Papers
Thu 9 Sep 2021
182 papers
- SanitAIs: Unsupervised Data Augmentation to Sanitize Trojaned Neural NetworksLLM safety and security → Backdoor and data poisoning attacks
- NEAT: Neural Attention Fields for End-to-End Autonomous DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
- Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic DataSynthetic data and self-improvement for LLMs → LLM synthetic data generation
- OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution MatchingOffline RL and imitation learning from data → Inverse reinforcement learning
- Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax LossMixture-of-experts → Vision mixture-of-experts
- Learning Forceful Manipulation Skills from Multi-modal Human DemonstrationsOffline RL and imitation learning from data → Robot learning from demonstration
- Fixing exposure bias with imitation learning needs powerful oraclesOffline RL and imitation learning from data → Imitation learning methods
- Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization
- Efficient Measuring of Readability to Improve Documents Accessibility for Arabic Language Learners
- A literature survey on student feedback assessment tools and their usage in sentiment analysis
- Modeling Systems with Machine Learning based Differential Equations
- A Large-Scale Study of Machine Translation in the Turkic Languages
- BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation
- Graph-Based Decoding for Task Oriented Semantic Parsing
- Trust your neighbors: A comprehensive survey of neighborhood-based methods for recommender systems
- Speechformer: Reducing Information Loss in Direct Speech Translation
- Object recognition for robotics from tactile time series data utilising different neural network architectures
- Deciphering Environmental Air Pollution with Large Scale City Data
- Open-World Distributed Robot Self-Localization with Transferable Visual Vocabulary and Both Absolute and Relative Features
- TENET: Temporal CNN with Attention for Anomaly Detection in Automotive Cyber-Physical Systems
- TIAGE: A Benchmark for Topic-Shift Aware Dialog Modeling
- Supervising the Decoder of Variational Autoencoders to Improve Scientific Utility
- Subword Mapping and Anchoring across Languages
- Feature-based Individual Fairness in k-Clustering
- Is Attention Better Than Matrix Decomposition?
- SPECTRA: Sparse Structured Text Rationalization
- SeDyT: A General Framework for Multi-Step Event Forecasting via Sequence Modeling on Dynamic Entity Embeddings
- Math Word Problem Generation with Mathematical Consistency and Problem Context Constraints
- Generic resources are what you need: Style transfer tasks without task-specific parallel training data
- Identifying Morality Frames in Political Tweets using Relational Learning
- FedCon: A Contrastive Framework for Federated Semi-Supervised Learning
- Notes on Generalizing the Maximum Entropy Principle to Uncertain Data
- CrowdDriven: A New Challenging Dataset for Outdoor Visual Localization
- Ergodic Limits, Relaxations, and Geometric Properties of Random Walk Node Embeddings
- Asynchronous Iterations in Optimization: New Sequence Results and Sharper Algorithmic Guarantees
- Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanation
- Filling the Gaps in Ancient Akkadian Texts: A Masked Language Modelling Approach
- Bootstrapped Meta-Learning
- Semantic Parsing in Task-Oriented Dialog with Recursive Insertion-based Encoder
- Truth Discovery in Sequence Labels from Crowds
- Leveraging Local Domains for Image-to-Image Translation
- Mining Points of Interest via Address Embeddings: An Unsupervised Approach
- Neural Latents Benchmark '21: Evaluating latent variable models of neural population activity
- Protein Folding Neural Networks Are Not Robust
- SONIC: A Sparse Neural Network Inference Accelerator with Silicon Photonics for Energy-Efficient Deep Learning
- ConvMLP: Hierarchical Convolutional MLPs for Vision
- Analysis of Language Change in Collaborative Instruction Following
- Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers
- Modeling Massive Spatial Datasets Using a Conjugate Bayesian Linear Regression Framework
- HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints
- FGOT: Graph Distances based on Filters and Optimal Transport
- Extreme Bandits using Robust Statistics
- Detecting and Mitigating Test-time Failure Risks via Model-agnostic Uncertainty Learning
- Talk-to-Edit: Fine-Grained Facial Editing via Dialog
- TxT: Crossmodal End-to-End Learning with Transformers
- AStitchInLanguageModels: Dataset and Methods for the Exploration of Idiomaticity in Pre-Trained Language Models
- Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoring
- Reconstructing and grounding narrated instructional videos in 3D
- Learning with Different Amounts of Annotation: From Zero to Many Labels
- All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality
- Cross-lingual Transfer for Text Classification with Dictionary-based Heterogeneous Graph
- Gradual (In)Compatibility of Fairness Criteria
- Neural-IMLS: Self-supervised Implicit Moving Least-Squares Network for Surface Reconstruction
- Fair Conformal Predictors for Applications in Medical Imaging
- ErfAct and Pserf: Non-monotonic Smooth Trainable Activation Functions
- Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification
- Copy-Move Image Forgery Detection Based on Evolving Circular Domains Coverage
- ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding
- Preservational Learning Improves Self-supervised Medical Image Models by Reconstructing Diverse Contexts
- Dynamic Modeling of Hand-Object Interactions via Tactile Sensing
- IFBiD: Inference-Free Bias Detection
- Tracking Turbulence Through Financial News During COVID-19
- Multi-granularity Textual Adversarial Attack with Behavior Cloning
- Cross DQN: Cross Deep Q Network for Ads Allocation in Feed
- PhysGNN: A Physics-Driven Graph Neural Network Based Model for Predicting Soft Tissue Deformation in Image-Guided Neurosurgery
- NeuralFMU: Towards Structural Integration of FMUs into Neural Networks
- Uncertainty Measures in Neural Belief Tracking and the Effects on Dialogue Policy Performance
- EvilModel 2.0: Bringing Neural Network Models into Malware Attacks
- Eliciting Truthful Reports with Partial Signals in Repeated Games
- UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer
- PPT: Pre-trained Prompt Tuning for Few-shot Learning
- Learning Opinion Summarizers by Selecting Informative Reviews
- Importance sampling based active learning for parametric seismic fragility curve estimation
- Smoothed Contrastive Learning for Unsupervised Sentence Embedding
- Discovery of New Multi-Level Features for Domain Generalization via Knowledge Corruption
- Estimation of Corporate Greenhouse Gas Emissions via Machine Learning
- Accounting for Variations in Speech Emotion Recognition with Nonparametric Hierarchical Neural Network
- Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog Systems
- Continuous Event-Line Constraint for Closed-Form Velocity Initialization
- MATE: Multi-view Attention for Table Transformer Efficiency
- Deep Hough Voting for Robust Global Registration
- Social Media Monitoring for IoT Cyber-Threats
- DAE-PINN: A Physics-Informed Neural Network Model for Simulating Differential-Algebraic Equations with Application to Power Networks
- On the use of Wasserstein metric in topological clustering of distributional data
- Energy Attack: On Transferring Adversarial Examples
- Quantum Machine Learning for Finance
- Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection
- NTS-NOTEARS: Learning Nonparametric DBNs With Prior Knowledge
- Towards Robust Cross-domain Image Understanding with Unsupervised Noise Removal
- Cartography Active Learning
All 182
- M5Product: Self-harmonized Contrastive Learning for E-commercial Multi-modal Pretraining
- Toward a Perspectivist Turn in Ground Truthing for Predictive Computing
- An objective function for order preserving hierarchical clustering
- Learning cortical representations through perturbed and adversarial dreaming
- Online Enhanced Semantic Hashing: Towards Effective and Efficient Retrieval for Streaming Multi-Modal Data
- GNisi: A graph network for reconstructing Ising models from multivariate binarized data
- Supervised Linear Dimension-Reduction Methods: Review, Extensions, and Comparisons
- IICNet: A Generic Framework for Reversible Image Conversion
- MetaXT: Meta Cross-Task Transfer between Disparate Label Spaces
- ECQx: Explainability-Driven Quantization for Low-Bit and Sparse DNNs
- EEGDnet: Fusing Non-Local and Local Self-Similarity for 1-D EEG Signal Denoising with 2-D Transformer
- A Systematic Approach to Group Fairness in Automated Decision Making
- Coordinate Descent Methods for DC Minimization: Optimality Conditions and Global Convergence
- Incentivizing an Unknown Crowd
- KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational Graphs
- Efficient Nearest Neighbor Language Models
- QUINT: Node embedding using network hashing
- DAN: Decentralized Attention-based Neural Network for the MinMax Multiple Traveling Salesman Problem
- Double-Scale Self-Supervised Hypergraph Learning for Group Recommendation
- A distillation-based approach integrating continual learning and federated learning for pervasive services
