Papers
Thu 2 Feb 2023
226 papers
- The unreasonable effectiveness of few-shot learning for machine translationLLM reasoning → Reasoning benchmarks and evaluation
- Multi-modal Gated Mixture of Local-to-Global Experts for Dynamic Image FusionMixture-of-experts → Vision mixture-of-experts
- Dreamix: Video Diffusion Models are General Video EditorsDiffusion models → Video generation
- Accelerating Large Language Model Decoding with Speculative SamplingEfficient LLM inference and serving → Speculative decoding
- Are Diffusion Models Vulnerable to Membership Inference Attacks?Diffusion models → Robustness, privacy and adversarial aspects +1
- A Theoretical Justification for Image Inpainting using Denoising Diffusion Probabilistic ModelsDiffusion models → 3D, point cloud and scene generation
- Paced-Curriculum Distillation with Prediction and Label Uncertainty for Image SegmentationKnowledge distillation → Distillation for medical imaging
- Visual Imitation Learning with Patch RewardsOffline RL and imitation learning from data → Imitation learning methods
- Policy Expansion for Bridging Offline-to-Online Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Multimodal Chain-of-Thought Reasoning in Language ModelsLLM reasoning → Multimodal reasoning
- QCM-SGM+: Improved Quantized Compressed Sensing With Score-Based Generative ModelsDiffusion models → Diffusion foundations and sampling
- Modeling Causal Mechanisms with Diffusion Models for Interventional and Counterfactual QueriesDiffusion models → Diffusion foundations and sampling
- Scaling Up Computer Vision Neural Networks Using Fast Fourier Transform
- Multivariate Systemic Risk Measures and Computation by Deep Learning Algorithms
- Merging satellite and gauge-measured precipitation using LightGBM with an emphasis on extreme quantiles
- Listen2Scene: Interactive material-aware binaural sound propagation for reconstructed 3D scenes
- Avalanche: A PyTorch Library for Deep Continual Learning
- Leveraging a Probabilistic PCA Model to Understand the Multivariate Statistical Network Monitoring Framework for Network Security Anomaly Detection
- Machine Learning Extreme Acoustic Non-reciprocity in a Linear Waveguide with Multiple Nonlinear Asymmetric Gates
- Benchmarking Algorithms for Submodular Optimization Problems Using IOHProfiler
- Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy
- A sliced-Wasserstein distance-based approach for out-of-class-distribution detection
- CTE: A Dataset for Contextualized Table Extraction
- Performance Bounds for Policy-Based Average Reward Reinforcement Learning Algorithms
- Out of Context: Investigating the Bias and Fairness Concerns of "Artificial Intelligence as a Service"
- DOR: A Novel Dual-Observation-Based Approach for News Recommendation Systems
- Commonsense-Aware Prompting for Controllable Empathetic Dialogue Generation
- Generalized Uncertainty of Deep Neural Networks: Taxonomy and Applications
- Target specific peptide design using latent space approximate trajectory collector
- Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation
- Benchmarking Probabilistic Deep Learning Methods for License Plate Recognition
- Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective
- Follower Agnostic Methods for Stackelberg Games
- A Convolutional-based Model for Early Prediction of Alzheimer's based on the Dementia Stage in the MRI Brain Images
- Neural Insights for Digital Marketing Content Design
- Hyperbolic Contrastive Learning
- Hypothesis Testing and Machine Learning: Interpreting Variable Effects in Deep Artificial Neural Networks using Cohen's f2
- Provably Bounding Neural Network Preimages
- Self-Supervised Relation Alignment for Scene Graph Generation
- Personalized Understanding of Blood Glucose Dynamics via Mobile Sensor Data
- Accelerating Policy Gradient by Estimating Value Function from Prior Computation in Deep Reinforcement Learning
- Continual Learning with Scaled Gradient Projection
- Hyper-parameter Tuning for Fair Classification without Sensitive Attribute Access
- Energy-Inspired Self-Supervised Pretraining for Vision Models
- Mixed Precision Post Training Quantization of Neural Networks with Sensitivity Guided Search
- Effective Robustness against Natural Distribution Shifts for Models with Different Training Data
- Learning with Exposure Constraints in Recommendation Systems
- On the Robustness of Randomized Ensembles to Adversarial Perturbations
- Neural Network Architecture for Database Augmentation Using Shared Features
