Papers
Wed 16 Nov 2022
195 papers
- Learning to Kindle the StarlightDiffusion models → Inverse problems and image restoration
- ToolFlowNet: Robotic Manipulation with Tools via Predicting Tool Flow from Point CloudsOffline RL and imitation learning from data → Robot manipulation imitation learning
- Fast Graph Generation via Spectral DiffusionDiffusion models → Flow matching, time series and science
- Analysis and Detectability of Offline Data Poisoning Attacks on Linear Dynamical SystemsLLM safety and security → Backdoor and data poisoning attacks
- PBSM: Backdoor attack against Keyword spotting based on pitch boosting and sound maskingLLM safety and security → Audio jailbreaks and speech backdoors
- LEMMA: Bootstrapping High-Level Mathematical Reasoning with Learned Symbolic AbstractionsLLM reasoning → Mathematical reasoning
- GLFF: Global and Local Feature Fusion for AI-synthesized Image DetectionDiffusion models → Image generation, text-to-image and editing
- CDialog: A Multi-turn Covid-19 Conversation Dataset for Entity-Aware Dialog Generation
- A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks
- The Infinity of Randomness
- Super-resolution Reconstruction of Single Image for Latent features
- Dwelling Type Classification for Disaster Risk Assessment Using Satellite Imagery
- A Neural Active Inference Model of Perceptual-Motor Learning
- Arbitrarily Accurate Classification Applied to Specific Emitter Identification
- Data efficient surrogate modeling for engineering design: Ensemble-free batch mode deep active learning for regression
- Few-shot Learning for Multi-modal Social Media Event Filtering
- Dueling Bandits: From Two-dueling to Multi-dueling
- Data-driven Real-time Short-term Prediction of Air Quality: Comparison of ES, ARIMA, and LSTM
- Hierarchical Estimation for Effective and Efficient Sampling Graph Neural Network
- GAMMT: Generative Ambiguity Modeling Using Multiple Transformers
- T-SEA: Transfer-based Self-Ensemble Attack on Object Detection
- Boosting Object Representation Learning via Motion and Object Continuity
- Features for the 0-1 knapsack problem based on inclusionwise maximal solutions
- Reflect, Not Reflex: Inference-Based Common Ground Improves Dialogue Response Quality
- Informative Initialization and Kernel Selection Improves t-SNE for Biological Sequences
- Task-aware Retrieval with Instructions
- The Missing Indicator Method: From Low to High Dimensions
- Beurling-Selberg Extremization for Dual-Blind Deconvolution Recovery in Joint Radar-Communications
- On the Power of Learning-Augmented Search Trees
- Stimulation of soy seeds using environmentally friendly magnetic and electric fields
- Learning unfolded networks with a cyclic group structure
- Artificial Disfluency Detection, Uh No, Disfluency Generation for the Masses
- Prompt Tuning for Parameter-efficient Medical Image Segmentation
- The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry
- Are we certain it's anomalous?
