Papers
Mon 13 Sep 2021
211 papers
- STraTA: Self-Training with Task Augmentation for Better Few-shot LearningSynthetic data and self-improvement for LLMs → Self-training for few-shot NLP
- KroneckerBERT: Learning Kronecker Decomposition for Pre-trained Language Models via Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
- Neural Network Guided Evolutionary Fuzzing for Finding Traffic Violations of Autonomous VehiclesEnd-to-end autonomous driving → Adversarial scenarios and safety testing
- Cross Domain Robot Imitation with Invariant RepresentationOffline RL and imitation learning from data → Imitation learning methods
- UniMS: A Unified Framework for Multimodal Summarization with Knowledge DistillationKnowledge distillation → Multimodal distillation
- How to Select One Among All? An Extensive Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language UnderstandingKnowledge distillation → Knowledge distillation for LLMs
- Abstract, Rationale, Stance: A Joint Model for Scientific Claim Verification
- Towards Fine-Grained Reasoning for Fake News Detection
- TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognition
- Fine Grained Human Evaluation for English-to-Chinese Machine Translation: A Case Study on Scientific Text
- Robust Multi-Domain Mitosis Detection
- The Concept of Semantic Value in Social Network Analysis: an Application to Comparative Mythology
- Meta-Path-based Fake News Detection Leveraging Multi-level Social Context Information
- Studying Fake News Spreading, Polarisation Dynamics, and Manipulation by Bots: a Tale of Networks and Language
- Auditing the Imputation Effect on Fairness of Predictive Analytics in Higher Education
- Predicting the outcome of team movements -- Player time series analysis using fuzzy and deep methods for representation learning
- AliMe MKG: A Multi-modal Knowledge Graph for Live-streaming E-commerce
- InceptionXML: A Lightweight Framework with Synchronized Negative Sampling for Short Text Extreme Classification
- Robust Contrastive Active Learning with Feature-guided Query Strategies
- Specified Certainty Classification, with Application to Read Classification for Reference-Guided Metagenomic Assembly
- Learnable Discrete Wavelet Pooling (LDW-Pooling) For Convolutional Networks
- Policy Optimization Using Semi-parametric Models for Dynamic Pricing
- From Heatmaps to Structural Explanations of Image Classifiers
- Sensor Adversarial Traits: Analyzing Robustness of 3D Object Detection Sensor Fusion Models
- Theoretical Guarantees of Fictitious Discount Algorithms for Episodic Reinforcement Learning and Global Convergence of Policy Gradient Methods
- POPCORN: Progressive Pseudo-labeling with Consistency Regularization and Neighboring
- A Practical Adversarial Attack on Contingency Detection of Smart Energy Systems
- Uncertainty-Aware Machine Translation Evaluation
- Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning
- Physics Driven Domain Specific Transporter Framework with Attention Mechanism for Ultrasound Imaging
- ML Based Lineage in Databases
- Connecting degree and polarity: An artificial language learning study
- Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach
- Evaluating Transferability of BERT Models on Uralic Languages
- safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Robotics
- A Massively Multilingual Analysis of Cross-linguality in Shared Embedding Space
- Mitigating Sampling Bias and Improving Robustness in Active Learning
- Learning Constraints and Descriptive Segmentation for Subevent Detection
- Learning-to-defer for sequential medical decision-making under uncertainty
- State Relevance for Off-Policy Evaluation
- Improving Scheduled Sampling with Elastic Weight Consolidation for Neural Machine Translation
- Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration
- Monocular Camera Localization for Automated Vehicles Using Image Retrieval
- On the regularized risk of distributionally robust learning over deep neural networks
- Graph Algorithms for Multiparallel Word Alignment
- MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Tasks
- Cross-Modality Domain Adaptation for Vestibular Schwannoma and Cochlea Segmentation
- Automatic Tuning of Tensorflow's CPU Backend using Gradient-Free Optimization Algorithms
- Program-to-Circuit: Exploiting GNNs for Program Representation and Circuit Translation
- Post-OCR Document Correction with large Ensembles of Character Sequence-to-Sequence Models
- Evaluating Multiway Multilingual NMT in the Turkic Languages
- Multi-Sentence Resampling: A Simple Approach to Alleviate Dataset Length Bias and Beam-Search Degradation
- Incremental Abstraction in Distributed Probabilistic SLAM Graphs
- Machine Learning for Online Algorithm Selection under Censored Feedback
- The Emergence of the Shape Bias Results from Communicative Efficiency
- When Stability meets Sufficiency: Informative Explanations that do not Overwhelm
- Deep Generative Models to Extend Active Directory Graphs with Honeypot Users
- TREATED:Towards Universal Defense against Textual Adversarial Attacks
- Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN
- CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
- On the Sins of Image Synthesis Loss for Self-supervised Depth Estimation
- SPARQLing Database Queries from Intermediate Question Decompositions
- Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Image
- Augmenting Decision Making via Interactive What-If Analysis
- SituatedQA: Incorporating Extra-Linguistic Contexts into QA
