Papers
Mon 12 Apr 2021
196 papers
- Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline EnvironmentWorld models → Latent dynamics models and model-based RL
- Dual Discriminator Adversarial Distillation for Data-free Model CompressionKnowledge distillation → General knowledge distillation methods
- UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic ModelsDiffusion models → Diffusion foundations and sampling
- Pure Exploration with Structured Preference FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- What Is Consciousness? Artificial Intelligence, Real Intelligence, Quantum Mind, And Qualia
- BERT based freedom to operate patent analysis
- What's in a Summary? Laying the Groundwork for Advances in Hospital-Course Summarization
- Advances on image interpolation based on ant colony algorithm
- Detecting Vehicle Type and License Plate Number of different Vehicles on Images
- A High-fidelity, Machine-learning Enhanced Queueing Network Simulation Model for Hospital Ultrasound Operations
- Real-time Forecast Models for TBM Load Parameters Based on Machine Learning Methods
- COVID-19 detection using chest X-rays: is lung segmentation important for generalization?
- Equivalence of quantum barren plateaus to cost concentration and narrow gorges
- On Representation Learning for Scientific News Articles Using Heterogeneous Knowledge Graphs
- Evaluating Pre-Trained Models for User Feedback Analysis in Software Engineering: A Study on Classification of App-Reviews
- Contextual HyperNetworks for Novel Feature Adaptation
- Rapid Exploration for Open-World Navigation with Latent Goal Models
- Exploring Geometric Consistency for Monocular 3D Object Detection
- From partners to populations: A hierarchical Bayesian account of coordination and convention
- Family of Origin and Family of Choice: Massively Parallel Lexiconized Iterative Pretraining for Severely Low Resource Machine Translation
- Targeted Adversarial Training for Natural Language Understanding
- Visual Goal-Step Inference using wikiHow
- Relational World Knowledge Representation in Contextual Language Models: A Review
- Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization
- SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning
- Enhancing User' s Income Estimation with Super-App Alternative Data
- Evidence-based Prescriptive Analytics, CAUSAL Digital Twin and a Learning Estimation Algorithm
- Learning to Synthesize Data for Semantic Parsing
- Evaluating Saliency Methods for Neural Language Models
- Localization-Based Tracking
- Learning from Executions for Semantic Parsing
- On the Linear Ordering Problem and the Rankability of Data
- Generalizable Multi-Camera 3D Pedestrian Detection
- Does My Representation Capture X? Probe-Ably
- Efficient Optimal Transport Algorithm by Accelerated Gradient descent
- Plot-guided Adversarial Example Construction for Evaluating Open-domain Story Generation
- Spatially Varying Label Smoothing: Capturing Uncertainty from Expert Annotations
- Understanding Fission Gas Bubble Distribution, Lanthanide Transportation, and Thermal Conductivity Degradation in Neutron-irradiated α-U Using Machine Learning
- A Recipe for Global Convergence Guarantee in Deep Neural Networks
- Censored Semi-Bandits for Resource Allocation
- Multi-View Image-to-Image Translation Supervised by 3D Pose
- Efficient Space-time Video Super Resolution using Low-Resolution Flow and Mask Upsampling
- Approximate Computing for Robotic path planning -- Experimentation, Case Study and Practical Implications
- Paragraph-level Simplification of Medical Texts
- Domain Adaptive Monocular Depth Estimation With Semantic Information
- Few-shot Intent Classification and Slot Filling with Retrieved Examples
- Deconfounding Scores: Feature Representations for Causal Effect Estimation with Weak Overlap
- Towards Extremely Compact RNNs for Video Recognition with Fully Decomposed Hierarchical Tucker Structure
- Tensor Processing Primitives: A Programming Abstraction for Efficiency and Portability in Deep Learning & HPC Workloads
- Towards a parallel corpus of Portuguese and the Bantu language Emakhuwa of Mozambique
- Fighting the COVID-19 Infodemic with a Holistic BERT Ensemble
- Practical Defences Against Model Inversion Attacks for Split Neural Networks
- Active learning for medical code assignment
- A Replication Study of Dense Passage Retriever
- Predicting the Accuracy of Early-est Earthquake Magnitude Estimates with an LSTM Neural Network: A Preliminary Analysis
- LocalViT: Analyzing Locality in Vision Transformers
- Towards Efficient Graph Convolutional Networks for Point Cloud Handling
- Escaping the Big Data Paradigm with Compact Transformers
- Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesis
- Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection
- Macro-Average: Rare Types Are Important Too
- Joint Universal Syntactic and Semantic Parsing
- On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic Dependencies
- Holistic Image Manipulation Detection using Pixel Co-occurrence Matrices