- Augmented Learning of Heterogeneous Treatment Effects via Gradient Boosting Trees
- Curriculum-Guided Abstractive Summarization
- Creating a Large Language Model of a Philosopher
- STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation
- Lower Bounds for Learning in Revealing POMDPs
- Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval
- SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections
- IC3: Image Captioning by Committee Consensus
- Dual PatchNorm
- Federated Analytics: A survey
- Randomized Greedy Learning for Non-monotone Stochastic Submodular Maximization Under Full-bandit Feedback
- Double Equivariance for Inductive Link Prediction for Both New Nodes and New Relation Types
- Normalizing Flow Ensembles for Rich Aleatoric and Epistemic Uncertainty Modeling
- Knowledge Gradient for Multi-Objective Bayesian Optimization with Decoupled Evaluations
- Large language models predict human sensory judgments across six modalities
- Bayesian Inference on Binary Spiking Networks Leveraging Nanoscale Device Stochasticity
- MARLIN: Soft Actor-Critic based Reinforcement Learning for Congestion Control in Real Networks
- Ditto in the House: Building Articulation Models of Indoor Scenes through Interactive Perception
- Multi-scale Feature Alignment for Continual Learning of Unlabeled Domains
- Convolutional Autoencoders, Clustering and POD for Low-dimensional Parametrization of Navier-Stokes Equations
- ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs
- Geometric Deep Learning for Autonomous Driving: Unlocking the Power of Graph Neural Networks With CommonRoad-Geometric
- adSformers: Personalization from Short-Term Sequences and Diversity of Representations in Etsy Ads
- Identifying regions of importance in wall-bounded turbulence through explainable deep learning
- Robust Markov Decision Processes without Model Estimation
- Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function
- Human not in the loop: objective sample difficulty measures for Curriculum Learning
- Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal
- Diagrammatization and Abduction to Improve AI Interpretability With Domain-Aligned Explanations for Medical Diagnosis
- Robust Estimation under the Wasserstein Distance
- A Machine Learning Approach to Measuring Climate Adaptation
- Dual Propagation: Accelerating Contrastive Hebbian Learning with Dyadic Neurons
- Factor Fields: A Unified Framework for Neural Fields and Beyond
- Practical Bandits: An Industry Perspective
- A novel automatic wind power prediction framework based on multi-time scale and temporal attention mechanisms
- Laplacian Change Point Detection for Single and Multi-view Dynamic Graphs
- Online Learning under Budget and ROI Constraints via Weak Adaptivity
- Causal Lifting and Link Prediction
- Imitating careful experts to avoid catastrophic events
- On the Efficacy of Differentially Private Few-shot Image Classification
- Best Possible Q-Learning
- The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing
- Diversity Through Exclusion (DTE): Niche Identification for Reinforcement Learning through Value-Decomposition
- Multi-Tour Set Traveling Salesman Problem in Planning Power Transmission Line Inspection
- Convolutional Neural Operators for robust and accurate learning of PDEs
- Unsupervised Learning of Sampling Distributions for Particle Filters
- STEP: Learning N:M Structured Sparsity Masks from Scratch with Precondition
- Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Prompt
- Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics
- Vehicle Fault-Tolerant Robust Power Transmission Line Inspection Planning
- Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model using Pixel-aligned Reconstruction Priors
All 226
- Vectorized Scenario Description and Motion Prediction for Scenario-Based Testing
- Deep COVID-19 Forecasting for Multiple States with Data Augmentation
- A comparative study of statistical and machine learning models on near-real-time daily emissions prediction
- Tab2KG: Semantic Table Interpretation with Lightweight Semantic Profiles
- Combining Deep Neural Reranking and Unsupervised Extraction for Multi-Query Focused Summarization
- UW-CVGAN: UnderWater Image Enhancement with Capsules Vectors Quantization
- SceneScape: Text-Driven Consistent Scene Generation
- De Novo Molecular Generation via Connection-aware Motif Mining
- Mnemosyne: Learning to Train Transformers with Transformers
