Papers
Mon 4 Oct 2021
147 papers
- Uncertainty-Based Offline Reinforcement Learning with Diversified Q-EnsembleOffline RL and imitation learning from data → Offline RL algorithms
- Revisiting Self-Training for Few-Shot Learning of Language ModelSynthetic data and self-improvement for LLMs → Self-training for few-shot NLP
- Optimal Placement of Roadside Infrastructure Sensors towards Safer Autonomous Vehicle DeploymentsEnd-to-end autonomous driving → Cooperative and V2X driving
- A moment-matching metric for latent variable generative models
- Classification of hierarchical text using geometric deep learning: the case of clinical trials corpus
- TBCOV: Two Billion Multilingual COVID-19 Tweets with Sentiment, Entity, Geo, and Gender Labels
- Quantifying the Suicidal Tendency on Social Media: A Survey
- Using Single-Trial Representational Similarity Analysis with EEG to track semantic similarity in emotional word processing
- Modeling Effect of Lockdowns and Other Effects on India Covid-19 Infections Using SEIR Model and Machine Learning
- Posture Recognition in the Critical Care Settings using Wearable Devices
- Towards efficient end-to-end speech recognition with biologically-inspired neural networks
- A Quantum Generative Adversarial Network for distributions
- Solving even-parity problems using traceless genetic programming
- Effects of Multi-Aspect Online Reviews with Unobserved Confounders: Estimation and Implication
- Epileptic Seizure Classification Using Combined Labels and a Genetic Algorithm
- AdjointBackMapV2: Precise Reconstruction of Arbitrary CNN Unit's Activation via Adjoint Operators
- Pre-Quantized Deep Learning Models Codified in ONNX to Enable Hardware/Software Co-Design
- Stochastic tensor space feature theory with applications to robust machine learning
- Wireless Link Scheduling via Graph Representation Learning: A Comparative Study of Different Supervision Levels
- Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning
- HYPPO: A Surrogate-Based Multi-Level Parallelism Tool for Hyperparameter Optimization
- AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts
- Learning, Computing, and Trustworthiness in Intelligent IoT Environments: Performance-Energy Tradeoffs
- How You Move Your Head Tells What You Do: Self-supervised Video Representation Learning with Egocentric Cameras and IMU Sensors
- Inductive learning for product assortment graph completion
- Deep Learning Approach Protecting Privacy in Camera-Based Critical Applications
- A manifold learning approach for gesture recognition from micro-Doppler radar measurements
- Learning to shortcut and shortlist order fulfillment deciding
- Estimating Potential Outcome Distributions with Collaborating Causal Networks
- Global Convergence and Stability of Stochastic Gradient Descent
- Rerunning OCR: A Machine Learning Approach to Quality Assessment and Enhancement Prediction
- HDR-cGAN: Single LDR to HDR Image Translation using Conditional GAN
- Cross-Modal Virtual Sensing for Combustion Instability Monitoring
- VTAMIQ: Transformers for Attention Modulated Image Quality Assessment
- Improved architectures and training algorithms for deep operator networks
- Learning to Solve the AC Optimal Power Flow via a Lagrangian Approach
- Robust Linear Classification from Limited Training Data
- Pixel-Level Bijective Matching for Video Object Segmentation
- Privacy enabled Financial Text Classification using Differential Privacy and Federated Learning
- Investigating Fairness of Ocular Biometrics Among Young, Middle-Aged, and Older Adults
- An Experimental Evaluation on Deepfake Detection using Deep Face Recognition
- An energy-based model for neuro-symbolic reasoning on knowledge graphs
- Inferring dark matter substructure with astrometric lensing beyond the power spectrum
- CertainNet: Sampling-free Uncertainty Estimation for Object Detection
- Clustering a Mixture of Gaussians with Unknown Covariance
- NeuFENet: Neural Finite Element Solutions with Theoretical Bounds for Parametric PDEs
- Encoder Adaptation of Dense Passage Retrieval for Open-Domain Question Answering
- Effectiveness of Optimization Algorithms in Deep Image Classification
- Solon: Communication-efficient Byzantine-resilient Distributed Training via Redundant Gradients
- Generalized Kernel Thinning
- Fast Scalable Image Restoration using Total Variation Priors and Expectation Propagation
- Information-theoretic generalization bounds for black-box learning algorithms
- Online Control of the False Discovery Rate under "Decision Deadlines"
- An Empirical Investigation of Learning from Biased Toxicity Labels
- Causal Representation Learning for Context-Aware Face Transfer
- A Modified Q-Learning Algorithm for Rate-Profiling of Polarization Adjusted Convolutional (PAC) Codes
- Perhaps PTLMs Should Go to School -- A Task to Assess Open Book and Closed Book QA
- Towards Theme Detection in Personal Finance Questions
- Stochastic Anderson Mixing for Nonconvex Stochastic Optimization
- Traffic Flow Forecasting with Maintenance Downtime via Multi-Channel Attention-Based Spatio-Temporal Graph Convolutional Networks
- Assessing glaucoma in retinal fundus photographs using Deep Feature Consistent Variational Autoencoders
- Differentiable Spline Approximations
- A Proposed Conceptual Framework for a Representational Approach to Information Retrieval
- Large Batch Experience Replay
- Balanced Masked and Standard Face Recognition
- Weak-shot Semantic Segmentation by Transferring Semantic Affinity and Boundary
- Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics
- Skill Induction and Planning with Latent Language
- A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning
- DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Models