- Backtranslation Feedback Improves User Confidence in MT, Not Quality
- Behavioral Research and Practical Models of Drivers' Attention
- GPflux: A Library for Deep Gaussian Processes
- Action-Conditioned 3D Human Motion Synthesis with Transformer VAE
- Learning Robust Visual-semantic Mapping for Zero-shot Learning
- View-Guided Point Cloud Completion
- Extraction and Analysis of Highway On-Ramp Merging Scenarios from Naturalistic Trajectory Data
- Towards Algorithmic Transparency: A Diversity Perspective
- End-to-End Mandarin Tone Classification with Short Term Context Information
- CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assembly
- Fruit Quality and Defect Image Classification with Conditional GAN Data Augmentation
- Common Limitations of Image Processing Metrics: A Picture Story
- Generalization bounds via distillation
- An Efficient Algorithm for Deep Stochastic Contextual Bandits
- A coevolutionary approach to deep multi-agent reinforcement learning
- Equivariant geometric learning for digital rock physics: estimating formation factor and effective permeability tensors from Morse graph
- Understanding Overparameterization in Generative Adversarial Networks
- Semantic Frame Forecast
- PAC Bayesian Performance Guarantees for Deep (Stochastic) Networks in Medical Imaging
- Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages
- Consequence-aware Sequential Counterfactual Generation
- DATE: Detecting Anomalies in Text via Self-Supervision of Transformers
- Accelerating Neural Network Training with Distributed Asynchronous and Selective Optimization (DASO)
- GAttANet: Global attention agreement for convolutional neural networks
- Using a Neural Network to Detect Anomalies given an N-gram Profile
- Learning from Subjective Ratings Using Auto-Decoded Deep Latent Embeddings
- Deep Learning for IoT
- Survey on reinforcement learning for language processing
- On Analyzing Churn Prediction in Mobile Games
- WHOSe Heritage: Classification of UNESCO World Heritage "Outstanding Universal Value" Documents with Soft Labels
- Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models
- Optimizing the Whole-life Cost in End-to-end CNN Acceleration
- Efficient Model Monitoring for Quality Control in Cardiac Image Segmentation
- Traffic Forecasting using Vehicle-to-Vehicle Communication
- A-FMI: Learning Attributions from Deep Networks via Feature Map Importance
- Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSx
All 196
- Cloth Interactive Transformer for Virtual Try-On
- Diamond in the rough: Improving image realism by traversing the GAN latent space
- Self-Training with Weak Supervision
- Noether: The More Things Change, the More Stay the Same
- Interpretable Methods for Identifying Product Variants
- Fine-Tuning Transformers for Identifying Self-Reporting Potential Cases and Symptoms of COVID-19 in Tweets
- Updater-Extractor Architecture for Inductive World State Representations
- L3DAS21 Challenge: Machine Learning for 3D Audio Signal Processing
- Modelling Brain Connectivity Networks by Graph Embedding for Dyslexia Diagnosis
- An MRF-UNet Product of Experts for Image Segmentation
- Continual Learning for Text Classification with Information Disentanglement Based Regularization
- CNN Encoding of Acoustic Parameters for Prominence Detection
- Predicting Pedestrian Crossing Intention with Feature Fusion and Spatio-Temporal Attention
- Learning Chebyshev Basis in Graph Convolutional Networks for Skeleton-based Action Recognition
- Building Mental Models through Preview of Autopilot Behaviors
- Understanding Prediction Discrepancies in Machine Learning Classifiers
- Scalable Power Control/Beamforming in Heterogeneous Wireless Networks with Graph Neural Networks
- Developing Annotated Resources for Internal Displacement Monitoring
- PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network
- Deep learning using Havrda-Charvat entropy for classification of pulmonary endomicroscopy
- Meta-Regularization: An Approach to Adaptive Choice of the Learning Rate in Gradient Descent
- Unsuitability of NOTEARS for Causal Graph Discovery
- Multilingual Language Models Predict Human Reading Behavior
- A Conceptual Framework for Establishing Trust in Real World Intelligent Systems
- Blazer: Laser Scanning Simulation using Physically Based Rendering
- An Approach to Symbolic Regression Using Feyn
- Breaking Community Boundary: Comparing Academic and Social Communication Preferences regarding Global Pandemics
- Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures
- Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer
- Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation
- Visiting the Invisible: Layer-by-Layer Completed Scene Decomposition
- The Great Misalignment Problem in Human Evaluation of NLP Methods
- Sparse Coding Frontend for Robust Neural Networks
- Dual-Octave Convolution for Accelerated Parallel MR Image Reconstruction
- How Sensitive are Meta-Learners to Dataset Imbalance?