- Metaverse: Requirements, Architecture, Standards, Status, Challenges, and Perspectives
- DirectMHP: Direct 2D Multi-Person Head Pose Estimation with Full-range Angles
- GraphReg: Dynamical Point Cloud Registration with Geometry-aware Graph Signal Processing
- A Survey on Efficient Training of Transformers
- LesionAid: Vision Transformers-based Skin Lesion Generation and Classification
- A general Markov decision process formalism for action-state entropy-regularized reward maximization
- New Linear-time Algorithm for SubTree Kernel Computation based on Root-Weighted Tree Automata
- NFRsTDO v1.2's Terms, Properties, and Relationships -- A Top-Domain Non-Functional Requirements Ontology
- Confidence and Dispersity Speak: Characterising Prediction Matrix for Unsupervised Accuracy Estimation
- Curriculum Learning for ab initio Deep Learned Refractive Optics
- Sketched Ridgeless Linear Regression: The Role of Downsampling
- Uncertainty in Fairness Assessment: Maintaining Stable Conclusions Despite Fluctuations
- MonoFlow: Rethinking Divergence GANs via the Perspective of Wasserstein Gradient Flows
- FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations
- A Survey on Compositional Generalization in Applications
- MLOps with enhanced performance control and observability
- Physics Constrained Motion Prediction with Uncertainty Quantification
- IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation
- Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial Defense
- Site-specific Deep Learning Path Loss Models based on the Method of Moments
- Randomized prior wavelet neural operator for uncertainty quantification
- Teaching MLOps in Higher Education through Project-Based Learning
- Real-Time Evaluation in Online Continual Learning: A New Hope
- TAPS Responsibility Matrix: A tool for responsible data science by design
- An Efficient Convex Hull-based Vehicle Pose Estimation Method for 3D LiDAR
- On Suppressing Range of Adaptive Stepsizes of Adam to Improve Generalisation Performance
- FCB-SwinV2 Transformer for Polyp Segmentation
- Semantic Coherence Markers for the Early Diagnosis of the Alzheimer Disease
- Meta Learning in Decentralized Neural Networks: Towards More General AI
- Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunities
- Predefined domain specific embeddings of food concepts and recipes: A case study on heterogeneous recipe datasets
- Over-parameterised Shallow Neural Networks with Asymmetrical Node Scaling: Global Convergence Guarantees and Feature Learning
- High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance
- Constrained Online Two-stage Stochastic Optimization: Near Optimal Algorithms via Adversarial Learning
- Open-Set Multi-Source Multi-Target Domain Adaptation
- Unpaired Multi-Domain Causal Representation Learning
- Exposing the CSI: A Systematic Investigation of CSI-based Wi-Fi Sensing Capabilities and Limitations
- Physics Informed Piecewise Linear Neural Networks for Process Optimization
- HaMuCo: Hand Pose Estimation via Multiview Collaborative Self-Supervised Learning
- Eloss in the way: A Sensitive Input Quality Metrics for Intelligent Driving
- Speed-Oblivious Online Scheduling: Knowing (Precise) Speeds is not Necessary
- Stochastic optimal transport in Banach Spaces for regularized estimation of multivariate quantiles
- Predicting Molecule-Target Interaction by Learning Biomedical Network and Molecule Representations
- Domain Generalization Emerges from Dreaming
- A Light-weight CNN Model for Efficient Parkinson's Disease Diagnostics
- Energy Efficiency of Training Neural Network Architectures: An Empirical Study
- FV-MgNet: Fully Connected V-cycle MgNet for Interpretable Time Series Forecasting
- Resilient Binary Neural Network
- Curriculum-guided Abstractive Summarization for Mental Health Online Posts
- Deep-Learning Tool for Early Identifying Non-Traumatic Intracranial Hemorrhage Etiology based on CT Scan
- QR-CLIP: Introducing Explicit Open-World Knowledge for Location and Time Reasoning
- TransFool: An Adversarial Attack against Neural Machine Translation Models
- Efficient Graph Field Integrators Meet Point Clouds
- A Robust Multi-Item Auction Design with Statistical Learning
- An optimization method for out-of-distribution anomaly detection models
- An Enhanced V-cycle MgNet Model for Operator Learning in Numerical Partial Differential Equations
- The Fewer Splits are Better: Deconstructing Readability in Sentence Splitting
