Papers
Thu 10 Feb 2022
168 papers
- Factored World Models for Zero-Shot Generalization in Robotic ManipulationWorld models → Embodied and robot world models
- Conditional Diffusion Probabilistic Model for Speech EnhancementDiffusion models → Audio, speech and music
- Memory-based gaze prediction in deep imitation learning for robot manipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
- Settling the Communication Complexity for Distributed Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- The Abduction of Sherlock Holmes: A Dataset for Visual Abductive ReasoningLLM reasoning → Multimodal reasoning
- Particle Swarm Optimization based on Novelty Search
- Using Navigational Information to Learn Visual Representations
- Development and Comparison of Scoring Functions in Curriculum Learning
- Information Flow in Deep Neural Networks
- Learning Branch Probabilities in Compiler from Datacenter Workloads
- STG-GAN: A spatiotemporal graph generative adversarial networks for short-term passenger flow prediction in urban rail transit systems
- Abstraction for Deep Reinforcement Learning
- Applications of Machine Learning to Lattice Quantum Field Theory
- Explainable Machine Learning for Breakdown Prediction in High Gradient RF Cavities
- The MeLa BitChute Dataset
- DDoS-UNet: Incorporating temporal information using Dynamic Dual-channel UNet for enhancing super-resolution of dynamic MRI
- Optimal Transport for Super Resolution Applied to Astronomy Imaging
- Domain Adversarial Training: A Game Perspective
- Development and Validation of an AI-Driven Model for the La Rance Tidal Barrage: A Generalisable Case Study
- Towards Disentangling Information Paths with Coded ResNeXt
- Closure operators: Complexity and applications to classification and decision-making
- Accountability in an Algorithmic Society: Relationality, Responsibility, and Robustness in Machine Learning
- Dynamic Background Subtraction by Generative Neural Networks
- Learning the Pedestrian-Vehicle Interaction for Pedestrian Trajectory Prediction
- Describing image focused in cognitive and visual details for visually impaired people: An approach to generating inclusive paragraphs
- Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning
- Integrating Testing and Operation-related Quantitative Evidences in Assurance Cases to Argue Safety of Data-Driven AI/ML Components
- Mining the manifolds of deep generative models for multiple data-consistent solutions of ill-posed tomographic imaging problems
- Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks
- Trust in AI: Interpretability is not necessary or sufficient, while black-box interaction is necessary and sufficient
- Face Beneath the Ink: Synthetic Data and Tattoo Removal with Application to Face Recognition
- Universal Learning Waveform Selection Strategies for Adaptive Target Tracking
- On One-Bit Quantization
- Translation and Rotation Equivariant Normalizing Flow (TRENF) for Optimal Cosmological Analysis
- Motion Puzzle: Arbitrary Motion Style Transfer by Body Part
- Towards a Guideline for Evaluation Metrics in Medical Image Segmentation
- A Field of Experts Prior for Adapting Neural Networks at Test Time
- A Deep Learning Approach for Digital Color Reconstruction of Lenticular Films
- A Plug-and-Play Approach to Multiparametric Quantitative MRI: Image Reconstruction using Pre-Trained Deep Denoisers
- HNF-Netv2 for Brain Tumor Segmentation using multi-modal MR Imaging
- On Real-time Image Reconstruction with Neural Networks for MRI-guided Radiotherapy
- Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging
- Block-NeRF: Scalable Large Scene Neural View Synthesis
- Locating and Editing Factual Associations in GPT
- Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks
- Characterizing, Detecting, and Predicting Online Ban Evasion
- Topogivity: A Machine-Learned Chemical Rule for Discovering Topological Materials
- Deep Learning in Random Neural Fields: Numerical Experiments via Neural Tangent Kernel
- Adaptive and Robust Multi-Task Learning
- Monotone Learning
- Benign-Overfitting in Conditional Average Treatment Effect Prediction with Linear Regression
- REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer
- ChemicalX: A Deep Learning Library for Drug Pair Scoring
- F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization
- Learnable Nonlinear Compression for Robust Speaker Verification
- Deadwooding: Robust Global Pruning for Deep Neural Networks
