Papers
Fri 21 Oct 2022
244 papers
- Sample Efficient Robot Learning with Structured World ModelsWorld models → Embodied and robot world models
- Implicit Offline Reinforcement Learning via Supervised LearningOffline RL and imitation learning from data → Real-world robot offline RL
- Enhancing Tabular Reasoning with Pattern Exploiting TrainingLLM reasoning → Knowledge- and tool-augmented reasoning
- Score-based Denoising Diffusion with Non-Isotropic Gaussian Noise ModelsDiffusion models → Diffusion foundations and sampling
- Conditional Diffusion with Less Explicit Guidance via Model Predictive ControlDiffusion models → Diffusion foundations and sampling
- Multitask Brain Tumor Inpainting with Diffusion Models: A Methodological ReportDiffusion models → Medical imaging and segmentation
- Boomerang: Local sampling on image manifolds using diffusion modelsDiffusion models → Diffusion foundations and sampling
- Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?LLM reasoning → Multimodal reasoning
- Neuro-Symbolic Causal Reasoning Meets Signaling Game for Emergent Semantic CommunicationsLLM reasoning → Reasoning benchmarks and evaluation
- A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language ModelsLLM reasoning → Mathematical reasoning
- Differentiable Constrained Imitation Learning for Robot Motion Planning and ControlOffline RL and imitation learning from data → Imitation and offline RL for driving
- Generative Range Imaging for Learning Scene Priors of 3D LiDAR DataWorld models → World modeling from LiDAR generation
- Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- Learning Robust Dynamics through Variational Sparse GatingWorld models → Latent predictive world models
- Towards Quantum-Enabled 6G Slicing
- Time Series Synthesis via Multi-scale Patch-based Generation of Wavelet Scalogram
- Combining Contrastive and Non-Contrastive Losses for Fine-Tuning Pretrained Models in Speech Analysis
- An agent-based approach to procedural city generation incorporating Land Use and Transport Interaction models
- On-Device Model Fine-Tuning with Label Correction in Recommender Systems
- How fair were COVID-19 restriction decisions? A data-driven investigation of England using the dominance-based rough sets approach
- Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networks
- MEEV: Body Mesh Estimation On Egocentric Video
- Isomorphic mesh generation from point clouds with multilayer perceptrons
- Detection of Real-time DeepFakes in Video Conferencing with Active Probing and Corneal Reflection
- Epistemic Monte Carlo Tree Search
- Calibration tests beyond classification
- Multimodal Model with Text and Drug Embeddings for Adverse Drug Reaction Classification
- Biologically Plausible Variational Policy Gradient with Spiking Recurrent Winner-Take-All Networks
- Navigating the challenges in creating complex data systems: a development philosophy
- Can Visual Context Improve Automatic Speech Recognition for an Embodied Agent?
- Dissecting Deep Metric Learning Losses for Image-Text Retrieval
- Meta Input: How to Leverage Off-the-Shelf Deep Neural Networks
- What do Large Language Models Learn beyond Language?
- Continual Vision-based Reinforcement Learning with Group Symmetries
- Feature selection intelligent algorithm with mutual information and steepest ascent strategy
- DL-Corrector-Remapper: A grid-free bias-correction deep learning methodology for data-driven high-resolution global weather forecasting
- Learning Ultrametric Trees for Optimal Transport Regression
- Exploring Representation-Level Augmentation for Code Search
- Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
- Bridging the Gap Between Target Networks and Functional Regularization
- The Stochastic Proximal Distance Algorithm
- Text Editing as Imitation Game
- Graphemic Normalization of the Perso-Arabic Script
- An Exploration of Neural Radiance Field Scene Reconstruction: Synthetic, Real-world and Dynamic Scenes
- On the Calibration of Massively Multilingual Language Models
- Group Distributionally Robust Reinforcement Learning with Hierarchical Latent Variables
- Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imagination
- Efficient Automatic Machine Learning via Design Graphs
- Uncertainty Estimates of Predictions via a General Bias-Variance Decomposition
- STAP: Sequencing Task-Agnostic Policies
- Benchmarking GPU and TPU Performance with Graph Neural Networks
- A Dataset for Plain Language Adaptation of Biomedical Abstracts
- FIND: An Unsupervised Implicit 3D Model of Articulated Human Feet
- Auto-Encoder Neural Network Incorporating X-Ray Fluorescence Fundamental Parameters with Machine Learning
- Uncertain Evidence in Probabilistic Models and Stochastic Simulators
- Sequential Gradient Descent and Quasi-Newton's Method for Change-Point Analysis
- Imbalanced Classification in Medical Imaging via Regrouping
- TCAB: A Large-Scale Text Classification Attack Benchmark
