Papers
Wed 22 Jun 2022
177 papers
- Curious Exploration via Structured World Models Yields Zero-Shot Object ManipulationWorld models → Latent dynamics models and model-based RL
- Latent Policies for Adversarial Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- Behavior Transformers: Cloning k modes with one stoneOffline RL and imitation learning from data → Robot manipulation imitation learning
- VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason ObjectivesLLM reasoning → Multimodal reasoning
- Conformer with dual-mode chunked attention for joint online and offline ASRKnowledge distillation → Speech and audio distillation
- Variational Causal Dynamics: Discovering Modular World Models from InterventionsWorld models → World models for language agents
- Auto-Encoding Adversarial Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- A Study on the Evaluation of Generative ModelsDiffusion models → Diffusion foundations and sampling
- Guided Diffusion Model for Adversarial Purification from Random NoiseDiffusion models → Robustness, privacy and adversarial aspects
- Imitation Learning for Generalizable Self-driving Policy with Sim-to-real TransferEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
- A Fast Text-Driven Approach for Generating Artistic Content
- Towards Systems Education for Artificial Intelligence: A Course Practice in Intelligent Computing Architectures
- Brain tumor detection using artificial convolutional neural networks
- A Comprehensive Survey on the Cyber-Security of Smart Grids: Cyber-Attacks, Detection, Countermeasure Techniques, and Future Directions
- Localisation And Imaging Methods for Moving Target Ghost Imaging Radar Based On Correlation Intensity Weighting
- Adaptive Attitude Estimation Using a Hybrid Model-Learning Approach
- Deep Learning to Jointly Schema Match, Impute, and Transform Databases
- Efficient fine-grained road segmentation using superpixel-based CNN and CRF models
- Consistency of Neural Networks with Regularization
- Can Population-based Engagement Improve Personalisation? A Novel Dataset and Experiments
- Mitigating Presentation Attack using DCGAN and Deep CNN
- Multi-Agent Car Parking using Reinforcement Learning
- A Simple Baseline for Domain Adaptation in End to End ASR Systems Using Synthetic Data
- Independent evaluation of state-of-the-art deep networks for mammography
- Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Lojasiewicz Functions when the Non-Convexity is Averaged-Out
- On a class of geodesically convex optimization problems solved via Euclidean MM methods
- Functional Nonlinear Learning
- Input-agnostic Certified Group Fairness via Gaussian Parameter Smoothing
- On Specifying for Trustworthiness
- PAC: Assisted Value Factorisation with Counterfactual Predictions in Multi-Agent Reinforcement Learning
- FINGER: Fast Inference for Graph-based Approximate Nearest Neighbor Search
- The ArtBench Dataset: Benchmarking Generative Models with Artworks
- Program Targeting with Machine Learning and Mobile Phone Data: Evidence from an Anti-Poverty Intervention in Afghanistan
- Multi-Horizon Representations with Hierarchical Forward Models for Reinforcement Learning
- Bi-stochastically normalized graph Laplacian: convergence to manifold Laplacian and robustness to outlier noise
- Real-Time Online Skeleton Extraction and Gesture Recognition on Pepper
- Monocular Spherical Depth Estimation with Explicitly Connected Weak Layout Cues
- GACT: Activation Compressed Training for Generic Network Architectures
- Doubly Reparameterized Importance Weighted Structure Learning for Scene Graph Generation
- Constrained Stochastic Nonconvex Optimization with State-dependent Markov Data
- Bayesian model calibration for block copolymer self-assembly: Likelihood-free inference and expected information gain computation via measure transport
- Synthetic Data-Based Simulators for Recommender Systems: A Survey
- DP-Parse: Finding Word Boundaries from Raw Speech with an Instance Lexicon
- Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer
- Regression Trees on Grassmann Manifold for Adapting Reduced-Order Models
- Graph-Based Multi-Robot Path Finding and Planning
- GODEL: Large-Scale Pre-Training for Goal-Directed Dialog
- Community Recovery in the Geometric Block Model
- Recommendations for Systematic Research on Emergent Language
- Neural Implicit Manifold Learning for Topology-Aware Density Estimation
- Optimally Weighted Ensembles of Regression Models: Exact Weight Optimization and Applications
- Few-shot Long-Tailed Bird Audio Recognition
- Langevin Monte Carlo for Contextual Bandits