- Relaxed Marginal Consistency for Differentially Private Query Answering
- Image Shape Manipulation from a Single Augmented Training Sample
- DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection
- On Tilted Losses in Machine Learning: Theory and Applications
- Application of Machine Learning in Early Recommendation of Cardiac Resynchronization Therapy
- Neuro-Symbolic AI: An Emerging Class of AI Workloads and their Characterization
- Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color
- Knowledge Graph-based Neurodegenerative Diseases and Diet Relationship Discovery
- Discovering the Unknown Knowns: Turning Implicit Knowledge in the Dataset into Explicit Training Examples for Visual Question Answering
- Blood vessel segmentation in en-face OCTA images: a frequency based method
- Beyond Isolated Utterances: Conversational Emotion Recognition
- Weakly Supervised Person Search with Region Siamese Networks
- NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic Rewriting into Gender-Neutral Alternatives
- Joint prediction of truecasing and punctuation for conversational speech in low-resource scenarios
- Uniform Generalization Bounds for Overparameterized Neural Networks
- The mathematics of adversarial attacks in AI -- Why deep learning is unstable despite the existence of stable neural networks
- The Grammar-Learning Trajectories of Neural Language Models
- Nonlinear matrix recovery using optimization on the Grassmann manifold
- Single-stream CNN with Learnable Architecture for Multi-source Remote Sensing Data
- Direct Advantage Estimation
- Concept Drift Detection in Federated Networked Systems
- On Pursuit of Designing Multi-modal Transformer for Video Grounding
- xGQA: Cross-Lingual Visual Question Answering
- Online Influence Maximization under the Independent Cascade Model with Node-Level Feedback
- Learning to Act and Observe in Partially Observable Domains
- On Language Models for Creoles
- An End-to-end Point of Interest (POI) Conflation Framework
- Packed Levitated Marker for Entity and Relation Extraction
- Learning Indoor Inverse Rendering with 3D Spatially-Varying Lighting
- Few-Shot Cross-Lingual Stance Detection with Sentiment-Based Pre-Training
- Augmented Abstractive Summarization With Document-LevelSemantic Graph
- Correcting the User Feedback-Loop Bias for Recommendation Systems
- Traffic Event Detection as a Slot Filling Problem
- Formalizing and Estimating Distribution Inference Risks
- Graph-based Retrieval for Claim Verification over Cross-Document Evidence
All 211
- When is Wall a Pared and when a Muro? -- Extracting Rules Governing Lexical Selection
- Learning to Ground Visual Objects for Visual Dialog
- Mutual Supervision for Dense Object Detection
- Keyword Extraction for Improved Document Retrieval in Conversational Search
- Balancing the Budget: Feature Selection and Tracking for Multi-Camera Visual-Inertial Odometry
- Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations
- Analysing Mixed Initiatives and Search Strategies during Conversational Search
- Adapting the Tesseract Open-Source OCR Engine for Tamil and Sinhala Legacy Fonts and Creating a Parallel Corpus for Tamil-Sinhala-English
- A deep learning guided memetic framework for graph coloring problems
- Task Guided Compositional Representation Learning for ZDA
- FaiREO: User Group Fairness for Equality of Opportunity in Course Recommendation
- Cross-Market Product Recommendation
- Vision-based system identification and 3D keypoint discovery using dynamics constraints
- Adversarial Examples for Evaluating Math Word Problem Solvers
- Low-Light Image Enhancement with Normalizing Flow
- r-GAT: Relational Graph Attention Network for Multi-Relational Graphs
- Efficient Multiple Constraint Acquisition
- Evolving Architectures with Gradient Misalignment toward Low Adversarial Transferability
- Online Learning of Optimally Diverse Rankings
- Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework
- Learning-Based UE Classification in Millimeter-Wave Cellular Systems With Mobility
- WeakSTIL: Weak whole-slide image level stromal tumor infiltrating lymphocyte scores are all you need
- Nonlocal Patch-Based Fully-Connected Tensor Network Decomposition for Remote Sensing Image Inpainting
- Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images
- Explaining Deep Learning Representations by Tracing the Training Process
- Cardinality Estimation in DBMS: A Comprehensive Benchmark Evaluation
- Construction of Grid Operators for Multilevel Solvers: a Neural Network Approach
- Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering
- Towards Stochastic Fault-tolerant Control using Precision Learning and Active Inference
- On Solving a Stochastic Shortest-Path Markov Decision Process as Probabilistic Inference
- Conditional MoCoGAN for Zero-Shot Video Generation
- Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions
- Prediction of gene expression time series and structural analysis of gene regulatory networks using recurrent neural networks
- IceNet for Interactive Contrast Enhancement
- Categorical Semantics of Reversible Pattern-Matching
- Process Discovery Using Graph Neural Networks
- Adversarial Bone Length Attack on Action Recognition
- Zeroth-order non-convex learning via hierarchical dual averaging
- Variational Disentanglement for Domain Generalization
- Improving the Robustness of Adversarial Attacks Using an Affine-Invariant Gradient Estimator
- Self supervised learning improves dMMR/MSI detection from histology slides across multiple cancers
