Papers
Mon 14 Feb 2022
181 papers
- Understanding DDPM Latent Codes Through Optimal TransportDiffusion models → Diffusion foundations and sampling
- Strategy Discovery and Mixture in Lifelong Learning from Heterogeneous DemonstrationOffline RL and imitation learning from data → Robot learning from demonstration
- Autonomous Vehicles on the Edge: A Survey on Autonomous Vehicle RacingEnd-to-end autonomous driving → Reinforcement learning for driving
- Continual Learning from Demonstration of Robotics SkillsOffline RL and imitation learning from data → Robot learning from demonstration
- Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training BenchmarkMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Learning Reward Models for Cooperative Trajectory Planning with Inverse Reinforcement Learning and Monte Carlo Tree SearchOffline RL and imitation learning from data → Imitation and offline RL for driving
- 2021 BEETL Competition: Advancing Transfer Learning for Subject Independence & Heterogenous EEG Data Sets
- Digital Signal Analysis based on Convolutional Neural Networks for Active Target Time Projection Chambers
- Approximate Nearest Neighbor Search under Neural Similarity Metric for Large-Scale Recommendation
- Deep Movement Primitives: toward Breast Cancer Examination Robot
- Stock Embeddings: Learning Distributed Representations for Financial Assets
- UserBERT: Modeling Long- and Short-Term User Preferences via Self-Supervision
- BED: A Real-Time Object Detection System for Edge Devices
- MGCVAE: Multi-objective Inverse Design via Molecular Graph Conditional Variational Autoencoder
- A Real-time System for Detecting Landslide Reports on Social Media using Artificial Intelligence
- Do Lessons from Metric Learning Generalize to Image-Caption Retrieval?
- Sequential Bayesian experimental designs via reinforcement learning
- SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation
- Federated Contrastive Learning for Dermatological Disease Diagnosis via On-device Learning
- Vau da muntanialas: Energy-efficient multi-die scalable acceleration of RNN inference
- Statistical Inference After Adaptive Sampling for Longitudinal Data
- Learning to Discover Medicines
- Matching Tweets With Applicable Fact-Checks Across Languages
- Scaling up Ranking under Constraints for Live Recommendations by Replacing Optimization with Prediction
- Graph Neural Networks for Graphs with Heterophily: A Survey
- Introducing the ICBe Dataset: Very High Recall and Precision Event Extraction from Narratives about International Crises
- Synthetically Controlled Bandits
- Regional Differences in Information Privacy Concerns After the Facebook-Cambridge Analytica Data Scandal
- Benchmarking Robot Manipulation with the Rubik's Cube
- Discriminability-enforcing loss to improve representation learning
- Motivating Physical Activity via Competitive Human-Robot Interaction
- Automatic Generation of Individual Fuzzy Cognitive Maps from Longitudinal Data
- Universal Adversarial Examples in Remote Sensing: Methodology and Benchmark
- Orthogonalising gradients to speed up neural network optimisation
- Artificial Intelligence-Based Smart Grid Vulnerabilities and Potential Solutions for Fake-Normal Attacks: A Short Review
- Principal Manifold Flows
- Benchmarking Online Sequence-to-Sequence and Character-based Handwriting Recognition from IMU-Enhanced Pens
- One Step at a Time: Long-Horizon Vision-and-Language Navigation with Milestones
- Analysis of Neural Fragility: Bounding the Norm of a Rank-One Perturbation Matrix
- Box Supervised Video Segmentation Proposal Network
- Exhaustivity and anti-exhaustivity in the RSA framework: Testing the effect of prior beliefs
- Recurrent Neural Networks for Dynamical Systems: Applications to Ordinary Differential Equations, Collective Motion, and Hydrological Modeling
- QuadSim: A Quadcopter Rotational Dynamics Simulation Framework For Reinforcement Learning Algorithms
- Robust Policy Learning over Multiple Uncertainty Sets
- Building Inspection Toolkit: Unified Evaluation and Strong Baselines for Damage Recognition
- A Survey of Visual Sensory Anomaly Detection
- Continuously Generalized Ordinal Regression for Linear and Deep Models
- Handcrafted Histological Transformer (H2T): Unsupervised Representation of Whole Slide Images
- Cross-Modality Neuroimage Synthesis: A Survey
- Unlabeled Data Help: Minimax Analysis and Adversarial Robustness
- Transformer Memory as a Differentiable Search Index
- Learned Turbulence Modelling with Differentiable Fluid Solvers: Physics-based Loss-functions and Optimisation Horizons
- ASC me to Do Anything: Multi-task Training for Embodied AI
- Deep Ensembles Work, But Are They Necessary?
