserving images, they are severely plagued by context overfitting, resulting in a lack of intra-class diversity of generated images and poor face recognition performance.
Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrative
While many advances in time series models focus exclusively on numerical data, research on multimodal time series, particularly those involving contextual textual information commonly encountered in real-world scenarios, remains in its infancy.
MADE: Graph Backdoor Defense with Masked Unlearning
Graph Neural Networks (GNNs) have garnered significant attention from researchers due to their outstanding performance in handling graph-related tasks, such as social network analysis, protein design, and so on.
Commitment and Randomization in Communication
In other words, commitment has no value if and only if a partitional experiment is optimal under commitment.
MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer
However, zero-shot generalization diminishes with the increase in the number of specialized parameters, making existing works a trade-off between zero-shot and close-set performance.
BACKTIME: Backdoor Attacks on Multivariate Time Series Forecasting
Multivariate Time Series (MTS) forecasting is a fundamental task with numerous real-world applications, such as transportation, climate, and epidemiology.
Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomy
The framework of IL consists of three primary components: a neural module, a reasoning engine, and a memory system.
SAM-LAD: Segment Anything Model Meets Zero-Shot Logic Anomaly Detection
Each object mask is multiplied with the entire image's feature map to obtain object feature maps.
Ranked #6 on
Anomaly Detection
on MVTec LOCO AD
Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation
(2) The second design is a Geometric-Aware Feature Aggregation module, which can efficiently integrate the local and global geometric information into keypoint features.
Task-Agnostic Detector for Insertion-Based Backdoor Attacks
Textual backdoor attacks pose significant security threats.
CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledge
Inspired by this motivation, we propose CLIPose, a novel 6D pose framework that employs the pre-trained vision-language model to develop better learning of object category information, which can fully leverage abundant semantic knowledge in image and text modalities.
Hybridnet for depth estimation and semantic segmentation
Semantic segmentation and depth estimation are two important tasks in the area of image processing.
RHOBIN Challenge: Reconstruction of Human Object Interaction
Modeling the interaction between humans and objects has been an emerging research direction in recent years.
Human Body Model based ID using Shape and Pose Parameters
We show that when our HMID network is trained using additional shape and pose losses, it shows a significant improvement in biometric identification performance when compared to an identical model that does not use such losses.
TransPose: 6D Object Pose Estimation with Geometry-Aware Transformer
To improve robustness to occlusion, we adopt Transformer to perform the exchange of global information, making each local feature contains global information.
Confidence Calibration for Systems with Cascaded Predictive Modules
Existing conformal prediction algorithms estimate prediction intervals at target confidence levels to characterize the performance of a regression model on new test samples.
SayNav: Grounding Large Language Models for Dynamic Planning to Navigation in New Environments
We evaluate SayNav on multi-object navigation (MultiON) task, that requires the agent to utilize a massive amount of human knowledge to efficiently search multiple different objects in an unknown environment.
Fine-Grained Spatiotemporal Motion Alignment for Contrastive Video Representation Learning
As the most essential property in a video, motion information is critical to a robust and generalized video representation.
Discrete Conditional Diffusion for Reranking in Recommendation
To overcome these challenges, we propose a novel Discrete Conditional Diffusion Reranking (DCDR) framework for recommendation.
TIJO: Trigger Inversion with Joint Optimization for Defending Multimodal Backdoored Models
We present a Multimodal Backdoor Defense technique TIJO (Trigger Inversion using Joint Optimization).
BeMap: Balanced Message Passing for Fair Graph Neural Network
Fairness in graph neural networks has been actively studied recently.
Tree based Progressive Regression Model for Watch-Time Prediction in Short-video Recommendation
An accurate prediction of watch time has been of vital importance to enhance user engagement in video recommender systems.
Efficient and Accurate Calibration to FX Market Skew with Fully Parameterized Local Volatility Model
When trading American and Asian options in the FX derivatives market, banks must calculate prices using a complex mathematical model.
Online Changepoint Detection on a Budget
In this paper, we are interested in changepoint detection algorithms which operate in an online setting in the sense that both its storage requirements and worst-case computational complexity per observation are independent of the number of previous observations.
Trigger Hunting with a Topological Prior for Trojan Detection
Despite their success and popularity, deep neural networks (DNNs) are vulnerable when facing backdoor attacks.
Improving Users' Mental Model with Attention-directed Counterfactual Edits
In the domain of Visual Question Answering (VQA), studies have shown improvement in users' mental model of the VQA system when they are exposed to examples of how these systems answer certain Image-Question (IQ) pairs.
Robust Aggregation of Correlated Information
In general decision problems, robustly optimal strategies combine multiple sources of information, but the number of information sources that are needed has a bound that only depends on the decision problem.
Modular Adaptation for Cross-Domain Few-Shot Learning
Adapting pre-trained representations has become the go-to recipe for learning new downstream tasks with limited examples.
Confidence Calibration for Domain Generalization under Covariate Shift
Existing calibration algorithms address the problem of covariate shift via unsupervised domain adaptation.
