Papers
Tue 12 Oct 2021
215 papers
- FILM: Following Instructions in Language with Modular MethodsOffline RL and imitation learning from data → Language-conditioned policies and VLAs
- Scalable Consistency Training for Graph Neural Networks via Self-Ensemble Self-DistillationKnowledge distillation → Graph neural network distillation
- LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot LearnersSynthetic data and self-improvement for LLMs → Self-training for few-shot NLP
- Offline Reinforcement Learning with Implicit Q-LearningOffline RL and imitation learning from data → Offline RL algorithms
- Deep Federated Learning for Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
- A modified gravity model based on network efficiency for vital nodes identification in complex networks
- Deep Learning for Bias Detection: From Inception to Deployment
- Surrogate and inverse modeling for two-phase flow in porous media via theory-guided convolutional neural network
- Analysis of False Data Injection Impact on AI based Solar Photovoltaic Power Generation Forecasting
- Multi-Modal Pre-Training for Automated Speech Recognition
- Early Diagnostic Prediction of Covid-19 using Gradient-Boosting Machine Model
- A Prior Guided Adversarial Representation Learning and Hypergraph Perceptual Network for Predicting Abnormal Connections of Alzheimer's Disease
- A Rate-Distortion Framework for Explaining Black-box Model Decisions
- Reliable Shot Identification for Complex Event Detection via Visual-Semantic Embedding
- Application of Homomorphic Encryption in Medical Imaging
- The Sigma-max System Induced from Randomness & Fuzziness and its Application in Time Series Prediction
- Deep Human-guided Conditional Variational Generative Modeling for Automated Urban Planning
- AIR-Net: Adaptive and Implicit Regularization Neural Network for Matrix Completion
- Topic-time Heatmaps for Human-in-the-loop Topic Detection and Tracking
- A Survey on Legal Question Answering Systems
- CyTran: A Cycle-Consistent Transformer with Multi-Level Consistency for Non-Contrast to Contrast CT Translation
- Dynamic Inference with Neural Interpreters
- CovXR: Automated Detection of COVID-19 Pneumonia in Chest X-Rays through Machine Learning
- An Overview of Ontologies and Tool Support for COVID-19 Analytics
- GridLearn: Multiagent Reinforcement Learning for Grid-Aware Building Energy Management
- Robust Neural Regression via Uncertainty Learning
- Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation
- Attention-guided Generative Models for Extractive Question Answering
- Learning ground states of quantum Hamiltonians with graph networks
- Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular Design
- HETFORMER: Heterogeneous Transformer with Sparse Attention for Long-Text Extractive Summarization
- AutoNLU: Detecting, root-causing, and fixing NLU model errors
- Real-time Drift Detection on Time-series Data
- A Survey of Open Source User Activity Traces with Applications to User Mobility Characterization and Modeling
- Meta Learning Low Rank Covariance Factors for Energy-Based Deterministic Uncertainty
- ALL Dolphins Are Intelligent and SOME Are Friendly: Probing BERT for Nouns' Semantic Properties and their Prototypicality
- Coupled and Uncoupled Dynamic Mode Decomposition in Multi-Compartmental Systems with Applications to Epidemiological and Additive Manufacturing Problems
- Enabling Level-4 Autonomous Driving on a Single 1k Off-the-Shelf Card
- Data-driven Leak Localization in Water Distribution Networks via Dictionary Learning and Graph-based Interpolation
- Voice-assisted Image Labelling for Endoscopic Ultrasound Classification using Neural Networks
- Time Masking for Temporal Language Models
- Fast Approximations for Job Shop Scheduling: A Lagrangian Dual Deep Learning Method
- Tangent Space and Dimension Estimation with the Wasserstein Distance
- Tell Me How to Survey: Literature Review Made Simple with Automatic Reading Path Generation
- Exact and Bounded Collision Probability for Motion Planning under Gaussian Uncertainty
- Learning Compact Metrics for MT
- Exploring Content Based Image Retrieval for Highly Imbalanced Melanoma Data using Style Transfer, Semantic Image Segmentation and Ensemble Learning
