Search Results for author:
Found 56 papers, 13 papers with code
Model-Agnostic Characterization of Fairness Trade-offs
There exist several inherent trade-offs while designing a fair model, such as those between the model’s predictive accuracy and fairness, or even among different notions of fairness.
Make-A-Character 2: Animatable 3D Character Generation From a Single Image
This report introduces Make-A-Character 2, an advanced system for generating high-quality 3D characters from single portrait photographs, ideal for game development and digital human applications.
Interpretable Enzyme Function Prediction via Residue-Level Detection
It uses a set of learnable functional queries to adaptatively extract different local representations from the sequence of residue-level features for predicting different EC numbers.
AEIOU: A Unified Defense Framework against NSFW Prompts in Text-to-Image Models
As text-to-image (T2I) models continue to advance and gain widespread adoption, their associated safety issues are becoming increasingly prominent.
NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentation
Neural Radiance Field (NeRF) has been widely recognized for its excellence in novel view synthesis and 3D scene reconstruction.
OS-FPI: A Coarse-to-Fine One-Stream Network for UAV Geo-Localization
Furthermore, its performance in meter-level localization accuracy is impressive, with 182. 62% improvement in 3-meter accuracy, 164. 17% improvement in 5-meter accuracy, and 137. 43% improvement in 10-meter accuracy.
G4G:A Generic Framework for High Fidelity Talking Face Generation with Fine-grained Intra-modal Alignment
Despite numerous completed studies, achieving high fidelity talking face generation with highly synchronized lip movements corresponding to arbitrary audio remains a significant challenge in the field.
Domain-adaptive and Subgroup-specific Cascaded Temperature Regression for Out-of-distribution Calibration
Although deep neural networks yield high classification accuracy given sufficient training data, their predictions are typically overconfident or under-confident, i. e., the prediction confidences cannot truly reflect the accuracy.
Make-A-Character: High Quality Text-to-3D Character Generation within Minutes
There is a growing demand for customized and expressive 3D characters with the emergence of AI agents and Metaverse, but creating 3D characters using traditional computer graphics tools is a complex and time-consuming task.
Facial Data Minimization: Shallow Model as Your Privacy Filter
Face recognition service has been used in many fields and brings much convenience to people.
Analysis of frequent trading effects of various machine learning models
This study aims to develop an advanced high-frequency trading algorithm and compare the performance of three different mathematical models: the combination of the cross-entropy loss function and the quasi-Newton algorithm, the FCNN model, and the vector machine.
Universal Defensive Underpainting Patch: Making Your Text Invisible to Optical Character Recognition
In this work, we propose a novel and effective defense mechanism termed the Universal Defensive Underpainting Patch (UDUP) that modifies the underpainting of text images instead of the characters.
Optical Character Recognition
Optical Character Recognition (OCR)
Atomic and Subgraph-aware Bilateral Aggregation for Molecular Representation Learning
In this paper, we introduce a new model for molecular representation learning called the Atomic and Subgraph-aware Bilateral Aggregation (ASBA), which addresses the limitations of previous atom-wise and subgraph-wise models by incorporating both types of information.
Toward Auto-evaluation with Confidence-based Category Relation-aware Regression
Auto-evaluation aims to automatically evaluate a trained model on any test dataset without human annotations.
Transfer Knowledge from Head to Tail: Uncertainty Calibration under Long-tailed Distribution
We adaptively transfer knowledge from head classes to get the target probability density of tail classes.
Enhancing Deep Knowledge Tracing with Auxiliary Tasks
In this paper, we proposed \emph{AT-DKT} to improve the prediction performance of the original deep knowledge tracing model with two auxiliary learning tasks, i. e., \emph{question tagging (QT) prediction task} and \emph{individualized prior knowledge (IK) prediction task}.
