Papers
Fri 28 Oct 2022
212 papers
- Teacher-Student Architecture for Knowledge Learning: A SurveyKnowledge distillation → General knowledge distillation methods
- Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language ModelsMixture-of-experts → MoE large language models
- Machine Unlearning of Federated ClustersLLM safety and security → Federated unlearning and poisoning
- Nonuniqueness and Convergence to Equivalent Solutions in Observer-based Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
- On the Vulnerability of Data Points under Multiple Membership Inference Attacks and Target ModelsLLM safety and security → Membership inference attacks
- Solving Math Word Problems via Cooperative Reasoning induced Language ModelsLLM reasoning → Mathematical reasoning
- Interactive Imitation Learning of Bimanual Movement PrimitivesOffline RL and imitation learning from data → Robot manipulation imitation learning
- Semi-UFormer: Semi-supervised Uncertainty-aware Transformer for Image DehazingKnowledge distillation → General knowledge distillation methods
- MagicMix: Semantic Mixing with Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- UPainting: Unified Text-to-Image Diffusion Generation with Cross-modal GuidanceDiffusion models → Image generation, text-to-image and editing
- LegoNet: A Fast and Exact Unlearning ArchitectureLLM safety and security → Machine unlearning
- Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human PreferencesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- When Life Gives You Lemons, Make Cherryade: Converting Feedback from Bad Responses into Good LabelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
- Introducing topography in convolutional neural networks
- Deep Temporal Modelling of Clinical Depression through Social Media Text
- Zero-Shot Text Matching for Automated Auditing using Sentence Transformers
- Moving beyond word lists: towards abstractive topic labels for human-like topics of scientific documents
- Improved Prediction of Beta-Amyloid and Tau Burden Using Hippocampal Surface Multivariate Morphometry Statistics and Sparse Coding
- Automatic Seizure Prediction using CNN and LSTM
- Spatial Graph Signal Interpolation with an Application for Merging BCI Datasets with Various Dimensionalities
- UniASM: Binary Code Similarity Detection without Fine-tuning
- Kuaipedia: a Large-scale Multi-modal Short-video Encyclopedia
- UNFIS: A Novel Neuro-Fuzzy Inference System with Unstructured Fuzzy Rules for Classification
- Conservative Likelihood Ratio Estimator for Infrequent Data Slightly above a Frequency Threshold
- I am Only Happy When There is Light: The Impact of Environmental Changes on Affective Facial Expressions Recognition
- Digital twins of physical printing-imaging channel
- Impact of PolSAR pre-processing and balancing methods on complex-valued neural networks segmentation tasks
- Fashion-Specific Attributes Interpretation via Dual Gaussian Visual-Semantic Embedding
- Bayesian Model Selection of Lithium-Ion Battery Models via Bayesian Quadrature
- A Long-term Dependent and Trustworthy Approach to Reactor Accident Prognosis based on Temporal Fusion Transformer
- Using Contrastive Samples for Identifying and Leveraging Possible Causal Relationships in Reinforcement Learning
- M3Care: Learning with Missing Modalities in Multimodal Healthcare Data
- Forecasting Local Behavior of Self-organizing Many-agent System without Reconstruction
- Anomaly Detection in Additive Manufacturing Processes using Supervised Classification with Imbalanced Sensor Data based on Generative Adversarial Network
- Reinforcement Learning-based Defect Mitigation for Quality Assurance of Additive Manufacturing
- GowFed -- A novel Federated Network Intrusion Detection System
- ODNet: A Convolutional Neural Network for Asteroid Occultation Detection
- Scalable Spectral Clustering with Group Fairness Constraints
- DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention
- Visually-Aware Audio Captioning With Adaptive Audio-Visual Attention
- Toward Unifying Text Segmentation and Long Document Summarization
- Meta-Learning Biologically Plausible Plasticity Rules with Random Feedback Pathways
- When does mixup promote local linearity in learned representations?