- Fairness and underspecification in acoustic scene classification: The case for disaggregated evaluations
- Risk-Aware Learning for Scalable Voltage Optimization in Distribution Grids
- JuriBERT: A Masked-Language Model Adaptation for French Legal Text
- Learning Online Visual Invariances for Novel Objects via Supervised and Self-Supervised Training
- Distributed Learning Approaches for Automated Chest X-Ray Diagnosis
- Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information
- HyperTeNet: Hypergraph and Transformer-based Neural Network for Personalized List Continuation
- Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits
- A new weakly supervised approach for ALS point cloud semantic segmentation
- Multi-Agent Path Planning Using Deep Reinforcement Learning
- Instrumental Variable-Driven Domain Generalization with Unobserved Confounders
- A curated, ontology-based, large-scale knowledge graph of artificial intelligence tasks and benchmarks
- Causality and Generalizability: Identifiability and Learning Methods
- Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detection
- Building a Noisy Audio Dataset to Evaluate Machine Learning Approaches for Automatic Speech Recognition Systems
- Unraveling the graph structure of tabular data through Bayesian and spectral analysis
- 3d sequential image mosaicing for underwater navigation and mapping
- Automating Privilege Escalation with Deep Reinforcement Learning
- Protagonists' Tagger in Literary Domain -- New Datasets and a Method for Person Entity Linkage
- Context-Aware Unsupervised Clustering for Person Search
- Pharmacoprint -- a combination of pharmacophore fingerprint and artificial intelligence as a tool for computer-aided drug design
- Identifying non-natural language artifacts in bug reports
- Blindness (Diabetic Retinopathy) Severity Scale Detection
- Analysis of the relation between smartphone usage changes during the COVID-19 pandemic and usage preferences on apps
- InfiniteForm: A synthetic, minimal bias dataset for fitness applications
- Automated Aerial Animal Detection When Spatial Resolution Conditions Are Varied
- ACDC: Online Unsupervised Cross-Domain Adaptation
- What is understandable in Bayesian network explanations?
- Towards General-purpose Infrastructure for Protecting Scientific Data Under Study
- Learning to Assist Agents by Observing Them
All 147
- Collective eXplainable AI: Explaining Cooperative Strategies and Agent Contribution in Multiagent Reinforcement Learning with Shapley Values
- Synthetic Velocity Mapping Cardiac MRI Coupled with Automated Left Ventricle Segmentation
- Incremental Class Learning using Variational Autoencoders with Similarity Learning
- SPaR.txt, a cheap Shallow Parsing approach for Regulatory texts
- Light-weight Deformable Registration using Adversarial Learning with Distilling Knowledge
- Implicit Riemannian Concave Potential Maps
- Leveraging Information Bottleneck for Scientific Document Summarization
- An AO-ADMM approach to constraining PARAFAC2 on all modes
- Git: Clustering Based on Graph of Intensity Topology
- PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds
- Behaviour-conditioned policies for cooperative reinforcement learning tasks
- Reinforcement Learning for Admission Control in Wireless Virtual Network Embedding
- Scaling Graph-based Deep Learning models to larger networks
- A Aelf-supervised Tibetan-chinese Vocabulary Alignment Method Based On Adversarial Learning
- GenCo: Generative Co-training for Generative Adversarial Networks with Limited Data
- Spatial Ensemble: a Novel Model Smoothing Mechanism for Student-Teacher Framework
- Consistency Regularization Can Improve Robustness to Label Noise
- A free lunch from ViT:Adaptive Attention Multi-scale Fusion Transformer for Fine-grained Visual Recognition
- Identifiability in Two-Layer Sparse Matrix Factorization
- Benchmarking Safety Monitors for Image Classifiers with Machine Learning
- Efficient Identification of Butterfly Sparse Matrix Factorizations
- DenDrift: A Drift-Aware Algorithm for Host Profiling
- Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation
- Max and Coincidence Neurons in Neural Networks
- Inducing Equilibria via Incentives: Simultaneous Design-and-Play Ensures Global Convergence
- Learning Structural Representations for Recipe Generation and Food Retrieval
- Row-clustering of a Point Process-valued Matrix
- AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks
- Molformer: Motif-based Transformer on 3D Heterogeneous Molecular Graphs
- LawSum: A weakly supervised approach for Indian Legal Document Summarization
- Text-based automatic personality prediction: A bibliographic review
- Improving Axial-Attention Network Classification via Cross-Channel Weight Sharing
- BPFNet: A Unified Framework for Bimodal Palmprint Alignment and Fusion
- Contextualized Semantic Distance between Highly Overlapped Texts
- Deep Kernel Representation for Image Reconstruction in PET
- Deep Fraud Detection on Non-attributed Graph
- Trustworthy AI: From Principles to Practices
- DESTRESS: Computation-Optimal and Communication-Efficient Decentralized Nonconvex Finite-Sum Optimization
- Decoupling Speaker-Independent Emotions for Voice Conversion Via Source-Filter Networks
- Enhance Images as You Like with Unpaired Learning
- Beyond Topics: Discovering Latent Healthcare Objectives from Event Sequences
- TLDR9+: A Large Scale Resource for Extreme Summarization of Social Media Posts
- An Analysis of Super-Net Heuristics in Weight-Sharing NAS
- Efficiency, Fairness, and Stability in Non-Commercial Peer-to-Peer Ridesharing
- Spiked Covariance Estimation from Modulo-Reduced Measurements
- On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis
- Structured abbreviation expansion in context