- End-to-End Entity Resolution and Question Answering Using Differentiable Knowledge Graphs
- Leveraging Clinical Characteristics for Improved Deep Learning-Based Kidney Tumor Segmentation on CT
- Exploring a Unified Sequence-To-Sequence Transformer for Medical Product Safety Monitoring in Social Media
- Expanding End-to-End Question Answering on Differentiable Knowledge Graphs with Intersection
- MLFW: A Database for Face Recognition on Masked Faces
- DisCERN:Discovering Counterfactual Explanations using Relevance Features from Neighbourhoods
- Show Me How To Revise: Improving Lexically Constrained Sentence Generation with XLNet
- Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions
- Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models
- Perceptions of Fairness and Trustworthiness Based on Explanations in Human vs. Automated Decision-Making
- DSNet: A Dual-Stream Framework for Weakly-Supervised Gigapixel Pathology Image Analysis
- The State of the Art when using GPUs in Devising Image Generation Methods Using Deep Learning
- Effectiveness of Pre-training for Few-shot Intent Classification
- Deep Joint Source-Channel Coding for Multi-Task Network
- Text is NOT Enough: Integrating Visual Impressions into Open-domain Dialogue Generation
- Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks
- Fast Variational AutoEncoder with Inverted Multi-Index for Collaborative Filtering
- Wine is Not v i n. -- On the Compatibility of Tokenizations Across Languages
- Perturbation CheckLists for Evaluating NLG Evaluation Metrics
- Computation Rate Maximum for Mobile Terminals in UAV-assisted Wireless Powered MEC Networks with Fairness Constraint
- DHA: End-to-End Joint Optimization of Data Augmentation Policy, Hyper-parameter and Architecture
- Global-Local Dynamic Feature Alignment Network for Person Re-Identification
- Adversarially Trained Object Detector for Unsupervised Domain Adaptation
- Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization
- Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning
- GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks
- Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal Intervention
- ChangeChip: A Reference-Based Unsupervised Change Detection for PCB Defect Detection
- Fine-grained Entity Typing via Label Reasoning
- Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation
- HCDG: A Hierarchical Consistency Framework for Domain Generalization on Medical Image Segmentation
- CEM: Commonsense-aware Empathetic Response Generation
- Region Invariant Normalizing Flows for Mobility Transfer
- Effective Tensor Completion via Element-wise Weighted Low-rank Tensor Train with Overlapping Ket Augmentation
- CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation
- ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment
- Low-Shot Validation: Active Importance Sampling for Estimating Classifier Performance on Rare Categories
- Fine-Grained Few Shot Learning with Foreground Object Transformation
- MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations
- Autonomous Navigation of Underactuated Bipedal Robots in Height-Constrained Environments
- Contrastive Learning for Context-aware Neural Machine TranslationUsing Coreference Information
- Robust Stability of Neural Network-controlled Nonlinear Systems with Parametric Variability
- Rethinking Lightweight Convolutional Neural Networks for Efficient and High-quality Pavement Crack Detection
- Mitigating Language-Dependent Ethnic Bias in BERT
- Applications of Recurrent Neural Network for Biometric Authentication & Anomaly Detection
- Exploiting Heterogeneity in Robust Federated Best-Arm Identification
- Detecting Textual Adversarial Examples through Randomized Substitution and Vote
- Finding Representative Group Fairness Metrics Using Correlation Estimations
- PAT: Pseudo-Adversarial Training For Detecting Adversarial Videos
- SCORE-IT: A Machine Learning-based Tool for Automatic Standardization of EEG Reports
- RADARS: Memory Efficient Reinforcement Learning Aided Differentiable Neural Architecture Search
- Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning
- Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition
- Barzilai and Borwein conjugate gradient method equipped with a non-monotone line search technique and its application on non-negative matrix factorization
- Reinforcement Learning for Load-balanced Parallel Particle Tracing
- An Adaptive Boosting Technique to Mitigate Popularity Bias in Recommender System
- Domain and Content Adaptive Convolution based Multi-Source Domain Generalization for Medical Image Segmentation
- Online Unsupervised Learning of Visual Representations and Categories
- Real-Time EMG Signal Classification via Recurrent Neural Networks
- FaceGuard: Proactive Deepfake Detection
- Shape-Biased Domain Generalization via Shock Graph Embeddings
- UMPNet: Universal Manipulation Policy Network for Articulated Objects
- AMI-FML: A Privacy-Preserving Federated Machine Learning Framework for AMI
- CANS: Communication Limited Camera Network Self-Configuration for Intelligent Industrial Surveillance
- Unsupervised domain adaptation for cross-modality liver segmentation via joint adversarial learning and self-learning
- Training Fair Models in Federated Learning without Data Privacy Infringement
- Source Inference Attacks in Federated Learning
- Restricted Hidden Cardinality Constraints in Causal Models
- Inferential Wasserstein Generative Adversarial Networks
- SHAPE: Shifted Absolute Position Embedding for Transformers