- A State-Augmented Approach for Learning Optimal Resource Management Decisions in Wireless Networks
- Recurrent Convolutional Deep Neural Networks for Modeling Time-Resolved Wildfire Spread Behavior
- Just-DREAM-about-it: Figurative Language Understanding with DREAM-FLUTE
- Evaluation of Categorical Generative Models -- Bridging the Gap Between Real and Synthetic Data
- GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity
- The Fisher-Rao Loss for Learning under Label Noise
- Flatter, faster: scaling momentum for optimal speedup of SGD
- U-Net-based Models for Skin Lesion Segmentation: More Attention and Augmentation
- System Demo: Tool and Infrastructure for Offensive Language Error Analysis (OLEA) in English
- Physics-aware Graph Neural Network for Accurate RNA 3D Structure Prediction
- Radically Lower Data-Labeling Costs for Visually Rich Document Extraction Models
- Non-Stationary Bandits with Auto-Regressive Temporal Dependency
- Incorporating Crowdsourced Annotator Distributions into Ensemble Modeling to Improve Classification Trustworthiness for Ancient Greek Papyri
- SoftBart: Soft Bayesian Additive Regression Trees
- Continuous Attribution of Episodical Outcomes for More Efficient and Targeted Online Measurement
- Distributed Black-box Attack: Do Not Overestimate Black-box Attacks
- Elastic Weight Consolidation Improves the Robustness of Self-Supervised Learning Methods under Transfer
- Predicting Brain Age using Transferable coVariance Neural Networks
- Improving Hyperspectral Adversarial Robustness Under Multiple Attacks
- Estimating oil recovery factor using machine learning: Applications of XGBoost classification
- Learning to Detect Interesting Anomalies
- Filter and evolve: progressive pseudo label refining for semi-supervised automatic speech recognition
- The secret role of undesired physical effects in accurate shape sensing with eccentric FBGs
- Beyond calibration: estimating the grouping loss of modern neural networks
- Hierarchical Automatic Power Plane Generation with Genetic Optimization and Multilayer Perceptron
- AGReE: A system for generating Automated Grammar Reading Exercises
- Investigating Ensemble Methods for Model Robustness Improvement of Text Classifiers
- Learning Modular Simulations for Homogeneous Systems
- A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks
- Boulders Identification on Small Bodies Under Varying Illumination Conditions
- SEMPAI: a Self-Enhancing Multi-Photon Artificial Intelligence for prior-informed assessment of muscle function and pathology
- Learning with Multigraph Convolutional Filters
- Space-Time Graph Neural Networks with Stochastic Graph Perturbations
- Efficient Speech Translation with Dynamic Latent Perceivers
- DOORS: Dataset fOr bOuldeRs Segmentation. Statistical properties and Blender setup
- Latent Space is Feature Space: Regularization Term for GANs Training on Limited Dataset
- Applying Physics-Informed Enhanced Super-Resolution Generative Adversarial Networks to Turbulent Non-Premixed Combustion on Non-Uniform Meshes and Demonstration of an Accelerated Simulation Workflow
- Nonparametric Probabilistic Regression with Coarse Learners
- Design of Convolutional Extreme Learning Machines for Vision-Based Navigation Around Small Bodies
- Towards solving model bias in cosmic shear forward modeling
- Differential Privacy has Bounded Impact on Fairness in Classification
- Universal speaker recognition encoders for different speech segments duration
- Probing for targeted syntactic knowledge through grammatical error detection
- Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions
- Applying Physics-Informed Enhanced Super-Resolution Generative Adversarial Networks to Finite-Rate-Chemistry Flows and Predicting Lean Premixed Gas Turbine Combustors
- Physics-Informed Convolutional Neural Networks for Corruption Removal on Dynamical Systems
- Applying Physics-Informed Enhanced Super-Resolution Generative Adversarial Networks to Turbulent Premixed Combustion and Engine-like Flame Kernel Direct Numerical Simulation Data
- Local Model Reconstruction Attacks in Federated Learning and their Uses
- TripletTrack: 3D Object Tracking using Triplet Embeddings and LSTM
- Convergence analysis of a quasi-Monte Carlo-based deep learning algorithm for solving partial differential equations
- Environment-aware Interactive Movement Primitives for Object Reaching in Clutter
- On the Exactness of Dantzig-Wolfe Relaxation for Rank Constrained Optimization Problems
- Transferable E(3) equivariant parameterization for Hamiltonian of molecules and solids
- Preferential Subsampling for Stochastic Gradient Langevin Dynamics
- Aggregation in the Mirror Space (AIMS): Fast, Accurate Distributed Machine Learning in Military Settings
- A Novel Sparse Bayesian Learning and Its Application to Fault Diagnosis for Multistation Assembly Systems
- Game-Theoretical Perspectives on Active Equilibria: A Preferred Solution Concept over Nash Equilibria
All 212
- Multimodal Transformer for Parallel Concatenated Variational Autoencoders
- LOFT: Finding Lottery Tickets through Filter-wise Training
- Feature Engineering vs BERT on Twitter Data
- Are Neural Topic Models Broken?