- Towards a Theory of Non-Log-Concave Sampling: First-Order Stationarity Guarantees for Langevin Monte Carlo
- Improving Automatic Speech Recognition for Non-Native English with Transfer Learning and Language Model Decoding
- Vehicle: Interfacing Neural Network Verifiers with Interactive Theorem Provers
- Zero Shot Learning for Predicting Energy Usage of Buildings in Sustainable Design
- Towards Predicting Fine Finger Motions from Ultrasound Images via Kinematic Representation
- Visual Servoing for Pose Control of Soft Continuum Arm in a Structured Environment
- A Human-Centered Machine-Learning Approach for Muscle-Tendon Junction Tracking in Ultrasound Images
- P-split formulations: A class of intermediate formulations between big-M and convex hull for disjunctive constraints
- Uncovering Instabilities in Variational-Quantum Deep Q-Networks
- Suboptimal Performance of the Bayes Optimal Algorithm in Frequentist Best Arm Identification
- Understanding Rare Spurious Correlations in Neural Networks
- Adults as Augmentations for Children in Facial Emotion Recognition with Contrastive Learning
- Discovering Quantum Phase Transitions with Fermionic Neural Networks
- Remote Contextual Bandits
- Feature-level augmentation to improve robustness of deep neural networks to affine transformations
- Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMET
- InPars: Data Augmentation for Information Retrieval using Large Language Models
- Transferable and Adaptable Driving Behavior Prediction
- Game of Privacy: Towards Better Federated Platform Collaboration under Privacy Restriction
- Quantization in Layer's Input is Matter
- Group-Agent Reinforcement Learning
- Help Me Explore: Minimal Social Interventions for Graph-Based Autotelic Agents
- Deep Learning for Computational Cytology: A Survey
- Unaligned but Safe -- Formally Compensating Performance Limitations for Imprecise 2D Object Detection
- Low-Rank Approximation with 1/ε1/3 Matrix-Vector Products
- Reinforcement Learning in the Wild: Scalable RL Dispatching Algorithm Deployed in Ridehailing Marketplace
- Probabilistic learning inference of boundary value problem with uncertainties based on Kullback-Leibler divergence under implicit constraints
- Adaptively Exploiting d-Separators with Causal Bandits
- AD-NEGF: An End-to-End Differentiable Quantum Transport Simulator for Sensitivity Analysis and Inverse Problems
- Near-Optimal Statistical Query Lower Bounds for Agnostically Learning Intersections of Halfspaces with Gaussian Marginals
- Two-Stage Deep Anomaly Detection with Heterogeneous Time Series Data
- Backpropagation Clipping for Deep Learning with Differential Privacy
- Complexity of Arithmetic in Warded Datalog+-
- Cross-speaker style transfer for text-to-speech using data augmentation
- Transfer-Learning Across Datasets with Different Input Dimensions: An Algorithm and Analysis for the Linear Regression Case
- Controlling the Complexity and Lipschitz Constant improves polynomial nets
- Natural Language in Requirements Engineering for Structure Inference -- An Integrative Review
- PCENet: High Dimensional Surrogate Modeling for Learning Uncertainty
- Equivariance Regularization for Image Reconstruction
- Exploiting Spatial Sparsity for Event Cameras with Visual Transformers
- Fair When Trained, Unfair When Deployed: Observable Fairness Measures are Unstable in Performative Prediction Settings
- Quantune: Post-training Quantization of Convolutional Neural Networks using Extreme Gradient Boosting for Fast Deployment
- On characterizations of learnability with computable learners
- Bias-Scalable Near-Memory CMOS Analog Processor for Machine Learning
All 168
- SUPA: A Lightweight Diagnostic Simulator for Machine Learning in Particle Physics
- N"UWA-LIP: Language Guided Image Inpainting with Defect-free VQGAN
- AA-TransUNet: Attention Augmented TransUNet For Nowcasting Tasks
- Slovene SuperGLUE Benchmark: Translation and Evaluation
- Mixture-of-Rookies: Saving DNN Computations by Predicting ReLU Outputs
- Semi-Supervised Convolutive NMF for Automatic Piano Transcription
- Generalization Bounds via Convex Analysis
- Barwise Compression Schemes for Audio-Based Music Structure Analysis
- Towards Assessing and Characterizing the Semantic Robustness of Face Recognition
- Needs-aware Artificial Intelligence: AI that 'serves [human] needs'
- Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory
- Real-Time Siamese Multiple Object Tracker with Enhanced Proposals
- Forecasting large-scale circulation regimes using deformable convolutional neural networks and global spatiotemporal climate data
- Feasible Low-thrust Trajectory Identification via a Deep Neural Network Classifier
- Monotonically Convergent Regularization by Denoising
- Loss-guided Stability Selection
- D2A-BSP: Distilled Data Association Belief Space Planning with Performance Guarantees Under Budget Constraints
- OWL (Observe, Watch, Listen): Audiovisual Temporal Context for Localizing Actions in Egocentric Videos
- Interpretable pipelines with evolutionarily optimized modules for RL tasks with visual inputs
- Spherical Transformer
- Robust Graph Representation Learning for Local Corruption Recovery
- Energy-Based Contrastive Learning of Visual Representations
- Decomposing neural networks as mappings of correlation functions
- Collaborative Filtering with Attribution Alignment for Review-based Non-overlapped Cross Domain Recommendation
- Random Forest Weighted Local Fr'echet Regression with Random Objects
- Instance-wise algorithm configuration with graph neural networks
- Investigating Explainability of Generative AI for Code through Scenario-based Design
- FILM: Frame Interpolation for Large Motion
- InterHT: Knowledge Graph Embeddings by Interaction between Head and Tail Entities
- Diffusion bridges vector quantized Variational AutoEncoders
- Differential Private Knowledge Transfer for Privacy-Preserving Cross-Domain Recommendation
- Case-based reasoning for rare events prediction on strategic sites
- Improving performance of aircraft detection in satellite imagery while limiting the labelling effort: Hybrid active learning
- TaxoEnrich: Self-Supervised Taxonomy Completion via Structure-Semantic Representations
- Towards the automated large-scale reconstruction of past road networks from historical maps
- PVSeRF: Joint Pixel-, Voxel- and Surface-Aligned Radiance Field for Single-Image Novel View Synthesis
- Distilling Hypernymy Relations from Language Models: On the Effectiveness of Zero-Shot Taxonomy Induction
- Online Learning for Min Sum Set Cover and Pandora's Box
- Understanding Value Decomposition Algorithms in Deep Cooperative Multi-Agent Reinforcement Learning
- Consistency and Diversity induced Human Motion Segmentation
- PPA: Preference Profiling Attack Against Federated Learning
- The USTC-Ximalaya system for the ICASSP 2022 multi-channel multi-party meeting transcription (M2MeT) challenge
- SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisition
- A Survey on Artificial Intelligence for Source Code: A Dialogue Systems Perspective
- Multi-relation Message Passing for Multi-label Text Classification
- Networks and Identity Drive Geographic Properties of the Diffusion of Linguistic Innovation
- Heterogeneous Calibration: A post-hoc model-agnostic framework for improved generalization
- Deconstructing the Inductive Biases of Hamiltonian Neural Networks
- Geometric Digital Twinning of Industrial Facilities: Retrieval of Industrial Shapes
- Bayesian Optimisation for Mixed-Variable Inputs using Value Proposals
- Target-aware Molecular Graph Generation
- Learning Latent Causal Dynamics
- Bias-Eliminated Semantic Refinement for Any-Shot Learning
- AdaPrompt: Adaptive Model Training for Prompt-based NLP
- Decreasing Annotation Burden of Pairwise Comparisons with Human-in-the-Loop Sorting: Application in Medical Image Artifact Rating
- Survey on Graph Neural Network Acceleration: An Algorithmic Perspective
- Measuring disentangled generative spatio-temporal representation
- L0Learn: A Scalable Package for Sparse Learning using L0 Regularization
- Royalflush Speaker Diarization System for ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge
- Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling
- Understanding Hyperdimensional Computing for Parallel Single-Pass Learning
- The leap to ordinal: detailed functional prognosis after traumatic brain injury with a flexible modelling approach
- Augmenting Neural Networks with Priors on Function Values
- Proceedings of the Robust Artificial Intelligence System Assurance (RAISA) Workshop 2022
- No-Regret Learning in Dynamic Stackelberg Games
- Multiclass histogram-based thresholding using kernel density estimation and scale-space representations
- Adversarial Attack and Defense of YOLO Detectors in Autonomous Driving Scenarios
- Exact Solutions of a Deep Linear Network