Papers
Fri 11 Jun 2021
188 papers
- Corruption-Robust Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Policy Gradient Bayesian Robust Optimization for Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- Keyframe-Focused Visual Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
- Offline Reinforcement Learning as Anti-ExplorationOffline RL and imitation learning from data → Offline RL algorithms
- PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive PriorDiffusion models → Audio, speech and music
- Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word SubstitutionLLM safety and security → Backdoor and data poisoning attacks
- On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student SettingKnowledge distillation → General knowledge distillation methods
- Generate, Annotate, and Learn: NLP with Synthetic TextKnowledge distillation → Knowledge distillation for LLMs
- Exploiting Large-scale Teacher-Student Training for On-device Acoustic ModelsKnowledge distillation → Speech and audio distillation
- Adversarial purification with Score-based generative modelsDiffusion models → Robustness, privacy and adversarial aspects
- Evaluating Deep Neural Networks for Image Document Enhancement
- Differentially Private Algorithms for Clustering with Stability Assumptions
- Analysis of the Evolution of Parametric Drivers of High-End Sea-Level Hazards
- Transformer-based Spatial-Temporal Feature Learning for EEG Decoding
- Scaling Laws for Acoustic Models
- RefBERT: Compressing BERT by Referencing to Pre-computed Representations
- ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection
- Cardiovascular Disease Prediction using Recursive Feature Elimination and Gradient Boosting Classification Techniques
- EPICURE Ensemble Pretrained Models for Extracting Cancer Mutations from Literature
- Posterior Temperature Optimization in Variational Inference for Inverse Problems
- Time Series Anomaly Detection with label-free Model Selection
- Cross-replication Reliability -- An Empirical Approach to Interpreting Inter-rater Reliability
- Federated Learning with Buffered Asynchronous Aggregation
- CAR-Net: Unsupervised Co-Attention Guided Registration Network for Joint Registration and Structure Learning
- Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR
- Optimal Counterfactual Explanations in Tree Ensembles
- Mirror3D: Depth Refinement for Mirror Surfaces
- Relaxing Local Robustness
- Pay Attention with Focus: A Novel Learning Scheme for Classification of Whole Slide Images
- Piecewise-constant Neural ODEs
- Robust Representation Learning via Perceptual Similarity Metrics
- Learning Competitive Equilibria in Exchange Economies with Bandit Feedback
- Precise characterization of the prior predictive distribution of deep ReLU networks
- A New Formalism, Method and Open Issues for Zero-Shot Coordination
- Scalars are universal: Equivariant machine learning, structured like classical physics
- Statistical Analysis from the Fourier Integral Theorem
- Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization
- Modeling Language Usage and Listener Engagement in Podcasts
- A Shuffling Framework for Local Differential Privacy
- Break-It-Fix-It: Unsupervised Learning for Program Repair
- Leveraging Pre-trained Language Model for Speech Sentiment Analysis
- Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect
- Toward Accurate and Realistic Outfits Visualization with Attention to Details
- Dise~no y desarrollo de aplicaci'on m'ovil para la clasificaci'on de flora nativa chilena utilizando redes neuronales convolucionales
- Visualization Techniques to Enhance Automated Event Extraction
- Classification algorithms applied to structure formation simulations
- Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns
- Deception Detection and Remote Physiological Monitoring: A Dataset and Baseline Experimental Results
- Federated Learning with Spiking Neural Networks
- A3C-S: Automated Agent Accelerator Co-Search towards Efficient Deep Reinforcement Learning
- Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators
- Understanding Deflation Process in Over-parametrized Tensor Decomposition
- Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology Problems
- GANs N' Roses: Stable, Controllable, Diverse Image to Image Translation (works for videos too!)
- HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers
- Robust Knowledge Graph Completion with Stacked Convolutions and a Student Re-Ranking Network
- Label Noise SGD Provably Prefers Flat Global Minimizers
- The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective
- Local Explanation of Dialogue Response Generation
- Online Continual Adaptation with Active Self-Training
- WAX-ML: A Python library for machine learning and feedback loops on streaming data
- Recovery of Meteorites Using an Autonomous Drone and Machine Learning
- N-Best ASR Transformer: Enhancing SLU Performance using Multiple ASR Hypotheses
- Probability Paths and the Structure of Predictions over Time
- Learning the optimal Tikhonov regularizer for inverse problems
- Measuring the robustness of Gaussian processes to kernel choice
- Step-Wise Hierarchical Alignment Network for Image-Text Matching
- Preferential Temporal Difference Learning
- Efficient Deep Learning Architectures for Fast Identification of Bacterial Strains in Resource-Constrained Devices
- How Should Agents Ask Questions For Situated Learning? An Annotated Dialogue Corpus
- An adaptive cognitive sensor node for ECG monitoring in the Internet of Medical Things
- Shallow Optical Flow Three-Stream CNN for Macro- and Micro-Expression Spotting from Long Videos
- Pedestrian Attribute Recognition in Video Surveillance Scenarios Based on View-attribute Attention Localization
- Towards Costless Model Selection in Contextual Bandits: A Bias-Variance Perspective
- Neural Network Modeling of Probabilities for Coding the Octree Representation of Point Clouds
- Multi-Receiver Online Bayesian Persuasion
- Data-Driven Multiscale Design of Cellular Composites with Multiclass Microstructures for Natural Frequency Maximization
- Analyzing the Travel and Charging Behavior of Electric Vehicles -- A Data-driven Approach
- Topological Detection of Trojaned Neural Networks
- Locally Sparse Neural Networks for Tabular Biomedical Data
- Semi-Supervised and Unsupervised Sense Annotation via Translations
- Coded-InvNet for Resilient Prediction Serving Systems
- K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets
- Learning Compositional Shape Priors for Few-Shot 3D Reconstruction
- An Image Forensic Technique Based on JPEG Ghosts
- Feature Selection Tutorial with Python Examples
- Continuous Herded Gibbs Sampling
- Neural Symbolic Regression that Scales
- Catch-A-Waveform: Learning to Generate Audio from a Single Short Example
- A Framework to Enhance Generalization of Deep Metric Learning methods using General Discriminative Feature Learning and Class Adversarial Neural Networks
- Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scales
- Attention-based Partial Face Recognition
- Zero-Shot Controlled Generation with Encoder-Decoder Transformers
- What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data
- Small Object Detection for Near Real-Time Egocentric Perception in a Manual Assembly Scenario
- Decoupled Greedy Learning of CNNs for Synchronous and Asynchronous Distributed Learning
- Deep Conditional Gaussian Mixture Model for Constrained Clustering
- Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment
- Courteous Behavior of Automated Vehicles at Unsignalized Intersections via Reinforcement Learning
- To Beam Or Not To Beam: That is a Question of Cooperation for Language GANs
All 188
- Visualizing Classifier Adjacency Relations: A Case Study in Speaker Verification and Voice Anti-Spoofing
- Conterfactual Generative Zero-Shot Semantic Segmentation
- Nonmyopic Multifidelity Active Search
- Part-aware Panoptic Segmentation
- Proximal Optimal Transport Modeling of Population Dynamics
- SimSwap: An Efficient Framework For High Fidelity Face Swapping
- Understanding approximate and unrolled dictionary learning for pattern recovery
- Invariant Information Bottleneck for Domain Generalization
- TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation
- ViT-Inception-GAN for Image Colourising
- Automatic Risk Adaptation in Distributional Reinforcement Learning
- Topology-Preserved Human Reconstruction with Details
- A Coupled Design of Exploiting Record Similarity for Practical Vertical Federated Learning
- HUI-Audio-Corpus-German: A high quality TTS dataset
- The Complexity of Sparse Tensor PCA
- Survey of Image Based Graph Neural Networks
- DG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm via Langevin Monte Carlo within Gibbs
- A Novel Approach to Lifelong Learning: The Plastic Support Structure
- Dynamic Language Models for Continuously Evolving Content
- Going Beyond Linear Transformers with Recurrent Fast Weight Programmers