- Towards Robust Blind Face Restoration with Codebook Lookup Transformer
- Leveraging RGB-D Data with Cross-Modal Context Mining for Glass Surface Detection
- GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
- Concentration inequalities and optimal number of layers for stochastic deep neural networks
- FedorAS: Federated Architecture Search under system heterogeneity
- Understanding the Properties of Generated Corpora
- Hierarchical Context Tagging for Utterance Rewriting
- Certifiable 3D Object Pose Estimation: Foundations, Learning Models, and Self-Training
- Constant-Factor Approximation Algorithms for Socially Fair k-Clustering
- Facke: a Survey on Generative Models for Face Swapping
- General Univariate Estimation-of-Distribution Algorithms
- Learning Optimal Treatment Strategies for Sepsis Using Offline Reinforcement Learning in Continuous Space
- Automated Compliance Blueprint Optimization with Artificial Intelligence
- Towards Unsupervised Content Disentanglement in Sentence Representations via Syntactic Roles
- Active Learning with Safety Constraints
- Vulnerability Prioritization: An Offensive Security Approach
- On the Role of Spatial, Spectral, and Temporal Processing for DNN-based Non-linear Multi-channel Speech Enhancement
- Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation
- Cold Posteriors through PAC-Bayes
- Neural Inverse Transform Sampler
- Attack Techniques and Threat Identification for Vulnerabilities
- Ordered Subgraph Aggregation Networks
- Sharing pattern submodels for prediction with missing values
- The Problem of Semantic Shift in Longitudinal Monitoring of Social Media: A Case Study on Mental Health During the COVID-19 Pandemic
- Then and Now: Quantifying the Longitudinal Validity of Self-Disclosed Depression Diagnoses
- reStructured Pre-training
- Modeling Emergent Lexicon Formation with a Self-Reinforcing Stochastic Process
- Discussion of `Multiscale Fisher's Independence Test for Multivariate Dependence'
- Hybrid Physical Metric For 6-DoF Grasp Pose Detection
- Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries
- Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization
- Multi-View Clustering for Open Knowledge Base Canonicalization
- tntorch: Tensor Network Learning with PyTorch
- CNN-based fully automatic wrist cartilage volume quantification in MR Image
- Explanation-based Counterfactual Retraining(XCR): A Calibration Method for Black-box Models
- A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta
- Near-optimal control of dynamical systems with neural ordinary differential equations
- ICC++: Explainable Image Retrieval for Art Historical Corpora using Image Composition Canvas
- Evolutionary Game-Theoretical Analysis for General Multiplayer Asymmetric Games
- Beyond RMSE: Do machine-learned models of road user interaction produce human-like behavior?
- OpenXAI: Towards a Transparent Evaluation of Model Explanations
- A High Resolution Multi-exposure Stereoscopic Image & Video Database of Natural Scenes
- Descent Steps of a Relation-Aware Energy Produce Heterogeneous Graph Neural Networks
- Motion Gait: Gait Recognition via Motion Excitation
- Noisy ℓ0-Sparse Subspace Clustering on Dimensionality Reduced Data
- AlphaMLDigger: A Novel Machine Learning Solution to Explore Excess Return on Investment
- Answer Fast: Accelerating BERT on the Tensor Streaming Processor
All 177
- Surgical-VQA: Visual Question Answering in Surgical Scenes using Transformer
- Dynamic Restrained Uncertainty Weighting Loss for Multitask Learning of Vocal Expression
- Automated GI tract segmentation using deep learning
- KeyCLD: Learning Constrained Lagrangian Dynamics in Keypoint Coordinates from Images
- ROSE: A RObust and SEcure DNN Watermarking
- Heterogeneous Graph Neural Networks for Software Effort Estimation
- Connecting a French Dictionary from the Beginning of the 20th Century to Wikidata
- Object Type Clustering using Markov Directly-Follow Multigraph in Object-Centric Process Mining
- Weakly-Supervised Temporal Action Localization by Progressive Complementary Learning
- Agent-based Graph Neural Networks
- A Systematic Comparison of Phonetic Aware Techniques for Speech Enhancement
- Neural Networks as Paths through the Space of Representations
- ProtoCLIP: Prototypical Contrastive Language Image Pretraining
- Understanding convolution on graphs via energies
- Identity Documents Authentication based on Forgery Detection of Guilloche Pattern
- AdvSmo: Black-box Adversarial Attack by Smoothing Linear Structure of Texture
