Papers
Wed 13 Oct 2021
218 papers
- Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration EnhancementEnd-to-end autonomous driving → Reinforcement learning for driving +1
- Poison Forensics: Traceback of Data Poisoning Attacks in Neural NetworksLLM safety and security → Backdoor and data poisoning attacks
- Safe Driving via Expert Guided Policy OptimizationEnd-to-end autonomous driving → Reinforcement learning for driving
- Simple or Complex? Complexity-Controllable Question Generation with Soft Templates and Deep Mixture of Experts ModelMixture-of-experts → MoE large language models
- On Covariate Shift of Latent Confounders in Imitation and Reinforcement LearningOffline RL and imitation learning from data → Imitation learning methods
- E-Commerce Dispute Resolution Prediction
- Decision Attentive Regularization to Improve Simultaneous Speech Translation Systems
- Improving the Search by Encoding Multiple Solutions in a Chromosome
- Positional-Spectral-Temporal Attention in 3D Convolutional Neural Networks for EEG Emotion Recognition
- A Review of 3D Face Reconstruction From a Single Image
- C-AllOut: Catching & Calling Outliers by Type
- Model-Agnostic Meta-Attack: Towards Reliable Evaluation of Adversarial Robustness
- Yformer: U-Net Inspired Transformer Architecture for Far Horizon Time Series Forecasting
- Inconsistent Few-Shot Relation Classification via Cross-Attentional Prototype Networks with Contrastive Learning
- A Field Guide to Scientific XAI: Transparent and Interpretable Deep Learning for Bioinformatics Research
- Quantifying Local Specialization in Deep Neural Networks
- Adversarial Attack across Datasets
- Adversarial Scene Reconstruction and Object Detection System for Assisting Autonomous Vehicle
- Multiple Style Transfer via Variational AutoEncoder
- The Impact of Spatiotemporal Augmentations on Self-Supervised Audiovisual Representation Learning
- Modeling and Analysis of Intermittent Federated Learning Over Cellular-Connected UAV Networks
- Fast Hand Detection in Collaborative Learning Environments
- CloudPred: Predicting Patient Phenotypes From Single-cell RNA-seq
- An algorithm for a fairer and better voting system
- Variance Minimization in the Wasserstein Space for Invariant Causal Prediction
- Subspace Regularizers for Few-Shot Class Incremental Learning
- Ego4D: Around the World in 3,000 Hours of Egocentric Video
- High-throughput Phenotyping of Nematode Cysts
- Continual learning using lattice-free MMI for speech recognition
- Robust MIMO Detection using Hypernetworks with Learned Regularizers
- Deep Metric Learning with Locality Sensitive Angular Loss for Self-Correcting Source Separation of Neural Spiking Signals
- Why Out-of-distribution Detection in CNNs Does Not Like Mahalanobis -- and What to Use Instead
- Data Incubation -- Synthesizing Missing Data for Handwriting Recognition
- Towards Efficient NLP: A Standard Evaluation and A Strong Baseline
- Bond Default Prediction with Text Embeddings, Undersampling and Deep Learning
- How Does Momentum Benefit Deep Neural Networks Architecture Design? A Few Case Studies
- Compliance checking in reified IO logic via SHACL
- Improving the Robustness to Variations of Objects and Instructions with a Neuro-Symbolic Approach for Interactive Instruction Following
- Adaptive Elastic Training for Sparse Deep Learning on Heterogeneous Multi-GPU Servers
- AI Total: Analyzing Security ML Models with Imperfect Data in Production
- Comparison of SVD and factorized TDNN approaches for speech to text
- Solving the Families In the Wild Kinship Verification Challenge by Program Synthesis
- Leveraging Generative Models for Covert Messaging: Challenges and Tradeoffs for "Dead-Drop" Deployments
- Out-of-Distribution Robustness in Deep Learning Compression
- On the Convergence Theory for Hessian-Free Bilevel Algorithms
- Sustainability Through Cognition Aware Safety Systems -- Next Level Human-Machine-Interaction
- Bag-of-Vectors Autoencoders for Unsupervised Conditional Text Generation
- Study of positional encoding approaches for Audio Spectrogram Transformers
- Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits
- A Novel Clustering-Based Algorithm for Continuous and Non-invasive Cuff-Less Blood Pressure Estimation
- Scalable Graph Embedding LearningOn A Single GPU
- Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers
- ADMM-DAD net: a deep unfolding network for analysis compressed sensing
- Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one Maps
- FlexiTerm: A more efficient implementation of flexible multi-word term recognition
- Output Space Entropy Search Framework for Multi-Objective Bayesian Optimization
- WAFFLE: Weighted Averaging for Personalized Federated Learning
- Representational Continuity for Unsupervised Continual Learning
- Block Contextual MDPs for Continual Learning
- Interpretable AI forecasting for numerical relativity waveforms of quasi-circular, spinning, non-precessing binary black hole mergers
- Open-Domain Question-Answering for COVID-19 and Other Emergent Domains
- Language Modelling via Learning to Rank
- Considering user agreement in learning to predict the aesthetic quality
- Challenges for Unsupervised Anomaly Detection in Particle Physics
- Style-based quantum generative adversarial networks for Monte Carlo events
- A neural simulation-based inference approach for characterizing the Galactic Center γ-ray excess
- Object DGCNN: 3D Object Detection using Dynamic Graphs
- DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries
- Semantics-aware Attention Improves Neural Machine Translation
- Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?
- Extracting Dynamical Models from Data
- Object-Region Video Transformers
- What Happens after SGD Reaches Zero Loss? --A Mathematical Framework
- OPEn: An Open-ended Physics Environment for Learning Without a Task
- On the Double Descent of Random Features Models Trained with SGD
- Reinforcement Learning for Standards Design
- PER-ETD: A Polynomially Efficient Emphatic Temporal Difference Learning Method
- Teaching Models new APIs: Domain-Agnostic Simulators for Task Oriented Dialogue
- Representing and Implementing Matrices Using Algebraic ZX-calculus
- Machine Learning For Elliptic PDEs: Fast Rate Generalization Bound, Neural Scaling Law and Minimax Optimality
- Audio-Visual Scene-Aware Dialog and Reasoning using Audio-Visual Transformers with Joint Student-Teacher Learning
- Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance
- TAG: Toward Accurate Social Media Content Tagging with a Concept Graph
- Extending Environments To Measure Self-Reflection In Reinforcement Learning
- ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answers
- A Review on Human Pose Estimation
- Automated Essay Scoring Using Transformer Models
- Two-argument activation functions learn soft XOR operations like cortical neurons
- Bayesian logistic regression for online recalibration and revision of risk prediction models with performance guarantees
- Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments
- ByteTrack: Multi-Object Tracking by Associating Every Detection Box
- Improving Users' Mental Model with Attention-directed Counterfactual Edits
- Attentive and Contrastive Learning for Joint Depth and Motion Field Estimation
- Morphosyntactic Tagging with Pre-trained Language Models for Arabic and its Dialects
- Fast Posterior Estimation of Cardiac Electrophysiological Model Parameters via Bayesian Active Learning
- Boosting the Certified Robustness of L-infinity Distance Nets
- Decoupled Contrastive Learning
- Ousiometrics: The essence of meaning aligns with a power-danger-structure framework instead of valence-arousal-dominance
- Compositional Generalization in Dependency Parsing
- On Language Model Integration for RNN Transducer based Speech Recognition
All 218
- CONetV2: Efficient Auto-Channel Size Optimization for CNNs
- Towards a fully RL-based Market Simulator
- NoisyActions2M: A Multimedia Dataset for Video Understanding from Noisy Labels
- A Speaker-aware Parallel Hierarchical Attentive Encoder-Decoder Model for Multi-turn Dialogue Generation