- A Discussion on Building Practical NLP Leaderboards: The Case of Machine Translation
- DRLD-SP: A Deep Reinforcement Learning-based Dynamic Service Placement in Edge-Enabled Internet of Vehicles
- Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall
- TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learning
- States of confusion: Eye and Head tracking reveal surgeons' confusion during arthroscopic surgery
- HPO-B: A Large-Scale Reproducible Benchmark for Black-Box HPO based on OpenML
- AugNet: End-to-End Unsupervised Visual Representation Learning with Image Augmentation
- FedNLP: An interpretable NLP System to Decode Federal Reserve Communications
- Model Selection for Bayesian Autoencoders
- Unsupervised Anomaly Detection Ensembles using Item Response Theory
- Safe Reinforcement Learning with Linear Function Approximation
- KRADA: Known-region-aware Domain Alignment for Open-set Domain Adaptation in Semantic Segmentation
- Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks
- A deep learning approach to clustering visual arts
- Enhancing Speaking Styles in Conversational Text-to-Speech Synthesis with Graph-based Multi-modal Context Modeling
- GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
- Sprachsynthese -- State-of-the-Art in englischer und deutscher Sprache
- From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding
- A Cooperative-Competitive Multi-Agent Framework for Auto-bidding in Online Advertising
- Graph Transformer Networks: Learning Meta-path Graphs to Improve GNNs
- Nested and Balanced Entity Recognition using Multi-Task Learning
- CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detection
- Learning to Pool in Graph Neural Networks for Extrapolation
- Towards User-Driven Neural Machine Translation
- LocoProp: Enhancing BackProp via Local Loss Optimization
- CausalAdv: Adversarial Robustness through the Lens of Causality
- MlTr: Multi-label Classification with Transformer
- Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation
- Improving RNN-T ASR Performance with Date-Time and Location Awareness
- Calibration and Auto-Refinement for Light Field Cameras
- Inter-domain Multi-relational Link Prediction
- Taylor Expansion of Discount Factors
- BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data
- HIFI: Anomaly Detection for Multivariate Time Series with High-order Feature Interactions
- Modeling Sequences as Distributions with Uncertainty for Sequential Recommendation
- Hybrid Generative-Contrastive Representation Learning
- Spoken Term Detection Methods for Sparse Transcription in Very Low-resource Settings
- Learning the Precise Feature for Cluster Assignment
- PyGAD: An Intuitive Genetic Algorithm Python Library
- Assessing Political Prudence of Open-domain Chatbots
- Towards Understanding Generalization via Decomposing Excess Risk Dynamics
- On the Robustness of Average Losses for Partial-Label Learning
- Anomalous Sound Detection Using a Binary Classification Model and Class Centroids
- Global Neighbor Sampling for Mixed CPU-GPU Training on Giant Graphs
- NAAQA: A Neural Architecture for Acoustic Question Answering
- Monotonic Neural Network: combining Deep Learning with Domain Knowledge for Chiller Plants Energy Optimization
- DORO: Distributional and Outlier Robust Optimization
- A comprehensive solution to retrieval-based chatbot construction
- Team RUC_AIM3 Technical Report at ActivityNet 2021: Entities Object Localization
- DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning
- Is Homophily a Necessity for Graph Neural Networks?
- Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification
- TellMeWhy: A Dataset for Answering Why-Questions in Narratives
- ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction
- Instance-Level Task Parameters: A Robust Multi-task Weighting Framework
- Differentially Private Federated Learning via Inexact ADMM
- Bridging Subword Gaps in Pretrain-Finetune Paradigm for Natural Language Generation
- Twin Neural Network Regression is a Semi-Supervised Regression Algorithm
- A Unified Framework for Constructing Nonconvex Regularizations
- Self-supervise, Refine, Repeat: Improving Unsupervised Anomaly Detection
- Interpreting Expert Annotation Differences in Animal Behavior
- Spectral Unsupervised Domain Adaptation for Visual Recognition
- Assessing the Effectiveness of Syntactic Structure to Learn Code Edit Representations
- Meta-Adaptive Nonlinear Control: Theory and Algorithms
- Neural Optimization Kernel: Towards Robust Deep Learning
- Sparse Bayesian Learning via Stepwise Regression
- Collaborative Multidisciplinary Design Optimization with Neural Networks
- DECORE: Deep Compression with Reinforcement Learning