Search Results for author:
Found 57 papers, 24 papers with code
Decoupled Doubly Contrastive Learning for Cross Domain Facial Action Unit Detection
To achieve the feature decoupling, D$^2$CA is trained to disentangle AU and domain factors by assessing the quality of synthesized faces in cross-domain scenarios when either AU or domain attributes are modified.
Beyond Overfitting: Doubly Adaptive Dropout for Generalizable AU Detection
To prevent excessive feature dropout, a progressive training strategy is used, allowing for selective exclusion of sensitive features at any model layer.
Predicting and Understanding College Student Mental Health with Interpretable Machine Learning
Mental health issues among college students have reached critical levels, significantly impacting academic performance and overall wellbeing.
Brain Foundation Models: A Survey on Advancements in Neural Signal Processing and Brain Discovery
Brain foundation models (BFMs) have emerged as a transformative paradigm in computational neuroscience, offering a revolutionary framework for processing diverse neural signals across different brain-related tasks.
Unveiling Environmental Impacts of Large Language Model Serving: A Functional Unit View
Large language models (LLMs) offer powerful capabilities but come with significant environmental costs, particularly in carbon emissions.
Unlocking Mental Health: Exploring College Students' Well-being through Smartphone Behaviors
The global mental health crisis is a pressing concern, with college students particularly vulnerable to rising mental health disorders.
Decoding Human Attentive States from Spatial-temporal EEG Patches Using Transformers
Learning the spatial topology of electroencephalogram (EEG) channels and their temporal dynamics is crucial for decoding attention states.
Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models
Our experiments demonstrate that fine-tuning InternVL2. 5-8B with MIS significantly outperforms both powerful open-source models and API-based models in challenging multi-image tasks requiring safety-related visual reasoning.
Exact Fit Attention in Node-Holistic Graph Convolutional Network for Improved EEG-Based Driver Fatigue Detection
EEG-based fatigue monitoring can effectively reduce the incidence of related traffic accidents.
Training-free Ultra Small Model for Universal Sparse Reconstruction in Compressed Sensing
Compressed Sensing (CS) is a well-proved theory that drives many recent breakthroughs in these applications.
SelectiveFinetuning: Enhancing Transfer Learning in Sleep Staging through Selective Domain Alignment
By finetuning the model with selective source data, our SelectiveFinetuning enhances the model's performance on target domain that exhibits domain shifts compared to the data used for training.
Towards Sustainable Large Language Model Serving
In this work, we study LLMs from a carbon emission perspective, addressing both operational and embodied emissions, and paving the way for sustainable LLM serving.
Enhancing Autonomous Driving Safety through World Model-Based Predictive Navigation and Adaptive Learning Algorithms for 5G Wireless Applications
Addressing the challenge of ensuring safety in ever-changing and unpredictable environments, particularly in the swiftly advancing realm of autonomous driving in today's 5G wireless communication world, we present Navigation Secure (NavSecure).
Test-Time Dynamic Image Fusion
The decomposed components represent the effective information from the source data, thus the gap between them reflects the Relative Dominability (RD) of the uni-source data in constructing the fusion image.
BiT-MamSleep: Bidirectional Temporal Mamba for EEG Sleep Staging
In this paper, we address the challenges in automatic sleep stage classification, particularly the high computational cost, inadequate modeling of bidirectional temporal dependencies, and class imbalance issues faced by Transformer-based models.
ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time
Vision Language Models (VLMs) have become essential backbones for multimodal intelligence, yet significant safety challenges limit their real-world application.
Discovery and inversion of the viscoelastic wave equation in inhomogeneous media
In scientific machine learning, the task of identifying partial differential equations accurately from sparse and noisy data poses a significant challenge.
Language-centered Human Activity Recognition
To address this, we propose LanHAR, a novel system that leverages Large Language Models (LLMs) to generate semantic interpretations of sensor readings and activity labels for cross-dataset HAR.
A Comprehensive Survey on EEG-Based Emotion Recognition: A Graph-Based Perspective
In this paper, we present a comprehensive survey of these studies, delivering a systematic review of graph-related methods in this field from a methodological perspective.
Uncertainty-Aware Decarbonization for Datacenters
We identify and analyze two types of uncertainty -- temporal and spatial -- and discuss their system implications.
