Papers
Thu 3 Nov 2022
197 papers
- Safe Real-World Autonomous Driving by Learning to Predict and Plan with a Mixture of ExpertsEnd-to-end autonomous driving → End-to-end system architecture
- Contrastive Value Learning: Implicit Models for Simple Offline RLOffline RL and imitation learning from data → Offline RL algorithms
- Efficient Spatially Sparse Inference for Conditional GANs and Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- Oracle Inequalities for Model Selection in Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- lilGym: Natural Language Visual Reasoning with Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
- Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness AssumptionsDiffusion models → Diffusion foundations and sampling
- Evaluating a Synthetic Image Dataset Generated with Stable DiffusionDiffusion models → Image generation, text-to-image and editing
- P4P: Conflict-Aware Motion Prediction for Planning in Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners
- PINTO: Faithful Language Reasoning Using Prompt-Generated RationalesLLM reasoning → Reasoning benchmarks and evaluation
- Using Large Pre-Trained Language Model to Assist FDA in Premarket Medical Device
- Discriminating sensor activation in activity recognition within multi-occupancy environments based on nearby interaction
- A Survey on Evaluation Metrics for Synthetic Material Micro-Structure Images from Generative Models
- Fair and Efficient Distributed Edge Learning with Hybrid Multipath TCP
- Physics-informed neural networks for gravity currents reconstruction from limited data
- Haven't I Seen You Before? Assessing Identity Leakage in Synthetic Irises
- Synthesis of separation processes with reinforcement learning
- DetAIL : A Tool to Automatically Detect and Analyze Drift In Language
- Privacy Aware Experiments without Cookies
- Unified Multi-View Orthonormal Non-Negative Graph Based Clustering Framework
- MolE: a molecular foundation model for drug discovery
- A Fuzzy-set-based Joint Distribution Adaptation Method for Regression and its Application to Online Damage Quantification for Structural Digital Twin
- Self-Adapting Noise-Contrastive Estimation for Energy-Based Models
- An Improved Time Feedforward Connections Recurrent Neural Networks
- Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecast
- Deep Learning based Defect classification and detection in SEM images: A Mask R-CNN approach
- Zero-shot Video Moment Retrieval With Off-the-Shelf Models
- MUSTACHE: Multi-Step-Ahead Predictions for Cache Eviction
- Large Scale Real-World Multi-Person Tracking
- Can RBMs be trained with zero step contrastive divergence?
- A k-additive Choquet integral-based approach to approximate the SHAP values for local interpretability in machine learning
- A Riemannian ADMM
- Time-aware Prompting for Text Generation
- Privacy-preserving Deep Learning based Record Linkage
- Decomposing Counterfactual Explanations for Consequential Decision Making
- 3D Reconstruction of Multiple Objects by mmWave Radar on UAV
- A Survey on Reinforcement Learning in Aviation Applications
- Robust Time Series Chain Discovery with Incremental Nearest Neighbors
- FactorMatte: Redefining Video Matting for Re-Composition Tasks
- No Agreement Without Loss: Learning and Social Choice in Peer Review
- Improving Semi-supervised Deep Learning by using Automatic Thresholding to Deal with Out of Distribution Data for COVID-19 Detection using Chest X-ray Images
- Shapes2Toon: Generating Cartoon Characters from Simple Geometric Shapes
- Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity
- Book Cover Synthesis from the Summary
- Logographic Information Aids Learning Better Representations for Natural Language Inference
- Streaming Audio-Visual Speech Recognition with Alignment Regularization
- A 3D-Shape Similarity-based Contrastive Approach to Molecular Representation Learning
- Efficient Information Sharing in ICT Supply Chain Social Network via Table Structure Recognition
- Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation
- Graph-Based Multi-Camera Soccer Player Tracker
- Handwritten Arabic Character Recognition for Children Writ-ing Using Convolutional Neural Network and Stroke Identification
- Abstract Images Have Different Levels of Retrievability Per Reverse Image Search Engine
- Translated Skip Connections -- Expanding the Receptive Fields of Fully Convolutional Neural Networks
- Sky-image-based solar forecasting using deep learning with multi-location data: training models locally, globally or via transfer learning?
- Federated Hypergradient Descent
- Geometry and convergence of natural policy gradient methods
- Overcoming Barriers to Skill Injection in Language Modeling: Case Study in Arithmetic
- Domain Adaptation under Missingness Shift
- Making Machine Learning Datasets and Models FAIR for HPC: A Methodology and Case Study
- Fairness in Federated Learning via Core-Stability
- Group Cohesion in Multi-Agent Scenarios as an Emergent Behavior
- Scaling Multimodal Pre-Training via Cross-Modality Gradient Harmonization
- LMentry: A Language Model Benchmark of Elementary Language Tasks
- Theta-Resonance: A Single-Step Reinforcement Learning Method for Design Space Exploration
- Adaptive Batch Normalization for Training Data with Heterogeneous Features
- Fast and robust Bayesian Inference using Gaussian Processes with GPry
- Could Giant Pretrained Image Models Extract Universal Representations?