- Reducing Training Sample Memorization in GANs by Training with Memorization Rejection
- Deep Reinforcement Learning for Stabilization of Large-scale Probabilistic Boolean Networks
- EDUKG: a Heterogeneous Sustainable K-12 Educational Knowledge Graph
- Low-Resource Multilingual and Zero-Shot Multispeaker TTS
- Considerations for Visualizing Uncertainty in Clinical Machine Learning Models
- Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning
- Feature Engineering and Classification Models for Partial Discharge in Power Transformers
- Gui at MixMT 2022 : English-Hinglish: An MT approach for translation of code mixed data
- Optimizing Bilingual Neural Transducer with Synthetic Code-switching Text Generation
- SpaBERT: A Pretrained Language Model from Geographic Data for Geo-Entity Representation
- Motion Policy Networks
- Probing with Noise: Unpicking the Warp and Weft of Embeddings
- High-Quality RGB-D Reconstruction via Multi-View Uncalibrated Photometric Stereo and Gradient-SDF
- Anonymous Bandits for Multi-User Systems
- Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processes
- Augmentation by Counterfactual Explanation -- Fixing an Overconfident Classifier
- Just Mix Once: Worst-group Generalization by Group Interpolation
- GraphNeT: Graph neural networks for neutrino telescope event reconstruction
- Syntactic Surprisal From Neural Models Predicts, But Underestimates, Human Processing Difficulty From Syntactic Ambiguities
- Improving the Factual Correctness of Radiology Report Generation with Semantic Rewards
- Attention-Based Scattering Network for Satellite Imagery
- A New Perspective for Understanding Generalization Gap of Deep Neural Networks Trained with Large Batch Sizes
- Neural Architectural Backdoors
- An unsupervised latent/output physics-informed convolutional-LSTM network for solving partial differential equations using peridynamic differential operator
- High-Fidelity Visual Structural Inspections through Transformers and Learnable Resizers
- Discovering Differences in the Representation of People using Contextualized Semantic Axes
- Joint Coreference Resolution for Zeros and non-Zeros in Arabic
- Task-Based Assessment for Neural Networks: Evaluating Undersampled MRI Reconstructions based on Human Observer Signal Detection
- On the connection between Bregman divergence and value in regularized Markov decision processes
- Graph Coloring via Neural Networks for Haplotype Assembly and Viral Quasispecies Reconstruction
- Error-Covariance Analysis of Monocular Pose Estimation Using Total Least Squares
- On amortizing convex conjugates for optimal transport
- WikiWhy: Answering and Explaining Cause-and-Effect Questions
- Unsupervised Multi-object Segmentation by Predicting Probable Motion Patterns
- Target Aware Poisson-Gaussian Noise Parameters Estimation from Noisy Images
- Explainability in autonomous pedagogically structured scenarios
- A Multi-Scale Deep Learning Framework for Projecting Weather Extremes
- Geometric Sparse Coding in Wasserstein Space
- Audio-to-Intent Using Acoustic-Textual Subword Representations from End-to-End ASR
- Graph Few-shot Learning with Task-specific Structures
- One-Shot Neural Fields for 3D Object Understanding
- Equivariant Networks for Zero-Shot Coordination
All 244
- Targeted active learning for probabilistic models
- Modelling Control Arguments via Cooperation Logic in Unforeseen Scenarios
- Describing Sets of Images with Textual-PCA
- Adversarial Permutation Invariant Training for Universal Sound Separation
- XAI for transparent wind turbine power curve models
- Neural Network Approximations of PDEs Beyond Linearity: A Representational Perspective
- Triplet Losses-based Matrix Factorization for Robust Recommendations
- Robust Singular Values based on L1-norm PCA
- Augmenting Multi-Turn Text-to-SQL Datasets with Self-Play
- Learning shape distributions from large databases of healthy organs: applications to zero-shot and few-shot abnormal pancreas detection
- AutoPrognosis 2.0: Democratizing Diagnostic and Prognostic Modeling in Healthcare with Automated Machine Learning
- A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges
- Decoding a Neural Retriever's Latent Space for Query Suggestion
- A Non-Asymptotic Moreau Envelope Theory for High-Dimensional Generalized Linear Models
- Monitoring Constraints in Business Processes Using Object-Centric Constraint Graphs
- Experiencer-Specific Emotion and Appraisal Prediction
- Efficient Dataset Distillation Using Random Feature Approximation
- Validation of Composite Systems by Discrepancy Propagation
- Efficient Global Planning in Large MDPs via Stochastic Primal-Dual Optimization
- Query Semantic Reconstruction for Background in Few-Shot Segmentation
- Towards Global Neural Network Abstractions with Locally-Exact Reconstruction
- The privacy issue of counterfactual explanations: explanation linkage attacks
- Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards
