Papers
Fri 11 Nov 2022
166 papers
- Handling Trade-Offs in Speech Separation with Sparsely-Gated Mixture of ExpertsMixture-of-experts → Multimodal MoE models
- NeuroCERIL: Robotic Imitation Learning via Hierarchical Cause-Effect Reasoning in Programmable Attractor Neural NetworksOffline RL and imitation learning from data → Robot manipulation imitation learning
- Improved HER2 Tumor Segmentation with Subtype Balancing using Deep Generative NetworksDiffusion models → Medical imaging and segmentation
- FAN-Trans: Online Knowledge Distillation for Facial Action Unit DetectionKnowledge distillation → General knowledge distillation methods
- Helping the Weak Makes You Strong: Simple Multi-Task Learning Improves Non-Autoregressive TranslatorsEfficient LLM inference and serving → Speculative decoding
- MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- Continuous Soft Pseudo-Labeling in ASRKnowledge distillation → General knowledge distillation methods
- Knowledge Distillation from Cross Teaching Teachers for Efficient Semi-Supervised Abdominal Organ Segmentation in CTKnowledge distillation → Distillation for medical imaging
- The Expertise Level
- Synthetic Expertise
- MAPPING: Model Average with Post-processing for Stroke Lesion Segmentation
- PatchBlender: A Motion Prior for Video Transformers
- Data-Driven Network Neuroscience: On Data Collection and Benchmark
- Understanding and eliminating spurious modes in variational Monte Carlo using collective variables
- Deep-Learning-Empowered Inverse Design for Freeform Reconfigurable Metasurfaces
- SPADE4: Sparsity and Delay Embedding based Forecasting of Epidemics
- Design of Unmanned Air Vehicles Using Transformer Surrogate Models
- Artificial neural networks for predicting the viscosity of lead-containing glasses
- The Far Side of Failure: Investigating the Impact of Speech Recognition Errors on Subsequent Dementia Classification
- Accounting for Temporal Variability in Functional Magnetic Resonance Imaging Improves Prediction of Intelligence
- Efficient Integration of Multi-Order Dynamics and Internal Dynamics in Stock Movement Prediction
- Age Prediction Performance Varies Across Deep, Superficial, and Cerebellar White Matter Connections
- FinBERT-LSTM: Deep Learning based stock price prediction using News Sentiment Analysis
- StereoISP: Rethinking Image Signal Processing for Dual Camera Systems
- Reconstruction of gene regulatory network via sparse optimization
- Controlling Commercial Cooling Systems Using Reinforcement Learning
- Bandits for Online Calibration: An Application to Content Moderation on Social Media Platforms
- Multilevel-in-Layer Training for Deep Neural Network Regression
- Stable and Transferable Hyper-Graph Neural Networks
- On the robustness of non-intrusive speech quality model by adversarial examples
- WindowSHAP: An Efficient Framework for Explaining Time-series Classifiers based on Shapley Values
- Spectral Evolution and Invariance in Linear-width Neural Networks
- Self-Supervised Isotropic Superresolution Fetal Brain MRI
- Social Construction of XAI: Do We Need One Definition to Rule Them All?
- Depth and Representation in Vision Models
- Equivariance with Learned Canonicalization Functions
- Augmenting Transformer-Transducer Based Speaker Change Detection With Token-Level Training Loss
- Exploring Sequence-to-Sequence Transformer-Transducer Models for Keyword Spotting
- Speech-to-Speech Translation For A Real-world Unwritten Language
- Federated Unsupervised Visual Representation Learning via Exploiting General Content and Personal Style
- The Implicit Delta Method
- Cross-Platform and Cross-Domain Abusive Language Detection with Supervised Contrastive Learning
- Probabilistic Debiasing of Scene Graphs
- Metaphors We Learn By
- Data Quality Over Quantity: Pitfalls and Guidelines for Process Analytics
- Efficient HLA imputation from sequential SNPs data by Transformer
- The Architectural Bottleneck Principle
- Re-Analyze Gauss: Bounds for Private Matrix Approximation via Dyson Brownian Motion
- RFFNet: Large-Scale Interpretable Kernel Methods via Random Fourier Features
- Capabilities for Better ML Engineering
- Physically-Based Face Rendering for NIR-VIS Face Recognition
- Control Transformer: Robot Navigation in Unknown Environments through PRM-Guided Return-Conditioned Sequence Modeling
- Behaviour Trees for Creating Conversational Explanation Experiences
- A Federated Approach to Predicting Emojis in Hindi Tweets