- High-dimensional variable clustering based on maxima of a weakly dependent random process
- Dynamic Ensemble of Low-fidelity Experts: Mitigating NAS "Cold-Start"
- Adaptive Siamese Tracking with a Compact Latent Network
- Rethinking Warm-Starts with Predictions: Learning Predictions Close to Sets of Optimal Solutions for Faster L-/L^natural-Convex Function Minimization
- LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergence
- Visual Realism Assessment for Face-swap Videos
- Cooperative Saliency-based Obstacle Detection and AR Rendering for Increased Situational Awareness
- Advances and Challenges in Multimodal Remote Sensing Image Registration
- Conditional expectation with regularization for missing data imputation
- Energy Efficient Training of SNN using Local Zeroth Order Method
- GANalyzer: Analysis and Manipulation of GANs Latent Space for Controllable Face Synthesis
- History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System
- No One Left Behind: Real-World Federated Class-Incremental Learning
- Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment
- Longformer: Longitudinal Transformer for Alzheimer's Disease Classification with Structural MRIs
- KST-Mixer: Kinematic Spatio-Temporal Data Mixer For Colon Shape Estimation
- How to choose "Good" Samples for Text Data Augmentation
- MetaTKG: Learning Evolutionary Meta-Knowledge for Temporal Knowledge Graph Reasoning
- Quantum Graph Learning: Frontiers and Outlook
- Neural Common Neighbor with Completion for Link Prediction
- AOP-Net: All-in-One Perception Network for Joint LiDAR-based 3D Object Detection and Panoptic Segmentation
- Exploring Invariant Representation for Visible-Infrared Person Re-Identification
- Synthesizing Physical Character-Scene Interactions
- Empirical Analysis of the AdaBoost's Error Bound
- The Contextual Lasso: Sparse Linear Models via Deep Neural Networks
- Vision Transformer-based Feature Extraction for Generalized Zero-Shot Learning
- Predicting the Silent Majority on Graphs: Knowledge Transferable Graph Neural Network
- Reliable Prediction Intervals with Directly Optimized Inductive Conformal Regression for Deep Learning
- Using In-Context Learning to Improve Dialogue Safety
- Disentanglement of Latent Representations via Causal Interventions
- Speech Enhancement for Virtual Meetings on Cellular Networks
- CLIPood: Generalizing CLIP to Out-of-Distributions
- SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling
- Online Continual Learning via the Knowledge Invariant and Spread-out Properties
- Algorithm Design for Online Meta-Learning with Task Boundary Detection
- idT5: Indonesian Version of Multilingual T5 Transformer
- Molecular Geometry-aware Transformer for accurate 3D Atomic System modeling
- Learning PDE Solution Operator for Continuous Modeling of Time-Series
- Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent
- Causal Effect Estimation: Recent Advances, Challenges, and Opportunities
- Coordinating Distributed Example Orders for Provably Accelerated Training
- Computational Dualism and Objective Superintelligence
- Fast Online Value-Maximizing Prediction Sets with Conformal Cost Control
- SHINE: Deep Learning-Based Accessible Parking Management System
- Improving Rare Words Recognition through Homophone Extension and Unified Writing for Low-resource Cantonese Speech Recognition
- Sharp Lower Bounds on Interpolation by Deep ReLU Neural Networks at Irregularly Spaced Data
- RobustNeRF: Ignoring Distractors with Robust Losses
- Inform the uninformed: Improving Online Informed Consent Reading with an AI-Powered Chatbot
- Analysis of Biomass Sustainability Indicators from a Machine Learning Perspective
- SpaceYOLO: A Human-Inspired Model for Real-time, On-board Spacecraft Feature Detection
- Recurrent Graph Convolutional Networks for Spatiotemporal Prediction of Snow Accumulation Using Airborne Radar
- Dynamic Atomic Column Detection in Transmission Electron Microscopy Videos via Ridge Estimation
- Stochastic Contextual Bandits with Long Horizon Rewards
- Goal Alignment: A Human-Aware Account of Value Alignment Problem
- ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints
- Deep neural operators can serve as accurate surrogates for shape optimization: A case study for airfoils
- Oracle-Preserving Latent Flows
- Conditioning Predictive Models: Risks and Strategies
- High-precision regressors for particle physics
- NDJIR: Neural Direct and Joint Inverse Rendering for Geometry, Lights, and Materials of Real Object