Papers
Thu 30 Jun 2022
183 papers
- Semantic Image Synthesis via Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Denoised MDPs: Learning World Models Better Than the World ItselfWorld models → Latent dynamics models and model-based RL
- Watch and Match: Supercharging Imitation with Regularized Optimal TransportOffline RL and imitation learning from data → Imitation learning methods
- Improving Visual Grounding by Encouraging Consistent Gradient-based ExplanationsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Improving Ensemble Distillation With Weight Averaging and Diversifying PerturbationKnowledge distillation → General knowledge distillation methods
- On Computing Probabilistic Explanations for Decision Trees
- Lagrangian Density Space-Time Deep Neural Network Topology
- Democratizing Ethical Assessment of Natural Language Generation Models
- Automatic Sleep Scoring from Large-scale Multi-channel Pediatric EEG
- Changepoint Detection for Real-Time Spectrum Sharing Radar
- Bio-inspired Machine Learning: programmed death and replication
- DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detection
- Code Translation with Compiler Representations
- CoVaxNet: An Online-Offline Data Repository for COVID-19 Vaccine Hesitancy Research
- Proteus: A Self-Designing Range Filter
- j-Wave: An open-source differentiable wave simulator
- Simulating reaction time for Eureka effect in visual object recognition using artificial neural network
- Customized Conversational Recommender Systems
- Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysis
- Predicting Ulnar Collateral Ligament Injury in Rookie Major League Baseball Pitchers
- Distribution-based Sketching of Single-Cell Samples
- A Rare Topic Discovery Model for Short Texts Based on Co-occurrence word Network
- Personalized Showcases: Generating Multi-Modal Explanations for Recommendations
- TENET: Transformer Encoding Network for Effective Temporal Flow on Motion Prediction
- Non-Parametric Inference of Relational Dependence
- Optimizing Training Trajectories in Variational Autoencoders via Latent Bayesian Optimization Approach
- ProSelfLC: Progressive Self Label Correction Towards A Low-Temperature Entropy State
- Rethinking Surgical Captioning: End-to-End Window-Based MLP Transformer Using Patches
- Language model compression with weighted low-rank factorization
- Ranking In Generalized Linear Bandits
- Discrimination in machine learning algorithms
- Modularity Optimization as a Training Criterion for Graph Neural Networks
- GaitForeMer: Self-Supervised Pre-Training of Transformers via Human Motion Forecasting for Few-Shot Gait Impairment Severity Estimation
- Measuring Forgetting of Memorized Training Examples
- End-to-end Learning for Image-based Detection of Molecular Alterations in Digital Pathology
- Threat Assessment in Machine Learning based Systems
- Rapid and stain-free quantification of viral plaque via lens-free holography and deep learning
- Towards Human-Agent Communication via the Information Bottleneck Principle
- DarKnight: An Accelerated Framework for Privacy and Integrity Preserving Deep Learning Using Trusted Hardware
- Sustainable Computing -- Without the Hot Air
- Efficient computation of rankings from pairwise comparisons
- Sparse Periodic Systolic Dataflow for Lowering Latency and Power Dissipation of Convolutional Neural Network Accelerators
- Rethinking Unsupervised Domain Adaptation for Semantic Segmentation
- Advances in Prediction of Readmission Rates Using Long Term Short Term Memory Networks on Healthcare Insurance Data
- MultiViz: Towards Visualizing and Understanding Multimodal Models
- Visual Pre-training for Navigation: What Can We Learn from Noise?
- Privacy-preserving Graph Analytics: Secure Generation and Federated Learning
- Performative Reinforcement Learning
- DP2-NILM: A Distributed and Privacy-preserving Framework for Non-intrusive Load Monitoring
- K-ARMA Models for Clustering Time Series Data
- DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale
- LaserMix for Semi-Supervised LiDAR Semantic Segmentation
- Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN
- On the Learning and Learnability of Quasimetrics
- AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection
- Causal Machine Learning: A Survey and Open Problems
- Forecasting Future World Events with Neural Networks
- On-Device Training Under 256KB Memory
- Dressing Avatars: Deep Photorealistic Appearance for Physically Simulated Clothing
- Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and Values
- Practical Black Box Hamiltonian Learning
- QUIDAM: A Framework for Quantization-Aware DNN Accelerator and Model Co-Exploration
- PhySRNet: Physics informed super-resolution network for application in computational solid mechanics
- Hate Speech Criteria: A Modular Approach to Task-Specific Hate Speech Definitions
- Learning Iterative Reasoning through Energy Minimization
- Asymmetry Disentanglement Network for Interpretable Acute Ischemic Stroke Infarct Segmentation in Non-Contrast CT Scans
- Learning Functions on Multiple Sets using Multi-Set Transformers
- Classical and learned MR to pseudo-CT mappings for accurate transcranial ultrasound simulation
- Understanding Instance-Level Impact of Fairness Constraints
- Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset
- Evaluation of Performance-Trust vs Moral-Trust Violation in 3D Environment
- Implicit Neural Spatial Filtering for Multichannel Source Separation in the Waveform Domain
- MEAD: A Multi-Armed Approach for Evaluation of Adversarial Examples Detectors
- Sub-8-Bit Quantization Aware Training for 8-Bit Neural Network Accelerator with On-Device Speech Recognition
- Shifts 2.0: Extending The Dataset of Real Distributional Shifts
- Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting
- PolarFormer: Multi-camera 3D Object Detection with Polar Transformer
- Randomized K-FACs: Speeding up K-FAC with Randomized Numerical Linear Algebra
- Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning
- How direct is the link between words and images?
- Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning
- Verification and search algorithms for causal DAGs
- No Reason for No Supervision: Improved Generalization in Supervised Models
- Online TSP with Predictions
- Why we do need Explainable AI for Healthcare
- Two-Stage Classifier for COVID-19 Misinformation Detection Using BERT: a Study on Indonesian Tweets
- Learning Underrepresented Classes from Decentralized Partially Labeled Medical Images
- Learning Citywide Patterns of Life from Trajectory Monitoring
- Deep Learning to See: Towards New Foundations of Computer Vision
- Revisiting Competitive Coding Approach for Palmprint Recognition: A Linear Discriminant Analysis Perspective
- GitHub Copilot AI pair programmer: Asset or Liability?
- Neural Annotation Refinement: Development of a New 3D Dataset for Adrenal Gland Analysis
- Anomaly Detection in Echocardiograms with Dynamic Variational Trajectory Models
- FL-Tuning: Layer Tuning for Feed-Forward Network in Transformer
- Transfer Learning with Deep Tabular Models
- Designs, Motion Mechanism, Motion Coordination, and Communication of Bionic Robot Fishes: A Survey
- Physics-informed machine learning for Structural Health Monitoring
- Self-SuperFlow: Self-supervised Scene Flow Prediction in Stereo Sequences
- Machine learning for automated quality control in injection moulding manufacturing
- Quantum Advantage Seeker with Kernels (QuASK): a software framework to speed up the research in quantum machine learning
All 183
- TINC: Temporally Informed Non-Contrastive Learning for Disease Progression Modeling in Retinal OCT Volumes
- R-MelNet: Reduced Mel-Spectral Modeling for Neural TTS
- Multiclass-SGCN: Sparse Graph-based Trajectory Prediction with Agent Class Embedding
- Augment like there's no tomorrow: Consistently performing neural networks for medical imaging
- Invariance Properties of the Natural Gradient in Overparametrised Systems
- Deep Reinforcement Learning with Swin Transformers
- Submission to Generic Event Boundary Detection Challenge@CVPR 2022: Local Context Modeling and Global Boundary Decoding Approach
- Neural Surface Reconstruction of Dynamic Scenes with Monocular RGB-D Camera
- Neural Rendering for Stereo 3D Reconstruction of Deformable Tissues in Robotic Surgery
- Localizing the Recurrent Laryngeal Nerve via Ultrasound with a Bayesian Shape Framework
- CTrGAN: Cycle Transformers GAN for Gait Transfer
- Benchmark Dataset for Precipitation Forecasting by Post-Processing the Numerical Weather Prediction
- Are Hitting Formulas Hard for Resolution?
