Papers
Fri 16 Apr 2021
194 papers
- Membership Inference Attack Susceptibility of Clinical Language ModelsLLM safety and security → Membership inference attacks
- Membership Inference Attacks on Knowledge GraphsLLM safety and security → Membership inference attacks
- FedCom: A Byzantine-Robust Local Model Aggregation Rule Using Data Commitment for Federated LearningLLM safety and security → Federated unlearning and poisoning
- Pylot: A Modular Platform for Exploring Latency-Accuracy Tradeoffs in Autonomous VehiclesEnd-to-end autonomous driving → End-to-end system architecture
- An interactive dashboard for searching and comparing soccer performance scores
- Memorisation versus Generalisation in Pre-trained Language Models
- AMMU : A Survey of Transformer-based Biomedical Pretrained Language Models
- WhatTheWikiFact: Fact-Checking Claims Against Wikipedia
- DEUX: An Attribute-Guided Framework for Sociable Recommendation Dialog Systems
- A digital score of tumour-associated stroma infiltrating lymphocytes predicts survival in head and neck squamous cell carcinoma
- COVID-19 Modeling: A Review
- Structural Beauty: A Structure-based Approach to Quantifying the Beauty of an Image
- Viking: Variational Bayesian Variance Tracking
- Deep Gaussian Processes for Biogeophysical Parameter Retrieval and Model Inversion
- EarthNet2021: A large-scale dataset and challenge for Earth surface forecasting as a guided video prediction task
- Learning-based Compression for Material and Texture Recognition
- HTN Planning Domain for Deployment of Cloud Applications
- Sequential Deconfounding for Causal Inference with Unobserved Confounders
- Inverse Bayesian Optimization: Learning Human Acquisition Functions in an Exploration vs Exploitation Search Task
- LAMPRET: Layout-Aware Multimodal PreTraining for Document Understanding
- Accurate 3D Facial Geometry Prediction by Multi-Task, Multi-Modal, and Multi-Representation Landmark Refinement Network
- Enriching a Model's Notion of Belief using a Persistent Memory
- Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
- Re-TACRED: Addressing Shortcomings of the TACRED Dataset
- Unsupervised Extractive Summarization by Human Memory Simulation
- Learning To Count Everything
- Universal Background Subtraction based on Arithmetic Distribution Neural Network
- Neural String Edit Distance
- "Wikily" Supervised Neural Translation Tailored to Cross-Lingual Tasks
- Optimal Pose and Shape Estimation for Category-level 3D Object Perception
- Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries
- Robust Object Detection via Instance-Level Temporal Cycle Confusion
- Accelerating Sparse Deep Neural Networks
- Concadia: Towards Image-Based Text Generation with a Purpose
- Constructing Robust Emotional State-based Feature with a Novel Voting Scheme for Multi-modal Deception Detection in Videos
- Motion Prediction Performance Analysis for Autonomous Driving Systems and the Effects of Tracking Noise
- Sync-Switch: Hybrid Parameter Synchronization for Distributed Deep Learning
- StylePeople: A Generative Model of Fullbody Human Avatars
- In Defense of the Paper
- I Only Have Eyes for You: The Impact of Masks On Convolutional-Based Facial Expression Recognition
- ESTER: A Machine Reading Comprehension Dataset for Event Semantic Relation Reasoning
- An Analysis of a BERT Deep Learning Strategy on a Technology Assisted Review Task
- Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure Analysis
- On the Robustness to Misspecification of α-Posteriors and Their Variational Approximations
- Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators
- On the Importance of Effectively Adapting Pretrained Language Models for Active Learning
- Multitask Learning for VVC Quality Enhancement and Super-Resolution
- LixCoO2 phase stability studied by machine learning-enabled scale bridging between electronic structure, statistical mechanics and phase field theories
- Surface Form Competition: Why the Highest Probability Answer Isn't Always Right
- High Performance Convolution Using Sparsity and Patterns for Inference in Deep Convolutional Neural Networks
- Does language help generalization in vision models?
