Papers
Tue 16 Aug 2022
117 papers
- Riemannian Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement LearningWorld models → Latent dynamics models and model-based RL
- Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion ModelDiffusion models → Diffusion foundations and sampling
- Mask and Reason: Pre-Training Knowledge Graph Transformers for Complex Logical QueriesMixture-of-experts → MoE large language models
- Neural network fragile watermarking with no model performance degradationLLM safety and security → Watermarking generated content and models
- Reliable Decision from Multiple Subtasks through Threshold Optimization: Content Moderation in the WildLLM safety and security → Safety alignment, refusal and guardrails
- CTI4AI: Threat Intelligence Generation and Sharing after Red Teaming AI ModelsLLM safety and security → Prompt injection and agent security
- "Are you okay, honey?": Recognizing Emotions among Couples Managing Diabetes in Daily Life using Multimodal Real-World Smartwatch Data
- Data-driven End-to-end Learning of Pole Placement Control for Nonlinear Dynamics via Koopman Invariant Subspaces
- Novel Deep Learning Approach to Derive Cytokeratin Expression and Epithelium Segmentation from DAPI
- Error Parity Fairness: Testing for Group Fairness in Regression Tasks
- Wave simulation in non-smooth media by PINN with quadratic neural network and PML condition
- SMPL-IK: Learned Morphology-Aware Inverse Kinematics for AI Driven Artistic Workflows
- Quantum Machine Learning for Material Synthesis and Hardware Security
- Enhancing Audio Perception of Music By AI Picked Room Acoustics
- DICE: Data-Efficient Clinical Event Extraction with Generative Models
- Private Estimation with Public Data
- Tiny-HR: Towards an interpretable machine learning pipeline for heart rate estimation on edge devices
- Enhancing Heterogeneous Federated Learning with Knowledge Extraction and Multi-Model Fusion
- Blind Users Accessing Their Training Images in Teachable Object Recognizers
- Mixed Quantum-Classical Method For Fraud Detection with Quantum Feature Selection
- Online Learning for Mixture of Multivariate Hawkes Processes
- Advancing Human-AI Complementarity: The Impact of User Expertise and Algorithmic Tuning on Joint Decision Making
- Generative Thermal Design Through Boundary Representation and Multi-Agent Cooperative Environment
- On the generalization of learning algorithms that do not converge
- TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments
- Measuring Statistical Dependencies via Maximum Norm and Characteristic Functions
- ViT-ReT: Vision and Recurrent Transformer Neural Networks for Human Activity Recognition in Videos
- FedPerm: Private and Robust Federated Learning by Parameter Permutation
- Ex-Ante Assessment of Discrimination in Dataset
- PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm
- FOLD-SE: An Efficient Rule-based Machine Learning Algorithm with Scalable Explainability
- Casual Indoor HDR Radiance Capture from Omnidirectional Images
- Collaborative causal inference on distributed data
- Language-guided Semantic Style Transfer of 3D Indoor Scenes
- BERTifying Sinhala -- A Comprehensive Analysis of Pre-trained Language Models for Sinhala Text Classification
- StyleFaceV: Face Video Generation via Decomposing and Recomposing Pretrained StyleGAN3
- Estimating Appearance Models for Image Segmentation via Tensor Factorization
- Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models
- TexPrax: A Messaging Application for Ethical, Real-time Data Collection and Annotation
- Parallel Hierarchical Transformer with Attention Alignment for Abstractive Multi-Document Summarization
- OrthoMAD: Morphing Attack Detection Through Orthogonal Identity Disentanglement
- Temporal Concept Drift and Alignment: An empirical approach to comparing Knowledge Organization Systems over time
- BERT(s) to Detect Multiword Expressions
- Diagnosis of COVID-19 disease using CT scan images and pre-trained models
- Learning Facial Liveness Representation for Domain Generalized Face Anti-spoofing
- A Deep Reinforcement Learning-based Adaptive Charging Policy for WRSNs
- Training Latent Variable Models with Auto-encoding Variational Bayes: A Tutorial
- SIERRA: A Modular Framework for Research Automation and Reproducibility
- Counterfactual Supervision-based Information Bottleneck for Out-of-Distribution Generalization
- Delaunay-Triangulation-Based Learning with Hessian Total-Variation Regularization
- Mining Large Independent Sets on Massive Graphs
- Unsupervised Domain Adaptation for Segmentation with Black-box Source Model
- Enhancing Dynamic Mode Decomposition Workflow with In-Situ Visualization and Data Compression
- Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignment
- PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation
- Subtype-Aware Dynamic Unsupervised Domain Adaptation
- A Policy Resonance Approach to Solve the Problem of Responsibility Diffusion in Multiagent Reinforcement Learning
- Predicting student performance using sequence classification with time-based windows
- Langevin Diffusion Variational Inference
- A Latent Feature Analysis-based Approach for Spatio-Temporal Traffic Data Recovery
- Learning Efficient Abstract Planning Models that Choose What to Predict
- Introducing Intermediate Domains for Effective Self-Training during Test-Time
- Rain Removal from Light Field Images with 4D Convolution and Multi-scale Gaussian Process
- Data Augmentation is a Hyperparameter: Cherry-picked Self-Supervision for Unsupervised Anomaly Detection is Creating the Illusion of Success
- Unsupervised domain adaptation semantic segmentation of high-resolution remote sensing imagery with invariant domain-level prototype memory
- Local Low-light Image Enhancement via Region-Aware Normalization
- Score-Based Diffusion meets Annealed Importance Sampling
- FALSE: Fake News Automatic and Lightweight Solution
- The LAM Dataset: A Novel Benchmark for Line-Level Handwritten Text Recognition
- Generating a Terrain-Robustness Benchmark for Legged Locomotion: A Prototype via Terrain Authoring and Active Learning
- FEC: Fast Euclidean Clustering for Point Cloud Segmentation
- FedMR: Fedreated Learning via Model Recombination
- Enhancement to Training of Bidirectional GAN : An Approach to Demystify Tax Fraud
- ConTextual Masked Auto-Encoder for Dense Passage Retrieval
- On Optimizing Back-Substitution Methods for Neural Network Verification
- M2HF: Multi-level Multi-modal Hybrid Fusion for Text-Video Retrieval
- Representation Learning on Graphs to Identifying Circular Trading in Goods and Services Tax
- DRAGON: Decentralized Fault Tolerance in Edge Federations
- Uconv-Conformer: High Reduction of Input Sequence Length for End-to-End Speech Recognition
- A Hybrid Deep Feature-Based Deformable Image Registration Method for Pathology Images
- Matching Multiple Perspectives for Efficient Representation Learning
- CorpusBrain: Pre-train a Generative Retrieval Model for Knowledge-Intensive Language Tasks
- American cultural regions mapped through the lexical analysis of social media
- A Review of the Convergence of 5G/6G Architecture and Deep Learning
- Online Learning for Non-monotone Submodular Maximization: From Full Information to Bandit Feedback
- FALCON: Scalable Reasoning over Inconsistent ALC Ontologies
- Algorithmic Assistance with Recommendation-Dependent Preferences
- KRACL: Contrastive Learning with Graph Context Modeling for Sparse Knowledge Graph Completion
- Does lossy image compression affect racial bias within face recognition?
- Rapid Discovery of Graphene Nanocrystals Using DFT and Bayesian Optimization with Neural Network Kernel
- Lp sampling numbers for the Fourier-analytic Barron space
- Manual-Guided Dialogue for Flexible Conversational Agents
- Multi-Point Integrated Sensing and Communication: Fusion Model and Functionality Selection
- Uncertainty-guided Source-free Domain Adaptation
- Neural Networks for Extreme Quantile Regression with an Application to Forecasting of Flood Risk
- Efficient Multimodal Transformer with Dual-Level Feature Restoration for Robust Multimodal Sentiment Analysis
- Making Reinforcement Learning Work on Swimmer
- HVS-Inspired Signal Degradation Network for Just Noticeable Difference Estimation
- Deletion Robust Non-Monotone Submodular Maximization over Matroids
All 117
- Regression modelling of spatiotemporal extreme U.S. wildfires via partially-interpretable neural networks
- Object Discovery via Contrastive Learning for Weakly Supervised Object Detection
- Machine Learning-Based Test Smell Detection
- Higher-order accurate two-sample network inference and network hashing
- Prediction of Seismic Intensity Distributions Using Neural Networks
- Traffic Analytics Development Kits (TADK): Enable Real-Time AI Inference in Networking Apps
- Self-supervised training of deep denoisers in multi-coil MRI considering noise correlations
- Multi-level Contrast Network for Wearables-based Joint Activity Segmentation and Recognition
- Knowledge-Injected Federated Learning
- Color Image Edge Detection using Multi-scale and Multi-directional Gabor filter
- Universal Solutions of Feedforward ReLU Networks for Interpolations
- Bucketized Active Sampling for Learning ACOPF
- SGM-Net: Semantic Guided Matting Net
- Temporal Action Localization with Multi-temporal Scales
- Deep convolutional surrogates and degrees of freedom in thermal design
- Context-Aware Streaming Perception in Dynamic Environments
- SOLBP: Second-Order Loopy Belief Propagation for Inference in Uncertain Bayesian Networks