Papers
Wed 24 Feb 2021
168 papers
- Information Directed Reward Learning for Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Localization Distillation for Dense Object DetectionKnowledge distillation → Detection and dense prediction distillation
- Learning to Shift Attention for Motion GenerationOffline RL and imitation learning from data → Robot manipulation imitation learning
- Reservoir Computing as a Tool for Climate Predictability Studies
- GraphBreak: Tool for Network Community based Regulatory Medicine, Gene co-expression, Linkage Disequilibrium analysis, functional annotation and more
- Semantically Constrained Memory Allocation (SCMA) for Embedding in Efficient Recommendation Systems
- A Memory Optimized Data Structure for Binary Chromosomes in Genetic Algorithm
- Hybrid Car-Following Strategy based on Deep Deterministic Policy Gradient and Cooperative Adaptive Cruise Control
- An overview of artificial intelligence techniques for diagnosis of Schizophrenia based on magnetic resonance imaging modalities: Methods, challenges, and future works
- Automatic Cell Counting in Flourescent Microscopy Using Deep Learning
- RoBERTa-wwm-ext Fine-Tuning for Chinese Text Classification
- Community Detection in Weighted Multilayer Networks with Ambient Noise
- Generalized and Transferable Patient Language Representation for Phenotyping with Limited Data
- Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning
- Learning to Make Compiler Optimizations More Effective
- Sleep Apnea and Respiratory Anomaly Detection from a Wearable Band and Oxygen Saturation
- A Quantitative Metric for Privacy Leakage in Federated Learning
- The INTERSPEECH 2021 Computational Paralinguistics Challenge: COVID-19 Cough, COVID-19 Speech, Escalation & Primates
- Deep learning based electrical noise removal enables high spectral optoacoustic contrast in deep tissue
- Bayesian OOD detection with aleatoric uncertainty and outlier exposure
- Credit Assignment with Meta-Policy Gradient for Multi-Agent Reinforcement Learning
- Modular Deep Reinforcement Learning for Continuous Motion Planning with Temporal Logic
- Constructing Evacuation Evolution Patterns and Decisions Using Mobile Device Location Data: A Case Study of Hurricane Irma
- Sequential Learning-based IaaS Composition
- Dynamic Social Media Monitoring for Fast-Evolving Online Discussions
- Railway Anomaly detection model using synthetic defect images generated by CycleGAN
- Directional Bias Amplification
- AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation
- A Stochastic Optimization Framework for Fair Risk Minimization
- Towards Safe Continuing Task Reinforcement Learning
- Partially Hidden Markov Chain Linear Autoregressive model: inference and forecasting
- Disentangling brain heterogeneity via semi-supervised deep-learning and MRI: dimensional representations of Alzheimer's Disease
- The Logical Options Framework
- Deep Compact Polyhedral Conic Classifier for Open and Closed Set Recognition
- Probabilistic feature extraction, dose statistic prediction and dose mimicking for automated radiation therapy treatment planning
- Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks
- Triplet loss based embeddings for forensic speaker identification in Spanish
- Generalised Boosted Forests
- PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
- Benchmarking Graph Neural Networks on Link Prediction
- Robust SleepNets
- Maximum Likelihood Constraint Inference from Stochastic Demonstrations
- Learning Emergent Discrete Message Communication for Cooperative Reinforcement Learning
- Auto-Detection of Tibial Plateau Angle in Canine Radiographs Using a Deep Learning Approach
- Entanglement Diagnostics for Efficient Quantum Computation
- Preserved central model for faster bidirectional compression in distributed settings
- Prior Image-Constrained Reconstruction using Style-Based Generative Models
- A Large-Scale, Automated Study of Language Surrounding Artificial Intelligence
- References in Wikipedia: The Editors' Perspective
- Kernel-based framework to estimate deformations of pneumothorax lung using relative position of anatomical landmarks
- Nested sampling with any prior you like
- 4D Panoptic LiDAR Segmentation
- On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)
- No-Regret Algorithms for Private Gaussian Process Bandit Optimization
