Papers
Sun 28 Aug 2022
50 papers
- Goal-Conditioned Q-Learning as Knowledge DistillationKnowledge distillation → On-policy and self-distillation for LLMs
- JARVIS: A Neuro-Symbolic Commonsense Reasoning Framework for Conversational Embodied AgentsLLM reasoning → Spatial and embodied reasoning +1
- Removing Rain Streaks via Task Transfer LearningKnowledge distillation → General knowledge distillation methods
- Machine Learning Models Evaluation and Feature Importance Analysis on NPL Dataset
- Automatic Infectious Disease Classification Analysis with Concept Discovery
- Neural Network Approximation of Continuous Functions in High Dimensions with Applications to Inverse Problems
- Predicting IMDb Rating of TV Series with Deep Learning: The Case of Arrow
- Adapting the LodView RDF Browser for Navigation over the Multilingual Linguistic Linked Open Data Cloud
- Domain Adaptation Principal Component Analysis: base linear method for learning with out-of-distribution data
- Statistical Inverse Problems in Hilbert Scales
- Learning Informative Health Indicators Through Unsupervised Contrastive Learning
- Computing with Hypervectors for Efficient Speaker Identification
- Unsupervised diffeomorphic cardiac image registration using parameterization of the deformation field
- Blending Neural Operators and Relaxation Methods in PDE Numerical Solvers
- Efficient liver segmentation with 3D CNN using computed tomography scans
- Podcast Summary Assessment: A Resource for Evaluating Summary Assessment Methods
- Detection and Classification of Brain tumors Using Deep Convolutional Neural Networks
- Bayesian Neural Network Language Modeling for Speech Recognition
- MANDO: Multi-Level Heterogeneous Graph Embeddings for Fine-Grained Detection of Smart Contract Vulnerabilities
- A preprocessing perspective for quantum machine learning classification advantage using NISQ algorithms
- FFCNN: Fast FPGA based Acceleration for Convolution neural network inference
- AutoQML: Automatic Generation and Training of Robust Quantum-Inspired Classifiers by Using Genetic Algorithms on Grayscale Images
- Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image
- Deep learning for automatic head and neck lymph node level delineation provides expert-level accuracy
- Visualizing high-dimensional loss landscapes with Hessian directions
- Leachable Component Clustering
- IDP-PGFE: An Interpretable Disruption Predictor based on Physics-Guided Feature Extraction
- Grounded Affordance from Exocentric View
- Towards Disentangled Speech Representations
- Towards Real-World Video Deblurring by Exploring Blur Formation Process
- Cross-domain Cross-architecture Black-box Attacks on Fine-tuned Models with Transferred Evolutionary Strategies
- Learning Heterogeneous Interaction Strengths by Trajectory Prediction with Graph Neural Network
- CJaFr-v3 : A Freely Available Filtered Japanese-French Aligned Corpus
- RUAD: unsupervised anomaly detection in HPC systems
- Influence Maximization (IM) in Complex Networks with Limited Visibility Using Statistical Methods
- Face Anti-Spoofing from the Perspective of Data Sampling
- Opinion Leader Detection in Online Social Networks Based on Output and Input Links
- Asynchronous Training Schemes in Distributed Learning with Time Delay
- Generative Modelling of the Ageing Heart with Cross-Sectional Imaging and Clinical Data
- Federated Learning of Large Models at the Edge via Principal Sub-Model Training
- ClusTR: Exploring Efficient Self-attention via Clustering for Vision Transformers
- Efficient Motion Modelling with Variable-sized blocks from Hierarchical Cuboidal Partitioning
- An Access Control Method with Secret Key for Semantic Segmentation Models
- Learning Clinical Concepts for Predicting Risk of Progression to Severe COVID-19
- Normality-Guided Distributional Reinforcement Learning for Continuous Control
- Delving into the Continuous Domain Adaptation
- An Empirical Study on the Usage of Automated Machine Learning Tools
- Accurate and Robust Lesion RECIST Diameter Prediction and Segmentation with Transformers
- Hydrogen atom confined inside an inverted-Gaussian potential
- Interpretable (not just posthoc-explainable) medical claims modeling for discharge placement to prevent avoidable all-cause readmissions or death