Search Results for author:
Found 75 papers, 34 papers with code
Essay Quality Signals as Weak Supervision for Source-based Essay Scoring
However, because AES typically uses supervised machine learning, a human-graded essay corpus is still required to train the AES model.
A Literature Review on Simulation in Conversational Recommender Systems
Conversational Recommender Systems (CRSs) have garnered attention as a novel approach to delivering personalized recommendations through multi-turn dialogues.
MedPAIR: Measuring Physicians and AI Relevance Alignment in Medical Question Answering
We compare these relevance estimates to those for LLMs, and further evaluate the impact of these "relevant" subsets on downstream task performance for both physician trainees and LLMs.
Connecting the Dots: A Chain-of-Collaboration Prompting Framework for LLM Agents
To address these challenges, we propose Cochain, a collaboration prompting framework that effectively solves business workflow collaboration problem by combining knowledge and prompts at a reduced cost.
Towards Optimal Heterogeneous Client Sampling in Multi-Model Federated Learning
In this work, we develop a novel convergence analysis of MMFL with arbitrary client sampling methods, theoretically demonstrating the strengths and limitations of previous well-established gradient-based methods.
Cross-Asset Risk Management: Integrating LLMs for Real-Time Monitoring of Equity, Fixed Income, and Currency Markets
Large language models (LLMs) have emerged as powerful tools in the field of finance, particularly for risk management across different asset classes.
Dynamic Hedging Strategies in Derivatives Markets with LLM-Driven Sentiment and News Analytics
Dynamic hedging strategies are essential for effective risk management in derivatives markets, where volatility and market sentiment can greatly impact performance.
Machine Learning for Health symposium 2024 -- Findings track
Works could be submitted to either the archival Proceedings track, or the non-archival Findings track.
Global Estimation of Building-Integrated Facade and Rooftop Photovoltaic Potential by Integrating 3D Building Footprint and Spatio-Temporal Datasets
This research tackles the challenges of estimating Building-Integrated Photovoltaics (BIPV) potential across various temporal and spatial scales, accounting for different geographical climates and urban morphology.
Towards Vision Mixture of Experts for Wildlife Monitoring on the Edge
Such proposed approaches should ideally process multiple types of data, including time series, audio, satellite images, and video, near the network edge as multiple data streams has been shown to improve the discriminative ability of learning algorithms, especially for generating fine grained results.
From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $α$-NeuS
We find that transparent and opaque surfaces align with the non-negative local minima and the zero iso-surface, respectively, in the learned distance field of NeuS.
BendVLM: Test-Time Debiasing of Vision-Language Embeddings
Vision-language model (VLM) embeddings have been shown to encode biases present in their training data, such as societal biases that prescribe negative characteristics to members of various racial and gender identities.
Identifying Implicit Social Biases in Vision-Language Models
Finally, we conduct an analysis of the source of such biases, by showing that the same harmful stereotypes are also present in a large image-text dataset used to train CLIP models for examples of biases that we find.
ING-VP: MLLMs cannot Play Easy Vision-based Games Yet
To bridge this gap, we present ING-VP, the first INteractive Game-based Vision Planning benchmark, specifically designed to evaluate the spatial imagination and multi-step reasoning abilities of MLLMs.
CLSP: High-Fidelity Contrastive Language-State Pre-training for Agent State Representation
Then, we deploy contrastive learning to train the CLSP encoder to effectively represent precise state information.
PromptTA: Prompt-driven Text Adapter for Source-free Domain Generalization
In this work, we propose Prompt-Driven Text Adapter (PromptTA) method, which is designed to better capture the distribution of style features and employ resampling to ensure thorough coverage of domain knowledge.
Single-View 3D Reconstruction via SO(2)-Equivariant Gaussian Sculpting Networks
This paper introduces SO(2)-Equivariant Gaussian Sculpting Networks (GSNs) as an approach for SO(2)-Equivariant 3D object reconstruction from single-view image observations.