- Prior-mean-assisted Bayesian optimization application on FRIB Front-End tunning
- STAR: A Session-Based Time-Aware Recommender System
- ~Optimal Differentially Private Learning of Thresholds and Quasi-Concave Optimization
- DistGNN-MB: Distributed Large-Scale Graph Neural Network Training on x86 via Minibatch Sampling
- Global and Local Analysis of Interestingness for Competency-Aware Deep Reinforcement Learning
- Intent-aware Multi-source Contrastive Alignment for Tag-enhanced Recommendation
- Enhancing and Adversarial: Improve ASR with Speaker Labels
- Phase-Shifting Coder: Predicting Accurate Orientation in Oriented Object Detection
- Analysis of Male and Female Speakers' Word Choices in Public Speeches
- Situating Recommender Systems in Practice: Towards Inductive Learning and Incremental Updates
- Rethinking Log Odds: Linear Probability Modelling and Expert Advice in Interpretable Machine Learning
- Emergency action termination for immediate reaction in hierarchical reinforcement learning
- Striving for data-model efficiency: Identifying data externalities on group performance
- Non-parametric Clustering of Multivariate Populations with Arbitrary Sizes
- Using Developer Discussions to Guide Fixing Bugs in Software
- Runtime data center temperature prediction using Grammatical Evolution techniques
- Sensor Visibility Estimation: Metrics and Methods for Systematic Performance Evaluation and Improvement
- GCondNet: A Novel Method for Improving Neural Networks on Small High-Dimensional Tabular Data
- A New Graph Node Classification Benchmark: Learning Structure from Histology Cell Graphs
- Do Bayesian Neural Networks Need To Be Fully Stochastic?
- Explainability in Practice: Estimating Electrification Rates from Mobile Phone Data in Senegal
- One-Time Model Adaptation to Heterogeneous Clients: An Intra-Client and Inter-Image Attention Design
- Towards Improved Learning in Gaussian Processes: The Best of Two Worlds
- A hybrid entity-centric approach to Persian pronoun resolution
- Re-visiting Reservoir Computing architectures optimized by Evolutionary Algorithms
- Disentangled Uncertainty and Out of Distribution Detection in Medical Generative Models
- Joint Deep Learning for Improved Myocardial Scar Detection from Cardiac MRI
- A Benchmark for Out of Distribution Detection in Point Cloud 3D Semantic Segmentation
- A monitoring framework for deployed machine learning models with supply chain examples
- Multitask Learning for Improved Late Mechanical Activation Detection of Heart from Cine DENSE MRI
- Efficient Deep Reinforcement Learning with Predictive Processing Proximal Policy Optimization
- HumanDiffusion: a Coarse-to-Fine Alignment Diffusion Framework for Controllable Text-Driven Person Image Generation
- Comparison of Uncertainty Quantification with Deep Learning in Time Series Regression
- Improving word mover's distance by leveraging self-attention matrix
- ALANNO: An Active Learning Annotation System for Mortals
- Total Variation Graph Neural Networks
- From Competition to Collaboration: Making Toy Datasets on Kaggle Clinically Useful for Chest X-Ray Diagnosis Using Federated Learning
- StrokeGAN+: Few-Shot Semi-Supervised Chinese Font Generation with Stroke Encoding
- Improving Factual Consistency in Summarization with Compression-Based Post-Editing
- HOReeNet: 3D-aware Hand-Object Grasping Reenactment
- DocuT5: Seq2seq SQL Generation with Table Documentation
- An introduction to computational complexity and statistical learning theory applied to nuclear models
- Investigating Enhancements to Contrastive Predictive Coding for Human Activity Recognition
- Unimodal and Multimodal Representation Training for Relation Extraction
- Dual Complementary Dynamic Convolution for Image Recognition
- Spatial Temporal Graph Convolution with Graph Structure Self-learning for Early MCI Detection
All 166
- Semi-supervised learning for continuous emotional intensity controllable speech synthesis with disentangled representations
- REVEL Framework to measure Local Linear Explanations for black-box models: Deep Learning Image Classification case of study
- Combining Multi-Fidelity Modelling and Asynchronous Batch Bayesian Optimization
- An unobtrusive quality supervision approach for medical image annotation
- Understanding Approximation for Bayesian Inference in Neural Networks
- Practical Approaches for Fair Learning with Multitype and Multivariate Sensitive Attributes
- Emergence of Concepts in DNNs?