SparseSSP: 3D Subcellular Structure Prediction from Sparse-View Transmitted Light Images
Traditional fluorescence staining is phototoxic to live cells, slow, and expensive; thus, the subcellular structure prediction (SSP) from transmitted light (TL) images is emerging as a label-free, faster, low-cost alternative.
EmT: A Novel Transformer for Generalized Cross-subject EEG Emotion Recognition
Furthermore, we design a temporal contextual transformer module (TCT) with two types of token mixers to learn the temporal contextual information.
Predictive Dynamic Fusion
Accordingly, we further propose a relative calibration strategy to calibrate the predicted Co-Belief for potential uncertainty.
EEG-Deformer: A Dense Convolutional Transformer for Brain-computer Interfaces
Effectively learning the temporal dynamics in electroencephalogram (EEG) signals is challenging yet essential for decoding brain activities using brain-computer interfaces (BCIs).
Noise Correction on Subjective Datasets
Incorporating every annotator's perspective is crucial for unbiased data modeling.
Turaco: Complexity-Guided Data Sampling for Training Neural Surrogates of Programs
We first characterize the proportion of data to sample from each region of a program's input space (corresponding to different execution paths of the program) based on the complexity of learning a surrogate of the corresponding execution path.
MASA-TCN: Multi-anchor Space-aware Temporal Convolutional Neural Networks for Continuous and Discrete EEG Emotion Recognition
A natural method is to learn the temporal dynamic patterns.
Aggregating Intrinsic Information to Enhance BCI Performance through Federated Learning
Though numerous research groups and institutes collect a multitude of EEG datasets for the same BCI task, sharing EEG data from multiple sites is still challenging due to the heterogeneity of devices.
An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs
We apply our sparse accelerator on widely-used Transformer-based language models including Bert-Mini, DistilBERT, Bert-Base, and BERT-Large.
Generalizability of PRS313 for breast cancer risk amongst non-Europeans in a Los Angeles biobank
We found that the PRS313 achieved overlapping Areas under the ROC Curve (AUCs) in females of Lantix (AUC, 0. 68; 95 CI, 0. 65-0. 71) and European ancestry (AUC, 0. 70; 95 CI, 0. 69-0. 71) but lower AUCs for the AFR and EAA populations (AFR: AUC, 0. 61; 95 CI, 0. 56-0. 65; EAA: AUC, 0. 64; 95 CI, 0. 60-0. 680).
Acela: Predictable Datacenter-level Maintenance Job Scheduling
While it is tempting to use prior machine learning techniques for predicting job duration, we find that the structure of the maintenance job scheduling problem creates a unique challenge.
Fast DistilBERT on CPUs
In this work, we propose a new pipeline for creating and running Fast Transformer models on CPUs, utilizing hardware-aware pruning, knowledge distillation, quantization, and our own Transformer inference runtime engine with optimized kernels for sparse and quantized operators.
SCOPE: Safe Exploration for Dynamic Computer Systems Optimization
Such solutions monitor past system executions to learn the system's behavior under different hardware resource allocations before dynamically tuning resources to optimize the application execution.
Cello: Efficient Computer Systems Optimization with Predictive Early Termination and Censored Regression
Our evaluation shows that compared to the state-of-the-art SEML approach in computer systems optimization, Cello improves latency by 1. 19X for minimizing latency under a power constraint, and improves energy by 1. 18X for minimizing energy under a latency constraint.
Continuous Emotion Recognition using Visual-audio-linguistic information: A Technical Report for ABAW3
The visual encoding from the visual block is concatenated with the attention feature to emphasize the visual information.
NURD: Negative-Unlabeled Learning for Online Datacenter Straggler Prediction
To predict stragglers accurately and early without labeled positive examples or assumptions on latency distributions, this paper presents NURD, a novel Negative-Unlabeled learning approach with Reweighting and Distribution-compensation that only trains on negative and unlabeled streaming data.
Statistical Learning for Individualized Asset Allocation
We show that our proposed Discretization and Regression with generalized fOlded concaVe penalty on Effect discontinuity (DROVE) approach enjoys desirable theoretical properties and allows for statistical inference of the optimal value associated with optimal decision-making.
Programming with Neural Surrogates of Programs
With surrogate adaptation, programmers develop a surrogate of a program then retrain that surrogate on a different task.
