Papers
Mon 18 Oct 2021
203 papers
- A Data Bootstrapping Recipe for Low Resource Multilingual Relation ClassificationSynthetic data and self-improvement for LLMs → LLM synthetic data generation
- Discovering and Achieving Goals via World ModelsWorld models → Embodied and robot world models
- Goal Agnostic Planning using Maximum Likelihood Paths in Hypergraph World ModelsWorld models → Latent predictive world models
- Value alignment: a formal approachLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
- SS-MAIL: Self-Supervised Multi-Agent Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- A Framework for Deprecating Datasets: Standardizing Documentation, Identification, and Communication
- A Survey of Human Activity Recognition in Smart Homes Based on IoT Sensors Algorithms: Taxonomies, Challenges, and Opportunities with Deep Learning
- BERMo: What can BERT learn from ELMo?
- Dendritic Self-Organizing Maps for Continual Learning
- Embracing advanced AI/ML to help investors achieve success: Vanguard Reinforcement Learning for Financial Goal Planning
- Self-supervised denoising for massive noisy images
- Game Redesign in No-regret Game Playing
- SCENIC: A JAX Library for Computer Vision Research and Beyond
- Trajectory Prediction using Generative Adversarial Network in Multi-Class Scenarios
- Channel redundancy and overlap in convolutional neural networks with channel-wise NNK graphs
- A Systematic Review on the Detection of Fake News Articles
- Enabling a Social Robot to Process Social Cues to Detect when to Help a User
- RL4RS: A Real-World Dataset for Reinforcement Learning based Recommender System
- Sequential Modeling with Multiple Attributes for Watchlist Recommendation in E-Commerce
- Hybrid-Layers Neural Network Architectures for Modeling the Self-Interference in Full-Duplex Systems
- Speech Representation Learning Through Self-supervised Pretraining And Multi-task Finetuning
- Minimal Multi-Layer Modifications of Deep Neural Networks
- CycleFlow: Purify Information Factors by Cycle Loss
- Conditional De-Identification of 3D Magnetic Resonance Images
- BEV-SGD: Best Effort Voting SGD for Analog Aggregation Based Federated Learning against Byzantine Attackers
- System Norm Regularization Methods for Koopman Operator Approximation
- Estimating the Arc Length of the Optimal ROC Curve and Lower Bounding the Maximal AUC
- Relational Neural Markov Random Fields
- Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement
- Dynamic Feature Alignment for Semi-supervised Domain Adaptation
- A cautionary tale on fitting decision trees to data from additive models: generalization lower bounds
- Personalized Speech Enhancement: New Models and Comprehensive Evaluation
- Ideal Partition of Resources for Metareasoning
- Robust Representation and Efficient Feature Selection Allows for Effective Clustering of SARS-CoV-2 Variants
- Sufficient Dimension Reduction for High-Dimensional Regression and Low-Dimensional Embedding: Tutorial and Survey
- Further Generalizations of the Jaccard Index
- Interpolating between sampling and variational inference with infinite stochastic mixtures
- A Survey on Machine Learning Techniques for Source Code Analysis
- Efficient Analysis of COVID-19 Clinical Data using Machine Learning Models
- Neural Synthesis of Footsteps Sound Effects with Generative Adversarial Networks
- Label-Descriptive Patterns and Their Application to Characterizing Classification Errors
- Adversarial Domain Adaptation with Paired Examples for Acoustic Scene Classification on Different Recording Devices
- A-Optimal Active Learning
- Permutation Invariance of Deep Neural Networks with ReLUs
- Multilingual Domain Adaptation for NMT: Decoupling Language and Domain Information with Adapters