Curriculum Prompting Foundation Models for Medical Image Segmentation
Adapting large pre-trained foundation models, e. g., SAM, for medical image segmentation remains a significant challenge.
NP-TCMtarget: a network pharmacology platform for exploring mechanisms of action of Traditional Chinese medicine
Finally, we can distinguish TCM direct and indirect targets by comparing the effect targets and binding targets to establish the action pathways of herbal components-direct targets-indirect targets by mapping TCM targets in the biological molecular network.
AutoPV: Automatically Design Your Photovoltaic Power Forecasting Model
We develop a brand new NAS search space that incorporates various data processing techniques from state-of-the-art (SOTA) TSF models and typical PVPF deep learning models.
LEMoN: Label Error Detection using Multimodal Neighbors
Our method leverages the multimodal neighborhood of image-caption pairs in the latent space of contrastively pretrained multimodal models to automatically identify label errors.
A Cross Spatio-Temporal Pathology-based Lung Nodule Dataset
Recently, intelligent analysis of lung nodules with the assistant of computer aided detection (CAD) techniques can improve the accuracy rate of lung cancer diagnosis.
Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation
Despite the growing popularity of methods which learn from unlabeled data, the extent to which these representations rely on spurious features for prediction is unclear.
Multimodal Information Interaction for Medical Image Segmentation
To address this issue, we introduce an innovative Multimodal Information Cross Transformer (MicFormer), which employs a dual-stream architecture to simultaneously extract features from each modality.
Fair Concurrent Training of Multiple Models in Federated Learning
We show how our fairness-based learning and incentive mechanisms impact training convergence and finally evaluate our algorithm with multiple sets of learning tasks on real world datasets.
A Phone-based Distributed Ambient Temperature Measurement System with An Efficient Label-free Automated Training Strategy
In this study, we propose a distributed phone-based ambient temperature estimation system which enables collaboration among multiple phones to accurately measure the ambient temperature in different areas of an indoor space.
The Fine Line: Navigating Large Language Model Pretraining with Down-streaming Capability Analysis
To address the aforementioned limitations, this paper undertakes a comprehensive comparison of model capabilities at various pretraining intermediate checkpoints.
Recent Advances, Applications, and Open Challenges in Machine Learning for Health: Reflections from Research Roundtables at ML4H 2023 Symposium
The organization of the research roundtables at the conference involved 17 Senior Chairs and 19 Junior Chairs across 11 tables.
TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables
We propose a novel approach, TimeXer, to ingest external information to enhance the forecasting of endogenous variables.
Tokenization Is More Than Compression
Tokenization is a foundational step in natural language processing (NLP) tasks, bridging raw text and language models.
Timer: Generative Pre-trained Transformers Are Large Time Series Models
Deep learning has contributed remarkably to the advancement of time series analysis.
A Literature Review on Fetus Brain Motion Correction in MRI
This paper provides a comprehensive review of the latest advancements in fetal motion correction in MRI.
SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval
We further annotate the image-text pairs with two-level subset-subcategory hierarchy annotations to facilitate a more comprehensive evaluation of the baselines.
CMMMU: A Chinese Massive Multi-discipline Multimodal Understanding Benchmark
We introduce CMMMU, a new Chinese Massive Multi-discipline Multimodal Understanding benchmark designed to evaluate LMMs on tasks demanding college-level subject knowledge and deliberate reasoning in a Chinese context.
A Closer Look at AUROC and AUPRC under Class Imbalance
First, we theoretically characterize the behavior of AUROC and AUPRC in the presence of model mistakes, establishing clearly that AUPRC is not generally superior in cases of class imbalance.
The Limits of Fair Medical Imaging AI In The Wild
As artificial intelligence (AI) rapidly approaches human-level performance in medical imaging, it is crucial that it does not exacerbate or propagate healthcare disparities.