- The non-overlapping statistical approximation to overlapping group lasso
- edBB-Demo: Biometrics and Behavior Analysis for Online Educational Platforms
- A Graph-Based Context-Aware Model to Understand Online Conversations
- Sobolev Spaces, Kernels and Discrepancies over Hyperspheres
- An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks
- CASPR: Customer Activity Sequence-based Prediction and Representation
- Deep Emotion Recognition in Textual Conversations: A Survey
- Engineering Monosemanticity in Toy Models
- Unified Question Answering in Slovene
- Learnable Graph Convolutional Network and Feature Fusion for Multi-view Learning
- A Unified Multimodal De- and Re-coupling Framework for RGB-D Motion Recognition
- Characterizing 4-string contact interaction using machine learning
- A Review of Intelligent Music Generation Systems
- AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders
- Token Turing Machines
- MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis
- On Measuring the Intrinsic Few-Shot Hardness of Datasets
- Holistic Evaluation of Language Models
- Robust Online Video Instance Segmentation with Track Queries
- Interpretable Few-shot Learning with Online Attribute Selection
- Prompting PaLM for Translation: Assessing Strategies and Performance
- Comparative Learning: A Sample Complexity Theory for Two Hypothesis Classes
- Global Optimization with Parametric Function Approximation
- ATEAM: Knowledge Integration from Federated Datasets for Vehicle Feature Extraction using Annotation Team of Experts
- Testing geometric representation hypotheses from simulated place cell recordings
- Experimental Analysis of Machine Learning Techniques for Finding Search Radius in Locality Sensitive Hashing
- Molecular Fingerprints for Robust and Efficient ML-Driven Molecular Generation
- Galactica: A Large Language Model for Science
- Technical Report on Neural Language Models and Few-Shot Learning for Systematic Requirements Processing in MDSE
- Learning Dense and Continuous Optical Flow from an Event Camera
- Where a Strong Backbone Meets Strong Features -- ActionFormer for Ego4D Moment Queries Challenge
- Mitigating Frequency Bias in Next-Basket Recommendation via Deconfounders
- Towards Computationally Verifiable Semantic Grounding for Language Models
- Ischemic Stroke Lesion Prediction using imbalanced Temporal Deep Gaussian Process (iTDGP)
- Egocentric Hand-object Interaction Detection
- Squeeze flow of micro-droplets: convolutional neural network with trainable and tunable refinement
- Anomaly Detection via Multi-Scale Contrasted Memory
- UniRel: Unified Representation and Interaction for Joint Relational Triple Extraction
- A Creative Industry Image Generation Dataset Based on Captions
- CL2R: Compatible Lifelong Learning Representations
- Label-Efficient Object Detection via Region Proposal Network Pre-Training
- Learning Reward Functions for Robotic Manipulation by Observing Humans
- Real Estate Attribute Prediction from Multiple Visual Modalities with Missing Data
- On the Accuracy of Hotelling-Type Tensor Deflation: A Random Tensor Analysis
- Multi-Timescale Modeling of Human Behavior
- Data-pooling Reinforcement Learning for Personalized Healthcare Intervention
- Dynamical Linear Bandits
- TSMind: Alibaba and Soochow University's Submission to the WMT22 Translation Suggestion Task
- Asynchronous Gradient Play in Zero-Sum Multi-agent Games
- New Frontiers in Graph Autoencoders: Joint Community Detection and Link Prediction
- Energy Reconstruction in Analysis of Cherenkov Telescopes Images in TAIGA Experiment Using Deep Learning Methods
- Vector-Valued Least-Squares Regression under Output Regularity Assumptions
- Weakly-supervised Fingerspelling Recognition in British Sign Language Videos
- Reasons for the Superiority of Stochastic Estimators over Deterministic Ones: Robustness, Consistency and Perceptual Quality
- Comparing Explanation Methods for Traditional Machine Learning Models Part 1: An Overview of Current Methods and Quantifying Their Disagreement
- Differentially Private Optimizers Can Learn Adversarially Robust Models
- Augmented Physics-Informed Neural Networks (APINNs): A gating network-based soft domain decomposition methodology