- Reliability of CKA as a Similarity Measure in Deep Learning
- Modeling structure-building in the brain with CCG parsing and large language models
- Towards trustworthy multi-modal motion prediction: Holistic evaluation and interpretability of outputs
- Federated Learning for Chronic Obstructive Pulmonary Disease Classification with Partial Personalized Attention Mechanism
- Localized Randomized Smoothing for Collective Robustness Certification
- Stop Measuring Calibration When Humans Disagree
- Imitation Learning-based Implicit Semantic-aware Communication Networks: Multi-layer Representation and Collaborative Reasoning
- Improving the Transferability of Adversarial Attacks on Face Recognition with Beneficial Perturbation Feature Augmentation
- Towards Reliable Neural Specifications
- Towards prediction of turbulent flows at high Reynolds numbers using high performance computing data and deep learning
- Efficient and Light-Weight Federated Learning via Asynchronous Distributed Dropout
- cRedAnno+: Annotation Exploitation in Self-Explanatory Lung Nodule Diagnosis
- A CNN-LSTM Combination Network for Cataract Detection using Eye Fundus Images
- ROMA: Run-Time Object Detection To Maximize Real-Time Accuracy
- Object Segmentation of Cluttered Airborne LiDAR Point Clouds
- RESUS: Warm-Up Cold Users via Meta-Learning Residual User Preferences in CTR Prediction
- Debiasing Masks: A New Framework for Shortcut Mitigation in NLU
- Adaptive Mask-based Pyramid Network for Realistic Bokeh Rendering
- Improving Chest X-Ray Classification by RNN-based Patient Monitoring
- DORE: Document Ordered Relation Extraction based on Generative Framework
- Neural Network based Formation of Cognitive Maps of Semantic Spaces and the Emergence of Abstract Concepts
- Deep network series for large-scale high-dynamic range imaging
- An Artificial Intelligence driven Learning Analytics Method to Examine the Collaborative Problem solving Process from a Complex Adaptive Systems Perspective
- Goal Exploration Augmentation via Pre-trained Skills for Sparse-Reward Long-Horizon Goal-Conditioned Reinforcement Learning
- Automated analysis of diabetic retinopathy using vessel segmentation maps as inductive bias
- Fuzzy Logic Model for Predicting the Heat Index
- Measuring the Confidence of Traffic Forecasting Models: Techniques, Experimental Comparison and Guidelines towards Their Actionability
- Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environments
- Towards zero-shot Text-based voice editing using acoustic context conditioning, utterance embeddings, and reference encoders
- Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models
- Review on Classification Techniques used in Biophysiological Stress Monitoring
- Deep Learning-Based Anomaly Detection in Synthetic Aperture Radar Imaging
- A Survey on Causal Representation Learning and Future Work for Medical Image Analysis
- Improving Multi-class Classifier Using Likelihood Ratio Estimation with Regularization
- Assessing Phrase Break of ESL speech with Pre-trained Language Models
- Addressing Bias in Face Detectors using Decentralised Data collection with incentives
- Data-driven discovery of Green's functions
- UzbekStemmer: Development of a Rule-Based Stemming Algorithm for Uzbek Language
- Development of a rule-based lemmatization algorithm through Finite State Machine for Uzbek language
- Evaluating the Impact of Loss Function Variation in Deep Learning for Classification
- Online Learning Models for Vehicle Usage Prediction During COVID-19
- Thermal Infrared Image Inpainting via Edge-Aware Guidance
- Benchmarking performance of object detection under image distortions in an uncontrolled environment
- Universal Adversarial Directions
- Towards Generalized Few-Shot Open-Set Object Detection
- Spectrograms Are Sequences of Patches
- NNSVS: A Neural Network-Based Singing Voice Synthesis Toolkit
- Differentially Private CutMix for Split Learning with Vision Transformer
- Understanding Adverse Biological Effect Predictions Using Knowledge Graphs
- FedVMR: A New Federated Learning method for Video Moment Retrieval
- BEBERT: Efficient and Robust Binary Ensemble BERT
- Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform
- Contextual Learning in Fourier Complex Field for VHR Remote Sensing Images
- System Network Analytics: Evolution and Stable Rules of a State Series
- Period VITS: Variational Inference with Explicit Pitch Modeling for End-to-end Emotional Speech Synthesis
- DPVIm: Differentially Private Variational Inference Improved
- Generalized Laplacian Positional Encoding for Graph Representation Learning
- Stanceosaurus: Classifying Stance Towards Multilingual Misinformation
- LBF:Learnable Bilateral Filter For Point Cloud Denoising
- IB-U-Nets: Improving medical image segmentation tasks with 3D Inductive Biased kernels
- Matching entropy based disparity estimation from light field
- NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields
- RoChBert: Towards Robust BERT Fine-tuning for Chinese
- Grafting Vision Transformers
- On the Use of Modality-Specific Large-Scale Pre-Trained Encoders for Multimodal Sentiment Analysis
- Multiresolution Signal Processing of Financial Market Objects
- PSFormer: Point Transformer for 3D Salient Object Detection
- Being Comes from Not-being: Open-vocabulary Text-to-Motion Generation with Wordless Training
- Comparison of Stereo Matching Algorithms for the Development of Disparity Map
- Incorporating Interactive Facts for Stock Selection via Neural Recursive ODEs
- DELFI: Deep Mixture Models for Long-term Air Quality Forecasting in the Delhi National Capital Region
- GeoGCN: Geometric Dual-domain Graph Convolution Network for Point Cloud Denoising
- Joint Semantic Transfer Network for IoT Intrusion Detection
- Subsidiary Prototype Alignment for Universal Domain Adaptation
- Long-HOT: A Modular Hierarchical Approach for Long-Horizon Object Transport
- Self-Supervised Learning with Multi-View Rendering for 3D Point Cloud Analysis
- Learning to Immunize Images for Tamper Localization and Self-Recovery
- Mitigating Health Disparities in EHR via Deconfounder
- Toward Equation of Motion for Deep Neural Networks: Continuous-time Gradient Descent and Discretization Error Analysis
- Single-Image HDR Reconstruction by Multi-Exposure Generation
- Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing
- Nonparallel High-Quality Audio Super Resolution with Domain Adaptation and Resampling CycleGANs
- Can Current Explainability Help Provide References in Clinical Notes to Support Humans Annotate Medical Codes?
- Complex Handwriting Trajectory Recovery: Evaluation Metrics and Algorithm
- Facial Action Unit Detection and Intensity Estimation from Self-supervised Representation
- Random Utterance Concatenation Based Data Augmentation for Improving Short-video Speech Recognition
- Exploring Spatial-Temporal Features for Deepfake Detection and Localization
- VLT: Vision-Language Transformer and Query Generation for Referring Segmentation
- "It's Not Just Hate'': A Multi-Dimensional Perspective on Detecting Harmful Speech Online
- Residual Adapters for Few-Shot Text-to-Speech Speaker Adaptation
- Completely Heterogeneous Federated Learning
- Domain Adaptation of Machine Translation with Crowdworkers
- You can't pick your neighbors, or can you? When and how to rely on retrieval in the kNN-LM
- Vox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representation
- Improving Zero-Shot Multilingual Translation with Universal Representations and Cross-Mappings
- Federated Learning based Energy Demand Prediction with Clustered Aggregation
- Bi-Directional Iterative Prompt-Tuning for Event Argument Extraction
- Leveraging Label Correlations in a Multi-label Setting: A Case Study in Emotion
- Risk-Aware Bid Optimization for Online Display Advertisement
- Domain Generalization through the Lens of Angular Invariance
- GM-TCNet: Gated Multi-scale Temporal Convolutional Network using Emotion Causality for Speech Emotion Recognition
- Federated Learning with Intermediate Representation Regularization
- Improving the Modality Representation with Multi-View Contrastive Learning for Multimodal Sentiment Analysis
- Instance-Optimal Differentially Private Estimation
- FUSSL: Fuzzy Uncertain Self Supervised Learning
- Differentiable Analog Quantum Computing for Optimization and Control
- Coverage-centric Coreset Selection for High Pruning Rates
- Hyper-Connected Transformer Network for Multi-Modality PET-CT Segmentation