Towards ultra-low-cost smartphone microscopy
The outbreak of COVID-19 exposed the inadequacy of our technical tools for home health surveillance, and recent studies have shown the potential of smartphones as a universal optical microscopic imaging platform for such applications.
iTransformer: Inverted Transformers Are Effective for Time Series Forecasting
These forecasters leverage Transformers to model the global dependencies over temporal tokens of time series, with each token formed by multiple variates of the same timestamp.
Ranked #59 on
Time Series Forecasting
on ETTh1 (336) Multivariate
Continuous Time Evidential Distributions for Irregular Time Series
Prevalent in many real-world settings such as healthcare, irregular time series are challenging to formulate predictions from.
Enhancing Building Semantic Segmentation Accuracy with Super Resolution and Deep Learning: Investigating the Impact of Spatial Resolution on Various Datasets
The development of remote sensing and deep learning techniques has enabled building semantic segmentation with high accuracy and efficiency.
Real-World Video for Zoom Enhancement based on Spatio-Temporal Coupling
In recent years, single-frame image super-resolution (SR) has become more realistic by considering the zooming effect and using real-world short- and long-focus image pairs.
OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection
Out-of-Distribution (OOD) detection is critical for the reliable operation of open-world intelligent systems.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Cross-attention learning enables real-time nonuniform rotational distortion correction in OCT
Nonuniform rotational distortion (NURD) correction is vital for endoscopic optical coherence tomography (OCT) imaging and its functional extensions, such as angiography and elastography.
Annotation-efficient learning for OCT segmentation
Compared to the widely-used U-Net model with 100% training data, our method only requires ~10% of the data for achieving the same segmentation accuracy, and it speeds the training up to ~3. 5 times.
A Meta-Summary of Challenges in Building Products with ML Components -- Collecting Experiences from 4758+ Practitioners
Incorporating machine learning (ML) components into software products raises new software-engineering challenges and exacerbates existing challenges.
Change is Hard: A Closer Look at Subpopulation Shift
Machine learning models often perform poorly on subgroups that are underrepresented in the training data.
SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling
By relating masked modeling to manifold learning, SimMTM proposes to recover masked time points by the weighted aggregation of multiple neighbors outside the manifold, which eases the reconstruction task by assembling ruined but complementary temporal variations from multiple masked series.
Efficient Estimation for Longitudinal Networks via Adaptive Merging
Longitudinal network consists of a sequence of temporal edges among multiple nodes, where the temporal edges are observed in real time.
"Why did the Model Fail?": Attributing Model Performance Changes to Distribution Shifts
In this work, we introduce the problem of attributing performance differences between environments to distribution shifts in the underlying data generating mechanisms.
Signed Network Embedding with Application to Simultaneous Detection of Communities and Anomalies
This paper develops a unified embedding model for signed networks to disentangle the intertwined balance structure and anomaly effect, which can greatly facilitate the downstream analysis, including community detection, anomaly detection, and network inference.
The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations
Across two different blackbox model architectures and four popular explainability methods, we find that the approximation quality of explanation models, also known as the fidelity, differs significantly between subgroups.
Target Confusion in End-to-end Speaker Extraction: Analysis and Approaches
However, its performance is often inferior to that of a blind source separation (BSS) counterpart with a similar network architecture, due to the auxiliary speaker encoder may sometimes generate ambiguous speaker embeddings.
Improving the Fairness of Chest X-ray Classifiers
We also find that methods which achieve group fairness do so by worsening performance for all groups.
Reinforcement Learning from Demonstrations by Novel Interactive Expert and Application to Automatic Berthing Control Systems for Unmanned Surface Vessel
A new expert data generation method, called Model Predictive Based Expert (MPBE) which combines Model Predictive Control and Deep Deterministic Policy Gradient, is developed to provide high quality supervision data for RLfD algorithms.
Learning Optimal Predictive Checklists
Our results show that our method can fit simple predictive checklists that perform well and that can easily be customized to obey a rich class of custom constraints.
Differentiable Projection for Constrained Deep Learning
In this paper, we propose to use a differentiable projection layer in DNN instead of directly solving time-consuming KKT conditions.