- An Efficient 2D Method for Training Super-Large Deep Learning Models
- Machine Translation Decoding beyond Beam Search
- MeToo Tweets Sentiment Analysis Using Multi Modal frameworks
- RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut 2D-Tree Representation
- MinkLoc++: Lidar and Monocular Image Fusion for Place Recognition
- Unsupervised foreign object detection based on dual-energy absorptiometry in the food industry
- Combining exogenous and endogenous signals with a semi-supervised co-attention network for early detection of COVID-19 fake tweets
- Stay Together: A System for Single and Split-antecedent Anaphora Resolution
- Better Feature Integration for Named Entity Recognition
- Machine learning and deep learning
- Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search
- Personalized Bundle Recommendation in Online Games
- A Hierarchical State-Machine-Based Framework for Platoon Manoeuvre Descriptions
- Intra-Class Uncertainty Loss Function for Classification
- StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Vision
- LearningCity: Knowledge Generation for Smart Cities
- Volume and leaf area calculation of cabbage with a neural network-based instance segmentation
- Approach for modeling single branches of meadow orchard trees with 3D point clouds
- Class-Balanced Distillation for Long-Tailed Visual Recognition
- Building a Swedish Open-Domain Conversational Language Model
- Learning to Remove: Towards Isotropic Pre-trained BERT Embedding
- Glance and Gaze: Inferring Action-aware Points for One-Stage Human-Object Interaction Detection
- Robust Classification from Noisy Labels: Integrating Additional Knowledge for Chest Radiography Abnormality Assessment
- Improving Online Performance Prediction for Semantic Segmentation
- Boltzmann Tuning of Generative Models
- All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training
- Distributed Learning Systems with First-order Methods
- On Unifying Misinformation Detection
- Factual Probing Is [MASK]: Learning vs. Learning to Recall
- Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation
- Neural Camera Simulators
- Artificial Intelligence Methods Based Hierarchical Classification of Frontotemporal Dementia to Improve Diagnostic Predictability
- Deep Attributed Network Representation Learning via Attribute Enhanced Neighborhood
- Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluation
- SuperSim: a test set for word similarity and relatedness in Swedish
- Edgeless-GNN: Unsupervised Representation Learning for Edgeless Nodes
- Estimating Subjective Crowd-Evaluations as an Additional Objective to Improve Natural Language Generation
- HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximization
- FUDGE: Controlled Text Generation With Future Discriminators
- ENOS: Energy-Aware Network Operator Search for Hybrid Digital and Compute-in-Memory DNN Accelerators
- Contextualized Knowledge-aware Attentive Neural Network: Enhancing Answer Selection with Knowledge
- SCPM-Net: An Anchor-free 3D Lung Nodule Detection Network using Sphere Representation and Center Points Matching
- Online Machine Learning Techniques for Coq: A Comparison
- A Fast Evidential Approach for Stock Forecasting
- StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer
- QZNs: Quantum Z-numbers
- Accelerating science with human versus alien artificial intelligences
- Automated Mechanism Design for Classification with Partial Verification
- GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completion
- Deep Recursive Embedding for High-Dimensional Data
- Memory-guided Unsupervised Image-to-image Translation
- Egocentric Pose Estimation from Human Vision Span
- Object-Centric Representation Learning for Video Question Answering
- A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds
- Learning dynamic and hierarchical traffic spatiotemporal features with Transformer
- Feature Decomposition and Reconstruction Learning for Effective Facial Expression Recognition
- Software-Hardware Co-design for Fast and Scalable Training of Deep Learning Recommendation Models
- Estimation of Summary-to-Text Inconsistency by Mismatched Embeddings
- Machine Learning Approach to Uncovering Residential Energy Consumption Patterns Based on Socioeconomic and Smart Meter Data
- Assessing Reference-Free Peer Evaluation for Machine Translation
- Event-based Timestamp Image Encoding Network for Human Action Recognition and Anticipation