- As Easy as ABC: Adaptive Binning Coincidence Test for Uniformity Testing
- A Multi-scale Time-series Dataset with Benchmark for Machine Learning in Decarbonized Energy Grids
- Incremental Community Detection in Distributed Dynamic Graph
- Exploring Wav2vec 2.0 fine-tuning for improved speech emotion recognition
- Fine-grained style control in Transformer-based Text-to-speech Synthesis
- Domain Generalization via Domain-based Covariance Minimization
- The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks
- Persistent Homology with Improved Locality Information for more Effective Delineation
- Decision-Theoretic Question Generation for Situated Reference Resolution: An Empirical Study and Computational Model
- Real-Time Learning from An Expert in Deep Recommendation Systems with Marginal Distance Probability Distribution
- Detecting Corrupted Labels Without Training a Model to Predict
- The Rich Get Richer: Disparate Impact of Semi-Supervised Learning
- S3PRL-VC: Open-source Voice Conversion Framework with Self-supervised Speech Representations
- Smaaprat: DialoGPT for Natural Language Generation of Swedish Dialogue by Transfer Learning
- Real Image Inversion via Segments
- Twice regularized MDPs and the equivalence between robustness and regularization
- Speech Summarization using Restricted Self-Attention
- Causal Discovery from Conditionally Stationary Time Series
- Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective
- Not all noise is accounted equally: How differentially private learning benefits from large sampling rates
- Molecular Graph Generation via Geometric Scattering
- Investigating the Effect of Natural Language Explanations on Out-of-Distribution Generalization in Few-shot NLI
- A Brief Introduction to Automatic Differentiation for Machine Learning
- Open-Set Recognition: a Good Closed-Set Classifier is All You Need?
- StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning
- ABO: Dataset and Benchmarks for Real-World 3D Object Understanding
- Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression
- Crystal Diffusion Variational Autoencoder for Periodic Material Generation
- GRAPE for Fast and Scalable Graph Processing and random walk-based Embedding
- Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes
- TAda! Temporally-Adaptive Convolutions for Video Understanding
- Tracking the risk of a deployed model and detecting harmful distribution shifts
- Mention Memory: incorporating textual knowledge into Transformers through entity mention attention
- M2GAN: A Multi-Stage Self-Attention Network for Image Rain Removal on Autonomous Vehicles
- Finding Relevant Points for Nearest-Neighbor Classification
- Sign Language Recognition via Skeleton-Aware Multi-Model Ensemble
- Memory-Efficient CNN Accelerator Based on Interlayer Feature Map Compression
- Extracting Feelings of People Regarding COVID-19 by Social Network Mining
- Sparsity in Partially Controllable Linear Systems
- Planning from Pixels in Environments with Combinatorially Hard Search Spaces
- Label scarcity in biomedicine: Data-rich latent factor discovery enhances phenotype prediction
- Regionalized models for Spanish language variations based on Twitter
- Spatial mixup: Directional loudness modification as data augmentation for sound event localization and detection
- Embracing Structure in Data for Billion-Scale Semantic Product Search
- Nonnegative spatial factorization
- Cubature Kalman Filter Based Training of Hybrid Differential Equation Recurrent Neural Network Physiological Dynamic Models
- Continuous Conditional Random Field Convolution for Point Cloud Segmentation
- Implicit Bias of Linear Equivariant Networks
- Efficient Bayesian network structure learning via local Markov boundary search
- On Expressivity and Trainability of Quadratic Networks
- Model-based analysis of brain activity reveals the hierarchy of language in 305 subjects
- Synergy: Resource Sensitive DNN Scheduling in Multi-Tenant Clusters
- Spectral analysis of re-parameterized light fields
All 215
- MEDUSA: Multi-scale Encoder-Decoder Self-Attention Deep Neural Network Architecture for Medical Image Analysis