Generating and Evaluating Explanations of Attended and Error-Inducing Input Regions for VQA Models
Hence, we propose Error Maps that clarify the error by highlighting image regions where the model is prone to err.
Surface Dyakonov-Cherenkov Radiation
Recent advances in engineered material technologies (e. g., photonic crystals, metamaterials, plasmonics, etc) provide valuable tools to control Cherenkov radiation.
Optics
Hybrid Consistency Training with Prototype Adaptation for Few-Shot Learning
Few-Shot Learning (FSL) aims to improve a model's generalization capability in low data regimes.
How to Sell Hard Information
The seller of an asset has the option to buy hard information about the value of the asset from an intermediary.
The Impact of Explanations on AI Competency Prediction in VQA
In this paper, we evaluate the impact of explanations on the user's mental model of AI agent competency within the task of visual question answering (VQA).
Semi-supervised Collaborative Filtering by Text-enhanced Domain Adaptation
This causes two difficulties in designing effective algorithms: first, the majority of users only have a few interactions with the system and there is no enough data for learning; second, there are no negative samples in the implicit feedbacks and it is a common practice to perform negative sampling to generate negative samples.
A Data-Efficient Mutual Information Neural Estimator for Statistical Dependency Testing
Measuring Mutual Information (MI) between high-dimensional, continuous, random variables from observed samples has wide theoretical and practical applications.
Image Classification with Hierarchical Multigraph Networks
Graph Convolutional Networks (GCNs) are a class of general models that can learn from graph structured data.
Data-Efficient Mutual Information Neural Estimator
We demonstrate the effectiveness of our estimators on synthetic benchmarks and a real world fMRI data, with application of inter-subject correlation analysis.
Integrating Text and Image: Determining Multimodal Document Intent in Instagram Posts
Computing author intent from multimodal data like Instagram posts requires modeling a complex relationship between text and image.
Graph based Dynamic Segmentation of Generic Objects in 3D
We propose a novel 3D segmentation method for RBGD stream data to deal with 3D object segmentation task in a generic scenario with frequent object interactions.
Personalized Re-ranking for Recommendation
Ranking is a core task in recommender systems, which aims at providing an ordered list of items to users.
BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
To address this problem, we train the bidirectional model using the Cloze task, predicting the masked items in the sequence by jointly conditioning on their left and right context.
Ranked #3 on
Recommendation Systems
on MovieLens 1M
(HR@10 (full corpus) metric)
Value-aware Recommendation based on Reinforced Profit Maximization in E-commerce Systems
Existing recommendation algorithms mostly focus on optimizing traditional recommendation measures, such as the accuracy of rating prediction in terms of RMSE or the quality of top-$k$ recommendation lists in terms of precision, recall, MAP, etc.
Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules
Spectral Graph Convolutional Networks (GCNs) are a generalization of convolutional networks to learning on graph-structured data.
Ranked #19 on
Graph Classification
on NCI109
Human Motion Modeling using DVGANs
We present a novel generative model for human motion modeling using Generative Adversarial Networks (GANs).
Online Compact Convexified Factorization Machine
To address this subsequent challenge, we follow the general projection-free algorithmic framework of Online Conditional Gradient and propose an Online Compact Convex Factorization Machine (OCCFM) algorithm that eschews the projection operation with efficient linear optimization steps.
An Approximate Bayesian Long Short-Term Memory Algorithm for Outlier Detection
In this study, we propose an approximate estimation of the weights uncertainty using Ensemble Kalman Filter, which is easily scalable to a large number of weights.
Active Learning for Visual Question Answering: An Empirical Study
We present an empirical study of active learning for Visual Question Answering, where a deep VQA model selects informative question-image pairs from a pool and queries an oracle for answers to maximally improve its performance under a limited query budget.
EnLLVM: Ensemble Based Nonlinear Bayesian Filtering Using Linear Latent Variable Models
Real-time nonlinear Bayesian filtering algorithms are overwhelmed by data volume, velocity and increasing complexity of computational models.
Approximate Computational Approaches for Bayesian Sensor Placement in High Dimensions
Then, sensors are placed where highest mutual information (lower bound) is achieved and QoI is inferred via Bayes rule given sensor measurements.
The Zero-Coupon Rate Model for Derivatives Pricing
The aim of this paper is to present a dual-term structure model of interest rate derivatives in order to solve the two hardest problems in financial modeling: the exact volatility calibration of the entire swaption matrix, and the calculation of bucket vegas for structured products.
Leveraging Visual Question Answering for Image-Caption Ranking
This allows the model to interpret images and captions from a wide variety of perspectives.
Learning Common Sense Through Visual Abstraction
We show that the commonsense knowledge we learn is complementary to what can be learnt from sources of text.
Don't Just Listen, Use Your Imagination: Leveraging Visual Common Sense for Non-Visual Tasks
But much of common sense knowledge is unwritten - partly because it tends not to be interesting enough to talk about, and partly because some common sense is unnatural to articulate in text.
Combining the Best of Graphical Models and ConvNets for Semantic Segmentation
We present a two-module approach to semantic segmentation that incorporates Convolutional Networks (CNNs) and Graphical Models.
