Papers
Tue 1 Mar 2022
168 papers
- DreamingV2: Reinforcement Learning with Discrete World Models without ReconstructionWorld models → Latent dynamics models and model-based RL
- MERIt: Meta-Path Guided Contrastive Learning for Logical ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- Interactive Human-in-the-loop Coordination of Manipulation Skills Learned from DemonstrationOffline RL and imitation learning from data → Robot learning from demonstration
- Semantic Sentence Composition Reasoning for Multi-Hop Question AnsweringLLM reasoning → Knowledge- and tool-augmented reasoning
- Exploring Descriptions of Movement Through Geovisual Analytics
- Multilingual Abusiveness Identification on Code-Mixed Social Media Text
- Bayesian Sequential Stacking Algorithm for Concurrently Designing Molecules and Synthetic Reaction Networks
- Compliance Checking with NLI: Privacy Policies vs. Regulations
- Explicitising The Implicit Intrepretability of Deep Neural Networks Via Duality
- AI Gone Astray: Technical Supplement
- System Cards for AI-Based Decision-Making for Public Policy
- Embedding Temporal Convolutional Networks for Energy-Efficient PPG-Based Heart Rate Monitoring
- Cognitive Diagnosis with Explicit Student Vector Estimation and Unsupervised Question Matrix Learning
- A Brief Overview of Unsupervised Neural Speech Representation Learning
- Improving Non-native Word-level Pronunciation Scoring with Phone-level Mixup Data Augmentation and Multi-source Information
- An Effective Graph Learning based Approach for Temporal Link Prediction: The First Place of WSDM Cup 2022
- Effect of Timing Error: A Case Study of Navigation Camera
- Colon Nuclei Instance Segmentation using a Probabilistic Two-Stage Detector
- Deep Temporal Interpolation of Radar-based Precipitation
- A Primal-Dual Approach to Bilevel Optimization with Multiple Inner Minima
- VaiPhy: a Variational Inference Based Algorithm for Phylogeny
- TANDEM: Learning Joint Exploration and Decision Making with Tactile Sensors
- Two-Level Supervised Contrastive Learning for Response Selection in Multi-Turn Dialogue
- Unified Physical Threat Monitoring System Aided by Virtual Building Simulation
- Image analysis for automatic measurement of crustose lichens
- Bayesian adaptive and interpretable functional regression for exposure profiles
- Low-Cost On-device Partial Domain Adaptation (LoCO-PDA): Enabling efficient CNN retraining on edge devices
- Multi-Sentence Knowledge Selection in Open-Domain Dialogue
- Topic Analysis for Text with Side Data
- Tricks and Plugins to GBM on Images and Sequences
- HyperPrompt: Prompt-based Task-Conditioning of Transformers
- There is a Time and Place for Reasoning Beyond the Image
- E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models
- Runtime Detection of Executional Errors in Robot-Assisted Surgery
- 3D Skeleton-based Human Motion Prediction with Manifold-Aware GAN
- Knock, knock. Who's there? -- Identifying football player jersey numbers with synthetic data
- Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shots
- A Conformer Based Acoustic Model for Robust Automatic Speech Recognition
- Learning Robust Real-Time Cultural Transmission without Human Data
- Determining Research Priorities for Astronomy Using Machine Learning
- CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding
- Advancing an Interdisciplinary Science of Conversation: Insights from a Large Multimodal Corpus of Human Speech
- Generalizable Person Re-Identification via Self-Supervised Batch Norm Test-Time Adaption
- Hierarchical Reinforcement Learning with AI Planning Models
- Generative Adversarial Networks
- ONBRA: Rigorous Estimation of the Temporal Betweenness Centrality in Temporal Networks
- Measuring the Impact of Individual Domain Factors in Self-Supervised Pre-Training
- Variational Autoencoders Without the Variation
- Multi-Task Multi-Scale Learning For Outcome Prediction in 3D PET Images
- PaSca: a Graph Neural Architecture Search System under the Scalable Paradigm
- Distributional Reinforcement Learning for Scheduling of Chemical Production Processes
- Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale
- Full RGB Just Noticeable Difference (JND) Modelling
- A Neural Ordinary Differential Equation Model for Visualizing Deep Neural Network Behaviors in Multi-Parametric MRI based Glioma Segmentation
- A unified 3D framework for Organs at Risk Localization and Segmentation for Radiation Therapy Planning
- Side Effects of Learning from Low-dimensional Data Embedded in a Euclidean Space
