Papers
Thu 22 Sep 2022
167 papers
- Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptionsDiffusion models → Diffusion foundations and sampling
- PACT: Perception-Action Causal Transformer for Autoregressive Robotics Pre-TrainingWorld models → Embodied and robot world models
- MIDMs: Matching Interleaved Diffusion Models for Exemplar-based Image TranslationDiffusion models → Image generation, text-to-image and editing
- Privacy Attacks Against Biometric Models with Fewer Samples: Incorporating the Output of Multiple ModelsLLM safety and security → Membership inference attacks
- Identifiability and generalizability from multiple experts in Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
- Proximal Point Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- Implementing and Experimenting with Diffusion Models for Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
- SimuShips -- A High Resolution Simulation Dataset for Ship Detection with Precise Annotations
- Self-supervised Learning for Clustering of Wireless Spectrum Activity
- Learning Disentangled Representations for Natural Language Definitions
- Embedding-Assisted Attentional Deep Learning for Real-World RF Fingerprinting of Bluetooth
- Forecasting Cryptocurrencies Log-Returns: a LASSO-VAR and Sentiment Approach
- Equitable Marketplace Mechanism Design
- Optimal Stopping with Gaussian Processes
- Deep learning based sferics recognition for AMT data processing in the dead band
- Characterizing Uncertainty in the Visual Text Analysis Pipeline
- Is your forecaster smarter than an energy engineer: a deep dive into electricity price forecasting
- A Case Report On The "A.I. Locked-In Problem": social concerns with modern NLP
- PiFold: Toward effective and efficient protein inverse folding
- Multistage Large Segment Imputation Framework Based on Deep Learning and Statistic Metrics
- Transformer-based Models to Deal with Heterogeneous Environments in Human Activity Recognition
- Evaluating Agent Interactions Through Episodic Knowledge Graphs
- Edge-oriented Implicit Neural Representation with Channel Tuning
- Rethinking Missing Data: Aleatoric Uncertainty-Aware Recommendation
- Oracle Analysis of Representations for Deep Open Set Detection
- Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration
- Fast Disparity Estimation from a Single Compressed Light Field Measurement
- A domain adaptive deep learning solution for scanpath prediction of paintings
- UNav: An Infrastructure-Independent Vision-Based Navigation System for People with Blindness and Low vision
- Privacy-Preserving Person Detection Using Low-Resolution Infrared Cameras
- Towards Faithful Model Explanation in NLP: A Survey
- FuTH-Net: Fusing Temporal Relations and Holistic Features for Aerial Video Classification
- StyleTime: Style Transfer for Synthetic Time Series Generation
- Colonoscopy Landmark Detection using Vision Transformers
- An Investigation of the Bias-Variance Tradeoff in Meta-Gradients
- ProgPrompt: Generating Situated Robot Task Plans using Large Language Models
- Deep Domain Adaptation for Detecting Bomb Craters in Aerial Images
- T2FPV: Dataset and Method for Correcting First-Person View Errors in Pedestrian Trajectory Prediction
- Automated detection of Alzheimer disease using MRI images and deep neural networks- A review
- Scalable Gaussian Process Hyperparameter Optimization via Coverage Regularization
- Environment Optimization for Multi-Agent Navigation
- FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusion
- Capsule Network based Contrastive Learning of Unsupervised Visual Representations
- Minimizing Human Assistance: Augmenting a Single Demonstration for Deep Reinforcement Learning
- Optimization of FPGA-based CNN Accelerators Using Metaheuristics
- Recurrence-free Survival Prediction under the Guidance of Automatic Gross Tumor Volume Segmentation for Head and Neck Cancers
- Computational Discovery of Energy-Efficient Heat Treatment for Microstructure Design using Deep Reinforcement Learning
- XF2T: Cross-lingual Fact-to-Text Generation for Low-Resource Languages
- Evaluating Latent Space Robustness and Uncertainty of EEG-ML Models under Realistic Distribution Shifts
- Hierarchical Graph Convolutional Network Built by Multiscale Atlases for Brain Disorder Diagnosis Using Functional Connectivity
- NamedMask: Distilling Segmenters from Complementary Foundation Models
- VToonify: Controllable High-Resolution Portrait Video Style Transfer
