Papers
Wed 15 Jun 2022
226 papers
- Adaptive Expert Models for Personalization in Federated LearningMixture-of-experts → Federated mixture-of-experts
- Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding SystemsKnowledge distillation → Knowledge distillation for LLMs
- Discrete Contrastive Diffusion for Cross-Modal Music and Image GenerationDiffusion models → Audio, speech and music
- Write and Paint: Generative Vision-Language Models are Unified Modal LearnersMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Diffusion Models for Video Prediction and InfillingDiffusion models → Video generation
- Coarse-to-Fine Vision-Language Pre-training with Fusion in the BackboneMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic ModelsDiffusion models → Diffusion foundations and sampling
- CARD: Classification and Regression Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Resource-Constrained Edge AI with Early Exit PredictionEfficient LLM inference and serving → Early exit and edge inference
- Reliability Analysis of Complex Multi-State System Based on Universal Generating Function and Bayesian Network
- Detecting Harmful Online Conversational Content towards LGBTQIA+ Individuals
- A Novel Implementation of Machine Learning for the Efficient, Explainable Diagnosis of COVID-19 from Chest CT
- SmartMask- Developing an automated self-care system
- A Proposed Bi-LSTM Method to Fake News Detection
- Psychologically-Inspired, Unsupervised Inference of Perceptual Groups of GUI Widgets from GUI Images
- Leveraging Uncertainty in Deep Learning for Pancreatic Adenocarcinoma Grading
- Discovery of the Content and Engagement with the Content
- Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification
- An AI tool for automated analysis of large-scale unstructured clinical cine CMR databases
- Conformal prediction set for time-series
- HF-NeuS: Improved Surface Reconstruction Using High-Frequency Details
- Action Spotting using Dense Detection Anchors Revisited: Submission to the SoccerNet Challenge 2022
- Queried Unlabeled Data Improves and Robustifies Class-Incremental Learning
- TOKEN is a MASK: Few-shot Named Entity Recognition with Pre-trained Language Models
- Architectural Backdoors in Neural Networks
- Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness
- Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization
- Personal Entity, Concept, and Named Entity Linking in Conversations
- Disentangling visual and written concepts in CLIP
- Efficient Approximation of Expected Hypervolume Improvement using Gauss-Hermite Quadrature
- Metric-Fair Classifier Derandomization
- Large-Scale Differentiable Causal Discovery of Factor Graphs
- Neural Network Normal Estimation and Bathymetry Reconstruction from Sidescan Sonar
- A Search-Based Testing Approach for Deep Reinforcement Learning Agents
- High-Resolution Bathymetric Reconstruction From Sidescan Sonar With Deep Neural Networks
- How Adults Understand What Young Children Say
- Improving generalization by mimicking the human visual diet
- Beyond Adult and COMPAS: Fairness in Multi-Class Prediction
- Gaussian Blue Noise
- FixEval: Execution-based Evaluation of Program Fixes for Programming Problems
- On Calibrated Model Uncertainty in Deep Learning
- Federated Data Analytics: A Study on Linear Models
- Strategic Coalition for Data Pricing in IoT Data Markets
- Evaluating Short-Term Forecasting of Multiple Time Series in IoT Environments
- A machine learning approach to predicting pore pressure response in liquefiable sands under cyclic loading
- Robust Attack Graph Generation
- Deep Learning and Handheld Augmented Reality Based System for Optimal Data Collection in Fault Diagnostics Domain
- HyperImpute: Generalized Iterative Imputation with Automatic Model Selection
- Kantorovich Strikes Back! Wasserstein GANs are not Optimal Transport?
- Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization
- SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos
- Physics-Infused Fuzzy Generative Adversarial Network for Robust Failure Prognosis
- Multiscale methods for signal selection in single-cell data
- Reconstructing Training Data from Trained Neural Networks
- Hybrid thermal modeling of additive manufacturing processes using physics-informed neural networks for temperature prediction and parameter identification
- On the Identifiability of Nonlinear ICA: Sparsity and Beyond
- Condensing Graphs via One-Step Gradient Matching
- When to intervene? Prescriptive Process Monitoring Under Uncertainty and Resource Constraints
- Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective
- Edge Inference with Fully Differentiable Quantized Mixed Precision Neural Networks
- Disparate Impact in Differential Privacy from Gradient Misalignment
- Improving Diversity with Adversarially Learned Transformations for Domain Generalization
- Taxonomy of Benchmarks in Graph Representation Learning
- On the Eve of True Explainability for OWL Ontologies: Description Logic Proofs with Evee and Evonne (Extended Version)
- PlanarRecon: Real-time 3D Plane Detection and Reconstruction from Posed Monocular Videos
- Variable Bitrate Neural Fields
- Masked Frequency Modeling for Self-Supervised Visual Pre-Training
- LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection
- Waymo Open Dataset: Panoramic Video Panoptic Segmentation
- Masked Siamese ConvNets
- Neural Deformable Voxel Grid for Fast Optimization of Dynamic View Synthesis
- MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields
- VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
- DIRECTOR: Generator-Classifiers For Supervised Language Modeling
- A Simple Data Mixing Prior for Improving Self-Supervised Learning
- ELUDE: Generating interpretable explanations via a decomposition into labelled and unlabelled features
- Structured Video Tokens @ Ego4D PNR Temporal Localization Challenge 2022
- Structured Sparsity Learning for Efficient Video Super-Resolution
- AVATAR: Unconstrained Audiovisual Speech Recognition
- Emergent Abilities of Large Language Models
- Learning to Accelerate Partial Differential Equations via Latent Global Evolution
- Learning Large-scale Subsurface Simulations with a Hybrid Graph Network Simulator
- Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling
- A Unified Sequence Interface for Vision Tasks
- Transformer-based Automatic Speech Recognition of Formal and Colloquial Czech in MALACH Project
- Region-enhanced Deep Graph Convolutional Networks for Rumor Detection
- CRISP - Reliable Uncertainty Estimation for Medical Image Segmentation
- SP-ViT: Learning 2D Spatial Priors for Vision Transformers
- Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity
- Hyperparameter Sensitivity in Deep Outlier Detection: Analysis and a Scalable Hyper-Ensemble Solution
- Convergence and Price of Anarchy Guarantees of the Softmax Policy Gradient in Markov Potential Games
- Statistical and Computational Phase Transitions in Group Testing
- Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays
- AI Ethics Issues in Real World: Evidence from AI Incident Database
- Real3D-Aug: Point Cloud Augmentation by Placing Real Objects with Occlusion Handling for 3D Detection and Segmentation
- Sublinear Algorithms for Hierarchical Clustering
- Clustered Scheduling and Communication Pipelining For Efficient Resource Management Of Wireless Federated Learning
- Rethinking Initialization of the Sinkhorn Algorithm
- Exploring Capabilities of Monolingual Audio Transformers using Large Datasets in Automatic Speech Recognition of Czech
- The SIGMORPHON 2022 Shared Task on Morpheme Segmentation
All 226
- Epistemic Deep Learning
- ARES: Locally Adaptive Reconstruction-based Anomaly Scoring
- Sparse Subspace Clustering in Diverse Multiplex Network Model
- How GNNs Facilitate CNNs in Mining Geometric Information from Large-Scale Medical Images
- BIO-CXRNET: A Robust Multimodal Stacking Machine Learning Technique for Mortality Risk Prediction of COVID-19 Patients using Chest X-Ray Images and Clinical Data
- Robust and Sparse Estimation of Linear Regression Coefficients with Heavy-tailed Noises and Covariates
- HICEM: A High-Coverage Emotion Model for Artificial Emotional Intelligence
- Characteristic kernels on Hilbert spaces, Banach spaces, and on sets of measures