- Generating and Blending Game Levels via Quality-Diversity in the Latent Space of a Variational Autoencoder
- MAPFAST: A Deep Algorithm Selector for Multi Agent Path Finding using Shortest Path Embeddings
- When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute
- Probing Classifiers: Promises, Shortcomings, and Advances
- A Straightforward Framework For Video Retrieval Using CLIP
- A generative, predictive model for menstrual cycle lengths that accounts for potential self-tracking artifacts in mobile health data
- Deep Reinforcement Learning for Safe Landing Site Selection with Concurrent Consideration of Divert Maneuvers
- Noisy Gradient Descent Converges to Flat Minima for Nonconvex Matrix Factorization
- Synthetic Returns for Long-Term Credit Assignment
- Rigid and non-rigid motion compensation in weight-bearing cone-beam CT of the knee using (noisy) inertial measurements
- Using Inverse Optimization to Learn Cost Functions in Generalized Nash Games
- Designing Explanations for Group Recommender Systems
- Computing Differential Privacy Guarantees for Heterogeneous Compositions Using FFT
- Task-Specific Pre-Training and Cross Lingual Transfer for Code-Switched Data
- Creolizing the Web
- Pre-Training on Dynamic Graph Neural Networks
- Transfer of Fully Convolutional Policy-Value Networks Between Games and Game Variants
- HiPaR: Hierarchical Pattern-aided Regression
- Wirelessly Powered Federated Edge Learning: Optimal Tradeoffs Between Convergence and Power Transfer
- On the Impact of Interpretability Methods in Active Image Augmentation Method
- Nonlinear Invariant Risk Minimization: A Causal Approach
- AutoAI-TS: AutoAI for Time Series Forecasting
- Memory-based Deep Reinforcement Learning for POMDPs
- Similarity measure for sparse time course data based on Gaussian processes
- Re-Evaluating GermEval17 Using German Pre-Trained Language Models
- An Overview of Direct Diagnosis and Repair Techniques in the WeeVis Recommendation Environment
- AGENT: A Benchmark for Core Psychological Reasoning
- GEM: Glare or Gloom, I Can Still See You -- End-to-End Multimodal Object Detection
- Set-valued classification -- overview via a unified framework
- Learning-Augmented Sketches for Hessians
- Hyperspectral Denoising Using Unsupervised Disentangled Spatio-Spectral Deep Priors
- "Train one, Classify one, Teach one" -- Cross-surgery transfer learning for surgical step recognition
- Balancing Rational and Other-Regarding Preferences in Cooperative-Competitive Environments
- A Framework for Integrating Gesture Generation Models into Interactive Conversational Agents
- Density Sketches for Sampling and Estimation
- Image Augmentation for Multitask Few-Shot Learning: Agricultural Domain Use-Case
- Two-way kernel matrix puncturing: towards resource-efficient PCA and spectral clustering
- Automatic Feature Extraction for Heartbeat Anomaly Detection
- Graphfool: Targeted Label Adversarial Attack on Graph Embedding
- Trajectory-Based Meta-Learning for Out-Of-Vocabulary Word Embedding Learning
- Sparse online variational Bayesian regression
- Classification with abstention but without disparities
- An Enhanced Prohibited Items Recognition Model
- LRG at SemEval-2021 Task 4: Improving Reading Comprehension with Abstract Words using Augmentation, Linguistic Features and Voting
- NLRG at SemEval-2021 Task 5: Toxic Spans Detection Leveraging BERT-based Token Classification and Span Prediction Techniques
- Estimation of Continuous Blood Pressure from PPG via a Federated Learning Approach
All 168
- State-of-the-Art in Human Scanpath Prediction
- Inductive Bias of Multi-Channel Linear Convolutional Networks with Bounded Weight Norm
- Abelian Neural Networks
- Multi-Task Attentive Residual Networks for Argument Mining
- A CP-Net based Qualitative Composition Approach for an IaaS Provider
- Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges
- Multi-Task Temporal Convolutional Networks for Joint Recognition of Surgical Phases and Steps in Gastric Bypass Procedures
- Unsupervised semantic discovery through visual patterns detection
- PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains
- Enabling the Network to Surf the Internet
- Identifying Untrustworthy Predictions in Neural Networks by Geometric Gradient Analysis