- UniColor: A Unified Framework for Multi-Modal Colorization with Transformer
- Concept Activation Regions: A Generalized Framework For Concept-Based Explanations
- Learning Dexterous Manipulation from Exemplar Object Trajectories and Pre-Grasps
- A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biases
- Beyond Heisenberg Limit Quantum Metrology through Quantum Signal Processing
- Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training
- Attention is All They Need: Exploring the Media Archaeology of the Computer Vision Research Paper
- OLIVES Dataset: Ophthalmic Labels for Investigating Visual Eye Semantics
- Learning Visual Explanations for DCNN-Based Image Classifiers Using an Attention Mechanism
- Poisson Flow Generative Models
- GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images
- Model-Assisted Labeling via Explainability for Visual Inspection of Civil Infrastructures
- MLGWSC-1: The first Machine Learning Gravitational-Wave Search Mock Data Challenge
- Automatic and effective discovery of quantum kernels
- A Generalist Neural Algorithmic Learner
- Neural Networks Based on Power Method and Inverse Power Method for Solving Linear Eigenvalue Problems
- Learning Interpretable Latent Dialogue Actions With Less Supervision
- A Bibliographic View on Constrained Clustering
- Modern Machine Learning Tools for Monitoring and Control of Industrial Processes: A Survey
- Training neural network ensembles via trajectory sampling
- Uncertainty-aware Perception Models for Off-road Autonomous Unmanned Ground Vehicles
- CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement
- Scope of Pre-trained Language Models for Detecting Conflicting Health Information
- Parallel Reinforcement Learning Simulation for Visual Quadrotor Navigation
- Query-based Industrial Analytics over Knowledge Graphs with Ontology Reshaping
- Prompting for a conversation: How to control a dialog model?
- Towards Ontology Reshaping for KG Generation with User-in-the-Loop: Applied to Bosch Welding
- Cross-domain Voice Activity Detection with Self-Supervised Representations
- Simulation-based inference of Bayesian hierarchical models while checking for model misspecification
- Efficient Few-Shot Learning Without Prompts
- Inverted Landing in a Small Aerial Robot via Deep Reinforcement Learning for Triggering and Control of Rotational Maneuvers
- MonoByte: A Pool of Monolingual Byte-level Language Models
- Google Coral-based edge computing person reidentification using human parsing combined with analytical method
- Approaching English-Polish Machine Translation Quality Assessment with Neural-based Methods
- Structure Guided Manifolds for Discovery of Disease Characteristics
- Avoiding Post-Processing with Event-Based Detection in Biomedical Signals
- Over-the-Air Computation over Balanced Numerals
- Predicting pairwise preferences between TTS audio stimuli using parallel ratings data and anti-symmetric twin neural networks
- Entropic Descent Archetypal Analysis for Blind Hyperspectral Unmixing
- Selecting Better Samples from Pre-trained LLMs: A Case Study on Question Generation
- Counterfactual Explanations Using Optimization With Constraint Learning
- Challenges in Visual Anomaly Detection for Mobile Robots
- Learning to Simulate Realistic LiDARs
- DLUNet: Semi-supervised Learning based Dual-Light UNet for Multi-organ Segmentation
- Adaptation of domain-specific transformer models with text oversampling for sentiment analysis of social media posts on Covid-19 vaccines
- COVID-19 Detection and Analysis From Lung CT Images using Novel Channel Boosted CNNs
- Developing, Evaluating and Scaling Learning Agents in Multi-Agent Environments
- XClusters: Explainability-first Clustering
All 167
- An Information Minimization Based Contrastive Learning Model for Unsupervised Sentence Embeddings Learning
- Learning Invariant Representations for Equivariant Neural Networks Using Orthogonal Moments
- Robust Collaborative Learning with Linear Gradient Overhead
- MGTR: End-to-End Mutual Gaze Detection with Transformer
- Equivariant Transduction through Invariant Alignment
- Learning to Write with Coherence From Negative Examples
- CAMRI Loss: Improving Recall of a Specific Class without Sacrificing Accuracy
- CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding
- Vanilla Feedforward Neural Networks as a Discretization of Dynamical Systems
- DRKF: Distilled Rotated Kernel Fusion for Efficient Rotation Invariant Descriptors in Local Feature Matching
- AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detection
- Pretraining the Vision Transformer using self-supervised methods for vision based Deep Reinforcement Learning
- A Capability and Skill Model for Heterogeneous Autonomous Robots
- Process Modeling and Conformance Checking in Healthcare: A COVID-19 Case Study
- mini-ELSA: using Machine Learning to improve space efficiency in Edge Lightweight Searchable Attribute-based encryption for Industry 4.0
- EPIC TTS Models: Empirical Pruning Investigations Characterizing Text-To-Speech Models
- Amortized Variational Inference: A Systematic Review
- A Multi-Stage Multi-Codebook VQ-VAE Approach to High-Performance Neural TTS
- Non-Negative Matrix Factorization with Scale Data Structure Preservation
- Beyond Voxel Prediction Uncertainty: Identifying brain lesions you can trust
- An Attention Matrix for Every Decision: Faithfulness-based Arbitration Among Multiple Attention-Based Interpretations of Transformers in Text Classification
- Semantically Consistent Data Augmentation for Neural Machine Translation via Conditional Masked Language Model
- Turning Normalizing Flows into Monge Maps with Geodesic Gaussian Preserving Flows
- A One-shot Framework for Distributed Clustered Learning in Heterogeneous Environments
- Efficient CNN with uncorrelated Bag of Features pooling
- A novel corrective-source term approach to modeling unknown physics in aluminum extraction process
- SCALES: From Fairness Principles to Constrained Decision-Making
- MnTTS: An Open-Source Mongolian Text-to-Speech Synthesis Dataset and Accompanied Baseline
- The SpeakIn System Description for CNSRC2022
- DIG: Draping Implicit Garment over the Human Body
- Identity-Aware Hand Mesh Estimation and Personalization from RGB Images
- Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization
- High-order Multi-view Clustering for Generic Data
- A Spatial-channel-temporal-fused Attention for Spiking Neural Networks
- Physical Interaction: Reconstructing Hand-object Interactions with Physics
- Boosting as Frank-Wolfe
- Nonsmooth Nonconvex-Nonconcave Minimax Optimization: Primal-Dual Balancing and Iteration Complexity Analysis
- Color Recommendation for Vector Graphic Documents based on Multi-Palette Representation
- Memory-Augmented Graph Neural Networks: A Brain-Inspired Review
- IntereStyle: Encoding an Interest Region for Robust StyleGAN Inversion
- Automated head and neck tumor segmentation from 3D PET/CT
- SR-GCL: Session-Based Recommendation with Global Context Enhanced Augmentation in Contrastive Learning
- Controllable Accented Text-to-Speech Synthesis
- Robust Forecasting for Robotic Control: A Game-Theoretic Approach
- STING: Self-attention based Time-series Imputation Networks using GAN
- DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation
- A CT-Based Airway Segmentation Using U2-net Trained by the Dice Loss Function
- Deep Learning Based Page Creation for Improving E-Commerce Organic Search Traffic
- Homophone Reveals the Truth: A Reality Check for Speech2Vec
- How Does It Feel? Self-Supervised Costmap Learning for Off-Road Vehicle Traversability
- Deep Lake: a Lakehouse for Deep Learning
- Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation
- Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training
- MUI-TARE: Multi-Agent Cooperative Exploration with Unknown Initial Position
- Multi-level Adversarial Spatio-temporal Learning for Footstep Pressure based FoG Detection
- DRAMA: Joint Risk Localization and Captioning in Driving
- AIR-JPMC@SMM4H'22: Classifying Self-Reported Intimate Partner Violence in Tweets with Multiple BERT-based Models
- INFINITY: A Simple Yet Effective Unsupervised Framework for Graph-Text Mutual Conversion
- Reinforcement Learning in Computing and Network Convergence Orchestration
- Common human diseases prediction using machine learning based on survey data
- Enhancing the Inductive Biases of Graph Neural ODE for Modeling Dynamical Systems
- CCR: Facial Image Editing with Continuity, Consistency and Reversibility
- FusionRCNN: LiDAR-Camera Fusion for Two-stage 3D Object Detection
- In Differential Privacy, There is Truth: On Vote Leakage in Ensemble Private Learning
- Fair Robust Active Learning by Joint Inconsistency
- Enhanced Decentralized Federated Learning based on Consensus in Connected Vehicles
- Batch Bayesian optimisation via density-ratio estimation with guarantees