- Hands Off: A Handshake Interaction Detection and Localization Model for COVID-19 Threat Control
- BGaitR-Net: Occluded Gait Sequence reconstructionwith temporally constrained model for gait recognition
- TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation
- Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks
- Wideband and Entropy-Aware Deep Soft Bit Quantization
- Eigenbehaviour as an Indicator of Cognitive Abilities
- Understanding GNN Computational Graph: A Coordinated Computation, IO, and Memory Perspective
- Unsupervised Finetuning
- Deep CNNs for Peripheral Blood Cell Classification
- Provable Hierarchy-Based Meta-Reinforcement Learning
- MEMO: Test Time Robustness via Adaptation and Augmentation
- Minimum ℓ1-norm interpolators: Precise asymptotics and multiple descent
- Protecting Anonymous Speech: A Generative Adversarial Network Methodology for Removing Stylistic Indicators in Text
- Unsupervised Image Fusion Using Deep Image Priors
- Sector Volatility Prediction Performance Using GARCH Models and Artificial Neural Networks
- Learning in High Dimension Always Amounts to Extrapolation
- Self-Supervised Monocular Depth Estimation with Internal Feature Fusion
- MTP: Multi-Hypothesis Tracking and Prediction for Reduced Error Propagation
- Recovery Guarantees for Kernel-based Clustering under Non-parametric Mixture Models
- DBSegment: Fast and robust segmentation of deep brain structures -- Evaluation of transportability across acquisition domains
- No RL, No Simulation: Learning to Navigate without Navigating
- Improving Robustness using Generated Data
- On Predictive Explanation of Data Anomalies
- In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications
- NormFormer: Improved Transformer Pretraining with Extra Normalization
- TLDR: Twin Learning for Dimensionality Reduction
- SentimentArcs: A Novel Method for Self-Supervised Sentiment Analysis of Time Series Shows SOTA Transformers Can Struggle Finding Narrative Arcs
- SPAP: Simultaneous Demand Prediction and Planning for Electric Vehicle Chargers in a New City
- Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning
- Beltrami Flow and Neural Diffusion on Graphs
- FMFCC-A: A Challenging Mandarin Dataset for Synthetic Speech Detection
- Comparing Deep Neural Nets with UMAP Tour
- Distinguishing Natural and Computer-Generated Images using Multi-Colorspace fused EfficientNet
- FacialGAN: Style Transfer and Attribute Manipulation on Synthetic Faces
- Don't Judge Me by My Face : An Indirect Adversarial Approach to Remove Sensitive Information From Multimodal Neural Representation in Asynchronous Job Video Interviews
- Measuring Cognitive Status from Speech in a Smart Home Environment
- Compositional Attention: Disentangling Search and Retrieval
- NeuralBlox: Real-Time Neural Representation Fusion for Robust Volumetric Mapping
- Exploiting Domain-Specific Features to Enhance Domain Generalization
- HRFormer: High-Resolution Transformer for Dense Prediction
- Mesh Convolutional Autoencoder for Semi-Regular Meshes of Different Sizes
- Ceasing hate withMoH: Hate Speech Detection in Hindi-English Code-Switched Language
- Neuro-Symbolic Forward Reasoning
- Learning multiplane images from single views with self-supervision
- Forecasting Nonverbal Social Signals during Dyadic Interactions with Generative Adversarial Neural Networks
- Ortho-Shot: Low Displacement Rank Regularization with Data Augmentation for Few-Shot Learning
- Efficient Exploration in Binary and Preferential Bayesian Optimization
- Prediction of liquid fuel properties using machine learning models with Gaussian processes and probabilistic conditional generative learning