- Leveraging redundancy in attention with Reuse Transformers
- Optical Character Recognition of 19th Century Classical Commentaries: the Current State of Affairs
- A Framework for Verification of Wasserstein Adversarial Robustness
- Learn to Ignore: Domain Adaptation for Multi-Site MRI Analysis
- Identification of Attack-Specific Signatures in Adversarial Examples
- SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systems
- Adapting to Dynamic LEO-B5G Systems: Meta-Critic Learning Based Efficient Resource Scheduling
- Optical Flow Reusing for High-Efficiency Space-Time Video Super Resolution
- Incremental Ensemble Gaussian Processes
- Leveraging Automated Unit Tests for Unsupervised Code Translation
- Next-Best-View Estimation based on Deep Reinforcement Learning for Active Object Classification
- Efficient Estimation in NPIV Models: A Comparison of Various Neural Networks-Based Estimators
- HEDP: A Method for Early Forecasting Software Defects based on Human Error Mechanisms
- Learning Meta Pattern for Face Anti-Spoofing
- Improving the sample-efficiency of neural architecture search with reinforcement learning
- Masader: Metadata Sourcing for Arabic Text and Speech Data Resources
- A Review of the Deep Sea Treasure problem as a Multi-Objective Reinforcement Learning Benchmark
- Dynamical Wasserstein Barycenters for Time-series Modeling
- Transform and Bitstream Domain Image Classification
- Collaborative Semantic Aggregation and Calibration for Federated Domain Generalization
- A Time Encoding approach to training Spiking Neural Networks
- Systematic Inequalities in Language Technology Performance across the World's Languages
- RelationRS: Relationship Representation Network for Object Detection in Aerial Images
- Scalable Anytime Algorithms for Learning Fragments of Linear Temporal Logic
- The Computerized Classification of Micro-Motions in the Hand using Waveforms from Mobile Phone
- On the Parameter Combinations That Matter and on Those That do Not
- Expert-driven Trace Clustering with Instance-level Constraints
- Semantic Image Fusion
- Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese
- DeepVecFont: Synthesizing High-quality Vector Fonts via Dual-modality Learning
- Plugging Self-Supervised Monocular Depth into Unsupervised Domain Adaptation for Semantic Segmentation
- Color Counting for Fashion, Art, and Design
- EditVAE: Unsupervised Part-Aware Controllable 3D Point Cloud Shape Generation
- Truthful AI: Developing and governing AI that does not lie
- The Deep Generative Decoder: MAP estimation of representations improves modeling of single-cell RNA data
- Tutorial on Deep Learning for Human Activity Recognition
- MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction
- Multistage linguistic conditioning of convolutional layers for speech emotion recognition
- Dictionary Learning with Convex Update (ROMD)
- Detecting Slag Formations with Deep Convolutional Neural Networks
- When saliency goes off on a tangent: Interpreting Deep Neural Networks with nonlinear saliency maps
- Knowledge Graph-enhanced Sampling for Conversational Recommender System
- ADOP: Approximate Differentiable One-Pixel Point Rendering
- End-to-end translation of human neural activity to speech with a dual-dual generative adversarial network
- Unsupervised Contrastive Learning with Simple Transformation for 3D Point Cloud Data
- Fuzzy Overclustering: Semi-Supervised Classification of Fuzzy Labels with Overclustering and Inverse Cross-Entropy
- Oriented Feature Alignment for Fine-grained Object Recognition in High-Resolution Satellite Imagery
- Identification of Metallic Objects using Spectral Magnetic Polarizability Tensor Signatures: Object Classification
- SSSNET: Semi-Supervised Signed Network Clustering
- Maximizing Efficiency of Language Model Pre-training for Learning Representation
- CLIP4Caption: CLIP for Video Caption
- Exploring Dense Retrieval for Dialogue Response Selection
- Metaparametric Neural Networks for Survival Analysis
- MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators
- THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling
- Vibration-Based Condition Monitoring By Ensemble Deep Learning
- Logic Constraints to Feature Importances
- Clustering-Based Interpretation of Deep ReLU Network
- Life is not black and white -- Combining Semi-Supervised Learning with fuzzy labels
- A Trust Crisis In Simulation-Based Inference? Your Posterior Approximations Can Be Unfaithful
- Hyperspectral 3D Mapping of Underwater Environments
- One to Multiple Mapping Dual Learning: Learning Multiple Sources from One Mixed Signal
- Deep Superpixel-based Network for Blind Image Quality Assessment
- Unsupervised Object Learning via Common Fate
- Infinitely Divisible Noise in the Low Privacy Regime
- LENS: Localization enhanced by NeRF synthesis
- Communication-Efficient Online Federated Learning Framework for Nonlinear Regression
- Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization
- Saliency Detection via Global Context Enhanced Feature Fusion and Edge Weighted Loss
- A Melody-Unsupervision Model for Singing Voice Synthesis
- EIHW-MTG DiCOVA 2021 Challenge System Report
- Well-classified Examples are Underestimated in Classification with Deep Neural Networks
- NeurIPS 2021 Competition IGLU: Interactive Grounded Language Understanding in a Collaborative Environment
- EventBERT: A Pre-Trained Model for Event Correlation Reasoning
- Finding Materialized Models for Model Reuse
- Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation
- Sub-Setting Algorithm for Training Data Selection in Pattern Recognition
- Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks
- Recommending POIs for Tourists by User Behavior Modeling and Pseudo-Rating
- 2D Multi-Class Model for Gray and White Matter Segmentation of the Cervical Spinal Cord at 7T
- Benchmarking the Robustness of Spatial-Temporal Models Against Corruptions
- MedNet: Pre-trained Convolutional Neural Network Model for the Medical Imaging Tasks
- The Dawn of Quantum Natural Language Processing
- Learning Stable Koopman Embeddings
- Perception Point: Identifying Critical Learning Periods in Speech for Bilingual Networks
- Prompt-tuning in ASR systems for efficient domain-adaptation
- Differentially Private Fine-tuning of Language Models
- Cross-lingual COVID-19 Fake News Detection
- Dict-BERT: Enhancing Language Model Pre-training with Dictionary
- The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program
- Understanding of Emotion Perception from Art
- Domain Adaptive Semantic Segmentation without Source Data
- Parallel Deep Neural Networks Have Zero Duality Gap
- Feudal Reinforcement Learning by Reading Manuals
- Winning the ICCV'2021 VALUE Challenge: Task-aware Ensemble and Transfer Learning with Visual Concepts
- SAR-Net: A Scenario-Aware Ranking Network for Personalized Fair Recommendation in Hundreds of Travel Scenarios
- ActiveEA: Active Learning for Neural Entity Alignment
- Graph-Fraudster: Adversarial Attacks on Graph Neural Network Based Vertical Federated Learning
- Dual-branch Attention-In-Attention Transformer for single-channel speech enhancement
- Breaking the Dilemma of Medical Image-to-image Translation
- Fake News Detection in Spanish Using Deep Learning Techniques
- Learning to Select Historical News Articles for Interaction based Neural News Recommendation
- Updating Street Maps using Changes Detected in Satellite Imagery
- Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment
- Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings
- Harnessing the Conditioning Sensorium for Improved Image Translation
- Non-local Recurrent Regularization Networks for Multi-view Stereo
- Dropout Prediction Uncertainty Estimation Using Neuron Activation Strength
- DeepA: A Deep Neural Analyzer For Speech And Singing Vocoding
- Dense Uncertainty Estimation
- Revisiting Latent-Space Interpolation via a Quantitative Evaluation Framework
- Federated Natural Language Generation for Personalized Dialogue System
- Stabilizing Dynamical Systems via Policy Gradient Methods
- MMIU: Dataset for Visual Intent Understanding in Multimodal Assistants