- Cross-lingual AMR Aligner: Paying Attention to Cross-Attention
- Theory of Machine Learning with Limited Data
- NatGen: Generative pre-training by "Naturalizing" source code
- Evaluating object detector ensembles for improving the robustness of artifact detection in endoscopic video streams
- A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions
- E2V-SDE: From Asynchronous Events to Fast and Continuous Video Reconstruction via Neural Stochastic Differential Equations
- AI and Pathology: Steering Treatment and Predicting Outcomes
- Calibrating Agent-based Models to Microdata with Graph Neural Networks
- Contrastive Learning as Goal-Conditioned Reinforcement Learning
- A Meta-Analysis of Distributionally-Robust Models
- Federated Learning with Uncertainty via Distilled Predictive Distributions
- Bayesian Learning of Parameterised Quantum Circuits
- Contextualization and Generalization in Entity and Relation Extraction
- How to Reduce Change Detection to Semantic Segmentation
- KE-QI: A Knowledge Enhanced Article Quality Identification Dataset
- On the fast convergence of minibatch heavy ball momentum
- Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation
- A Deep Generative Model of Neonatal Cortical Surface Development
- Body Gesture Recognition to Control a Social Robot
- Autonomous Platoon Control with Integrated Deep Reinforcement Learning and Dynamic Programming
- BaIT: Barometer for Information Trustworthiness
- Density-Based Algorithms for Corruption-Robust Contextual Search and Convex Optimization
- QONNX: Representing Arbitrary-Precision Quantized Neural Networks
- Investigating Multi-Feature Selection and Ensembling for Audio Classification
- Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation
- Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning
- On the complexity of finding set repairs for data-graphs
- Towards ML Methods for Biodiversity: A Novel Wild Bee Dataset and Evaluations of XAI Methods for ML-Assisted Rare Species Annotations
- Collaborative Knowledge Graph Fusion by Exploiting the Open Corpus
- PolyU-BPCoMa: A Dataset and Benchmark Towards Mobile Colorized Mapping Using a Backpack Multisensorial System
- Conformance Checking with Uncertainty via SMT (Extended Version)
- Coarse-to-fine Deep Video Coding with Hyperprior-guided Mode Prediction
- READ: Aggregating Reconstruction Error into Out-of-distribution Detection
- VisageSynTalk: Unseen Speaker Video-to-Speech Synthesis via Speech-Visage Feature Selection
- Boosting DNN Cold Inference on Edge Devices
- Predicting Gender via Eye Movements
- Multi-Objective Hyperparameter Optimization in Machine Learning -- An Overview
- Forecasting of depth and ego-motion with transformers and self-supervision
- Self-Supervised Implicit Attention: Guided Attention by The Model Itself
- Physically-admissible polarimetric data augmentation for road-scene analysis
- Estimating Confidence of Predictions of Individual Classifiers and Their Ensembles for the Genre Classification Task
- Local Identifiability of Deep ReLU Neural Networks: the Theory
- Zero-shot object goal visual navigation
- Deep Neural Network Pruning for Nuclei Instance Segmentation in Hematoxylin & Eosin-Stained Histological Images
- Interpretable differential diagnosis for Alzheimer's disease and Frontotemporal dementia
- Hardening DNNs against Transfer Attacks during Network Compression using Greedy Adversarial Pruning
- Automating the resolution of flight conflicts: Deep reinforcement learning in service of air traffic controllers
- Efficient Adaptive Ensembling for Image Classification
- "Why Here and Not There?" -- Diverse Contrasting Explanations of Dimensionality Reduction
- Ultra Fast Deep Lane Detection with Hybrid Anchor Driven Ordinal Classification
- Subsurface Depths Structure Maps Reconstruction with Generative Adversarial Networks
- The Manifold Hypothesis for Gradient-Based Explanations
- Finite-Sample Guarantees for High-Dimensional DML
- Sparse Structure Search for Parameter-Efficient Tuning
- Mean-Semivariance Policy Optimization via Risk-Averse Reinforcement Learning
- NatiQ: An End-to-end Text-to-Speech System for Arabic
- MonoGround: Detecting Monocular 3D Objects from the Ground
- Lattice Convolutional Networks for Learning Ground States of Quantum Many-Body Systems
- DiffWire: Inductive Graph Rewiring via the Lov'asz Bound
- Modern Machine-Learning Predictive Models for Diagnosing Infectious Diseases