- DermX: an end-to-end framework for explainable automated dermatological diagnosis
- Semi-Equivariant GNN Architectures for Jet Tagging
- Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text
- Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection
- Tensor Moments of Gaussian Mixture Models: Theory and Applications
- Do Gradient Inversion Attacks Make Federated Learning Unsafe?
- Convex Programs and Lyapunov Functions for Reinforcement Learning: A Unified Perspective on the Analysis of Value-Based Methods
- Stochastic linear optimization never overfits with quadratically-bounded losses on general data
- A Generic Self-Supervised Framework of Learning Invariant Discriminative Features
- FOLD-RM: A Scalable, Efficient, and Explainable Inductive Learning Algorithm for Multi-Category Classification of Mixed Data
- DeCorus: Hierarchical Multivariate Anomaly Detection at Cloud-Scale
- Counterfactual inference in sequential experiments
- COLA: COarse LAbel pre-training for 3D semantic segmentation of sparse LiDAR datasets
- Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation
- Black-Box Generalization: Stability of Zeroth-Order Learning
- A Graphical Approach For Brain Haemorrhage Segmentation
- Visual Acoustic Matching
- Sequence-to-Sequence Resources for Catalan
- Delaunay Component Analysis for Evaluation of Data Representations
- Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond
- Physics-Informed Deep Monte Carlo Quantile Regression method for Interval Multilevel Bayesian Network-based Satellite Heat Reliability Analysis
- An experimental study of the vision-bottleneck in VQA
- A Graph-Matching Approach for Cross-view Registration of Over-view 2 and Street-view based Point Clouds
- Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization
- Random Laplacian Features for Learning with Hyperbolic Space
- Agent-Based Model Framework for the North Carolina Modeling Infectious Diseases Program (NC MInD ABM) Overview, Design Concepts, and Details Protocol
- HAKE: A Knowledge Engine Foundation for Human Activity Understanding
- On Pitfalls of Identifiability in Unsupervised Learning. A Note on: "Desiderata for Representation Learning: A Causal Perspective"
- What Do They Capture? -- A Structural Analysis of Pre-Trained Language Models for Source Code
- A Machine Learning Framework for Event Identification via Modal Analysis of PMU Data
- Online Approval Committee Elections
- Permutation invariant matrix statistics and computational language tasks
- On the Convergence of SARSA with Linear Function Approximation
- Robust Estimation of Discrete Distributions under Local Differential Privacy
- CATs++: Boosting Cost Aggregation with Convolutions and Transformers
- Flexible learning of quantum states with generative query neural networks
- Design of Explainability Module with Experts in the Loop for Visualization and Dynamic Adjustment of Continual Learning
- Multi-scale Attention Guided Pose Transfer
- Aspect Based Sentiment Analysis Using Spectral Temporal Graph Neural Network
- Punctuation restoration in Swedish through fine-tuned KB-BERT
- Probabilistic Embeddings Revisited
- Machine Learning-Aided Discovery of Superionic Solid-State Electrolyte for Li-Ion Batteries
- Trace norm regularization for multi-task learning with scarce data
- Attention-based Deep Neural Networks for Battery Discharge Capacity Forecasting
- A Data-Centric Approach to Generate Invariants for a Smart Grid Using Machine Learning
- How Do Vision Transformers Work?
All 181
- Spiking Cochlea with System-level Local Automatic Gain Control
- Versatile Dueling Bandits: Best-of-both-World Analyses for Online Learning from Preferences
- ArgSciChat: A Dataset for Argumentative Dialogues on Scientific Papers
- CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming Sequences
- Geometric Transformer for Fast and Robust Point Cloud Registration
- Domain Adaptation via Prompt Learning
- Partially Fake Audio Detection by Self-attention-based Fake Span Discovery
- Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?
- Convolutional Neural Network with Convolutional Block Attention Module for Finger Vein Recognition
- Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings
- Learning Weakly-Supervised Contrastive Representations
- PFGE: Parsimonious Fast Geometric Ensembling of DNNs
- The Impact of Batch Learning in Stochastic Linear Bandits
- Out of Thin Air: Is Zero-Shot Cross-Lingual Keyword Detection Better Than Unsupervised?
- On the Importance of Building High-quality Training Datasets for Neural Code Search
- On the Complexity of Object Detection on Real-world Public Transportation Images for Social Distancing Measurement
- Continuous-time stochastic gradient descent for optimizing over the stationary distribution of stochastic differential equations
- FlowEval: A Consensus-Based Dialogue Evaluation Framework Using Segment Act Flows
- MuZero with Self-competition for Rate Control in VP9 Video Compression
- Measurably Stronger Explanation Reliability via Model Canonization
- What is Next when Sequential Prediction Meets Implicitly Hard Interaction?