- Towards Federated Bayesian Network Structure Learning with Continuous Optimization
- FAST3D: Flow-Aware Self-Training for 3D Object Detectors
- An Analysis and Implementation of the HDR+ Burst Denoising Method
- Understanding Dimensional Collapse in Contrastive Self-supervised Learning
- ifMixup: Interpolating Graph Pair to Regularize Graph Classification
- Contextual Hate Speech Detection in Code Mixed Text using Transformer Based Approaches
- A portfolio approach to massively parallel Bayesian optimization
All 203
- Regression with Missing Data, a Comparison Study of TechniquesBased on Random Forests
- Result Diversification by Multi-objective Evolutionary Algorithms with Theoretical Guarantees
- Self-Supervised Representation Learning: Introduction, Advances and Challenges
- Graph convolutional network for predicting abnormal grain growth in Monte Carlo simulations of microstructural evolution
- Automatic Learning of Subword Dependent Model Scales
- Incremental Cross-Domain Adaptation for Robust Retinopathy Screening via Bayesian Deep Learning
- Energon: Towards Efficient Acceleration of Transformers Using Dynamic Sparse Attention
- "Sparse + Low-Rank'' Tensor Completion Approach for Recovering Images and Videos
- Fair Tree Classifier using Strong Demographic Parity
- A Lightweight and Accurate Recognition Framework for Signs of X-ray Weld Images
- Natural Attribute-based Shift Detection
- pygrank: A Python Package for Graph Node Ranking
- Boosting Image Outpainting with Semantic Layout Prediction
- Intent Classification Using Pre-trained Language Agnostic Embeddings For Low Resource Languages
- A Unified Framework for Generalized Low-Shot Medical Image Segmentation with Scarce Data
- Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection
- Efficient Sequence Training of Attention Models using Approximative Recombination
- Leveraging MoCap Data for Human Mesh Recovery
- Video Coding for Machine: Compact Visual Representation Compression for Intelligent Collaborative Analytics
- Color Image Segmentation Using Multi-Objective Swarm Optimizer and Multi-level Histogram Thresholding
- The Arabic Parallel Gender Corpus 2.0: Extensions and Analyses
- Noise-Resilient Ensemble Learning using Evidence Accumulation Clustering
- Graph-based Local Climate Classification in Iran
- Correlation-based Discovery of Disease Patterns for Syndromic Surveillance
- Finding Strong Gravitational Lenses Through Self-Attention
- On the Completeness and Complexity of the Lifted Dynamic Junction Tree Algorithm
- Option Transfer and SMDP Abstraction with Successor Features
- Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks
- Topologically Regularized Data Embeddings
- Learning Optimal Conformal Classifiers
- Graph Partner Neural Networks for Semi-Supervised Learning on Graphs
- Analysis of French Phonetic Idiosyncrasies for Accent Recognition
- A Formalisation of Abstract Argumentation in Higher-Order Logic
- Projected Model Counting: Beyond Independent Support
- Continuation of Famous Art with AI: A Conditional Adversarial Network Inpainting Approach
- Domain Generalisation for Apparent Emotional Facial Expression Recognition across Age-Groups
- RKHS-SHAP: Shapley Values for Kernel Methods
- Speeding-Up Back-Propagation in DNN: Approximate Outer Product with Memory
- A Dimensionality Reduction Approach for Convolutional Neural Networks
- Newsalyze: Effective Communication of Person-Targeting Biases in News Articles
- Disentangled Representation with Dual-stage Feature Learning for Face Anti-spoofing
- Lifting DecPOMDPs for Nanoscale Systems -- A Work in Progress
- How to Effectively Identify and Communicate Person-Targeting Media Bias in Daily News Consumption?