- Combining Off and On-Policy Training in Model-Based Reinforcement Learning
- Multiplicative Reweighting for Robust Neural Network Optimization
- DeepCervix: A Deep Learning-based Framework for the Classification of Cervical Cells Using Hybrid Deep Feature Fusion Techniques
- Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration
- Multichannel LSTM-CNN for Telugu Technical Domain Identification
- Learning to Generate Wasserstein Barycenters
- Efficient Low-Latency Dynamic Licensing for Deep Neural Network Deployment on Edge Devices
- From Universal Language Model to Downstream Task: Improving RoBERTa-Based Vietnamese Hate Speech Detection
- Multi-Level Adaptive Region of Interest and Graph Learning for Facial Action Unit Recognition
- Dual-Awareness Attention for Few-Shot Object Detection
- CoreDiag: Eliminating Redundancy in Constraint Sets
- Sentiment Analysis of Code-Mixed Social Media Text (Hinglish)
- A New Pairwise Deep Learning Feature For Environmental Microorganism Image Analysis
- GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator
- Gaussian boson sampling and multi-particle event optimization by machine learning in the quantum phase space
- Interpreting the Latent Space of Generative Adversarial Networks using Supervised Learning
- SFANet: A Spectrum-aware Feature Augmentation Network for Visible-Infrared Person Re-Identification
- Augmenting Part-of-speech Tagging with Syntactic Information for Vietnamese and Chinese
- Efficient and Accurate Multi-scale Topological Network for Single Image Dehazing
- Self-Domain Adaptation for Face Anti-Spoofing
- OneStop QAMaker: Extract Question-Answer Pairs from Text in a One-Stop Approach
- Efficient Palm-Line Segmentation with U-Net Context Fusion Module
- Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
- Deep Learning Approach for Singer Voice Classification of Vietnamese Popular Music
- Automatic Meter Classification of Kurdish Poems
- The Promises and Pitfalls of Deep Kernel Learning
- FIXAR: A Fixed-Point Deep Reinforcement Learning Platform with Quantization-Aware Training and Adaptive Parallelism
- Lossless Compression of Efficient Private Local Randomizers
- PFRL: Pose-Free Reinforcement Learning for 6D Pose Estimation
- Synergy Between Semantic Segmentation and Image Denoising via Alternate Boosting
- Combinatorial Pure Exploration with Bottleneck Reward Function
- PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features
- Zero-Shot Text-to-Image Generation
- Continuous Mean-Covariance Bandits
- Fast Approximate Solutions using Reinforcement Learning for Dynamic Capacitated Vehicle Routing with Time Windows
- Modern Koopman Theory for Dynamical Systems
- Hopeful_Men@LT-EDI-EACL2021: Hope Speech Detection Using Indic Transliteration and Transformers
- Perspective: Purposeful Failure in Artificial Life and Artificial Intelligence
- SocialNLP EmotionGIF 2020 Challenge Overview: Predicting Reaction GIF Categories on Social Media
- Learning optimal multigrid smoothers via neural networks
- Spatio-Temporal Look-Ahead Trajectory Prediction using Memory Neural Network
- On the Minimal Error of Empirical Risk Minimization
- Deep Video Prediction for Time Series Forecasting
- Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing
- Multi-Slice Low-Rank Tensor Decomposition Based Multi-Atlas Segmentation: Application to Automatic Pathological Liver CT Segmentation
- Active Learning to Classify Macromolecular Structures in situ for Less Supervision in Cryo-Electron Tomography
- Conditional Image Generation by Conditioning Variational Auto-Encoders
- DNN2LR: Automatic Feature Crossing for Credit Scoring
- Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks
- Theoretical Understandings of Product Embedding for E-commerce Machine Learning
- Annotating Motion Primitives for Simplifying Action Search in Reinforcement Learning
- Understanding and Mitigating Accuracy Disparity in Regression
- PixSet : An Opportunity for 3D Computer Vision to Go Beyond Point Clouds With a Full-Waveform LiDAR Dataset
- Adversarial Robustness with Non-uniform Perturbations
- On Relative Pose Recovery for Multi-Camera Systems
- A Genetic Algorithm with Tree-structured Mutation for Hyperparameter Optimisation of Graph Neural Networks
- Characterization and recognition of handwritten digits using Julia