- Towards a Common Speech Analysis Engine
- Learning Intermediate Representations using Graph Neural Networks for NUMA and Prefetchers Optimization
- Beyond Ans"atze: Learning Quantum Circuits as Unitary Operators
- Dual Embodied-Symbolic Concept Representations for Deep Learning
- Path sampling of recurrent neural networks by incorporating known physics
- Parameter estimation for WMTI-Watson model of white matter using encoder-decoder recurrent neural network
- SwitchHit: A Probabilistic, Complementarity-Based Switching System for Improved Visual Place Recognition in Changing Environments
- Structural invariants and semantic fingerprints in the "ego network" of words
- Self-Supervised Vision Transformers Learn Visual Concepts in Histopathology
- Contrasting random and learned features in deep Bayesian linear regression
- Towards a unified view of unsupervised non-local methods for image denoising: the NL-Ridge approach
- Descriptellation: Deep Learned Constellation Descriptors
- Topological Data Analysis for Word Sense Disambiguation
- DeepNet: Scaling Transformers to 1,000 Layers
- Neural Score Matching for High-Dimensional Causal Inference
- Global-Local Regularization Via Distributional Robustness
- Bayesian Optimisation for Robust Model Predictive Control under Model Parameter Uncertainty
- Optimal quantum dataset for learning a unitary transformation
- DAMO-NLP at SemEval-2022 Task 11: A Knowledge-based System for Multilingual Named Entity Recognition
- On the Generalization of Representations in Reinforcement Learning
- Towards deep learning-powered IVF: A large public benchmark for morphokinetic parameter prediction
- On genetic programming representations and fitness functions for interpretable dimensionality reduction
- Multi-Objective Latent Space Optimization of Generative Molecular Design Models
- E-LMC: Extended Linear Model of Coregionalization for Spatial Field Prediction
- Towards Creativity Characterization of Generative Models via Group-based Subset Scanning
- A Transformational Characterization of Unconditionally Equivalent Bayesian Networks
- Particle-based Fast Jet Simulation at the LHC with Variational Autoencoders
- A predictive analytics approach for stroke prediction using machine learning and neural networks
- Attention-based Contextual Multi-View Graph Convolutional Networks for Short-term Population Prediction
- Beyond Gradients: Exploiting Adversarial Priors in Model Inversion Attacks
- Compliance Challenges in Forensic Image Analysis Under the Artificial Intelligence Act
- Belief propagation for supply networks: Efficient clustering of their factor graphs
- JOINED : Prior Guided Multi-task Learning for Joint Optic Disc/Cup Segmentation and Fovea Detection
- Bridge the Gap between Supervised and Unsupervised Learning for Fine-Grained Classification
- Boundary Corrected Multi-scale Fusion Network for Real-time Semantic Segmentation
- Towards Practices for Human-Centered Machine Learning
- Making use of supercomputers in financial machine learning
- Recovery of Missing Sensor Data by Reconstructing Time-varying Graph Signals
- Beam-Shape Effects and Noise Removal from THz Time-Domain Images in Reflection Geometry in the 0.25-6 THz Range
- OpenDR: An Open Toolkit for Enabling High Performance, Low Footprint Deep Learning for Robotics
- Nonlinear Kernel Support Vector Machine with 0-1 Soft Margin Loss
- A Theory of Abstraction in Reinforcement Learning
- Motion-aware Dynamic Graph Neural Network for Video Compressive Sensing
- CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP
All 168
- Data-efficient learning of object-centric grasp preferences
- Addressing Randomness in Evaluation Protocols for Out-of-Distribution Detection
- Exploring Wilderness Characteristics Using Explainable Machine Learning in Satellite Imagery
- Popularity Bias in Collaborative Filtering-Based Multimedia Recommender Systems
- Approximating a deep reinforcement learning docking agent using linear model trees
- Explaining a Deep Reinforcement Learning Docking Agent Using Linear Model Trees with User Adapted Visualization
- Non-linear manifold ROM with Convolutional Autoencoders and Reduced Over-Collocation method
- Tempera: Spatial Transformer Feature Pyramid Network for Cardiac MRI Segmentation
- Improving Performance of Automated Essay Scoring by using back-translation essays and adjusted scores
- Affordance Learning from Play for Sample-Efficient Policy Learning
- Read before Generate! Faithful Long Form Question Answering with Machine Reading