- A Differential Entropy Estimator for Training Neural Networks
- An Application of Online Learning to Spacecraft Memory Dump Optimization
- Toward Unsupervised Test Scenario Extraction for Automated Driving Systems from Urban Naturalistic Road Traffic Data
- Research on Dual Channel News Headline Classification Based on ERNIE Pre-training Model
- Multi-Atlas Segmentation and Spatial Alignment of the Human Embryo in First Trimester 3D Ultrasound
- Deep Monte Carlo Quantile Regression for Quantifying Aleatoric Uncertainty in Physics-informed Temperature Field Reconstruction
- Statistical Inference for the Dynamic Time Warping Distance, with Application to Abnormal Time-Series Detection
- Memory Replay with Data Compression for Continual Learning
- A Pragmatic Machine Learning Approach to Quantify Tumor Infiltrating Lymphocytes in Whole Slide Images
- Conditional Generation Net for Medication Recommendation
- Improved Aggregating and Accelerating Training Methods for Spatial Graph Neural Networks on Fraud Detection
- I-Tuning: Tuning Frozen Language Models with Image for Lightweight Image Captioning
- Anytime Capacity Expansion in Medical Residency Match by Monte Carlo Tree Search
- Online-updated High-order Collaborative Networks for Single Image Deraining
- Single-stage Rotate Object Detector via Two Points with Solar Corona Heatmap
- Saving RNN Computations with a Neuron-Level Fuzzy Memoization Scheme
- Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation
- Reinforcement Learning in Presence of Discrete Markovian Context Evolution
- A resource-efficient deep learning framework for low-dose brain PET image reconstruction and analysis
- Video2IMU: Realistic IMU features and signals from videos
- Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization
- Deduplicating Training Data Mitigates Privacy Risks in Language Models
- QA4QG: Using Question Answering to Constrain Multi-Hop Question Generation
- An Introduction to Neural Data Compression
- Benign Overfitting in Two-layer Convolutional Neural Networks
- Tight integration of neural- and clustering-based diarization through deep unfolding of infinite Gaussian mixture model
- MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts
- Source Code Summarization with Structural Relative Position Guided Transformer
- Semantic Matching from Different Perspectives
- Context-Preserving Instance-Level Augmentation and Deformable Convolution Networks for SAR Ship Detection
- Benchmarking of DL Libraries and Models on Mobile Devices
- GAMMA Challenge:Glaucoma grAding from Multi-Modality imAges
- Mixing and Shifting: Exploiting Global and Local Dependencies in Vision MLPs
- EMGSE: Acoustic/EMG Fusion for Multimodal Speech Enhancement
- Opinions Vary? Diagnosis First!
- Analytic Learning of Convolutional Neural Network For Pattern Recognition
- Adaptive Graph Convolutional Networks for Weakly Supervised Anomaly Detection in Videos
- Real World Large Scale Recommendation Systems Reproducibility and Smooth Activations
- Task-Adaptive Feature Transformer with Semantic Enrichment for Few-Shot Segmentation
- FLHub: a Federated Learning model sharing service
- Adversarial Graph Contrastive Learning with Information Regularization
- Finding Dynamics Preserving Adversarial Winning Tickets
- D2ADA: Dynamic Density-aware Active Domain Adaptation for Semantic Segmentation
- BiFSMN: Binary Neural Network for Keyword Spotting
- Splitting numerical integration for matrix completion
- A Survey on Machine Learning Approaches for Modelling Intuitive Physics
- Homogenous and Heterogenous Parallel Clustering: An Overview
- Modeling Intention, Emotion and External World in Dialogue Systems
- Extracting Label-specific Key Input Features for Neural Code Intelligence Models
- Asymptotically Unbiased Estimation for Delayed Feedback Modeling via Label Correction
- Tightly Coupled Learning Strategy for Weakly Supervised Hierarchical Place Recognition
- NeuroMixGDP: A Neural Collapse-Inspired Random Mixup for Private Data Release
- Measuring "Why" in Recommender Systems: a Comprehensive Survey on the Evaluation of Explainable Recommendation
- A State-of-the-art Survey of U-Net in Microscopic Image Analysis: from Simple Usage to Structure Mortification
- Synthetic Data Can Also Teach: Synthesizing Effective Data for Unsupervised Visual Representation Learning
- Simultaneous Transport Evolution for Minimax Equilibria on Measures
- Faster hyperspectral image classification based on selective kernel mechanism using deep convolutional networks
- Input-to-State Stable Neural Ordinary Differential Equations with Applications to Transient Modeling of Circuits
- Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality
- Fast algorithm for overcomplete order-3 tensor decomposition