- Development of Deep Transformer-Based Models for Long-Term Prediction of Transient Production of Oil Wells
- Multi-Modal Interaction Graph Convolutional Network for Temporal Language Localization in Videos
- Gated Information Bottleneck for Generalization in Sequential Environments
- Improved Pillar with Fine-grained Feature for 3D Object Detection
- The Terminating-Random Experiments Selector: Fast High-Dimensional Variable Selection with False Discovery Rate Control
- Topic Model Supervised by Understanding Map
- SlideGraph+: Whole Slide Image Level Graphs to Predict HER2Status in Breast Cancer
- SoftNeuro: Fast Deep Inference using Multi-platform Optimization
- Federated Phish Bowl: LSTM-Based Decentralized Phishing Email Detection
- Embedded-model flows: Combining the inductive biases of model-free deep learning and explicit probabilistic modeling
- On out-of-distribution detection with Bayesian neural networks
- On the Security Risks of AutoML
- Rethinking Supervised Pre-training for Better Downstream Transferring
- Robust Glare Detection: Review, Analysis, and Dataset Release
- DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformer
- Word Order Does Not Matter For Speech Recognition
- Weighted Model Counting in FO2 with Cardinality Constraints and Counting Quantifiers: A Closed Form Formula
- A Categorical Semantics of Fuzzy Concepts in Conceptual Spaces
- Early Melanoma Diagnosis with Sequential Dermoscopic Images
- Can machines learn to see without visual databases?
- Improving Character Error Rate Is Not Equal to Having Clean Speech: Speech Enhancement for ASR Systems with Black-box Acoustic Models
- Weakly-Supervised Semantic Segmentation by Learning Label Uncertainty
- Trivial or impossible -- dichotomous data difficulty masks model differences (on ImageNet and beyond)
- Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixes
- Video Is Graph: Structured Graph Module for Video Action Recognition
- LaoPLM: Pre-trained Language Models for Lao
- Investigation on Data Adaptation Techniques for Neural Named Entity Recognition
- Discovery of Single Independent Latent Variable
- MGH: Metadata Guided Hypergraph Modeling for Unsupervised Person Re-identification
- Monocular Depth Estimation with Sharp Boundary
- Fourier-based Video Prediction through Relational Object Motion
- OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languages
- Label-Aware Ranked Loss for robust People Counting using Automotive in-cabin Radar
- MetricGAN-U: Unsupervised speech enhancement/ dereverberation based only on noisy/ reverberated speech
- Disentangling intrinsic motion from neighbourhood effects in heterogeneous collective motion
- Convolutional Neural Networks Are Not Invariant to Translation, but They Can Learn to Be
- text2sdg: An R package to Monitor Sustainable Development Goals from Text
- A scalable and fast artificial neural network syndrome decoder for surface codes
- Joint Learning On The Hierarchy Representation for Fine-Grained Human Action Recognition
- On the Self-Penalization Phenomenon in Feature Selection
- Improving Binary Neural Networks through Fully Utilizing Latent Weights
- Sharing FANCI Features: A Privacy Analysis of Feature Extraction for DGA Detection
- Fine-Grained Adversarial Semi-supervised Learning
- Evaluation of Abstractive Summarisation Models with Machine Translation in Deliberative Processes
- Fast Block Linear System Solver Using Q-Learning Schduling for Unified Dynamic Power System Simulations
- Across-Task Neural Architecture Search via Meta Learning
- Relative Molecule Self-Attention Transformer
- PLNet: Plane and Line Priors for Unsupervised Indoor Depth Estimation
- Balancing Average and Worst-case Accuracy in Multitask Learning
- AVoE: A Synthetic 3D Dataset on Understanding Violation of Expectation for Artificial Cognition
- CoarSAS2hvec: Heterogeneous Information Network Embedding with Balanced Network Sampling
- Event-Based high-speed low-latency fiducial marker tracking
- Satellite Image Semantic Segmentation
- Open Player Modeling: Empowering Players through Data Transparency
- Couple Learning for semi-supervised sound event detection
- Optimizing Ranking Systems Online as Bandits