Sparse Fusion for Multimodal Transformers
Multimodal classification is a core task in human-centric machine learning.
Continuous Emotion Recognition with Audio-visual Leader-follower Attentive Fusion
We propose an audio-visual spatial-temporal deep neural network with: (1) a visual block containing a pretrained 2D-CNN followed by a temporal convolutional network (TCN); (2) an aural block containing several parallel TCNs; and (3) a leader-follower attentive fusion block combining the audio-visual information.
LGGNet: Learning from Local-Global-Graph Representations for Brain-Computer Interface
It captures temporal dynamics of EEG which then serves as input to the proposed local and global graph-filtering layers.
TSception: Capturing Temporal Dynamics and Spatial Asymmetry from EEG for Emotion Recognition
TSception consists of dynamic temporal, asymmetric spatial, and high-level fusion layers, which learn discriminative representations in the time and channel dimensions simultaneously.
Augmentation Strategies for Learning with Noisy Labels
In this paper, we evaluate different augmentation strategies for algorithms tackling the "learning with noisy labels" problem.
Ranked #9 on
Image Classification
on Clothing1M
(using extra training data)
Multiple Instance Segmentation in Brachial Plexus Ultrasound Image Using BPMSegNet
In this paper, a network called Brachial Plexus Multi-instance Segmentation Network (BPMSegNet) is proposed to identify different tissues (nerves, arteries, veins, muscles) in ultrasound images.
A Multi-View Dynamic Fusion Framework: How to Improve the Multimodal Brain Tumor Segmentation from Multi-Views?
Moreover, the multi-view fusion loss, which consists of the segmentation loss, the transition loss and the decision loss, is proposed to facilitate the training process of multi-view learning networks so as to keep the consistency of appearance and space, not only in the process of fusing segmentation results, but also in the process of training the learning network.
DeepKeyGen: A Deep Learning-based Stream Cipher Generator for Medical Image Encryption and Decryption
In this paper, a novel deep learning-based key generation network (DeepKeyGen) is proposed as a stream cipher generator to generate the private key, which can then be used for encrypting and decrypting of medical images.
Channel Pruning Guided by Spatial and Channel Attention for DNNs in Intelligent Edge Computing
Guided by the scale values generated by SCA for measuring channel importance, we further propose a new channel pruning approach called Channel Pruning guided by Spatial and Channel Attention (CPSCA).
Planimation
Planimation is a modular and extensible open source framework to visualise sequential solutions of planning problems specified in PDDL.
A polynomial-time algorithm for learning nonparametric causal graphs
We establish finite-sample guarantees for a polynomial-time algorithm for learning a nonlinear, nonparametric directed acyclic graphical (DAG) model from data.
DeepEDN: A Deep Learning-based Image Encryption and Decryption Network for Internet of Medical Things
Specifically, in DeepEDN, the Cycle-Generative Adversarial Network (Cycle-GAN) is employed as the main learning network to transfer the medical image from its original domain into the target domain.
TSception: A Deep Learning Framework for Emotion Detection Using EEG
TSception consists of temporal and spatial convolutional layers, which learn discriminative representations in the time and channel domains simultaneously.
Improving Sepsis Treatment Strategies by Combining Deep and Kernel-Based Reinforcement Learning
On a large retrospective cohort, this mixture-based approach outperforms physician, kernel only, and DRL-only experts.
Dynamical systems theory for causal inference with application to synthetic control methods
In this setting, we propose to screen out control units that have a weak dynamical relationship to the single treated unit before the model is fit.
Methodology
Evaluating Reinforcement Learning Algorithms in Observational Health Settings
Much attention has been devoted recently to the development of machine learning algorithms with the goal of improving treatment policies in healthcare.
RUN:Residual U-Net for Computer-Aided Detection of Pulmonary Nodules without Candidate Selection
The early detection and early diagnosis of lung cancer are crucial to improve the survival rate of lung cancer patients.
Multiresolution Kernel Approximation for Gaussian Process Regression
Gaussian process regression generally does not scale to beyond a few thousands data points without applying some sort of kernel approximation method.
Adaptive Subgradient Methods for Online AUC Maximization
Despite their encouraging results reported, the existing online AUC maximization algorithms often adopt simple online gradient descent approaches that fail to exploit the geometrical knowledge of the data observed during the online learning process, and thus could suffer from relatively larger regret.