- Fleet Rebalancing for Expanding Shared e-Mobility Systems: A Multi-agent Deep Reinforcement Learning Approach
- Active Task Randomization: Learning Robust Skills via Unsupervised Generation of Diverse and Feasible Tasks
- Physically Consistent Neural ODEs for Learning Multi-Physics Systems
- English Contrastive Learning Can Learn Universal Cross-lingual Sentence Embeddings
- SSGVS: Semantic Scene Graph-to-Video Synthesis
- How Much Hate with #china? A Preliminary Analysis on China-related Hateful Tweets Two Years After the Covid Pandemic Began
- Treatment classification of posterior capsular opacification (PCO) using automated ground truths
- Towards automating Numerical Consistency Checks in Financial Reports
- RaLiBEV: Radar and LiDAR BEV Fusion Learning for Anchor Box Free Object Detection Systems
- Identifying, measuring, and mitigating individual unfairness for supervised learning models and application to credit risk models
- Bounding Box Priors for Cell Detection with Point Annotations
- Interactive Context-Aware Network for RGB-T Salient Object Detection
- A Generative Approach for Production-Aware Industrial Network Traffic Modeling
- RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization
- Token Transformer: Can class token help window-based transformer build better long-range interactions?
- Multi-modal Fusion Technology based on Vehicle Information: A Survey
- Overparameterized random feature regression with nearly orthogonal data
- SceneFake: An Initial Dataset and Benchmarks for Scene Fake Audio Detection
- CoRAL: a Context-aware Croatian Abusive Language Dataset
- Integrated Convolutional and Recurrent Neural Networks for Health Risk Prediction using Patient Journey Data with Many Missing Values
- Online Linearized LASSO
- Does Deep Learning REALLY Outperform Non-deep Machine Learning for Clinical Prediction on Physiological Time Series?
- Dance of SNN and ANN: Solving binding problem by combining spike timing and reconstructive attention
- Progressive Motion Context Refine Network for Efficient Video Frame Interpolation
- Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Tasks
- Gradient Imitation Reinforcement Learning for General Low-Resource Information Extraction
- Masked Contrastive Representation Learning
- GeoAI for Knowledge Graph Construction: Identifying Causality Between Cascading Events to Support Environmental Resilience Research
- What's the Situation with Intelligent Mesh Generation: A Survey and Perspectives
- A Comprehensive Survey of Transformers for Computer Vision
- An Improved End-to-End Multi-Target Tracking Method Based on Transformer Self-Attention
- LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation
- In-game Toxic Language Detection: Shared Task and Attention Residuals
- A Survey of Knowledge Enhanced Pre-trained Language Models
- Delay Embedded Echo-State Network: A Predictor for Partially Observed Systems
- MF2-MVQA: A Multi-stage Feature Fusion method for Medical Visual Question Answering
- CCPrefix: Counterfactual Contrastive Prefix-Tuning for Many-Class Classification
- DeepG2P: Fusing Multi-Modal Data to Improve Crop Production
- Using Persuasive Writing Strategies to Explain and Detect Health Misinformation
- Getting the Most out of Simile Recognition
- Hardness-guided domain adaptation to recognise biomedical named entities under low-resource scenarios
- Semi-supervised Variational Autoencoder for Regression: Application on Soft Sensors
- Detection of Strongly Lensed Arcs in Galaxy Clusters with Transformers
- Palm Vein Recognition via Multi-task Loss Function and Attention Layer
- Align, Write, Re-order: Explainable End-to-End Speech Translation via Operation Sequence Generation
- Thompson Sampling for High-Dimensional Sparse Linear Contextual Bandits
- JSRNN: Joint Sampling and Reconstruction Neural Networks for High Quality Image Compressed Sensing
- Feature-aggregated spatiotemporal spine surface estimation for wearable patch ultrasound volumetric imaging
- Inverse Kernel Decomposition
- MINION: a Large-Scale and Diverse Dataset for Multilingual Event Detection
- MEE: A Novel Multilingual Event Extraction Dataset
- Breadth-First Pipeline Parallelism
- Efficient Domain Coverage for Vehicles with Second-Order Dynamics via Multi-Agent Reinforcement Learning
- CR-LSO: Convex Neural Architecture Optimization in the Latent Space of Graph Variational Autoencoder with Input Convex Neural Networks
- Deep Reinforcement Learning Microgrid Optimization Strategy Considering Priority Flexible Demand Side
- Deep equilibrium models as estimators for continuous latent variables
- pyRDDLGym: From RDDL to Gym Environments
- Inferring probabilistic Boolean networks from steady-state gene data samples
- Optimal Condition Training for Target Source Separation