- The Projected Covariance Measure for assumption-lean variable significance testing
- Inverse scaling can become U-shaped
- SAP-DETR: Bridging the Gap Between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency
- Private Blind Model Averaging - Distributed, Non-interactive, and Convergent
- Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model
- Dynamic Kernels and Channel Attention for Low Resource Speaker Verification
- Quantifying Model Uncertainty for Semantic Segmentation using Operators in the RKHS
- Probing Statistical Representations For End-To-End ASR
- Leveraging Fully Observable Policies for Learning under Partial Observability
- Sybil-Proof Diffusion Auction in Social Networks
- Grounding Scene Graphs on Natural Images via Visio-Lingual Message Passing
- MarginNCE: Robust Sound Localization with a Negative Margin
- Machine Learning Methods for Device Identification Using Wireless Fingerprinting
- GEC: A Unified Framework for Interactive Decision Making in MDP, POMDP, and Beyond
- Revisiting and Optimising a CNN Colour Constancy Method for Multi-Illuminant Estimation
- Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation
- Automatic Crater Shape Retrieval using Unsupervised and Semi-Supervised Systems
- Photorealistic Facial Wrinkles Removal
- Expanding Accurate Person Recognition to New Altitudes and Ranges: The BRIAR Dataset
- Uncertainty Quantification for Rule-Based Models
- FedGen: Generalizable Federated Learning for Sequential Data
- Large Language Models Are Human-Level Prompt Engineers
- A Consistent Estimator for Confounding Strength
- Martian Ionosphere Electron Density Prediction Using Bagged Trees
- Deep meta-learning for the selection of accurate ultrasound based breast mass classifier
- When to Laugh and How Hard? A Multimodal Approach to Detecting Humor and its Intensity
- Analysing the effectiveness of a generative model for semi-supervised medical image segmentation
- Using U-Net Network for Efficient Brain Tumor Segmentation in MRI Images
- Faster Adaptive Momentum-Based Federated Methods for Distributed Composition Optimization
- Convex Clustering through MM: An Efficient Algorithm to Perform Hierarchical Clustering
- Contextual information integration for stance detection via cross-attention
- Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systems
- ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations
- Computed tomography coronary angiogram images, annotations and associated data of normal and diseased arteries
All 197
- Relating graph auto-encoders to linear models
- Conditional Generative Models for Simulation of EMG During Naturalistic Movements
- Revisiting Hyperparameter Tuning with Differential Privacy
- Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization
- Circling Back to Recurrent Models of Language
- Seeing the Unseen: Errors and Bias in Visual Datasets
- Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammars
- LE3D: A Lightweight Ensemble Framework of Data Drift Detectors for Resource-Constrained Devices
- HyperSound: Generating Implicit Neural Representations of Audio Signals with Hypernetworks
- Latent Prompt Tuning for Text Summarization
- Toward Unsupervised Outlier Model Selection
- Extra-Newton: A First Approach to Noise-Adaptive Accelerated Second-Order Methods
- Demo: LE3D: A Privacy-preserving Lightweight Data Drift Detection Framework
- Fast Noise Removal in Hyperspectral Images via Representative Coefficient Total Variation
- Human in the loop approaches in multi-modal conversational task guidance system development
- Liability regimes in the age of AI: a use-case driven analysis of the burden of proof
- Self Similarity Matrix based CNN Filter Pruning
- Phase Transitions in Learning and Earning under Price Protection Guarantee
- Query-based Instance Discrimination Network for Relational Triple Extraction
- Crosslingual Generalization through Multitask Finetuning
- Rethinking Hierarchies in Pre-trained Plain Vision Transformer
- MALUNet: A Multi-Attention and Light-weight UNet for Skin Lesion Segmentation
- Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks
- Video Event Extraction via Tracking Visual States of Arguments
- Exploring explicit coarse-grained structure in artificial neural networks
- Progressive Transformation Learning for Leveraging Virtual Images in Training
- Exploring Explainability Methods for Graph Neural Networks
- Optimal Algorithms for Stochastic Complementary Composite Minimization
- Iterative autoregression: a novel trick to improve your low-latency speech enhancement model
- Log-density gradient covariance and automatic metric tensors for Riemann manifold Monte Carlo methods
- Task Tree Retrieval for Robotic Cooking
- Analysis of a Deep Learning Model for 12-Lead ECG Classification Reveals Learned Features Similar to Diagnostic Criteria
- Transformers on Multilingual Clause-Level Morphology