- Domain Adaptive Pretraining for Multilingual Acronym Extraction
- Implicit U-Net for volumetric medical image segmentation
- Learning nonparametric ordinary differential equations from noisy data
- Depth-CUPRL: Depth-Imaged Contrastive Unsupervised Prioritized Representations in Reinforcement Learning for Mapless Navigation of Unmanned Aerial Vehicles
- Black-box Generalization of Machine Teaching
- Data-Efficient Learning via Minimizing Hyperspherical Energy
- The Topological BERT: Transforming Attention into Topology for Natural Language Processing
- Privacy-preserving household load forecasting based on non-intrusive load monitoring: A federated deep learning approach
- Recovering network topology and dynamics via sequence characterization
- Multi-Granularity Regularized Re-Balancing for Class Incremental Learning
- Out-of-Distribution Detection for Long-tailed and Fine-grained Skin Lesion Images
- Neural Network Assisted Depth Map Packing for Compression Using Standard Hardware Video Codecs
- The (de)biasing effect of GAN-based augmentation methods on skin lesion images
- D2-LRR: A Dual-Decomposed MDLatLRR Approach for Medical Image Fusion
- Large deviations for interacting particle dynamics for finding mixed equilibria in zero-sum games
- Graph-Time Convolutional Neural Networks: Architecture and Theoretical Analysis
- LiDAR-as-Camera for End-to-End Driving
- Efficient Entity Candidate Generation for Low-Resource Languages
- Using Person Embedding to Enrich Features and Data Augmentation for Classification
- HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection
- Pulse Shape Simulation and Discrimination using Machine-Learning Techniques
- BoxGraph: Semantic Place Recognition and Pose Estimation from 3D LiDAR
- esCorpius: A Massive Spanish Crawling Corpus
- Neural Networks can Learn Representations with Gradient Descent
- Scalable K-FAC Training for Deep Neural Networks with Distributed Preconditioning
- DFGC 2022: The Second DeepFake Game Competition
- InsMix: Towards Realistic Generative Data Augmentation for Nuclei Instance Segmentation
- AI for CSI Feedback Enhancement in 5G-Advanced
- Personalized Detection of Cognitive Biases in Actions of Users from Their Logs: Anchoring and Recency Biases
- Detecting and Recovering Adversarial Examples from Extracting Non-robust and Highly Predictive Adversarial Perturbations
- MKIoU Loss: Towards Accurate Oriented Object Detection in Aerial Images
- The maximum capability of a topological feature in link prediction
- Colonoscopy Navigation using End-to-End Deep Visuomotor Control: A User Study
- Skeleton-based Action Recognition via Adaptive Cross-Form Learning
- UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask Calibration
- Prediction of Dilatory Behavior in eLearning: A Comparison of Multiple Machine Learning Models
- Laplacian Autoencoders for Learning Stochastic Representations
- BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing
- COVID Detection and Severity Prediction with 3D-ConvNeXt and Custom Pretrainings
- PVT-COV19D: Pyramid Vision Transformer for COVID-19 Diagnosis
- Story-thinking, computational-thinking, programming and software engineering
- A note on Linear Bottleneck networks and their Transition to Multilinearity
- FeaRLESS: Feature Refinement Loss for Ensembling Self-Supervised Learning Features in Robust End-to-end Speech Recognition
- Group-invariant tensor train networks for supervised learning
- ZeroC: A Neuro-Symbolic Model for Zero-shot Concept Recognition and Acquisition at Inference Time
- Automated Wheat Disease Detection using a ROS-based Autonomous Guided UAV
- A Causal Approach to Detecting Multivariate Time-series Anomalies and Root Causes
- Timestamp-Supervised Action Segmentation with Graph Convolutional Networks
- Modern Question Answering Datasets and Benchmarks: A Survey
- On the Convergence of Distributed Stochastic Bilevel Optimization Algorithms over a Network
- Exploring Temporally Dynamic Data Augmentation for Video Recognition
- Compressing Pre-trained Transformers via Low-Bit NxM Sparsity for Natural Language Understanding
- "Diversity and Uncertainty in Moderation" are the Key to Data Selection for Multilingual Few-shot Transfer
- GSCLIP : A Framework for Explaining Distribution Shifts in Natural Language
- Continuous-Time and Multi-Level Graph Representation Learning for Origin-Destination Demand Prediction
- Spatial Transformer Network with Transfer Learning for Small-scale Fine-grained Skeleton-based Tai Chi Action Recognition
- Understanding Physical Effects for Effective Tool-use
- Cross-domain Federated Object Detection
- Bridging Mean-Field Games and Normalizing Flows with Trajectory Regularization
- A Unified End-to-End Retriever-Reader Framework for Knowledge-based VQA
- Towards Federated Long-Tailed Learning
- Lookback for Learning to Branch
- A Validity Perspective on Evaluating the Justified Use of Data-driven Decision-making Algorithms
- Building Multilingual Machine Translation Systems That Serve Arbitrary X-Y Translations
- Randomized Coordinate Subgradient Method for Nonsmooth Composite Optimization
- Semi-Supervised Generative Adversarial Network for Stress Detection Using Partially Labeled Physiological Data
- Benchmarking the Robustness of Deep Neural Networks to Common Corruptions in Digital Pathology
- Machine Learning Approaches to Predict Breast Cancer: Bangladesh Perspective
- Boosting 3D Object Detection by Simulating Multimodality on Point Clouds
- Masked Part-Of-Speech Model: Does Modeling Long Context Help Unsupervised POS-tagging?