Improving Interpretability of Deep Sequential Knowledge Tracing Models with Question-centric Cognitive Representations
The results demonstrate that our approach is superior on the KT prediction task, and it outperforms a wide range of deep learning based KT models in terms of prediction accuracy with better model interpretability.
simpleKT: A Simple But Tough-to-Beat Baseline for Knowledge Tracing
Knowledge tracing (KT) is the problem of predicting students' future performance based on their historical interactions with intelligent tutoring systems.
Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity
In this paper, we first demonstrate that simply querying for fairness metrics, such as statistical parity and equalized odds can leak the protected attributes of individuals to the model developers.
Drone Referring Localization: An Efficient Heterogeneous Spatial Feature Interaction Method For UAV Self-Localization
However, IR-based methods face several challenges: 1) Pre- and post-processing incur significant computational and storage overhead; 2) The lack of interaction between dual-source features impairs precise spatial perception.
Differentially Private Counterfactuals via Functional Mechanism
Counterfactual, serving as one emerging type of model explanation, has attracted tons of attentions recently from both industry and academia.
Wide & Deep Learning for Judging Student Performance in Online One-on-one Math Classes
In this paper, we investigate the opportunities of automating the judgment process in online one-on-one math classes.
Detecting and Recovering Adversarial Examples from Extracting Non-robust and Highly Predictive Adversarial Perturbations
Experimental results show that the proposed method can not only detect the adversarial examples with high accuracy, but also detect the specific category of the AEs.
Dryland evapotranspiration from remote sensing solar-induced chlorophyll fluorescence: constraining an optimal stomatal model within a two-source energy balance model
For the CSIF model, the average R2 for ET estimates also improved when including the effect of soil moisture: from 0. 65 (0. 79) to 0. 71 (0. 84), with RMSE ranging between 0. 023 (0. 22) and 0. 043 (0. 54) mm depending on the site.
Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Tale
We further show that MinDiff optimization is very sensitive to choice of batch size in the under-parameterized regime.
SC-Ques: A Sentence Completion Question Dataset for English as a Second Language Learners
Sentence completion (SC) questions present a sentence with one or more blanks that need to be filled in, three to five possible words or phrases as options.
DialogID: A Dialogic Instruction Dataset for Improving Teaching Effectiveness in Online Environments
In spite of the popularity and advantages of online learning, the education technology and educational data mining communities still suffer from the lack of large-scale, high-quality, and well-annotated teaching instruction datasets to study computational approaches to automatically detect online dialogic instructions and further improve the online teaching effectiveness.
A Design of A Simple Yet Effective Exercise Recommendation System in K-12 Online Learning
We propose a simple but effective method to recommend exercises with high quality and diversity for students.
pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing Models
However, the success behind deep learning based knowledge tracing (DLKT) approaches is still left somewhat unknown and proper measurement and analysis of these DLKT approaches remain a challenge.
Residual-Guided Non-Intrusive Speech Quality Assessment
We generate an enhanced speech on the impaired speech to compensate for the absence of the reference audio, then pair the information of residuals with the impaired speech.
The four-fifths rule is not disparate impact: a woeful tale of epistemic trespassing in algorithmic fairness
Computer scientists are trained to create abstractions that simplify and generalize.
Are My Deep Learning Systems Fair? An Empirical Study of Fixed-Seed Training
Our study of 22 mitigation techniques and five baselines reveals up to 12. 6% fairness variance across identical training runs with identical seeds.
On the Current and Emerging Challenges of Developing Fair and Ethical AI Solutions in Financial Services
Artificial intelligence (AI) continues to find more numerous and more critical applications in the financial services industry, giving rise to fair and ethical AI as an industry-wide objective.
Sample-specific and Context-aware Augmentation for Long Tail Image Classification
We apply STG to samples of tail classes for augmentation in the classifier-tuning stage.
Seven challenges for harmonizing explainability requirements
Regulators have signalled an interest in adopting explainable AI(XAI) techniques to handle the diverse needs for model governance, operational servicing, and compliance in the financial services industry.
