Papers
Sat 4 Jun 2022
97 papers
- Hybrid Value Estimation for Off-policy Evaluation and Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Reward Poisoning Attacks on Offline Multi-Agent Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Extreme Compression for Pre-trained Transformers Made Simple and EfficientKnowledge distillation → Knowledge distillation for LLMs
- Forecasting the production of Distillate Fuel Oil Refinery and Propane Blender net production by using Time Series Algorithms
- Optimizing Indoor Navigation Policies For Spatial Distancing
- Study on Image Filtering -- Techniques, Algorithm and Applications
- Understanding EFL Student Idea Generation Strategies for Creative Writing with NLG Tools
- AI in 6G: Energy-Efficient Distributed Machine Learning for Multilayer Heterogeneous Networks
- Fault-Aware Neural Code Rankers
- Future Artificial Intelligence tools and perspectives in medicine
- NeMF: Neural Motion Fields for Kinematic Animation
- Zeroth-Order SciML: Non-intrusive Integration of Scientific Software with Deep Learning
- Intake Monitoring in Free-Living Conditions: Overview and Lessons we Have Learned
- Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning
- Priors in Deep Image Restoration and Enhancement: A Survey
- Learning Robust Representations Of Generative Models Using Set-Based Artificial Fingerprints
- PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers
- Active Bayesian Causal Inference
- Low Power Neuromorphic EMG Gesture Classification
- Empowering GNNs via Edge-Aware Weisfeiler-Leman Algorithm
- When Personalization Harms: Reconsidering the Use of Group Attributes in Prediction
- Interpretable Models Capable of Handling Systematic Missingness in Imbalanced Classes and Heterogeneous Datasets
- Fast and Accurate Error Simulation for CNNs against Soft Errors
- Learning Speaker-specific Lip-to-Speech Generation
- On the Generalization Power of the Overfitted Three-Layer Neural Tangent Kernel Model
- UAV-Aided Multi-Community Federated Learning
- Developing hierarchical anticipations via neural network-based event segmentation
- First-Order Algorithms for Min-Max Optimization in Geodesic Metric Spaces
- MetaNOR: A Meta-Learnt Nonlocal Operator Regression Approach for Metamaterial Modeling
- Beyond Value: CHECKLIST for Testing Inferences in Planning-Based RL
- Interpolating Between Softmax Policy Gradient and Neural Replicator Dynamics with Capped Implicit Exploration
- A Control Theoretic Framework for Adaptive Gradient Optimizers in Machine Learning
- A Neural Network Approach for Homogenization of Multiscale Problems
- Guided Deep Metric Learning
- Implicit Neural Representation for Mesh-Free Inverse Obstacle Scattering
- Between Rate-Distortion Theory & Value Equivalence in Model-Based Reinforcement Learning
- Symmetry as a Representation of Intuitive Geometry?
- Is L2 Physics-Informed Loss Always Suitable for Training Physics-Informed Neural Network?
- APES: Articulated Part Extraction from Sprite Sheets
- Actuarial Applications of Natural Language Processing Using Transformers: Case Studies for Using Text Features in an Actuarial Context
- Causal Discovery in Heterogeneous Environments Under the Sparse Mechanism Shift Hypothesis
- Combinatorial optimization for low bit-width neural networks
- CVNets: High Performance Library for Computer Vision
- A PDE-based Explanation of Extreme Numerical Sensitivities and Edge of Stability in Training Neural Networks
- MSR: Making Self-supervised learning Robust to Aggressive Augmentations
- Combinatorial Causal Bandits
- CAINNFlow: Convolutional block Attention modules and Invertible Neural Networks Flow for anomaly detection and localization tasks
- Constructing unbiased gradient estimators with finite variance for conditional stochastic optimization
- Cross-modal Clinical Graph Transformer for Ophthalmic Report Generation
- Atypical lexical abbreviations identification in Russian medical texts
- Delving into the Openness of CLIP
- Geodesic Properties of a Generalized Wasserstein Embedding for Time Series Analysis
- Evaluation of Xilinx Deep Learning Processing Unit under Neutron Irradiation
- Modelling and Mining of Patient Pathways: A Scoping Review
- MACC: Cross-Layer Multi-Agent Congestion Control with Deep Reinforcement Learning
- Formal Specifications from Natural Language
- C3Fusion: Consistent Contrastive Colon Fusion, Towards Deep SLAM in Colonoscopy
- Instance-wise Prompt Tuning for Pretrained Language Models
- MPE inference using an Incremental Build-Infer-Approximate Paradigm
- Comparing Performance of Different Linguistically-Backed Word Embeddings for Cyberbullying Detection
- Exploring the Potential of Feature Density in Estimating Machine Learning Classifier Performance with Application to Cyberbullying Detection
- Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile
- Occlusion-Resistant Instance Segmentation of Piglets in Farrowing Pens Using Center Clustering Network
- Learning Generative Factors of EEG Data with Variational auto-encoders
- Stochastic Multiple Target Sampling Gradient Descent
- Discovering Ancestral Instrumental Variables for Causal Inference from Observational Data
- Investigating Brain Connectivity with Graph Neural Networks and GNNExplainer
- Variational Monte Carlo Approach to Partial Differential Equations with Neural Networks
- From Pixels to Objects: Cubic Visual Attention for Visual Question Answering
- Classification at the Accuracy Limit -- Facing the Problem of Data Ambiguity
- Automated Audio Captioning with Epochal Difficult Captions for Curriculum Learning
- Nerfels: Renderable Neural Codes for Improved Camera Pose Estimation
- Neural Lyapunov Control of Unknown Nonlinear Systems with Stability Guarantees
- The Spike Gating Flow: A Hierarchical Structure Based Spiking Neural Network for Online Gesture Recognition
- Toward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentation
- Video-based Human-Object Interaction Detection from Tubelet Tokens
- Distributed Machine Learning in D2D-Enabled Heterogeneous Networks: Architectures, Performance, and Open Challenges
- Soft Adversarial Training Can Retain Natural Accuracy
- Deep Radiomic Analysis for Predicting Coronavirus Disease 2019 in Computerized Tomography and X-ray Images
- Estimating counterfactual treatment outcomes over time in complex multiagent scenarios
- Evaluation of creating scoring opportunities for teammates in soccer via trajectory prediction
- Saliency Attack: Towards Imperceptible Black-box Adversarial Attack
- Modeling of Textures to Predict Immune Cell Status and Survival of Brain Tumour Patients
- Adaptive Tree Backup Algorithms for Temporal-Difference Reinforcement Learning
- Initial Study into Application of Feature Density and Linguistically-backed Embedding to Improve Machine Learning-based Cyberbullying Detection
- A Superimposed Divide-and-Conquer Image Recognition Method for SEM Images of Nanoparticles on The Surface of Monocrystalline silicon with High Aggregation Degree
- Face Recognition Accuracy Across Demographics: Shining a Light Into the Problem
- Learning in Congestion Games with Bandit Feedback
- An Unpooling Layer for Graph Generation
- Estimating the Effect of Team Hitting Strategies Using Counterfactual Virtual Simulation in Baseball
- SPGNet: Spatial Projection Guided 3D Human Pose Estimation in Low Dimensional Space
- Model-Informed Generative Adversarial Network (MI-GAN) for Learning Optimal Power Flow
- Recursive Deformable Image Registration Network with Mutual Attention
- Image Data collection and implementation of deep learning-based model in detecting Monkeypox disease using modified VGG16
- ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers
- Design and Implementation of an Heuristic-Enhanced Branch-and-Bound Solver for MILP
- Poisson2Sparse: Self-Supervised Poisson Denoising From a Single Image