- Towards IID representation learning and its application on biomedical data
- Machine Learning for Particle Flow Reconstruction at CMS
- BERT-LID: Leveraging BERT to Improve Spoken Language Identification
- Differentially private training of residual networks with scale normalisation
- Graph Normalized-LMP Algorithm for Signal Estimation Under Impulsive Noise
- Explainability for identification of vulnerable groups in machine learning models
- First do not fall: learning to exploit a wall with a damaged humanoid robot
- VScript: Controllable Script Generation with Visual Presentation
- Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection
- Comprehensive Analysis of the Object Detection Pipeline on UAVs
- Automatic Depression Detection via Learning and Fusing Features from Visual Cues
- Adversarial samples for deep monocular 6D object pose estimation
- A Domain-Theoretic Framework for Robustness Analysis of Neural Networks
- FP-Loc: Lightweight and Drift-free Floor Plan-assisted LiDAR Localization
- Efficient Globally-Optimal Correspondence-Less Visual Odometry for Planar Ground Vehicles
- "Is Whole Word Masking Always Better for Chinese BERT?": Probing on Chinese Grammatical Error Correction
- ProgressLabeller: Visual Data Stream Annotation for Training Object-Centric 3D Perception
- Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation
- TableFormer: Robust Transformer Modeling for Table-Text Encoding
- ArabGend: Gender Analysis and Inference on Arabic Twitter
- Private Convex Optimization via Exponential Mechanism
- Separable-HoverNet and Instance-YOLO for Colon Nuclei Identification and Counting
- Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection
- When A Conventional Filter Meets Deep Learning: Basis Composition Learning on Image Filters
- Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors
- Improving Time Sensitivity for Question Answering over Temporal Knowledge Graphs
- A Versatile Agent for Fast Learning from Human Instructors
- Exploring and Adapting Chinese GPT to Pinyin Input Method
- An Information-Theoretic Framework for Supervised Learning
- Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment
- Uncertainty categories in medical image segmentation: a study of source-related diversity
- TRILLsson: Distilled Universal Paralinguistic Speech Representations
- Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR
- FedREP: Towards Horizontal Federated Load Forecasting for Retail Energy Providers
- Understanding the Challenges When 3D Semantic Segmentation Faces Class Imbalanced and OOD Data
- Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settings
- Riemannian statistics meets random matrix theory: towards learning from high-dimensional covariance matrices
- RMBR: A Regularized Minimum Bayes Risk Reranking Framework for Machine Translation
- Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks
- Private Frequency Estimation via Projective Geometry
- EPPAC: Entity Pre-typing Relation Classification with Prompt AnswerCentralizing
- Layer Adaptive Deep Neural Networks for Out-of-distribution Detection
- NeuRecover: Regression-Controlled Repair of Deep Neural Networks with Training History
- Semi-supervised Deep Learning for Image Classification with Distribution Mismatch: A Survey
- Robots Autonomously Detecting People: A Multimodal Deep Contrastive Learning Method Robust to Intraclass Variations
- ACTIVE:Augmentation-Free Graph Contrastive Learning for Partial Multi-View Clustering
- T3 OMVP: A Transformer-based Time and Team Reinforcement Learning Scheme for Observation-constrained Multi-Vehicle Pursuit in Urban Area
- When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guarantee
- Enhancing Local Feature Learning for 3D Point Cloud Processing using Unary-Pairwise Attention
- A Standardized Pipeline for Colon Nuclei Identification and Counting Challenge
- On Testability of the Front-Door Model via Verma Constraints
- GROW: A Row-Stationary Sparse-Dense GEMM Accelerator for Memory-Efficient Graph Convolutional Neural Networks
- Simultaneous Semantic and Instance Segmentation for Colon Nuclei Identification and Counting
- Preemptive Motion Planning for Human-to-Robot Indirect Placement Handovers
- Performance of Distribution Regression with Doubling Measure under the seek of Closest Point
- Molecular Dynamics of Polymer-lipids in Solution from Supervised Machine Learning
- Explaining RADAR features for detecting spoofing attacks in Connected Autonomous Vehicles