Papers
Thu 7 Oct 2021
237 papers
- Reinforcement Learning in Reward-Mixing MDPsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Cross-Domain Imitation Learning via Optimal TransportOffline RL and imitation learning from data → Imitation learning methods
- Peer Collaborative Learning for Polyphonic Sound Event DetectionKnowledge distillation → Speech and audio distillation
- Knowledge Distillation for Neural Transducers from Large Self-Supervised Pre-trained ModelsKnowledge distillation → Speech and audio distillation
- Offline RL With Resource Constrained Online DeploymentOffline RL and imitation learning from data → Offline RL algorithms
- Improving Robot-Centric Learning from Demonstration via Personalized EmbeddingsOffline RL and imitation learning from data → Robot learning from demonstration
- Solving classification problems using Traceless Genetic Programming
- Distributed Proximal Policy Optimization for Contention-Based Spectrum Access
- Highly Accurate and Reliable Wireless Network Slicing in 5th Generation Networks: A Hybrid Deep Learning Approach
- Using Traceless Genetic Programming for Solving Multiobjective Optimization Problems
- Impact of COVID-19 Policies and Misinformation on Social Unrest
- Pre-training Molecular Graph Representation with 3D Geometry
- EEG functional connectivity and deep learning for automatic diagnosis of brain disorders: Alzheimer's disease and schizophrenia
- Designing Composites with Target Effective Young's Modulus using Reinforcement Learning
- Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution
- The Impact of Visualizing Design Gradients for Human Designers
- Arachnophobia Exposure Therapy using Experience-driven Procedural Content Generation via Reinforcement Learning (EDPCGRL)
- Learning post-processing for QRS detection using Recurrent Neural Network
- Ensemble Neural Representation Networks
- A Multi-viewpoint Outdoor Dataset for Human Action Recognition
- Detecting adversaries in Crowdsourcing
- Flow Plugin Network for conditional generation
- Generative Pre-Trained Transformer for Cardiac Abnormality Detection
- FAST-RIR: Fast neural diffuse room impulse response generator
- Curating Subject ID Labels using Keypoint Signatures
- SkullEngine: A Multi-stage CNN Framework for Collaborative CBCT Image Segmentation and Landmark Detection
- Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks
- StyleGAN-induced data-driven regularization for inverse problems
- FOCUS: Familiar Objects in Common and Uncommon Settings
- Hitting the Target: Stopping Active Learning at the Cost-Based Optimum
- CCGG: A Deep Autoregressive Model for Class-Conditional Graph Generation
- A Probabilistic Graphical Model Approach to the Structure-and-Motion Problem
- Scaling Bayesian Optimization With Game Theory
- Knowledge Sheaves: A Sheaf-Theoretic Framework for Knowledge Graph Embedding
- Efficient large-scale image retrieval with deep feature orthogonality and Hybrid-Swin-Transformers
- Addressing practical challenges in Active Learning via a hybrid query strategy
- Machine Learning approaches to do size based reasoning on Retail Shelf objects to classify product variants
- 5G Traffic Prediction with Time Series Analysis
- A composable autoencoder-based iterative algorithm for accelerating numerical simulations
- Wake-Cough: cough spotting and cougher identification for personalised long-term cough monitoring
- De-randomizing MCMC dynamics with the diffusion Stein operator
- Spectroscopy Approaches for Food Safety Applications: Improving Data Efficiency Using Active Learning and Semi-Supervised Learning
- Label Propagation across Graphs: Node Classification using Graph Neural Tangent Kernels
- A simple equivariant machine learning method for dynamics based on scalars
- Design Strategy Network: A deep hierarchical framework to represent generative design strategies in complex action spaces
- Explanation as a process: user-centric construction of multi-level and multi-modal explanations
- Predictive Maintenance for General Aviation Using Convolutional Transformers
- Sonorant spectra and coarticulation distinguish speakers with different dialects
- Process Extraction from Text: Benchmarking the State of the Art and Paving the Way for Future Challenges
- From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness
- Global sensitivity analysis in probabilistic graphical models
- Adversarial Attack by Limited Point Cloud Surface Modifications
