Papers
Thu 14 Oct 2021
212 papers
- Diffusion Normalizing FlowDiffusion models → Diffusion foundations and sampling
- Offline Reinforcement Learning with Soft Behavior RegularizationOffline RL and imitation learning from data → Offline RL algorithms
- P-Adapters: Robustly Extracting Factual Information from Language Models with Diverse PromptsMixture-of-experts → MoE large language models
- Symbolic Knowledge Distillation: from General Language Models to Commonsense ModelsKnowledge distillation → Knowledge distillation for LLMs
- Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style TransferLLM safety and security → Backdoor and data poisoning attacks
- EdgeML: Towards Network-Accelerated Federated Learning over Wireless Edge
- Transformer for Polyp Detection
- CORAA: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian Portuguese
- Bank transactions embeddings help to uncover current macroeconomics
- Towards Using Clothes Style Transfer for Scenario-aware Person Video Generation
- Comparative Analysis of Deep Learning Algorithms for Classification of COVID-19 X-Ray Images
- The AI Triplet: Computational, Conceptual, and Mathematical Knowledge in AI Education
- CT-SGAN: Computed Tomography Synthesis GAN
- Abstract Interpretation of Fixpoint Iterators with Applications to Neural Networks
- Training Neural Networks for Solving 1-D Optimal Piecewise Linear Approximation
- A Framework for Learning to Request Rich and Contextually Useful Information from Humans
- Learning Semantics: An Opportunity for Effective 6G Communications
- Multi-Layer Pseudo-Supervision for Histopathology Tissue Semantic Segmentation using Patch-level Classification Labels
- Creating User Interface Mock-ups from High-Level Text Descriptions with Deep-Learning Models
- 4D flight trajectory prediction using a hybrid Deep Learning prediction method based on ADS-B technology: a case study of Hartsfield-Jackson Atlanta International Airport(ATL)
- Areas on the space of smooth probability density functions on S2
- 3D Reconstruction of Curvilinear Structures with Stereo Matching DeepConvolutional Neural Networks
- "Knights": First Place Submission for VIPriors21 Action Recognition Challenge at ICCV 2021
- Learning Mean-Field Equations from Particle Data Using WSINDy
- Hindsight: Posterior-guided training of retrievers for improved open-ended generation
- Leveraging Spatial and Temporal Correlations in Sparsified Mean Estimation
- Attention-Free Keyword Spotting
- A deep learning model for classification of diabetic retinopathy in eye fundus images based on retinal lesion detection
- Beyond Classification: Directly Training Spiking Neural Networks for Semantic Segmentation
- Model-Change Active Learning in Graph-Based Semi-Supervised Learning
- Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models
- Continual Learning on Noisy Data Streams via Self-Purified Replay
- The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization
- CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training
- Gray Matter Segmentation in Ultra High Resolution 7 Tesla ex vivo T2w MRI of Human Brain Hemispheres
- Semi-automated checking for regulatory compliance in e-Health
- ASK: Adaptively Selecting Key Local Features for RGB-D Scene Recognition
- Exposing Query Identification for Search Transparency
- Hindsight Network Credit Assignment: Efficient Credit Assignment in Networks of Discrete Stochastic Units
- Safe Autonomous Racing via Approximate Reachability on Ego-vision
- Is Stance Detection Topic-Independent and Cross-topic Generalizable? -- A Reproduction Study
- Shaping embodied agent behavior with activity-context priors from egocentric video
- Making Document-Level Information Extraction Right for the Right Reasons
- Don't Knock! Rowhammer at the Backdoor of DNN Models
- Sound and Complete Neural Network Repair with Minimality and Locality Guarantees
- Large Scale Substitution-based Word Sense Induction
- GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systems
- Appearance Editing with Free-viewpoint Neural Rendering
- Augmenting Imitation Experience via Equivariant Representations
- Interactive Analysis of CNN Robustness
- Distribution-Free Federated Learning with Conformal Predictions
- A Semi-Supervised Approach for Abnormal Event Prediction on Large Operational Network Time-Series Data
- Predicting Solar Flares with Remote Sensing and Machine Learning
- Residual2Vec: Debiasing graph embedding with random graphs
- Federated learning and next generation wireless communications: A survey on bidirectional relationship
- Towards Understanding the Data Dependency of Mixup-style Training
- Talking Detection In Collaborative Learning Environments
- Non-deep Networks
- Sparks: Inspiration for Science Writing using Language Models
- A Survey of Machine Learning Algorithms for Detecting Ransomware Encryption Activity
- More Efficient Sampling for Tensor Decomposition With Worst-Case Guarantees
- Function-space Inference with Sparse Implicit Processes
- Non-contact Atrial Fibrillation Detection from Face Videos by Learning Systolic Peaks
- 3D Structure from 2D Microscopy images using Deep Learning
- HumBugDB: A Large-scale Acoustic Mosquito Dataset
- NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild
- Sub-word Level Lip Reading With Visual Attention
- P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks
- Retrieval-guided Counterfactual Generation for QA
- Compressibility of Distributed Document Representations
- The Neural MMO Platform for Massively Multiagent Research
- DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterances
- Playing for 3D Human Recovery
- Can Explanations Be Useful for Calibrating Black Box Models?
- Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a Loop
- Near optimal sample complexity for matrix and tensor normal models via geodesic convexity
- Network Representation Learning: From Preprocessing, Feature Extraction to Node Embedding
- Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representations
- Graph Condensation for Graph Neural Networks
- Learning Temporal 3D Human Pose Estimation with Pseudo-Labels
- UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning
- Spoken ObjectNet: A Bias-Controlled Spoken Caption Dataset
- Can Machines Learn Morality? The Delphi Experiment
- LAGr: Labeling Aligned Graphs for Improving Systematic Generalization in Semantic Parsing
- MGC: A Complex-Valued Graph Convolutional Network for Directed Graphs
- Resource-constrained Federated Edge Learning with Heterogeneous Data: Formulation and Analysis
- Practical Benefits of Feature Feedback Under Distribution Shift
- Composable Sparse Fine-Tuning for Cross-Lingual Transfer
- Looper: An end-to-end ML platform for product decisions
- BI-RADS BERT & Using Section Segmentation to Understand Radiology Reports
- The Irrationality of Neural Rationale Models
- Time Series Clustering for Human Behavior Pattern Mining
- Toward Degradation-Robust Voice Conversion
- Deep learning models for predicting RNA degradation via dual crowdsourcing
- Sentence-aware Contrastive Learning for Open-Domain Passage Retrieval
- Multi-objective Clustering: A Data-driven Analysis of MOCLE, MOCK and Delta-MOCK
- Comparative Opinion Summarization via Collaborative Decoding
- SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures
- Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision
- Contrastive Proposal Extension with LSTM Network for Weakly Supervised Object Detection
All 212
- Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning
- TDACNN: Target-domain-free Domain Adaptation Convolutional Neural Network for Drift Compensation in Gas Sensors
- Simple Baseline for Single Human Motion Forecasting
- On the Pitfalls of Analyzing Individual Neurons in Language Models
- Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition
- VABO: Violation-Aware Bayesian Optimization for Closed-Loop Control Performance Optimization with Unmodeled Constraints
- Inferring manifolds using Gaussian processes
- RecInDial: A Unified Framework for Conversational Recommendation with Pretrained Language Models
- Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding
- MReD: A Meta-Review Dataset for Structure-Controllable Text Generation
- Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?
- Stability Analysis of Unfolded WMMSE for Power Allocation
- Universally Rank Consistent Ordinal Regression in Neural Networks
- Hybrid Quantum-Classical Neural Network for Cloud-supported In-Vehicle Cyberattack Detection
- On Adversarial Vulnerability of PHM algorithms: An Initial Study
- IB-GAN: A Unified Approach for Multivariate Time Series Classification under Class Imbalance
- Human-robot collaboration and machine learning: a systematic review of recent research
- Designing Language Technologies for Social Good: The Road not Taken
- DeepOrder: Deep Learning for Test Case Prioritization in Continuous Integration Testing
- Inverse Problems Leveraging Pre-trained Contrastive Representations
- Asymmetric Graph Representation Learning
- Adaptive Differentially Private Empirical Risk Minimization
- Possibilistic Fuzzy Local Information C-Means with Automated Feature Selection for Seafloor Segmentation
- Towards More Effective and Economic Sparsely-Activated Model
- Detecting Renewal States in Chains of Variable Length via Intrinsic Bayes Factors
- Understanding Model Robustness to User-generated Noisy Texts
- Automatic Modeling of Social Concepts Evoked by Art Images as Multimodal Frames
- PARE: A Simple and Strong Baseline for Monolingual and Multilingual Distantly Supervised Relation Extraction
- RGB-D Image Inpainting Using Generative Adversarial Network with a Late Fusion Approach
- Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning
- The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs
- Self-Supervised Learning by Estimating Twin Class Distributions
- Provably Efficient Multi-Agent Reinforcement Learning with Fully Decentralized Communication
- Few-shot Controllable Style Transfer for Low-Resource Multilingual Settings
- The Neglected Sibling: Isotropic Gaussian Posterior for VAE
- Transferring Semantic Knowledge Into Language Encoders
- Domain Adaptation on Semantic Segmentation with Separate Affine Transformation in Batch Normalization
- Physics informed neural networks for continuum micromechanics
- RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking
- Domain generalization in deep learning for contrast-enhanced imaging
- Interpretable transformed ANOVA approximation on the example of the prevention of forest fires
- Improved Drug-target Interaction Prediction with Intermolecular Graph Transformer
- Plug-Tagger: A Pluggable Sequence Labeling Framework Using Language Models