- Data Shapley Valuation for Efficient Batch Active Learning
- Neural Transfer Learning for Repairing Security Vulnerabilities in C Code
- Capturing Row and Column Semantics in Transformer Based Question Answering over Tables
- Text2App: A Framework for Creating Android Apps from Text Descriptions
- Learning to Reason for Text Generation from Scientific Tables
- Better Latent Spaces for Better Autoencoders
- Controlled abstention neural networks for identifying skillful predictions for classification problems
- Testing for Outliers with Conformal p-values
- Fusing the Old with the New: Learning Relative Camera Pose with Geometry-Guided Uncertainty
- Divide-and-Conquer for Lane-Aware Diverse Trajectory Prediction
- Learning Evolved Combinatorial Symbols with a Neuro-symbolic Generative Model
- TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval
- Data Augmentation for Voice-Assistant NLU using BERT-based Interchangeable Rephrase
- Adaptive Robust Model Predictive Control with Matched and Unmatched Uncertainty
- Context-Adaptive Document-Level Neural Machine Translation
- Modeling Fuzzy Cluster Transitions for Topic Tracing
- Condenser: a Pre-training Architecture for Dense Retrieval
- proScript: Partially Ordered Scripts Generation via Pre-trained Language Models
- What to Pre-Train on? Efficient Intermediate Task Selection
- Open data for Moroccan license plates for OCR applications : data collection, labeling, and model construction
- Predicting the Binding of SARS-CoV-2 Peptides to the Major Histocompatibility Complex with Recurrent Neural Networks
- Controlled abstention neural networks for identifying skillful predictions for regression problems
- An Adversarially-Learned Turing Test for Dialog Generation Models
- Point-Based Modeling of Human Clothing
- Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base Priors
- MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement
- Flexible Instance-Specific Rationalization of NLP Models
- "BNN - BN = ?": Training Binary Neural Networks without Batch Normalization
- MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale
- Robust Open-Vocabulary Translation from Visual Text Representations
- Why Machine Learning Integrated Patient Flow Simulation?
- Q2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering
- Semantic Image Matting
- IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation
- Probing artificial neural networks: insights from neuroscience
- Towards Standardising Reinforcement Learning Approaches for Production Scheduling Problems
- Spatiotemporal Deformable Scene Graphs for Complex Activity Detection
- PAC-Bayesian Matrix Completion with a Spectral Scaled Student Prior
- TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Prediction
- I Find Your Lack of Uncertainty in Computer Vision Disturbing
- CSAFL: A Clustered Semi-Asynchronous Federated Learning Framework
- Shadow-Mapping for Unsupervised Neural Causal Discovery
- Word2rate: training and evaluating multiple word embeddings as statistical transitions
- Safe Exploration in Model-based Reinforcement Learning using Control Barrier Functions
- Improving Hyper-Relational Knowledge Graph Completion
- Automatic Termination for Hyperparameter Optimization
- Editing Factual Knowledge in Language Models
- Finding Motifs in Knowledge Graphs using Compression
- Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema
All 194
- Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration
- Capturing patterns of variation unique to a specific dataset
- Fast ABC with joint generative modelling and subset simulation
- Counter-Interference Adapter for Multilingual Machine Translation
- An Empirical Study of Graph-Based Approaches for Semi-Supervised Time Series Classification
- Uncertainty Surrogates for Deep Learning
- Supervising Model Attention with Human Explanations for Robust Natural Language Inference
- Towards Variable-Length Textual Adversarial Attacks
- Sharp bounds for the number of regions of maxout networks and vertices of Minkowski sums
- Integrating Domain Knowledge in Data-driven Earth Observation with Process Convolutions
- Automatic quality control of brain T1-weighted magnetic resonance images for a clinical data warehouse
- Exploiting Global and Local Attentions for Heavy Rain Removal on Single Images
- Orthogonal Features Based EEG Signals Denoising Using Fractional and Compressed One-Dimensional CNN AutoEncoder
- Temporal Adaptation of BERT and Performance on Downstream Document Classification: Insights from Social Media
- Grassmann Iterative Linear Discriminant Analysis with Proxy Matrix Optimization
- LU-BZU at SemEval-2021 Task 2: Word2Vec and Lemma2Vec performance in Arabic Word-in-Context disambiguation
- Split Learning Meets Koopman Theory for Wireless Remote Monitoring and Prediction
- Cross-Modal Retrieval Augmentation for Multi-Modal Classification
- Citations are not opinions: a corpus linguistics approach to understanding how citations are made
- Improving Zero-Shot Multi-Lingual Entity Linking
- To Share or not to Share: Predicting Sets of Sources for Model Transfer Learning
- Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models
- MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks
- Signed Distance Function Computation from an Implicit Surface
- ScreenSeg: On-Device Screenshot Layout Analysis
- A Novel Surrogate-assisted Evolutionary Algorithm Applied to Partition-based Ensemble Learning
- TeLCoS: OnDevice Text Localization with Clustering of Script
- Holmes: An Efficient and Lightweight Semantic Based Anomalous Email Detector
- Data Generating Process to Evaluate Causal Discovery Techniques for Time Series Data
- Cost-effective End-to-end Information Extraction for Semi-structured Document Images
- Noise-Aware Video Saliency Prediction
- Temporally smooth online action detection using cycle-consistent future anticipation
- T-LEAP: Occlusion-robust pose estimation of walking cows using temporal information
- Back to the Basics: A Quantitative Analysis of Statistical and Graph-Based Term Weighting Schemes for Keyword Extraction
- Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders
- NoisyCUR: An algorithm for two-cost budgeted matrix completion
- BERT2Code: Can Pretrained Language Models be Leveraged for Code Search?