- Adaptive Early-Learning Correction for Segmentation from Noisy Annotations
- Adversarial Unlearning of Backdoors via Implicit Hypergradient
- UoB at SemEval-2021 Task 5: Extending Pre-Trained Language Models to Include Task and Domain-Specific Information for Toxic Span Prediction
- Contextual Sentence Classification: Detecting Sustainability Initiatives in Company Reports
- Bisimulations for Neural Network Reduction
- A Meta-learning Approach to Reservoir Computing: Time Series Prediction with Limited Data
- Gaussian Process for Trajectories
- SVG-Net: An SVG-based Trajectory Prediction Model
- Direct design of biquad filter cascades with deep learning by sampling random polynomials
- Learning Higher-Order Dynamics in Video-Based Cardiac Measurement
- DeepECMP: Predicting Extracellular Matrix Proteins using Deep Learning
- Predicting Chemical Hazard across Taxa through Machine Learning
- Neural Tangent Kernel Empowered Federated Learning
- Burst Image Restoration and Enhancement
- Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect
- ATISS: Autoregressive Transformers for Indoor Scene Synthesis
- Dense Gaussian Processes for Few-Shot Segmentation
- Tighter Sparse Approximation Bounds for ReLU Neural Networks
- Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design
- Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks
- Neural Estimation of Statistical Divergences
- Neural Networks, Inside Out: Solving for Inputs Given Parameters (A Preliminary Investigation)
- Using Keypoint Matching and Interactive Self Attention Network to verify Retail POSMs
- From Weighted Conditionals of Multilayer Perceptrons to Gradual Argumentation and Back
- Using Contrastive Learning and Pseudolabels to learn representations for Retail Product Image Classification
- Enabling On-Device Training of Speech Recognition Models with Federated Dropout
- Boxhead: A Dataset for Learning Hierarchical Representations
- Time Series Forecasting Using Manifold Learning
- On the Complexity of Inductively Learning Guarded Rules
- Hyperparameter Tuning with Renyi Differential Privacy
- Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP
- A Data-Centric Approach for Training Deep Neural Networks with Less Data
- Adversarial Retriever-Ranker for dense text retrieval
- Applying Phonological Features in Multilingual Text-To-Speech
- How to Sense the World: Leveraging Hierarchy in Multimodal Perception for Robust Reinforcement Learning Agents
- Robust Feature-Level Adversaries are Interpretability Tools
- Online Markov Decision Processes with Non-oblivious Strategic Adversary
- Generalization in Deep RL for TSP Problems via Equivariance and Local Search
- Ship Performance Monitoring using Machine-learning
- TranSalNet: Towards perceptually relevant visual saliency prediction
- A transformer-based deep learning approach for classifying brain metastases into primary organ sites using clinical whole brain MRI
- To Charge or to Sell? EV Pack Useful Life Estimation via LSTMs, CNNs, and Autoencoders
- A Model Selection Approach for Corruption Robust Reinforcement Learning
- Towards Accurate Cross-Domain In-Bed Human Pose Estimation
- Training Stable Graph Neural Networks Through Constrained Learning
- Estimating Image Depth in the Comics Domain
- A New Simple Vision Algorithm for Detecting the Enzymic Browning Defects in Golden Delicious Apples
- Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot Filling
All 237
- Human in the Loop for Machine Creativity
- GeSERA: General-domain Summary Evaluation by Relevance Analysis
- Weakly Supervised Human-Object Interaction Detection in Video via Contrastive Spatiotemporal Regions
- Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0
- Shift-BNN: Highly-Efficient Probabilistic Bayesian Neural Network Training via Memory-Friendly Pattern Retrieving
- Heterogeneous Overdispersed Count Data Regressions via Double Penalized Estimations
- Bias-Variance Tradeoffs in Single-Sample Binary Gradient Estimators
- mRAT-SQL+GAP:A Portuguese Text-to-SQL Transformer
- 3D Unsupervised Region-Aware Registration Transformer
- A Broad Ensemble Learning System for Drifting Stream Classification
- Data-Driven Methods for Balancing Fairness and Efficiency in Ride-Pooling
- Accelerated Componentwise Gradient Boosting using Efficient Data Representation and Momentum-based Optimization
- Mandarin-English Code-switching Speech Recognition with Self-supervised Speech Representation Models
- Pretrained Language Models are Symbolic Mathematics Solvers too!