- Ollivier-Ricci Curvature for Hypergraphs: A Unified Framework
- BlanketGen - A synthetic blanket occlusion augmentation pipeline for MoCap datasets
- Evolution of Neural Tangent Kernels under Benign and Adversarial Training
- Adversarial Transformer for Repairing Human Airway Segmentation
- Bootstrapping NLP tools across low-resourced African languages: an overview and prospects
- Ontology Development is Consensus Creation, Not (Merely) Representation
- Performance-Efficiency Trade-Offs in Adapting Language Models to Text Classification Tasks
- HCL: Improving Graph Representation with Hierarchical Contrastive Learning
- Ethics for Digital Medicine: A Path for Ethical Emerging Medical IoT Design
- Integrated Brier Score based Survival Cobra -- A regression based approach
- HDHumans: A Hybrid Approach for High-fidelity Digital Humans
- When Expressivity Meets Trainability: Fewer than n Neurons Can Work
- On-Board Pedestrian Trajectory Prediction Using Behavioral Features
- Extending F1 metric, probabilistic approach
- Real-time Detection of 2D Tool Landmarks with Synthetic Training Data
- Optimizing text representations to capture (dis)similarity between political parties
- Joint Speech Translation and Named Entity Recognition
- Shift-Reduce Task-Oriented Semantic Parsing with Stack-Transformers
- Named Entity Detection and Injection for Direct Speech Translation
- Face Pyramid Vision Transformer
- Real-Time Constrained 6D Object-Pose Tracking of An In-Hand Suture Needle for Minimally Invasive Robotic Surgery
- CobNet: Cross Attention on Object and Background for Few-Shot Segmentation
- A GA-like Dynamic Probability Method With Mutual Information for Feature Selection
- Learning Graphical Factor Models with Riemannian Optimization
- Generalizing over Long Tail Concepts for Medical Term Normalization
- Automatic Cattle Identification using YOLOv5 and Mosaic Augmentation: A Comparative Analysis
- Fine-grained Semantic Alignment Network for Weakly Supervised Temporal Language Grounding
- Deep Reinforcement Learning for Inverse Inorganic Materials Design
- LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling
- Unbiased constrained sampling with Self-Concordant Barrier Hamiltonian Monte Carlo
- Men Also Do Laundry: Multi-Attribute Bias Amplification
- Multi-scale data reconstruction of turbulent rotating flows with Gappy POD, Extended POD and Generative Adversarial Networks
- Efficient identification of informative features in simulation-based inference
- NEREL-BIO: A Dataset of Biomedical Abstracts Annotated with Nested Named Entities
- m4Adapter: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adapter
- Boosting vision transformers for image retrieval
- Collaborative Image Understanding
- Exploration of the Usage of Color Terms by Color-blind Participants in Online Discussion Platforms
- Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translation
- A Semi-supervised Approach for a Better Translation of Sentiment in Dialectical Arabic UGT
- Spoken Term Detection and Relevance Score Estimation using Dot-Product of Pronunciation Embeddings
- BioLORD: Learning Ontological Representations from Definitions (for Biomedical Concepts and their Textual Descriptions)
- STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing
- Deep LSTM Spoken Term Detection using Wav2Vec 2.0 Recognizer
- GLCC: A General Framework for Graph-Level Clustering
- Blind Polynomial Regression
- LittleBird: Efficient Faster & Longer Transformer for Question Answering
- Spectral Probing
- Learning in RKHM: a C^*-Algebraic Twist for Kernel Machines
- Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities
- Cox-Hawkes: doubly stochastic spatiotemporal Poisson processes
- Diffusion Visual Counterfactual Explanations
- The use of the word "gammaupsionnuαiotakappaomicronkappaτomicronnuiotaα" (femicide) in Greek-speaking Twitter
- Structural Kernel Search via Bayesian Optimization and Symbolical Optimal Transport
- A Textless Metric for Speech-to-Speech Comparison
- Optimal Contextual Bandits with Knapsacks under Realizability via Regression Oracles
- Improving the Anomaly Detection in GPR Images by Fine-Tuning CNNs with Synthetic Data
- AI-HRI Brings New Dimensions to Human-Aware Design for Human-Aware AI
- Management of Machine Learning Lifecycle Artifacts: A Survey
- 3D Human Pose Estimation in Multi-View Operating Room Videos Using Differentiable Camera Projections
- Integrating Policy Summaries with Reward Decomposition for Explaining Reinforcement Learning Agents
- Valuing Vicinity: Memory attention framework for context-based semantic segmentation in histopathology
- Motion Matters: A Novel Motion Modeling For Cross-View Gait Feature Learning
- Self-Supervised Pretraining on Satellite Imagery: a Case Study on Label-Efficient Vehicle Detection
- Unsupervised Image Semantic Segmentation through Superpixels and Graph Neural Networks
- Is Encoder-Decoder Redundant for Neural Machine Translation?