Ontology drift is a challenge for explainable data governance
We introduce the needs for explainable AI that arise from Standard No.
Beyond Fairness Metrics: Roadblocks and Challenges for Ethical AI in Practice
We review practical challenges in building and deploying ethical AI at the scale of contemporary industrial and societal uses.
An Educational System for Personalized Teacher Recommendation in K-12 Online Classrooms
In this paper, we propose a simple yet effective solution to build practical teacher recommender systems for online one-on-one classes.
Counterfactual Explanations for Arbitrary Regression Models
We present a new method for counterfactual explanations (CFEs) based on Bayesian optimisation that applies to both classification and regression models.
Model-Based Counterfactual Synthesizer for Interpretation
To address these limitations, we propose a Model-based Counterfactual Synthesizer (MCS) framework for interpreting machine learning models.
Time Series Counterfactual Inference with Hidden Confounders
We present augmented counterfactual ordinary differential equations (ACODEs), a new approach to counterfactual inference on time series data with a focus on healthcare applications.
Provable Multi-Objective Reinforcement Learning with Generative Models
Multi-objective reinforcement learning (MORL) is an extension of ordinary, single-objective reinforcement learning (RL) that is applicable to many real-world tasks where multiple objectives exist without known relative costs.
Debiasing classifiers: is reality at variance with expectation?
We present an empirical study of debiasing methods for classifiers, showing that debiasers often fail in practice to generalize out-of-sample, and can in fact make fairness worse rather than better.
Towards Self-Regulating AI: Challenges and Opportunities of AI Model Governance in Financial Services
As a part of the outlook, we present a system-level framework towards increased self-regulation for robustness and compliance.
Paying down metadata debt: learning the representation of concepts using topic models
We introduce a data management problem called metadata debt, to identify the mapping between data concepts and their logical representations.
CryptoCredit: Securely Training Fair Models
When developing models for regulated decision making, sensitive features like age, race and gender cannot be used and must be obscured from model developers to prevent bias.
3D Correspondence Grouping with Compatibility Features
We present a simple yet effective method for 3D correspondence grouping.
Half-skyrmions and Bimerons in an antiferromagnetic insulator at room temperature
In the quest for post-CMOS technologies, ferromagnetic skyrmions and their anti-particles have shown great promise as topologically protected solitonic information carriers in memory-in-logic or neuromorphic devices.
Materials Science
Neural Multi-Task Learning for Teacher Question Detection in Online Classrooms
Asking questions is one of the most crucial pedagogical techniques used by teachers in class.
SiBert: Enhanced Chinese Pre-trained Language Model with Sentence Insertion
However, some studies show that customized self-supervised tasks for a particular type of downstream task can effectively help the pre-trained model to capture more corresponding knowledge and semantic information.
Heuristics for Link Prediction in Multiplex Networks
Through experiments with simulated and real world scientific collaboration, transportation and global trade networks, we demonstrate that the proposed heuristics show increased performance with the richness of connection type correlation structure and significantly outperform their baseline heuristics for ordinary networks with a single connection type.
FACT: A Diagnostic for Group Fairness Trade-offs
Group fairness, a class of fairness notions that measure how different groups of individuals are treated differently according to their protected attributes, has been shown to conflict with one another, often with a necessary cost in loss of model's predictive performance.
A Multimodal Alerting System for Online Class Quality Assurance
To warn the unqualified instructors and ensure the overall education quality, we build a monitoring and alerting system by utilizing multimodal information from the online environment.
Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobserved
We also propose an alternative weighted estimator that uses soft classification, and show that its bias arises simply from the conditional covariance of the outcome with the true class membership.
Fair lending needs explainable models for responsible recommendation
The financial services industry has unique explainability and fairness challenges arising from compliance and ethical considerations in credit decisioning.
Fast Flexible Function Dispatch in Julia
Technical computing is a challenging application area for programming languages to address.