- Towards Fully Automated Segmentation of Rat Cardiac MRI by Leveraging Deep Learning Frameworks
- Fine-grained Data Distribution Alignment for Post-Training Quantization
- Towards Transferable Adversarial Attacks on Vision Transformers
- Relating Graph Neural Networks to Structural Causal Models
- From Philosophy to Interfaces: an Explanatory Method and a Tool Inspired by Achinstein's Theory of Explanation
- Compositional Clustering: Applications to Multi-Label Object Recognition and Speaker Identification
- Deep Active Inference for Pixel-Based Discrete Control: Evaluation on the Car Racing Problem
- Single Image 3D Object Estimation with Primitive Graph Networks
- Lexico-semantic and affective modelling of Spanish poetry: A semi-supervised learning approach
- Self-supervised Reinforcement Learning with Independently Controllable Subgoals
- DROP: Deep relocating option policy for optimal ride-hailing vehicle repositioning
- PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition
- Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning
- Robot Localization and Navigation through Predictive Processing using LiDAR
- Multilingual Audio-Visual Smartphone Dataset And Evaluation
- Fusing task-oriented and open-domain dialogues in conversational agents
- Tiny CNN for feature point description for document analysis: approach and dataset
- Word-Level Coreference Resolution
- HSMD: An object motion detection algorithm using a Hybrid Spiking Neural Network Architecture
- AutoSmart: An Efficient and Automatic Machine Learning framework for Temporal Relational Data
- MapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extraction
- TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting
- Taming Self-Supervised Learning for Presentation Attack Detection: De-Folding and De-Mixing
- ARMAN: Pre-training with Semantically Selecting and Reordering of Sentences for Persian Abstractive Summarization
- A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation
- Debiasing Methods in Natural Language Understanding Make Bias More Accessible
- An Experimental Study of Class Imbalance in Federated Learning
- Learning Cross-Scale Visual Representations for Real-Time Image Geo-Localization
- Mapping the Structure and Evolution of Software Testing Research Over the Past Three Decades
- Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems
- User Tampering in Reinforcement Learning Recommender Systems
- Risk-Averse Decision Making Under Uncertainty
- DeepEMO: Deep Learning for Speech Emotion Recognition
- Low-Resource Dialogue Summarization with Domain-Agnostic Multi-Source Pretraining
- Self Supervision to Distillation for Long-Tailed Visual Recognition
- Enhanced Speaker-aware Multi-party Multi-turn Dialogue Comprehension
- Table-based Fact Verification with Salience-aware Learning
- BeamTransformer: Microphone Array-based Overlapping Speech Detection
- Application of the Singular Spectrum Analysis on electroluminescence images of thin-film photovoltaic modules
- ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection
- Trust-ya: design of a multiplayer game for the study of small group processes
- New Versions of Gradient Temporal Difference Learning
- Bag of Tricks for Optimizing Transformer Efficiency
- Automated Security Assessment for the Internet of Things
- On the Approximation of Cooperative Heterogeneous Multi-Agent Reinforcement Learning (MARL) using Mean Field Control (MFC)
- Multi-Tensor Network Representation for High-Order Tensor Completion
- Supervised Contrastive Learning for Detecting Anomalous Driving Behaviours from Multimodal Videos
- Distributionally Robust Multilingual Machine Translation
- Graphine: A Dataset for Graph-aware Terminology Definition Generation
- Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation
- Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering
- Popularity Adjusted Block Models are Generalized Random Dot Product Graphs
- Graph Based Network with Contextualized Representations of Turns in Dialogue
- MaterialsAtlas.org: A Materials Informatics Web App Platform for Materials Discovery and Survey of State-of-the-Art
- OpenClinicalAI: enabling AI to diagnose diseases in real-world clinical settings
- Improving Deep Metric Learning by Divide and Conquer
- Competence-based Curriculum Learning for Multilingual Machine Translation
- Deep Reinforcement Learning for Equal Risk Pricing and Hedging under Dynamic Expectile Risk Measures
- Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategies
- Stationary Density Estimation of Ito Diffusions Using Deep Learning
- The challenge of reproducible ML: an empirical study on the impact of bugs
- Detecting Attacks on IoT Devices using Featureless 1D-CNN