- Seeking Common Ground While Reserving Differences: Multiple Anatomy Collaborative Framework for Undersampled MRI Reconstruction
- SciTweets -- A Dataset and Annotation Framework for Detecting Scientific Online Discourse
- The Emotion is Not One-hot Encoding: Learning with Grayscale Label for Emotion Recognition in Conversation
- Robust SAR ATR on MSTAR with Deep Learning Models trained on Full Synthetic MOCEM data
- XMorpher: Full Transformer for Deformable Medical Image Registration via Cross Attention
- Unsupervised multi-branch Capsule for Hyperspectral and LiDAR classification
- Automatic Detection of Rice Disease in Images of Various Leaf Sizes
- Cautious Learning of Multiattribute Preferences
- On Numerical Integration in Neural Ordinary Differential Equations
- Detection of magnetohydrodynamic waves by using machine learning
- A Survey : Neural Networks for AMR-to-Text
- Exploiting Cross-domain And Cross-Lingual Ultrasound Tongue Imaging Features For Elderly And Dysarthric Speech Recognition
- Recent Advances in Scene Image Representation and Classification
- Morphence-2.0: Evasion-Resilient Moving Target Defense Powered by Out-of-Distribution Detection
- CMNEROne at SemEval-2022 Task 11: Code-Mixed Named Entity Recognition by leveraging multilingual data
- Online Contextual Decision-Making with a Smart Predict-then-Optimize Method
- Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack
- Can pruning improve certified robustness of neural networks?
- VCT: A Video Compression Transformer
- Diffusion Transport Alignment
- Knowledge Management System with NLP-Assisted Annotations: A Brief Survey and Outlook
- From Outcome-Based to Language-Based Preferences
- S2-FPN: Scale-ware Strip Attention Guided Feature Pyramid Network for Real-time Semantic Segmentation
- Enhanced Knowledge Selection for Grounded Dialogues via Document Semantic Graphs
- FOLD-TR: A Scalable and Efficient Inductive Learning Algorithm for Learning To Rank
- Differentiable Top-k Classification Learning
- Text-Aware End-to-end Mispronunciation Detection and Diagnosis
- A Survey on Gradient Inversion: Attacks, Defenses and Future Directions
- Human Eyes Inspired Recurrent Neural Networks are More Robust Against Adversarial Noises
- Super-resolution image display using diffractive decoders
- ERNAS: An Evolutionary Neural Architecture Search for Magnetic Resonance Image Reconstructions
- Global Convergence of Federated Learning for Mixed Regression
- A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noise
- Machine vision for vial positioning detection toward the safe automation of material synthesis
- Human heuristics for AI-generated language are flawed
- Rethinking Generalization in Few-Shot Classification
- Born for Auto-Tagging: Faster and better with new objective functions
- Latency Control for Keyword Spotting
- On Enforcing Better Conditioned Meta-Learning for Rapid Few-Shot Adaptation
- Self-Supervised Learning of Image Scale and Orientation
- CLNode: Curriculum Learning for Node Classification
- Investigation of stellar magnetic activity using variational autoencoder based on low-resolution spectroscopic survey
- Noise Covariance Estimation in Multi-Task High-dimensional Linear Models
- GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifolds
- TeKo: Text-Rich Graph Neural Networks with External Knowledge
- Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions
- Fair Ranking as Fair Division: Impact-Based Individual Fairness in Ranking
- Quantum computing overview: discrete vs. continuous variable models
- An Extractive-and-Abstractive Framework for Source Code Summarization
- Test-Time Adaptation for Visual Document Understanding
- A Multiple kernel testing procedure for non-proportional hazards in factorial designs
- Location-based Twitter Filtering for the Creation of Low-Resource Language Datasets in Indonesian Local Languages
- Query-Adaptive Predictive Inference with Partial Labels
- Training Discrete Deep Generative Models via Gapped Straight-Through Estimator
- Brownian Noise Reduction: Maximizing Privacy Subject to Accuracy Constraints
- Accurate Emotion Strength Assessment for Seen and Unseen Speech Based on Data-Driven Deep Learning
- A Projection-Based K-space Transformer Network for Undersampled Radial MRI Reconstruction with Limited Training Subjects
- A smile is all you need: Predicting limiting activity coefficients from SMILES with natural language processing