Papers
Fri 15 Oct 2021
232 papers
- Trigger Hunting with a Topological Prior for Trojan DetectionLLM safety and security → Backdoor and data poisoning attacks
- Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble ArchitectureLLM safety and security → Membership inference attacks
- From Multimodal to Unimodal Attention in Transformers using Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- Textual Backdoor Attacks Can Be More Harmful via Two Simple TricksLLM safety and security → Backdoor and data poisoning attacks
- Collaborating with Humans without Human DataOffline RL and imitation learning from data → Imitation learning methods
- Value Penalized Q-Learning for Recommender SystemsOffline RL and imitation learning from data → Decision transformers and sequence modeling
- RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP ModelsLLM safety and security → Backdoor and data poisoning attacks
- Multilingual Neural Machine Translation:Can Linguistic Hierarchies Help?Knowledge distillation → Knowledge distillation for LLMs
- ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind
- Detecting Gender Bias in Transformer-based Models: A Case Study on BERT
- Named Entity Recognition in Unstructured Medical Text Documents
- Anticipation-driven Adaptive Architecture for Assisted Living
- Robust physics discovery via supervised and unsupervised pattern recognition using the Euler characteristic
- Resolving Anomalies in the Behaviour of a Modularity Inducing Problem Domain with Distributional Fitness Evaluation
- Data-driven intrinsic localized mode detection and classification in one-dimensional crystal lattice model
- Law Smells: Defining and Detecting Problematic Patterns in Legal Drafting
- Video-Data Pipelines for Machine Learning Applications
- Accelerating Genetic Programming using GPUs
- Continuous Authentication Using Mouse Movements, Machine Learning, and Minecraft
- SleepPriorCL: Contrastive Representation Learning with Prior Knowledge-based Positive Mining and Adaptive Temperature for Sleep Staging
- Keep it Tighter -- A Story on Analytical Mean Embeddings
- SGEN: Single-cell Sequencing Graph Self-supervised Embedding Network
- Using Psychological Characteristics of Situations for Social Situation Comprehension in Support Agents
- Streaming Machine Learning and Online Active Learning for Automated Visual Inspection
- Automatic Detection of COVID-19 and Pneumonia from Chest X-Ray using Deep Learning
- Gait-based Human Identification through Minimum Gait-phases and Sensors
- Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining
- Bridging the gap between paired and unpaired medical image translation
- Surrogate- and invariance-boosted contrastive learning for data-scarce applications in science
- sbp-env: Sampling-based Motion Planners' Testing Environment
- Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks
- Comparing Human and Machine Bias in Face Recognition
- DS-TOD: Efficient Domain Specialization for Task Oriented Dialog
- Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learning
- A Bayesian Approach for Medical Inquiry and Disease Inference in Automated Differential Diagnosis
- Probing as Quantifying Inductive Bias
- Generated Knowledge Prompting for Commonsense Reasoning
- Robust Correlation Clustering with Asymmetric Noise
- Training Conversational Agents with Generative Conversational Networks
- A Neural Network Ensemble Approach to System Identification
- On The Ingredients of an Effective Zero-shot Semantic Parser
- FedSLD: Federated Learning with Shared Label Distribution for Medical Image Classification
- Starkit: RoboCup Humanoid KidSize 2021 Worldwide Champion Team Paper
- Training Dynamics for Text Summarization Models
- Dropping diversity of products of large US firms: Models and measures
- Counting Objects by Diffused Index: geometry-free and training-free approach
- Spatio-temporal extreme event modeling of terror insurgencies
- Clean or Annotate: How to Spend a Limited Data Collection Budget
- Revisiting Popularity and Demographic Biases in Recommender Evaluation and Effectiveness
- Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet
- Differentiable Network Pruning for Microcontrollers
- Towards Transparent Interactive Semantic Parsing via Step-by-Step Correction
- Hyperseed: Unsupervised Learning with Vector Symbolic Architectures
- Return migration of German-affiliated researchers: Analyzing departure and return by gender, cohort, and discipline using Scopus bibliometric data 1996-2020
- Exploratory Lagrangian-Based Particle Tracing Using Deep Learning
- A New Approach for Interpretability and Reliability in Clinical Risk Prediction: Acute Coronary Syndrome Scenario
- Nothing Wasted: Full Contribution Enforcement in Federated Edge Learning
- Control Prefixes for Parameter-Efficient Text Generation
- Solving Image PDEs with a Shallow Network
- On Learning the Transformer Kernel
- Robustness of different loss functions and their impact on networks learning capability
- Efficient privacy-preserving inference for convolutional neural networks
- Dynamic probabilistic logic models for effective abstractions in RL
- 3D Human Pose Estimation for Free-form Activity Using WiFi Signals
- Reduced Order Dynamical Models For Complex Dynamics in Manufacturing and Natural Systems Using Machine Learning
- GrowSpace: Learning How to Shape Plants
- Memory-augmented Adversarial Autoencoders for Multivariate Time-series Anomaly Detection with Deep Reconstruction and Prediction
- The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail
- ASPECTNEWS: Aspect-Oriented Summarization of News Documents
- Nonlinear proper orthogonal decomposition for convection-dominated flows
- Coherence boosting: When your pretrained language model is not paying enough attention
- Tree-based local explanations of machine learning model predictions, AraucanaXAI
- Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations
- Explainable Student Performance Prediction With Personalized Attention for Explaining Why A Student Fails
- PG2Net: Personalized and Group Preferences Guided Network for Next Place Prediction
- Knowledge-driven Active Learning
- Self-supervised Contrastive Attributed Graph Clustering
- FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling
- Direct Simultaneous Speech-to-Speech Translation with Variational Monotonic Multihead Attention
- Probabilistic Time Series Forecasts with Autoregressive Transformation Models
- Tricks for Training Sparse Translation Models
- Rule Induction in Knowledge Graphs Using Linear Programming
- Performance, Successes and Limitations of Deep Learning Semantic Segmentation of Multiple Defects in Transmission Electron Micrographs
- Neural Dubber: Dubbing for Videos According to Scripts
- Intent-based Product Collections for E-commerce using Pretrained Language Models
- Learn Proportional Derivative Controllable Latent Space from Pixels
- Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction
- Cross-Domain Data Integration for Named Entity Disambiguation in Biomedical Text
- Guiding Visual Question Generation
- Simultaneous Missing Value Imputation and Structure Learning with Groups
- DialFact: A Benchmark for Fact-Checking in Dialogue
- Combining Diverse Feature Priors
- Choice functions based multi-objective Bayesian optimisation
- From Start to Finish: Latency Reduction Strategies for Incremental Speech Synthesis in Simultaneous Speech-to-Speech Translation
- Towards Identity Preserving Normal to Dysarthric Voice Conversion
- NNK-Means: Data summarization using dictionary learning with non-negative kernel regression
- Astronomical source finding services for the CIRASA visual analytic platform
- Multitask Prompted Training Enables Zero-Shot Task Generalization
- Fast Online Changepoint Detection via Functional Pruning CUSUM statistics
- Shared Visual Representations of Drawing for Communication: How do different biases affect human interpretability and intent?
All 232
- Evaluation of Hyperparameter-Optimization Approaches in an Industrial Federated Learning System
- BBQ: A Hand-Built Bias Benchmark for Question Answering
- Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation
- Why don't people use character-level machine translation?
- Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm
- Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation
- Crop Rotation Modeling for Deep Learning-Based Parcel Classification from Satellite Time Series
- Propagation on Multi-relational Graphs for Node Regression
- The World of an Octopus: How Reporting Bias Influences a Language Model's Perception of Color
- MixQG: Neural Question Generation with Mixed Answer Types
- Rewire-then-Probe: A Contrastive Recipe for Probing Biomedical Knowledge of Pre-trained Language Models
- Simulation of emergence in artificial societies: a practical model-based approach with the EB-DEVS formalism
- Containerized Distributed Value-Based Multi-Agent Reinforcement Learning
- DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization
- Accurate Fine-grained Layout Analysis for the Historical Tibetan Document Based on the Instance Segmentation
- Online False Discovery Rate Control for LORD & SAFFRON Under Positive, Local Dependence
- Kronecker Decomposition for GPT Compression
- mLUKE: The Power of Entity Representations in Multilingual Pretrained Language Models
- Halpern-Type Accelerated and Splitting Algorithms For Monotone Inclusions
- milIE: Modular & Iterative Multilingual Open Information Extraction
- Multi-Tailed, Multi-Headed, Spatial Dynamic Memory refined Text-to-Image Synthesis
- Convergence of Laplacian Eigenmaps and its Rate for Submanifolds with Singularities
- Trade-offs of Local SGD at Scale: An Empirical Study
- Breaking Down Multilingual Machine Translation
- Label-Wise Graph Convolutional Network for Heterophilic Graphs
- Effects of Different Optimization Formulations in Evolutionary Reinforcement Learning on Diverse Behavior Generation
- Few-Shot Bot: Prompt-Based Learning for Dialogue Systems
- Hand Me Your PIN! Inferring ATM PINs of Users Typing with a Covered Hand
- An active learning approach for improving the performance of equilibrium based chemical simulations
- Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings
- An Artificial Neural Network-Based Model Predictive Control for Three-phase Flying Capacitor Multi-Level Inverter
- A Review of Evolutionary Multi-objective Clustering Approaches
- Jurassic is (almost) All You Need: Few-Shot Meaning-to-Text Generation for Open-Domain Dialogue
- Equivariant and Invariant Reynolds Networks
- Using DeepProbLog to perform Complex Event Processing on an Audio Stream
- Causal Identification with Additive Noise Models: Quantifying the Effect of Noise
- Prediction of Lung CT Scores of Systemic Sclerosis by Cascaded Regression Neural Networks
- Gradient Descent on Infinitely Wide Neural Networks: Global Convergence and Generalization
- Deep multi-modal aggregation network for MR image reconstruction with auxiliary modality
- Automated Quality Control of Vacuum Insulated Glazing by Convolutional Neural Network Image Classification
- SAT Encodings for Pseudo-Boolean Constraints Together With At-Most-One Constraints
- Dual-Arm Adversarial Robot Learning
- FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes
- Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits
- Compressive Independent Component Analysis: Theory and Algorithms
- Adversarial Attacks on ML Defense Models Competition
- Generating Natural Language Adversarial Examples through An Improved Beam Search Algorithm
- UniDS: A Unified Dialogue System for Chit-Chat and Task-oriented Dialogues
- Identifying Incorrect Classifications with Balanced Uncertainty
- Improving Hyperparameter Optimization by Planning Ahead
- StreaMulT: Streaming Multimodal Transformer for Heterogeneous and Arbitrary Long Sequential Data
- Multimodal Emotion-Cause Pair Extraction in Conversations
- Structural Characterization for Dialogue Disentanglement
- Efficiently Solve the Max-cut Problem via a Quantum Qubit Rotation Algorithm
- Crisis Domain Adaptation Using Sequence-to-sequence Transformers
- Joint Channel and Weight Pruning for Model Acceleration on Moblie Devices
- A Survey on State-of-the-art Techniques for Knowledge Graphs Construction and Challenges ahead
- Modeling Proficiency with Implicit User Representations
- Transformer-based Multi-task Learning for Disaster Tweet Categorisation
- MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining
- A Broad-persistent Advising Approach for Deep Interactive Reinforcement Learning in Robotic Environments
- Pyramid Correlation based Deep Hough Voting for Visual Object Tracking
- Pose-guided Generative Adversarial Net for Novel View Action Synthesis
- BayesAoA: A Bayesian method for Computation Efficient Angle of Arrival Estimation
- On Generating Identifiable Virtual Faces
- On-Policy Model Errors in Reinforcement Learning
- NeuroLKH: Combining Deep Learning Model with Lin-Kernighan-Helsgaun Heuristic for Solving the Traveling Salesman Problem
