Papers
Fri 26 Nov 2021
121 papers
- An Investigation on Learning, Polluting, and Unlearning the Spam Emails for Lifelong LearningLLM safety and security → Machine unlearning
- Conditional Image Generation with Score-Based Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Measuring Data Quality for Dataset Selection in Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language ModelMultimodal LLMs / vision-language models → Image editing and quality assessment
- Ensembling of Distilled Models from Multi-task Teachers for Constrained Resource Language PairsKnowledge distillation → Knowledge distillation for LLMs
- DSNet: Dynamic Skin Deformation Prediction by Recurrent Neural Network
- Correlation Based Feature Subset Selection for Multivariate Time-Series Data
- Active Learning for Event Extraction with Memory-based Loss Prediction Model
- Natural Scene Text Editing Based on AI
- TEGDetector: A Phishing Detector that Knows Evolving Transaction Behaviors
- AI and the Everything in the Whole Wide World Benchmark
- Bayesian Optimization for auto-tuning GPU kernels
- Dynamic Network-Assisted D2D-Aided Coded Distributed Learning
- Cyclic Graph Attentive Match Encoder (CGAME): A Novel Neural Network For OD Estimation
- WiFi-based Multi-task Sensing
- DeepGate: Learning Neural Representations of Logic Gates
- Particle Dynamics for Learning EBMs
- A Fast Evolutionary adaptation for MCTS in Pommerman
- Unsupervised MKL in Multi-layer Kernel Machines
- The Implicit Values of A Good Hand Shake: Handheld Multi-Frame Neural Depth Refinement
- Failure Modes of Domain Generalization Algorithms
- Towards Efficient Ansatz Architecture for Variational Quantum Algorithms
- BCH-NLP at BioCreative VII Track 3: medications detection in tweets using transformer networks and multi-task learning
- SARS-CoV-2 Dissemination using a Network of the United States Counties
- A Ubiquitous Unifying Degeneracy in Two-Body Microlensing Systems
- Enforcing and Discovering Structure in Machine Learning
- ManiFest: Manifold Deformation for Few-shot Image Translation
- GMFlow: Learning Optical Flow via Global Matching
- NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images
- SWAT: Spatial Structure Within and Among Tokens
- Weakly-guided Self-supervised Pretraining for Temporal Activity Detection
- Neural Fields as Learnable Kernels for 3D Reconstruction
- Mask Transfiner for High-Quality Instance Segmentation
- Immortal Tracker: Tracklet Never Dies
- On the combination of graph data for assessing thin-file borrowers' creditworthiness
- 3D shape sensing and deep learning-based segmentation of strawberries
- Amazon SageMaker Model Monitor: A System for Real-Time Insights into Deployed Machine Learning Models
- Towards Low-Cost and Efficient Malaria Detection
- Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs
- Gradient-SDF: A Semi-Implicit Surface Representation for 3D Reconstruction
- Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning
- Latent Space Smoothing for Individually Fair Representations
- Dimension Reduction with Prior Information for Knowledge Discovery
- Efficient Multi-Organ Segmentation Using SpatialConfiguration-Net with Low GPU Memory Requirements
- Nonequilibrium Monte Carlo for unfreezing variables in hard combinatorial optimization
- DP-SGD vs PATE: Which Has Less Disparate Impact on GANs?
- The Geometry of Adversarial Training in Binary Classification
- Predicting Document Coverage for Relation Extraction
- A Reinforcement Learning Approach for the Continuous Electricity Market of Germany: Trading from the Perspective of a Wind Park Operator
- Graph-based Solutions with Residuals for Intrusion Detection: the Modified E-GraphSAGE and E-ResGAT Algorithms
- VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition
- Semi-supervised t-SNE for Millimeter-wave Wireless Localization
- Asian Giant Hornet Control based on Image Processing and Biological Dispersal
- On Recurrent Neural Networks for learning-based control: recent results and ideas for future developments
- Using Fictitious Class Representations to Boost Discriminative Zero-Shot Learners
- Inside Out Visual Place Recognition
- μNCA: Texture Generation with Ultra-Compact Neural Cellular Automata
- GeoNeRF: Generalizing NeRF with Geometry Priors
- A model of semantic completion in generative episodic memory
- Uncovering the Dark Side of Telegram: Fakes, Clones, Scams, and Conspiracy Movements
- An Optimization Framework for Federated Edge Learning
- Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation
- Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features
- SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection
- SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddings
- When Creators Meet the Metaverse: A Survey on Computational Arts
- Learning Long-Term Reward Redistribution via Randomized Return Decomposition
- QMagFace: Simple and Accurate Quality-Aware Face Recognition
- TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNs
- Generating Usage-related Questions for Preference Elicitation in Conversational Recommender Systems
- A Taxonomy of Anomalies in Log Data
- Morphology Decoder: A Machine Learning Guided 3D Vision Quantifying Heterogenous Rock Permeability for Planetary Surveillance and Robotic Functions
- A Novel Machine Learning Approach to Data Inconsistency with respect to a Fuzzy Relation
- How Well Do Sparse Imagenet Models Transfer?