- WMDecompose: A Framework for Leveraging the Interpretable Properties of Word Mover's Distance in Sociocultural Analysis
- Modeling dynamic target deformation in camera calibration
- ReGVD: Revisiting Graph Neural Networks for Vulnerability Detection
- Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks
- SpecSinGAN: Sound Effect Variation Synthesis Using Single-Image GANs
- Solving Aspect Category Sentiment Analysis as a Text Generation Task
- FocusNet: Classifying Better by Focusing on Confusing Classes
- DI-AA: An Interpretable White-box Attack for Fooling Deep Neural Networks
- An Empirical Investigation of Multi-bridge Multilingual NMT models
- Aspect-Sentiment-Multiple-Opinion Triplet Extraction
- Multi-task problems are not multi-objective
- LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5
- Sign and Relevance Learning
- View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums
- DeepMoCap: Deep Optical Motion Capture Using Multiple Depth Sensors and Retro-Reflectors
- Carousel Memory: Rethinking the Design of Episodic Memory for Continual Learning
- Order Constraints in Optimal Transport
- An Approach to Mispronunciation Detection and Diagnosis with Acoustic, Phonetic and Linguistic (APL) Embeddings
- Divide-and-Conquer Fusion
- Rethinking Point Cloud Filtering: A Non-Local Position Based Approach
- HAVEN: Hierarchical Cooperative Multi-Agent Reinforcement Learning with Dual Coordination Mechanism
- Building Chinese Biomedical Language Models via Multi-Level Text Discrimination
- Causal Transformers Perform Below Chance on Recursive Nested Constructions, Unlike Humans
- Solving Large Break Minimization Problems in a Mirrored Double Round-robin Tournament Using Quantum Annealing
- On the difficulty of learning chaotic dynamics with RNNs
- HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Media
- On the Stability of Low Pass Graph Filter With a Large Number of Edge Rewires
- Procrastinated Tree Search: Black-box Optimization with Delayed, Noisy, and Multi-Fidelity Feedback
- Learning a Compressive Sensing Matrix with Structural Constraints via Maximum Mean Discrepancy Optimization
- Improve Cross-lingual Voice Cloning Using Low-quality Code-switched Data
- A Dual-Attention Neural Network for Pun Location and Using Pun-Gloss Pairs for Interpretation
- Task-Driven Deep Image Enhancement Network for Autonomous Driving in Bad Weather
- SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing
- Unrolled Variational Bayesian Algorithm for Image Blind Deconvolution
- Coarse to Fine: Video Retrieval before Moment Localization
- Rethinking Self-Supervision Objectives for Generalizable Coherence Modeling
- Semi-supervised Multi-task Learning for Semantics and Depth
- CNN-DST: ensemble deep learning based on Dempster-Shafer theory for vibration-based fault recognition
- Why Propagate Alone? Parallel Use of Labels and Features on Graphs
- Revisiting IPA-based Cross-lingual Text-to-speech
- VLBInet: Radio Interferometry Data Classification for EHT with Neural Networks
- Self-Supervised Domain Adaptation for Visual Navigation with Global Map Consistency
- Adversarial examples by perturbing high-level features in intermediate decoder layers
- Relation-aware Heterogeneous Graph for User Profiling
- Context-gloss Augmentation for Improving Word Sense Disambiguation
- SGoLAM: Simultaneous Goal Localization and Mapping for Multi-Object Goal Navigation
- CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarization
- Semantically Distributed Robust Optimization for Vision-and-Language Inference
- Neural Attention-Aware Hierarchical Topic Model
- Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence
- Interpreting the Robustness of Neural NLP Models to Textual Perturbations
- DeepSSM: A Blueprint for Image-to-Shape Deep Learning Models
- Cross-Lingual Open-Domain Question Answering with Answer Sentence Generation
- Unsupervised Data-Driven Nuclei Segmentation For Histology Images
- bert2BERT: Towards Reusable Pretrained Language Models
- SoGCN: Second-Order Graph Convolutional Networks
- A CLIP-Enhanced Method for Video-Language Understanding
- Region Semantically Aligned Network for Zero-Shot Learning
- Deconfounded Causal Collaborative Filtering
- Secure Precoding in MIMO-NOMA: A Deep Learning Approach
- Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools
- Nuisance-Label Supervision: Robustness Improvement by Free Labels
- On the Sample Complexity of Decentralized Linear Quadratic Regulator with Partially Nested Information Structure
- Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast
- Video-based cattle identification and action recognition
- A Cubic Regularization Approach for Finding Local Minimax Points in Nonconvex Minimax Optimization
- A Comprehensive Study on Torchvision Pre-trained Models for Fine-grained Inter-species Classification
- Identifying Introductions in Podcast Episodes from Automatically Generated Transcripts
- MIMICause: Representation and automatic extraction of causal relation types from clinical notes