- Benchmarking Graph Neural Networks for FMRI analysis
- Dual Class-Aware Contrastive Federated Semi-Supervised Learning
- On the Connection of Generative Models and Discriminative Models for Anomaly Detection
- SelfOdom: Self-supervised Egomotion and Depth Learning via Bi-directional Coarse-to-Fine Scale Recovery
- Cross-Mode Knowledge Adaptation for Bike Sharing Demand Prediction using Domain-Adversarial Graph Neural Networks
- Convergence analysis of unsupervised Legendre-Galerkin neural networks for linear second-order elliptic PDEs
- AdaTriplet-RA: Domain Matching via Adaptive Triplet and Reinforced Attention for Unsupervised Domain Adaptation
- ELDA: Using Edges to Have an Edge on Semantic Segmentation Based UDA
All 195
- Stare at What You See: Masked Image Modeling without Reconstruction
- Identifying the Causes of Pyrocumulonimbus (PyroCb)
- Learning linear operators: Infinite-dimensional regression as a well-behaved non-compact inverse problem
- McNet: Fuse Multiple Cues for Multichannel Speech Enhancement
- Unsupervised Domain Adaptation Based on the Predictive Uncertainty of Models
- PrivacyProber: Assessment and Detection of Soft-Biometric Privacy-Enhancing Techniques
- ChartParser: Automatic Chart Parsing for Print-Impaired
- Creative divergent synthesis with generative models
- Attacking Object Detector Using A Universal Targeted Label-Switch Patch
- Challenges in creative generative models for music: a divergence maximization perspective
- Graph Filters for Signal Processing and Machine Learning on Graphs
- Consecutive Question Generation via Dynamic Multitask Learning
- L2 proficiency assessment using self-supervised speech representations
- Improving Speech Emotion Recognition with Unsupervised Speaking Style Transfer
- Fast and Accurate FSA System Using ELBERT: An Efficient and Lightweight BERT
- Semi-Supervised and Self-Supervised Collaborative Learning for Prostate 3D MR Image Segmentation
- RF-Annotate: Automatic RF-Supervised Image Annotation of Common Objects in Context
- A Generalized Framework for Video Instance Segmentation
- Neurodevelopmental Phenotype Prediction: A State-of-the-Art Deep Learning Model
- Cognitive Simplification Operations Improve Text Simplification
- SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking
- Interacting Hand-Object Pose Estimation via Dense Mutual Attention
- Giving Feedback on Interactive Student Programs with Meta-Exploration
- Adapting to noise distribution shifts in flow-based gravitational-wave inference
- Speeding Up Recommender Systems Using Association Rules
- Model Based Residual Policy Learning with Applications to Antenna Control
- Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representations
- Structural Segmentation and Labeling of Tabla Solo Performances
- CSCD-NS: a Chinese Spelling Check Dataset for Native Speakers
- Uncertainty-Aware Multi-Parametric Magnetic Resonance Image Information Fusion for 3D Object Segmentation
- An Efficient COarse-to-fiNE Alignment Framework @ Ego4D Natural Language Queries Challenge 2022
- Unbalanced Optimal Transport, from Theory to Numerics
- MIMT: Multi-Illuminant Color Constancy via Multi-Task Local Surface and Light Color Learning
- On the symmetries in the dynamics of wide two-layer neural networks
- RetroMAE v2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models
- Separable PINN: Mitigating the Curse of Dimensionality in Physics-Informed Neural Networks
- SVD-PINNs: Transfer Learning of Physics-Informed Neural Networks via Singular Value Decomposition
- Advanced Situational Graphs for Robot Navigation in Structured Indoor Environments
- Indoor Positioning via Gradient Boosting Enhanced with Feature Augmentation using Deep Learning
- Yield Evaluation of Citrus Fruits based on the YoloV5 compressed by Knowledge Distillation
- Auditing Algorithmic Fairness in Machine Learning for Health with Severity-Based LOGAN
- Minimum information divergence of Q-functions for dynamic treatment resumes
- Near-Term Quantum Computing Techniques: Variational Quantum Algorithms, Error Mitigation, Circuit Compilation, Benchmarking and Classical Simulation
- AlignVE: Visual Entailment Recognition Based on Alignment Relations
- Can Strategic Data Collection Improve the Performance of Poverty Prediction Models?