- Feedback is Good, Active Feedback is Better: Block Attention Active Feedback Codes
- Learning Control by Iterative Inversion
- H_eval: A new hybrid evaluation metric for automatic speech recognition tasks
- Learning Hypergraphs From Signals With Dual Smoothness Prior
- Discussion of Features for Acoustic Anomaly Detection under Industrial Disturbing Noise in an End-of-Line Test of Geared Motors
- A speech corpus for chronic kidney disease
- Cutting Through the Noise: An Empirical Comparison of Psychoacoustic and Envelope-based Features for Machinery Fault Detection
- 2 × 2 Zero-Sum Games with Commitments and Noisy Observations
- Scaling up the self-optimization model by means of on-the-fly computation of weights
- An Empirical Bayes Analysis of Object Trajectory Representation Models
- Data-efficient End-to-end Information Extraction for Statistical Legal Analysis
- Isotropic Gaussian Processes on Finite Spaces of Graphs
- Repeatable Random Permutation Set
- Spam Review Detection Using Deep Learning
- Visual Adversarial Attacks and Defenses in the Physical World: A Survey
- Active CT Reconstruction with a Learned Sampling Policy
- Quantum Similarity Testing with Convolutional Neural Networks
- PointSee: Image Enhances Point Cloud
- GRAIMATTER Green Paper: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs)
- Towards federated multivariate statistical process control (FedMSPC)
- StereoPose: Category-Level 6D Transparent Object Pose Estimation from Stereo Images via Back-View NOCS
- Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively
- Temporal Consistency Learning of inter-frames for Video Super-Resolution
- Joint Chinese Word Segmentation and Span-based Constituency Parsing
- Revisiting Grammatical Error Correction Evaluation and Beyond
- X-Metric: An N-Dimensional Information-Theoretic Framework for Groupwise Registration and Deep Combined Computing
- Image-based Early Detection System for Wildfires
- Private Semi-supervised Knowledge Transfer for Deep Learning from Noisy Labels
- From Spelling to Grammar: A New Framework for Chinese Grammatical Error Correction
- Leveraging Domain Features for Detecting Adversarial Attacks Against Deep Speech Recognition in Noise
- Self Supervised Low Dose Computed Tomography Image Denoising Using Invertible Network Exploiting Inter Slice Congruence
- Proximal Subgradient Norm Minimization of ISTA and FISTA
- ImageCAS: A Large-Scale Dataset and Benchmark for Coronary Artery Segmentation based on Computed Tomography Angiography Images
- Meta-PDE: Learning to Solve PDEs Quickly Without a Mesh
- Using Signal Processing in Tandem With Adapted Mixture Models for Classifying Genomic Signals
- Optimal Behavior Prior: Data-Efficient Human Models for Improved Human-AI Collaboration
- nerf2nerf: Pairwise Registration of Neural Radiance Fields
- Robust Few-shot Learning Without Using any Adversarial Samples
- Reinforcement Learning in Non-Markovian Environments
- Try to Avoid Attacks: A Federated Data Sanitization Defense for Healthcare IoMT Systems
- A Bayesian Semiparametric Method For Estimating Causal Quantile Effects
- PolyBuilding: Polygon Transformer for End-to-End Building Extraction
- A Convergence Theory for Federated Average: Beyond Smoothness
- Eliciting Knowledge from Large Pre-Trained Models for Unsupervised Knowledge-Grounded Conversation
- Data-based Polymer-Unit Fingerprint (PUFp): A Newly Accessible Expression of Polymer Organic Semiconductors for Machine Learning
- Data-free Defense of Black Box Models Against Adversarial Attacks
- Open-Vocabulary Argument Role Prediction for Event Extraction
- Sequence-Based Plan Feasibility Prediction for Efficient Task and Motion Planning
- Are Synthetic Control Weights Balancing Score?
- FedTP: Federated Learning by Transformer Personalization
- Fine-Tuning Language Models via Epistemic Neural Networks
- Galaxy Image Deconvolution for Weak Gravitational Lensing with Unrolled Plug-and-Play ADMM
- NaRPA: Navigation and Rendering Pipeline for Astronautics
- Benefits of Monotonicity in Safe Exploration with Gaussian Processes
- The ProfessionAl Go annotation datasEt (PAGE)
- Ground Plane Matters: Picking Up Ground Plane Prior in Monocular 3D Object Detection
- Embed and Emulate: Learning to estimate parameters of dynamical systems with uncertainty quantification
- Crime Prediction using Machine Learning with a Novel Crime Dataset
- Client Selection in Federated Learning: Principles, Challenges, and Opportunities
- INGREX: An Interactive Explanation Framework for Graph Neural Networks
- Continual Learning of Neural Machine Translation within Low Forgetting Risk Regions
- Reliable Malware Analysis and Detection using Topology Data Analysis
- Fair and Optimal Classification via Post-Processing
- Sensor Control for Information Gain in Dynamic, Sparse and Partially Observed Environments