Search Results for author:
Found 24 papers, 6 papers with code
$C^3$: Confidence Calibration Model Cascade for Inference-Efficient Cross-Lingual Natural Language Understanding
Existing model cascade methods seek to enhance inference efficiency by greedily selecting the lightest model capable of processing the current input from a variety of models, based on model confidence scores.
Lens: A Foundation Model for Network Traffic in Cybersecurity
Network traffic refers to the amount of data being sent and received over the internet or any system that connects computers.
Enhancing Compositional Generalization via Compositional Feature Alignment
To delve into the CG challenge, we develop CG-Bench, a suite of CG benchmarks derived from existing real-world image datasets, and observe that the prevalent pretraining-finetuning paradigm on foundational models, such as CLIP and DINOv2, struggles with the challenge.
General-Purpose Multi-Modal OOD Detection Framework
To reach this goal, we propose a general-purpose weakly-supervised OOD detection framework, called WOOD, that combines a binary classifier and a contrastive learning component to reap the benefits of both.
Neural Symbolic Regression using Control Variables
Experimental results demonstrate that the proposed SRCV significantly outperforms state-of-the-art baselines in discovering mathematical expressions with multiple variables.
Condensed Prototype Replay for Class Incremental Learning
In this paper, we propose YONO that You Only Need to replay One condensed prototype per class, which for the first time can even outperform memory-costly exemplar-replay methods.
Balancing Privacy Protection and Interpretability in Federated Learning
Federated learning (FL) aims to collaboratively train the global model in a distributed manner by sharing the model parameters from local clients to a central server, thereby potentially protecting users' private information.
Pre-Training Representations of Binary Code Using Contrastive Learning
To the best of our knowledge, COMBO is the first language representation model that incorporates source code, binary code, and comments into contrastive code representation learning and unifies multiple tasks for binary code analysis.
Phy-Taylor: Physics-Model-Based Deep Neural Networks
To do so, the PhN augments neural network layers with two key components: (i) monomials of Taylor series expansion of nonlinear functions capturing physical knowledge, and (ii) a suppressor for mitigating the influence of noise.
Rethinking Controllable Variational Autoencoders
It has shown success in a variety of applications, such as image generation, disentangled representation learning, and language modeling.
Unsupervised Belief Representation Learning with Information-Theoretic Variational Graph Auto-Encoders
Inspired by total correlation in information theory, we propose the Information-Theoretic Variational Graph Auto-Encoder (InfoVGAE) that learns to project both users and content items (e. g., posts that represent user views) into an appropriate disentangled latent space.
A Unified Knowledge Distillation Framework for Deep Directed Graphical Models
Moreover, our method achieves good performance for discriminative deep DGMs compression.
On Orthogonality Constraints for Transformers
Orthogonality constraints encourage matrices to be orthogonal for numerical stability.
Controllable and Diverse Text Generation in E-commerce
The algorithm is injected into a Conditional Variational Autoencoder (CVAE), allowing \textit{Apex} to control both (i) the order of keywords in the generated sentences (conditioned on the input keywords and their order), and (ii) the trade-off between diversity and accuracy.
Deep Compressive Offloading: Speeding Up Neural Network Inference by Trading Edge Computation for Network Latency
With comprehensive evaluations, our system can consistently reduce end-to-end latency by 2× to 4× with 1% accuracy loss, compared to state-of-the-art neural network offloading systems.
Scheduling Real-time Deep Learning Services as Imprecise Computations
The paper presents an efficient real-time scheduling algorithm for intelligent real-time edge services, defined as those that perform machine intelligence tasks, such as voice recognition, LIDAR processing, or machine vision, on behalf of local embedded devices that are themselves unable to support extensive computations.
ControlVAE: Tuning, Analytical Properties, and Performance Analysis
ControlVAE is a new variational autoencoder (VAE) framework that combines the automatic control theory with the basic VAE to stabilize the KL-divergence of VAE models to a specified value.
DynamicVAE: Decoupling Reconstruction Error and Disentangled Representation Learning
Existing methods, such as $\beta$-VAE and FactorVAE, assign a large weight to the KL-divergence term in the objective function, leading to high reconstruction errors for the sake of better disentanglement.
ControlVAE: Controllable Variational Autoencoder
Variational Autoencoders (VAE) and their variants have been widely used in a variety of applications, such as dialog generation, image generation and disentangled representation learning.
paper2repo: GitHub Repository Recommendation for Academic Papers
Motivated by this trend, we describe a novel item-item cross-platform recommender system, $\textit{paper2repo}$, that recommends relevant repositories on GitHub that match a given paper in an academic search system such as Microsoft Academic.
Hierarchical Overlapping Belief Estimation by Structured Matrix Factorization
In the synthetic dataset, our model reduces error by 40%.
STFNets: Learning Sensing Signals from the Time-Frequency Perspective with Short-Time Fourier Neural Networks
IoT applications, however, often measure physical phenomena, where the underlying physics (such as inertia, wireless signal propagation, or the natural frequency of oscillation) are fundamentally a function of signal frequencies, offering better features in the frequency domain.
FastDeepIoT: Towards Understanding and Optimizing Neural Network Execution Time on Mobile and Embedded Devices
We show that changing neural network size does not proportionally affect performance attributes of interest, such as execution time.
RDeepSense: Reliable Deep Mobile Computing Models with Uncertainty Estimations
Recent advances in deep learning have led various applications to unprecedented achievements, which could potentially bring higher intelligence to a broad spectrum of mobile and ubiquitous applications.