- Robustifying Sentiment Classification by Maximally Exploiting Few Counterfactuals
- Discovering New Intents Using Latent Variables
- Revisiting Checkpoint Averaging for Neural Machine Translation
- Random Actions vs Random Policies: Bootstrapping Model-Based Direct Policy Search
- Rescue Implicit and Long-tail Cases: Nearest Neighbor Relation Extraction
- PoseScript: Linking 3D Human Poses and Natural Language
- Diffuser: Efficient Transformers with Multi-hop Attention Diffusion for Long Sequences
- FoSR: First-order spectral rewiring for addressing oversquashing in GNNs
- Modeling Document-level Temporal Structures for Building Temporal Dependency Graphs
- Correlating sparse sensing for large-scale traffic speed estimation: A Laplacian-enhanced low-rank tensor kriging approach
- Reaching Through Latent Space: From Joint Statistics to Path Planning in Manipulation
- Analyzing and Evaluating Faithfulness in Dialogue Summarization
- SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrieval
- InforMask: Unsupervised Informative Masking for Language Model Pretraining
- Augmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation
- CEFR-Based Sentence Difficulty Annotation and Assessment
- Detecting Unintended Social Bias in Toxic Language Datasets
- Syntax-guided Localized Self-attention by Constituency Syntactic Distance
- University of Cape Town's WMT22 System: Multilingual Machine Translation for Southern African Languages
- online and lightweight kernel-based approximated policy iteration for dynamic p-norm linear adaptive filtering
- TransLIST: A Transformer-Based Linguistically Informed Sanskrit Tokenizer
- AfroLID: A Neural Language Identification Tool for African Languages
- Bayesian deep learning framework for uncertainty quantification in high dimensions
- Analogical Concept Memory for Architectures Implementing the Common Model of Cognition
- Privacy-Preserved Neural Graph Similarity Learning
- An Exploration of Data Efficiency in Intra-Dataset Task Transfer for Dialog Understanding
- Distilling the Undistillable: Learning from a Nasty Teacher
- AROS: Affordance Recognition with One-Shot Human Stances
- Evidence of Vocal Tract Articulation in Self-Supervised Learning of Speech
- Adaptive re-calibration of channel-wise features for Adversarial Audio Classification
- MCSCSet: A Specialist-annotated Dataset for Medical-domain Chinese Spelling Correction
- Context-Enhanced Stereo Transformer
- CRT-6D: Fast 6D Object Pose Estimation with Cascaded Refinement Transformers
- A Survey of Dataset Refinement for Problems in Computer Vision Datasets
- Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection
- Design a Sustainable Micro-mobility Future: Trends and Challenges in the United States and European Union Using Natural Language Processing Techniques
- Modelling Multi-relations for Convolutional-based Knowledge Graph Embedding
- Video Summarization Overview
- Efficiently Tuned Parameters are Task Embeddings
- Global Counterfactual Explainer for Graph Neural Networks
- Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem
- Amos: An Adam-style Optimizer with Adaptive Weight Decay towards Model-Oriented Scale
- Competing Bandits in Time Varying Matching Markets
- SLING: Sino Linguistic Evaluation of Large Language Models
- Twin Contrastive Learning for Online Clustering
- Granular-Ball Fuzzy Set and Its Implementation in SVM
- Stochastic Adaptive Activation Function
- SIT at MixMT 2022: Fluent Translation Built on Giant Pre-trained Models
- RGB-Only Reconstruction of Tabletop Scenes for Collision-Free Manipulator Control
- Doctors Handwritten Prescription Recognition System In Multi Language Using Deep Learning
- InfraRed Investigation in Singapore (IRIS) Observatory: Urban heat island contributors and mitigators analysis using neighborhood-scale thermal imaging
- Local Bayesian optimization via maximizing probability of descent
- Learning Action Duration and Synergy in Task Planning for Human-Robot Collaboration
- MnEdgeNet -- Accurate Decomposition of Mixed Oxidation States for Mn XAS and EELS L2,3 Edges without Reference and Calibration
- PaCo: Parameter-Compositional Multi-Task Reinforcement Learning