- Scribosermo: Fast Speech-to-Text models for German and other Languages
- Reappraising Domain Generalization in Neural Networks
- Tracing Origins: Coreference-aware Machine Reading Comprehension
- Low-rank Matrix Recovery With Unknown Correspondence
- Don't speak too fast: The impact of data bias on self-supervised speech models
- Attention-based Estimation and Prediction of Human Intent to augment Haptic Glove aided Control of Robotic Hand
- Wasserstein Unsupervised Reinforcement Learning
- Identifying Causal Influences on Publication Trends and Behavior: A Case Study of the Computational Linguistics Community
- Unifying Cross-lingual Summarization and Machine Translation with Compression Rate
- Relation Preserving Triplet Mining for Stabilising the Triplet Loss in Re-identification Systems
- Anomaly Detection in Multi-Agent Trajectories for Automated Driving
- Content Preserving Image Translation with Texture Co-occurrence and Spatial Self-Similarity for Texture Debiasing and Domain Adaptation
- Combining CNNs With Transformer for Multimodal 3D MRI Brain Tumor Segmentation With Self-Supervised Pretraining
- Estimating the Level and Direction of Phonetic Dialect Change in the Northern Netherlands
- Learning to Infer Kinematic Hierarchies for Novel Object Instances
- SaLinA: Sequential Learning of Agents
- Multilingual Speech Recognition using Knowledge Transfer across Learning Processes
- Towards Better Plasticity-Stability Trade-off in Incremental Learning: A Simple Linear Connector
- SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer
- Certainty Modeling of a Decision Support System for Mobile Monitoring of Exercise induced Respiratory Conditions
- Improving Unsupervised Domain Adaptive Re-Identification via Source-Guided Selection of Pseudo-Labeling Hyperparameters
- A Machine Learning Approach for Delineating Similar Sound Symptoms of Respiratory Conditions on a Smartphone
- ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network
- PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation
- ktexttt-experts -- Online Policies and Fundamental Limits
- Advances and Challenges in Deep Lip Reading
- Single volume lung biomechanics from chest computed tomography using a mode preserving generative adversarial network
- Graph Neural Networks with Learnable Structural and Positional Representations
- Role Similarity Metric Based on Spanning Rooted Forest
- Socially Aware Bias Measurements for Hindi Language Representations
- DPGNN: Dual-Perception Graph Neural Network for Representation Learning
- FedMe: Federated Learning via Model Exchange
- Exploring Universal Intrinsic Task Subspace via Prompt Tuning
- Receptive Field Broadening and Boosting for Salient Object Detection
- Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation
- Hierarchical Curriculum Learning for AMR Parsing
- End-to-End Segmentation-based News Summarization
- Modeling Endorsement for Multi-Document Abstractive Summarization
- FOLD-R++: A Scalable Toolset for Automated Inductive Learning of Default Theories from Mixed Data
- ESPnet2-TTS: Extending the Edge of TTS Research
- Cross-Lingual Fine-Grained Entity Typing
- Span Detection for Aspect-Based Sentiment Analysis in Vietnamese
- A Modern Analysis of Aging Machine Learning Based IoT Cybersecurity Methods
- FedSEAL: Semi-Supervised Federated Learning with Self-Ensemble Learning and Negative Learning
- DirectQuote: A Dataset for Direct Quotation Extraction and Attribution in News Articles
- Machine Learning Algorithms In User Authentication Schemes
- On Extending Amdahl's law to Learn Computer Performance
- Gait-based Frailty Assessment using Image Representation of IMU Signals and Deep CNN
- Meta-learning via Language Model In-context Tuning
- Cascaded Fast and Slow Models for Efficient Semantic Code Search
- Towards Statistical and Computational Complexities of Polyak Step Size Gradient Descent
- PTQ-SL: Exploring the Sub-layerwise Post-training Quantization
- Provable Regret Bounds for Deep Online Learning and Control
- Alternative Input Signals Ease Transfer in Multilingual Machine Translation
- Attacking Open-domain Question Answering by Injecting Misinformation
- Adversarial Purification through Representation Disentanglement
- EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation
- Occupancy Estimation from Thermal Images
- A Multilingual Bag-of-Entities Model for Zero-Shot Cross-Lingual Text Classification
- DG-Labeler and DGL-MOTS Dataset: Boost the Autonomous Driving Perception
- Gaussian Process Bandit Optimization with Few Batches
- Learning the Koopman Eigendecomposition: A Diffeomorphic Approach
- Scalable Causal Structure Learning: Scoping Review of Traditional and Deep Learning Algorithms and New Opportunities in Biomedicine
- Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite Images
- NeuroView: Explainable Deep Network Decision Making