- On the Complexity of SHAP-Score-Based Explanations: Tractability via Knowledge Compilation and Non-Approximability Results
- Data-Driven 3D Reconstruction of Dressed Humans From Sparse Views
- Implementing CNN Layers on the Manticore Cluster-Based Many-Core Architecture
- ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation
- Efficient and Generic 1D Dilated Convolution Layer for Deep Learning
- Write-a-speaker: Text-based Emotional and Rhythmic Talking-head Generation
- Self-supervised Video Retrieval Transformer Network
- Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image
- Probabilistic water demand forecasting using quantile regression algorithms
- Occlusion-aware Visual Tracker using Spatial Structural Information and Dominant Features
- Language Models are Few-Shot Butlers
- OpenCSI: An Open-Source Dataset for Indoor Localization Using CSI-Based Fingerprinting
- Advanced Deep Networks for 3D Mitochondria Instance Segmentation
- OmniFlow: Human Omnidirectional Optical Flow
- LAI Estimation of Cucumber Crop Based on Improved Fully Convolutional Network
- Towards Human-Understandable Visual Explanations:Imperceptible High-frequency Cues Can Better Be Removed
- Optimal Size-Performance Tradeoffs: Weighing PoS Tagger Models
- A Million Tweets Are Worth a Few Points: Tuning Transformers for Customer Service Tasks
- Broccoli: Sprinkling Lightweight Vocabulary Learning into Everyday Information Diets
- Achieving differential privacy for k-nearest neighbors based outlier detection by data partitioning
- Interval-censored Hawkes processes
- Attention! Stay Focus!
- A Comparative Study on Collecting High-Quality Implicit Reasonings at a Large-scale
- VGNMN: Video-grounded Neural Module Network to Video-Grounded Language Tasks
- An expressiveness hierarchy of Behavior Trees and related architectures
- Weakly Supervised Object Localization and Detection: A Survey
- Hop-Count Based Self-Supervised Anomaly Detection on Attributed Networks
- Augmenting Deep Classifiers with Polynomial Neural Networks
- Intelligent Monitoring of Stress Induced by Water Deficiency in Plants using Deep Learning
- An Empirical Study of Extrapolation in Text Generation with Scalar Control
- MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning
- Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos
- Generating Bug-Fixes Using Pretrained Transformers
- Faithful and Plausible Explanations of Medical Code Predictions
- Higher-Order Attribute-Enhancing Heterogeneous Graph Neural Networks
- Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks
- Probing Across Time: What Does RoBERTa Know and When?
- Histopathology WSI Encoding based on GCNs for Scalable and Efficient Retrieval of Diagnostically Relevant Regions
- A De-raining semantic segmentation network for real-time foreground segmentation
- Deep Stable Learning for Out-Of-Distribution Generalization
- Translational NLP: A New Paradigm and General Principles for Natural Language Processing Research
- Segmenting Subtitles for Correcting ASR Segmentation Errors
- SGL: Spectral Graph Learning from Measurements
- SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network
- Matching-oriented Product Quantization For Ad-hoc Retrieval
- ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning
- Distributed TD(0) with Almost No Communication
- On the Importance of Trust in Next-Generation Networked CPS Systems: An AI Perspective
- Comparison of Grammatical Error Correction Using Back-Translation Models
- Multivalent Entailment Graphs for Question Answering
- Pareto Self-Supervised Training for Few-Shot Learning
- Are Classes Clusters?
- Investigating Failures of Automatic Translation in the Case of Unambiguous Gender
- Cross-lingual Entity Alignment with Adversarial Kernel Embedding and Adversarial Knowledge Translation
- Tracing Topic Transitions with Temporal Graph Clusters
- Human-like informative conversations: Better acknowledgements using conditional mutual information
- A Masked Segmental Language Model for Unsupervised Natural Language Segmentation