- Human-AI communication for human-human communication: Applying interpretable unsupervised anomaly detection to executive coaching
- Traffic Congestion Prediction Using Machine Learning Techniques
- Diagnostic Tool for Out-of-Sample Model Evaluation
- Multi-task twin support vector machine with Universum data
- Single Morphing Attack Detection using Siamese Network and Few-shot Learning
- Polar Parametrization for Vision-based Surround-View 3D Detection
- Defect Prediction Using Stylistic Metrics
- Toward An Optimal Selection of Dialogue Strategies: A Target-Driven Approach for Intelligent Outbound Robots
- POGEMA: Partially Observable Grid Environment for Multiple Agents
- List-Decodable Covariance Estimation
- Evaluation of Embedding Models for Automatic Extraction and Classification of Acknowledged Entities in Scientific Documents
- Information Geometry of Dropout Training
- SoccerCPD: Formation and Role Change-Point Detection in Soccer Matches Using Spatiotemporal Tracking Data
- Enhancing Networking Cipher Algorithms with Natural Language
- FairGrad: Fairness Aware Gradient Descent
- Recognising Affordances in Predicted Futures to Plan with Consideration of Non-canonical Affordance Effects
- Comparing Formulaic Language in Human and Machine Translation: Insight from a Parliamentary Corpus
- Understanding the effect of sparsity on neural networks robustness
- Template-based Approach to Zero-shot Intent Recognition
- AI-based software for lung nodule detection in chest X-rays -- Time for a second reader approach?
- Influence of uncertainty estimation techniques on false-positive reduction in liver lesion detection
- SpA-Former: Transformer image shadow detection and removal via spatial attention
- UniUD-FBK-UB-UniBZ Submission to the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge 2022
- S2TNet: Spatio-Temporal Transformer Networks for Trajectory Prediction in Autonomous Driving
- How to Combine Variational Bayesian Networks in Federated Learning
- I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimation
- Optical Flow Regularization of Implicit Neural Representations for Video Frame Interpolation
- KiloNeuS: A Versatile Neural Implicit Surface Representation for Real-Time Rendering
- Multi-LexSum: Real-World Summaries of Civil Rights Lawsuits at Multiple Granularities
- Symmetric Network with Spatial Relationship Modeling for Natural Language-based Vehicle Retrieval
- Feature Re-calibration based Multiple Instance Learning for Whole Slide Image Classification
- Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks
- NVIDIA-UNIBZ Submission for EPIC-KITCHENS-100 Action Anticipation Challenge 2022
- UniCon+: ICTCAS-UCAS Submission to the AVA-ActiveSpeaker Task at ActivityNet Challenge 2022
- Bregman Power k-Means for Clustering Exponential Family Data
- Robust Universal Adversarial Perturbations
- Play It Cool: Dynamic Shifting Prevents Thermal Throttling
- DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation
- Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI
- Parallel Pre-trained Transformers (PPT) for Synthetic Data-based Instance Segmentation
- Quantization Robust Federated Learning for Efficient Inference on Heterogeneous Devices
- Learning Debiased Classifier with Biased Committee
- Learning Distribution Grid Topologies: A Tutorial
- Robust Bayesian Recourse
- MultiEarth 2022 Deforestation Challenge -- ForestGump
- A Feature Memory Rearrangement Network for Visual Inspection of Textured Surface Defects Toward Edge Intelligent Manufacturing
- Efficient Interdependent Systems Recovery Modeling with DeepONets
- Coupling Visual Semantics of Artificial Neural Networks and Human Brain Function via Synchronized Activations
- Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming
- FedBC: Calibrating Global and Local Models via Federated Learning Beyond Consensus
- A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift
- SSMI: How to Make Objects of Interest Disappear without Accessing Object Detectors?
- Jointist: Joint Learning for Multi-instrument Transcription and Its Applications
- SVoRT: Iterative Transformer for Slice-to-Volume Registration in Fetal Brain MRI
- Automated Cancer Subtyping via Vector Quantization Mutual Information Maximization
- Multi-Resolution, Multi-Horizon Distributed Solar PV Power Forecasting with Forecast Combinations
- Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
- Generative Pretraining for Black-Box Optimization
- Federated Latent Class Regression for Hierarchical Data
- Efficient and effective training of language and graph neural network models
- Not Just Streaks: Towards Ground Truth for Single Image Deraining