- True Few-Shot Learning with Prompts -- A Real-World Perspective
- Towards Explainable End-to-End Prostate Cancer Relapse Prediction from H&E Images Combining Self-Attention Multiple Instance Learning with a Recurrent Neural Network
- ContIG: Self-supervised Multimodal Contrastive Learning for Medical Imaging with Genetics
- Confounder Identification-free Causal Visual Feature Learning
- KazNERD: Kazakh Named Entity Recognition Dataset
- ESCADA: Efficient Safety and Context Aware Dose Allocation for Precision Medicine
- TRIP: Refining Image-to-Image Translation via Rival Preferences
- Modeling Annotator Preference and Stochastic Annotation Error for Medical Image Segmentation
- Reinforcement Explanation Learning
- Deep Learning for Reaction-Diffusion Glioma Growth Modelling: Towards a Fully Personalised Model?
- Non-IID data and Continual Learning processes in Federated Learning: A long road ahead
- POEM: 1-bit Point-wise Operations based on Expectation-Maximization for Efficient Point Cloud Processing
- Machines & Influence: An Information Systems Lens
- PicArrange -- Visually Sort, Search, and Explore Private Images on a Mac Computer
- Data Invariants to Understand Unsupervised Out-of-Distribution Detection
- Geometric Multimodal Deep Learning with Multi-Scaled Graph Wavelet Convolutional Network
- Neural Collaborative Graph Machines for Table Structure Recognition
- Contrastive Vicinal Space for Unsupervised Domain Adaptation
- Jointly Learning Agent and Lane Information for Multimodal Trajectory Prediction
- A multitask transfer learning framework for the prediction of virus-human protein-protein interactions
- MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection
- Testability-Aware Low Power Controller Design with Evolutionary Learning
- Impact of classification difficulty on the weight matrices spectra in Deep Learning and application to early-stopping
- ArchRepair: Block-Level Architecture-Oriented Repairing for Deep Neural Networks
- A Variational Inference Approach to Inverse Problems with Gamma Hyperpriors
- Traditional Chinese Synthetic Datasets Verified with Labeled Data for Scene Text Recognition
All 121
- Evacuation Shelter Scheduling Problem
- Hierarchical Motion Encoder-Decoder Network for Trajectory Forecasting
- Random-reshuffled SARAH does not need a full gradient computations
- Learning source-aware representations of music in a discrete latent space
- Amercing: An Intuitive, Elegant and Effective Constraint for Dynamic Time Warping
- Blaschke Product Neural Networks (BPNN): A Physics-Infused Neural Network for Phase Retrieval of Meromorphic Functions
- Data Augmented 3D Semantic Scene Completion with 2D Segmentation Priors
- Self-supervised Correlation Mining Network for Person Image Generation
- Data Fusion Challenges Privacy: What Can Privacy Regulation Do?
- Equivalence between algorithmic instability and transition to replica symmetry breaking in perceptron learning systems
- Simple Contrastive Representation Adversarial Learning for NLP Tasks
- A Robust Volumetric Transformer for Accurate 3D Tumor Segmentation
- Exploiting full Resolution Feature Context for Liver Tumor and Vessel Segmentation via Integrate Framework: Application to Liver Tumor and Vessel 3D Reconstruction under embedded microprocessor
- Latent Space based Memory Replay for Continual Learning in Artificial Neural Networks
- Approximate Bayesian Computation for Physical Inverse Modeling
- Medial Spectral Coordinates for 3D Shape Analysis
- KNAS: Green Neural Architecture Search
- 3D Pose Estimation and Future Motion Prediction from 2D Images
- Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey
- Efficient Self-Ensemble for Semantic Segmentation
- Disentangled Unsupervised Image Translation via Restricted Information Flow