- On the relationship between disentanglement and multi-task learning
- Scale Invariant Domain Generalization Image Recapture Detection
- Cartoon Explanations of Image Classifiers
- Creating Training Sets via Weak Indirect Supervision
- Learning to Regress Bodies from Images using Differentiable Semantic Rendering
- Camera Calibration through Camera Projection Loss
- Complex-valued Federated Learning with Differential Privacy and MRI Applications
- InfoSeg: Unsupervised Semantic Image Segmentation with Mutual Information Maximization
- Unsupervised Image Decomposition with Phase-Correlation Networks
- Federated Learning from Small Datasets
- Belief Evolution Network-based Probability Transformation and Fusion
- Differential Anomaly Detection for Facial Images
- Self-Evolutionary Optimization for Pareto Front Learning
- Recent Advances in Heterogeneous Relation Learning for Recommendation
- Multi-Head ReLU Implicit Neural Representation Networks
- Towards Robust and Transferable IIoT Sensor based Anomaly Classification using Artificial Intelligence
- From the Head or the Heart? An Experimental Design on the Impact of Explanation on Cognitive and Affective Trust
- Fast learning from label proportions with small bags
- Bad-Policy Density: A Measure of Reinforcement Learning Hardness
- SERAB: A multi-lingual benchmark for speech emotion recognition
- Curved Markov Chain Monte Carlo for Network Learning
- Joint calibration and mapping of satellite altimetry data using trainable variational models
- AnoSeg: Anomaly Segmentation Network Using Self-Supervised Learning
- SLASH: Embracing Probabilistic Circuits into Neural Answer Set Programming
- Multivariate Anomaly Detection based on Prediction Intervals Constructed using Deep Learning
- Beam Search with Bidirectional Strategies for Neural Response Generation
- Deep Learning Model Explainability for Inspection Accuracy Improvement in the Automotive Industry
- Advancing the dimensionality reduction of speaker embeddings for speaker diarisation: disentangling noise and informing speech activity
- Learning Pessimism for Robust and Efficient Off-Policy Reinforcement Learning
- Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data
- WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition
- The Connection between Out-of-Distribution Generalization and Privacy of ML Models
- A Baseline Framework for Part-level Action Parsing and Action Recognition
- Evaluating model-based planning and planner amortization for continuous control
- Multi-scale speaker embedding-based graph attention networks for speaker diarisation
- Sparse MoEs meet Efficient Ensembles
- Uncertainty Set Prediction of Aggregated Wind Power Generation based on Bayesian LSTM and Spatio-Temporal Analysis
- barGmst:An Unbiased Stratified Statistic and a Fast Gradient Optimization Algorithm Based on It
- Noisy Text Data: Achilles' Heel of popular transformer based NLP models
- Optimized U-Net for Brain Tumor Segmentation
- MSHCNet: Multi-Stream Hybridized Convolutional Networks with Mixed Statistics in Euclidean/Non-Euclidean Spaces and Its Application to Hyperspectral Image Classification
- Uncertainty-aware GAN with Adaptive Loss for Robust MRI Image Enhancement
- VisualTTS: TTS with Accurate Lip-Speech Synchronization for Automatic Voice Over
- Cross-Language Learning for Entity Matching
- Moment evolution equations and moment matching for stochastic image EPDiff
- Frame Averaging for Invariant and Equivariant Network Design
- CLEVA-Compass: A Continual Learning EValuation Assessment Compass to Promote Research Transparency and Comparability
- Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition
- Back from the future: bidirectional CTC decoding using future information in speech recognition
- A Logic-Based Framework for Natural Language Inference in Dutch
- Robustness and Reliability When Training With Noisy Labels
- Automated Testing of AI Models
- Towards Federated Learning-Enabled Visible Light Communication in 6G Systems
- On the Latent Holes of VAEs for Text Generation
- Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees
- Solving the Dirichlet problem for the Monge-Amp`ere equation using neural networks
- Universal Approximation Under Constraints is Possible with Transformers
- MPSN: Motion-aware Pseudo Siamese Network for Indoor Video Head Detection in Buildings
- EvadeDroid: A Practical Evasion Attack on Machine Learning for Black-box Android Malware Detection
- Permutation Compressors for Provably Faster Distributed Nonconvex Optimization
- End-To-End Label Uncertainty Modeling for Speech-based Arousal Recognition Using Bayesian Neural Networks
- End-to-End Supermask Pruning: Learning to Prune Image Captioning Models
- EF21 with Bells & Whistles: Six Algorithmic Extensions of Modern Error Feedback
- Robotic Lever Manipulation using Hindsight Experience Replay and Shapley Additive Explanations