OneFlow: Redesign the Distributed Deep Learning Framework from Scratch
Aiming at a simple, neat redesign of distributed deep learning frameworks for various parallelism paradigms, we present OneFlow, a novel distributed training framework based on an SBP (split, broadcast and partial-value) abstraction and the actor model.
An open GPS trajectory dataset and benchmark for travel mode detection
In this study, we propose and open GPS trajectory dataset marked with travel mode and benchmark for the travel mode detection.
Pulling Up by the Causal Bootstraps: Causal Data Augmentation for Pre-training Debiasing
This systematic investigation underlines the importance of accounting for the underlying data-generating mechanisms and fortifying data-preprocessing pipelines with a causal framework to develop methods robust to confounding biases.
A comparison of approaches to improve worst-case predictive model performance over patient subpopulations
Predictive models for clinical outcomes that are accurate on average in a patient population may underperform drastically for some subpopulations, potentially introducing or reinforcing inequities in care access and quality.
Invariance-based Multi-Clustering of Latent Space Embeddings for Equivariant Learning
Variational Autoencoders (VAEs) have been shown to be remarkably effective in recovering model latent spaces for several computer vision tasks.
Reading Race: AI Recognises Patient's Racial Identity In Medical Images
Methods: Using private and public datasets we evaluate: A) performance quantification of deep learning models to detect race from medical images, including the ability of these models to generalize to external environments and across multiple imaging modalities, B) assessment of possible confounding anatomic and phenotype population features, such as disease distribution and body habitus as predictors of race, and C) investigation into the underlying mechanism by which AI models can recognize race.
An Empirical Framework for Domain Generalization in Clinical Settings
In this work, we benchmark the performance of eight domain generalization methods on multi-site clinical time series and medical imaging data.
Theory-guided hard constraint projection (HCP): a knowledge-based data-driven scientific machine learning method
Machine learning models have been successfully used in many scientific and engineering fields.
Incorporating Inner-word and Out-word Features for Mongolian Morphological Segmentation
The inner-word encoder uses the self-attention mechanisms to capture the inner-word features of the target word.
An Empirical Study of Representation Learning for Reinforcement Learning in Healthcare
Reinforcement Learning (RL) has recently been applied to sequential estimation and prediction problems identifying and developing hypothetical treatment strategies for septic patients, with a particular focus on offline learning with observational data.
Active Learning Approaches to Enhancing Neural Machine Translation
Active learning is an efficient approach for mitigating data dependency when training neural machine translation (NMT) models.
Automated Topical Component Extraction Using Neural Network Attention Scores from Source-based Essay Scoring
While automated essay scoring (AES) can reliably grade essays at scale, automated writing evaluation (AWE) additionally provides formative feedback to guide essay revision.
COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation
To combat COVID-19, both clinicians and scientists need to digest vast amounts of relevant biomedical knowledge in scientific literature to understand the disease mechanism and related biological functions.
Hurtful Words: Quantifying Biases in Clinical Contextual Word Embeddings
In this work, we examine the extent to which embeddings may encode marginalized populations differently, and how this may lead to a perpetuation of biases and worsened performance on clinical tasks.
Word Embedding for Response-To-Text Assessment of Evidence
Our long-term goal is to also use this scoring method to provide formative feedback to students and teachers about students' writing quality.
eRevise: Using Natural Language Processing to Provide Formative Feedback on Text Evidence Usage in Student Writing
Writing a good essay typically involves students revising an initial paper draft after receiving feedback.
Co-Attention Based Neural Network for Source-Dependent Essay Scoring
This paper presents an investigation of using a co-attention based neural network for source-dependent essay scoring.
Dose-response modeling in high-throughput cancer drug screenings: An end-to-end approach
Personalized cancer treatments based on the molecular profile of a patient's tumor are an emerging and exciting class of treatments in oncology.
Applications
The Holdout Randomization Test for Feature Selection in Black Box Models
We propose the holdout randomization test (HRT), an approach to feature selection using black box predictive models.
Methodology