- SDWNet: A Straight Dilated Network with Wavelet Transformation for Image Deblurring
- Codabench: Flexible, Easy-to-Use and Reproducible Benchmarking Platform
- Adapting TTS models For New Speakers using Transfer Learning
- Zero-bias Deep Neural Network for Quickest RF Signal Surveillance
- Information Theoretic Structured Generative Modeling
- Aspect-driven User Preference and News Representation Learning for News Recommendation
- BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications
- We've had this conversation before: A Novel Approach to Measuring Dialog Similarity
- Quantifying Cognitive Factors in Lexical Decline
- HyperCube: Implicit Field Representations of Voxelized 3D Models
- Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents
- Music Sentiment Transfer
- Detecting Damage Building Using Real-time Crowdsourced Images and Transfer Learning
- Predicting the Efficiency of CO2 Sequestering by Metal Organic Frameworks Through Machine Learning Analysis of Structural and Electronic Properties
- UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training
- SportsSum2.0: Generating High-Quality Sports News from Live Text Commentary
- SEPP: Similarity Estimation of Predicted Probabilities for Defending and Detecting Adversarial Text
- Seamless Copy Move Manipulation in Digital Images
- VarArray: Array-Geometry-Agnostic Continuous Speech Separation
- Program Transfer for Answering Complex Questions over Knowledge Bases
- Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization
- Temporal Abstraction in Reinforcement Learning with the Successor Representation
- Learning Efficient Multi-Agent Cooperative Visual Exploration
- Guided-GAN: Adversarial Representation Learning for Activity Recognition with Wearables
- Topic Scene Graph Generation by Attention Distillation from Caption
- Rethinking the Spatial Route Prior in Vision-and-Language Navigation
- Anatomy of OntoGUM--Adapting GUM to the OntoNotes Scheme to Evaluate Robustness of SOTA Coreference Algorithms
- Query-Reward Tradeoffs in Multi-Armed Bandits
- Prediction of Political Leanings of Chinese Speaking Twitter Users
- LightSeq2: Accelerated Training for Transformer-based Models on GPUs
- Action-Sufficient State Representation Learning for Control with Structural Constraints
- Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations
- Relation-aware Video Reading Comprehension for Temporal Language Grounding
- DecGAN: Decoupling Generative Adversarial Network detecting abnormal neural circuits for Alzheimer's disease
- On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning
- Deep Fusion Prior for Plenoptic Super-Resolution All-in-Focus Imaging
- Auditing Robot Learning for Safety and Compliance during Deployment
- On Exploring and Improving Robustness of Scene Text Detection Models
- On Releasing Annotator-Level Labels and Information in Datasets
- Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videos
- The Mirrornet : Learning Audio Synthesizer Controls Inspired by Sensorimotor Interaction
- Doubly-Trained Adversarial Data Augmentation for Neural Machine Translation
- Partial Counterfactual Identification from Observational and Experimental Data
- Hiding Images into Images with Real-world Robustness
- Inclusive Design: Accessibility Settings for People with Cognitive Disabilities
- RWN: Robust Watermarking Network for Image Cropping Localization
- Provably Efficient Reinforcement Learning in Decentralized General-Sum Markov Games
- Large Language Models Can Be Strong Differentially Private Learners
- Improved Heatmap-based Landmark Detection
- Deviance Matrix Factorization
- Predicting the Stereoselectivity of Chemical Transformations by Machine Learning
- NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks
- Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks
- Are you doing what I say? On modalities alignment in ALFRED
- Accurate and Generalizable Quantitative Scoring of Liver Steatosis from Ultrasound Images via Scalable Deep Learning
- Learned Construction Grammars Converge Across Registers Given Increased Exposure
- BotNet Detection on Social Media
- Defocus Map Estimation and Deblurring from a Single Dual-Pixel Image