- MC-LCR: Multi-modal contrastive classification by locally correlated representations for effective face forgery detection
- Detecting Autism Spectrum Disorders with Machine Learning Models Using Speech Transcripts
- Virtual Multi-Modality Self-Supervised Foreground Matting for Human-Object Interaction
- Inferring Substitutable and Complementary Products with Knowledge-Aware Path Reasoning based on Dynamic Policy Network
- AgFlow: Fast Model Selection of Penalized PCA via Implicit Regularization Effects of Gradient Flow
- Injecting Planning-Awareness into Prediction and Detection Evaluation
- Multi-tasking Dialogue Comprehension with Discourse Parsing
- Propagating State Uncertainty Through Trajectory Forecasting
- Lagrangian Neural Network with Differentiable Symmetries and Relational Inductive Bias
- Situated Dialogue Learning through Procedural Environment Generation
- An Uncertainty-aware Loss Function for Training Neural Networks with Calibrated Predictions
- Layer-wise Pruning of Transformer Attention Heads for Efficient Language Modeling
- Multimodal Colored Point Cloud to Image Alignment
- Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver
- Understanding Domain Randomization for Sim-to-real Transfer
- Score-based Generative Neural Networks for Large-Scale Optimal Transport
- Self-Supervised Depth Completion for Active Stereo
- Design of an Intelligent Vision Algorithm for Recognition and Classification of Apples in an Orchard Scene
- Darts: User-Friendly Modern Machine Learning for Time Series
- Goal-Directed Design Agents: Integrating Visual Imitation with One-Step Lookahead Optimization for Generative Design
- Gradient Step Denoiser for convergent Plug-and-Play
- Joint optimization of system design and reconstruction in MIMO radar imaging
- Towards Continual Knowledge Learning of Language Models
- Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates
- Universality of Winning Tickets: A Renormalization Group Perspective
- Coresets for Decision Trees of Signals
- GNN is a Counter? Revisiting GNN for Question Answering
- On the Optimal Memorization Power of ReLU Neural Networks
- Explaining Deep Reinforcement Learning Agents In The Atari Domain through a Surrogate Model
- Attention is All You Need? Good Embeddings with Statistics are enough:Large Scale Audio Understanding without Transformers/ Convolutions/ BERTs/ Mixers/ Attention/ RNNs or ....
- Tile Embedding: A General Representation for Procedural Level Generation via Machine Learning
- HowSumm: A Multi-Document Summarization Dataset Derived from WikiHow Articles
- EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits
- Fingerprinting Multi-exit Deep Neural Network Models via Inference Time
- Transferring Voice Knowledge for Acoustic Event Detection: An Empirical Study
- Multi-objective Optimization by Learning Space Partitions
- Assemblies of neurons learn to classify well-separated distributions
- TreeGCN-ED: Encoding Point Cloud using a Tree-Structured Graph Network
- Transliteration of Foreign Words in Burmese
- StrengthNet: Deep Learning-based Emotion Strength Assessment for Emotional Speech Synthesis
- Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Regularized Exploration in Reinforcement Learning
- DoubleStar: Long-Range Attack Towards Depth Estimation based Obstacle Avoidance in Autonomous Systems
- Transcribe-to-Diarize: Neural Speaker Diarization for Unlimited Number of Speakers using End-to-End Speaker-Attributed ASR
- Data-driven behavioural biometrics for continuous and adaptive user verification using Smartphone and Smartwatch
- PRRS Outbreak Prediction via Deep Switching Auto-Regressive Factorization Modeling
- Solving Multistage Stochastic Linear Programming via Regularized Linear Decision Rules: An Application to Hydrothermal Dispatch Planning
- Conceptual Expansion Neural Architecture Search (CENAS)
- Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning
- A Comparative Study of Transformer-Based Language Models on Extractive Question Answering
- Efficient Sharpness-aware Minimization for Improved Training of Neural Networks
- Label Noise in Adversarial Training: A Novel Perspective to Study Robust Overfitting
- Generic tool for numerical simulation of transformation-diffusion processes in complex volume geometric shapes: application to microbial decomposition of organic matter
- On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications
- Reliable Probability Intervals For Classification Using Inductive Venn Predictors Based on Distance Learning
- Improving Adversarial Robustness for Free with Snapshot Ensemble
- Improving Prediction Confidence in Learning-Enabled Autonomous Systems
- Assurance Monitoring of Learning Enabled Cyber-Physical Systems Using Inductive Conformal Prediction based on Distance Learning
- A fast and effective kernel two-sample test for large-scale data
- A Stochastic Newton Algorithm for Distributed Convex Optimization