- Body Part Regression for CT Images
- BEAMetrics: A Benchmark for Language Generation Evaluation Evaluation
- SynCoLFinGer: Synthetic Contactless Fingerprint Generator
- Learning Prototype-oriented Set Representations for Meta-Learning
- State-Space Constraints Can Improve the Generalisation of the Differentiable Neural Computer to Input Sequences With Unseen Length
- GAN-based disentanglement learning for chest X-ray rib suppression
- Online Sign Identification: Minimization of the Number of Errors in Thresholding Bandits
- EmbRace: Accelerating Sparse Communication for Distributed Training of NLP Neural Networks
- Ensembling Graph Predictions for AMR Parsing
- Deep Models with Fusion Strategies for MVP Point Cloud Registration
- SpecTNT: a Time-Frequency Transformer for Music Audio
- Real Additive Margin Softmax for Speaker Verification
- Salt and pepper noise removal method based on stationary Framelet transform with non-convex sparsity regularization
- Analyzing Wikipedia Membership Dataset and PredictingUnconnected Nodes in the Signed Networks
- Graph Convolution Neural Network For Weakly Supervised Abnormality Localization In Long Capsule Endoscopy Videos
- Patch-Based Deep Autoencoder for Point Cloud Geometry Compression
- Asymmetric Modality Translation For Face Presentation Attack Detection
- Differentiable Rendering with Perturbed Optimizers
- LDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speech
- Vega: A 10-Core SoC for IoT End-Nodes with DNN Acceleration and Cognitive Wake-Up From MRAM-Based State-Retentive Sleep Mode
- Using Natural Language Processing to Understand Reasons and Motivators Behind Customer Calls in Financial Domain
- ViraPart: A Text Refinement Framework for Automatic Speech Recognition and Natural Language Processing Tasks in Persian
- Learning to Learn a Cold-start Sequential Recommender
- An actor-critic algorithm with policy gradients to solve the job shop scheduling problem using deep double recurrent agents
- Boosting the Transferability of Video Adversarial Examples via Temporal Translation
- Towards General Deep Leakage in Federated Learning
- Semi-asynchronous Hierarchical Federated Learning for Cooperative Intelligent Transportation Systems
- Unsupervised Shot Boundary Detection for Temporal Segmentation of Long Capsule Endoscopy Videos
- Discovery-and-Selection: Towards Optimal Multiple Instance Learning for Weakly Supervised Object Detection
- Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization
- Strategizing University Rank Improvement using Interpretable Machine Learning and Data Visualization
- Abnormal Occupancy Grid Map Recognition using Attention Network
- Kernel-based estimation for partially functional linear model: Minimax rates and randomized sketches
- A Bayesian approach to multi-task learning with network lasso
- Capsule Graph Neural Networks with EM Routing
- Ranking Facts for Explaining Answers to Elementary Science Questions
- Edge Rewiring Goes Neural: Boosting Network Resilience without Rich Features
- Fast tree skeleton extraction using voxel thinning based on tree point cloud
- Arjun: An Efficient Independent Support Computation Technique and its Applications to Counting and Sampling
- Utilizing Active Machine Learning for Quality Assurance: A Case Study of Virtual Car Renderings in the Automotive Industry
- Mitigating Memorization of Noisy Labels via Regularization between Representations
- Reinforcement Learning-Based Coverage Path Planning with Implicit Cellular Decomposition
- When Are Linear Stochastic Bandits Attackable?
- Natural Image Reconstruction from fMRI using Deep Learning: A Survey
- Unsupervised Learned Kalman Filtering
- NYU-VPR: Long-Term Visual Place Recognition Benchmark with View Direction and Data Anonymization Influences
- Deep Learning-Based Power Control for Uplink Cell-Free Massive MIMO Systems
- Finding Everything within Random Binary Networks
- CMTR: Cross-modality Transformer for Visible-infrared Person Re-identification
- Dimensionality Reduction for Wasserstein Barycenter
- Valid and Exact Statistical Inference for Multi-dimensional Multiple Change-Points by Selective Inference
- FEANet: Feature-Enhanced Attention Network for RGB-Thermal Real-time Semantic Segmentation
- StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis
- Optimistic Policy Optimization is Provably Efficient in Non-stationary MDPs
- Accurate and Robust Object-oriented SLAM with 3D Quadric Landmark Construction in Outdoor Environment
- Deep Transfer Learning & Beyond: Transformer Language Models in Information Systems Research
- Improving Robustness of Reinforcement Learning for Power System Control with Adversarial Training
- Predicting Rebar Endpoints using Sin Exponential Regression Model
- Uncertainty-Aware Semi-Supervised Few Shot Segmentation
- Sim-to-Real Transfer in Multi-agent Reinforcement Networking for Federated Edge Computing