- Lesion Guided Explainable Few Weak-shot Medical Report Generation
- Exploring State Change Capture of Heterogeneous Backbones @ Ego4D Hands and Objects Challenge 2022
- Streaming Joint Speech Recognition and Disfluency Detection
- PAANet:Visual Perception based Four-stage Framework for Salient Object Detection using High-order Contrast Operator
- Noisy Pairing and Partial Supervision for Stylized Opinion Summarization
- Learning with Noisy Labels over Imbalanced Subpopulations
- SWIN-SFTNet : Spatial Feature Expansion and Aggregation using Swin Transformer For Whole Breast micro-mass segmentation
- Conditional variational autoencoder to improve neural audio synthesis for polyphonic music sound
- Reward Gaming in Conditional Text Generation
- Improving Feature-based Visual Localization by Geometry-Aided Matching
- Efficiently Finding Adversarial Examples with DNN Preprocessing
- Resource Allocation of Federated Learning for the Metaverse with Mobile Augmented Reality
- A Simple Transformer-Based Model for Ego4D Natural Language Queries Challenge
- SATVSR: Scenario Adaptive Transformer for Cross Scenarios Video Super-Resolution
- PointInverter: Point Cloud Reconstruction and Editing via a Generative Model with Shape Priors
- Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction
- Towards Long-Tailed 3D Detection
- Improving Interpretability via Regularization of Neural Activation Sensitivity
- Automated Analysis of Drawing Process for Detecting Prodromal and Clinical Dementia
- Neural Unsupervised Reconstruction of Protolanguage Word Forms
- Parameter-Efficient Tuning on Layer Normalization for Pre-trained Language Models
- Interclass Prototype Relation for Few-Shot Segmentation
- XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaverse
- Mitigating Urban-Rural Disparities in Contrastive Representation Learning with Satellite Imagery
- Addressing the issue of stochastic environments and local decision-making in multi-objective reinforcement learning
- Revisiting Training-free NAS Metrics: An Efficient Training-based Method
- SETAR-Tree: A Novel and Accurate Tree Algorithm for Global Time Series Forecasting
- Consistent Direct Time-of-Flight Video Depth Super-Resolution
- Person Text-Image Matching via Text-Feature Interpretability Embedding and External Attack Node Implantation
- Prediction and Uncertainty Quantification of SAFARI-1 Axial Neutron Flux Profiles with Neural Networks
- #maskUp: Selective Attribute Encryption for Sensitive Vocalization for English language on Social Media Platforms
- Using explainability to design physics-aware CNNs for solving subsurface inverse problems
- Deep Intention-Aware Network for Click-Through Rate Prediction
- Keep Your Friends Close & Enemies Farther: Debiasing Contrastive Learning with Spatial Priors in 3D Radiology Images
- Hierarchical Dynamic Image Harmonization
- Semantic keypoint extraction for scanned animals using multi-depth-camera systems
- MT Metrics Correlate with Human Ratings of Simultaneous Speech Translation
- Leveraging Heteroscedastic Uncertainty in Learning Complex Spectral Mapping for Single-channel Speech Enhancement
- Impact of Redundancy on Resilience in Distributed Optimization and Learning
- CoNFies: Controllable Neural Face Avatars
- R-Pred: Two-Stage Motion Prediction Via Tube-Query Attention-Based Trajectory Refinement
- LightDepth: A Resource Efficient Depth Estimation Approach for Dealing with Ground Truth Sparsity via Curriculum Learning
- PU GNN: Chargeback Fraud Detection in P2E MMORPGs via Graph Attention Networks with Imbalanced PU Labels
- Asynchronous Bayesian Learning over a Network
- SketchySGD: Reliable Stochastic Optimization via Randomized Curvature Estimates
- Orthogonal Polynomials Approximation Algorithm (OPAA):a functional analytic approach to estimating probability densities
- Exploring Supervised Machine Learning for Multi-Phase Identification and Quantification from Powder X-Ray Diffraction Spectra
- Disentangling Task Relations for Few-shot Text Classification via Self-Supervised Hierarchical Task Clustering
- Bandit Algorithms for Prophet Inequality and Pandora's Box
- Cyclic Generative Adversarial Networks With Congruent Image-Report Generation For Explainable Medical Image Analysis