Papers
Fri 24 Sep 2021
150 papers
- Beyond Distillation: Task-level Mixture-of-Experts for Efficient InferenceMixture-of-experts → MoE large language models
- Learning Relative Interactions through ImitationOffline RL and imitation learning from data → Robot manipulation imitation learning
- Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement LearningWorld models → Latent dynamics models and model-based RL
- Unbiased Gradient Estimation with Balanced Assignments for Mixtures of ExpertsMixture-of-experts → MoE theory and gating functions
- CPT: Colorful Prompt Tuning for Pre-trained Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- A Proposal of Automatic Error Correction in Text
- Adversarial Factor Models for the Generation of Improved Autism Diagnostic Biomarkers
- Integrating Deep Event-Level and Script-Level Information for Script Event Prediction
- Towards a Multi-Agent System Architecture for Supply Chain Management
- Detecting Harmful Memes and Their Targets
- Interpretability in Safety-Critical FinancialTrading Systems
- Go-Blend behavior and affect
- Contextual Fine-to-Coarse Distillation for Coarse-grained Response Selection in Open-Domain Conversations
- RuleBert: Teaching Soft Rules to Pre-trained Language Models
- Bringing Generalization to Deep Multi-View Pedestrian Detection
- Accelerated nonlinear primal-dual hybrid gradient methods with applications to supervised machine learning
- Ground material classification for UAV-based photogrammetric 3D data A 2D-3D Hybrid Approach
- Influence of Mobility Restrictions on Transmission of COVID-19 in the state of Maryland -- the USA
- Long-Range Transformers for Dynamic Spatiotemporal Forecasting
- Adaptive Sampling Quasi-Newton Methods for Zeroth-Order Stochastic Optimization
- An animated picture says at least a thousand words: Selecting Gif-based Replies in Multimodal Dialog
- Style Control for Schema-Guided Natural Language Generation
- MIIDL: a Python package for microbial biomarkers identification powered by interpretable deep learning
- NanoBatch Privacy: Enabling fast Differentially Private learning on the IPU
- Predicting Attention Sparsity in Transformers
- Constrained Optimization with Qualitative Preferences
- MLIM: Vision-and-Language Model Pre-training with Masked Language and Image Modeling
- On the Fairness of Swarm Learning in Skin Lesion Classification
- Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversations
- NICE: Robust Scheduling through Reinforcement Learning-Guided Integer Programming
- Unsupervised Cross-Modality Domain Adaptation for Segmenting Vestibular Schwannoma and Cochlea with Data Augmentation and Model Ensemble
- Bayesian non-parametric non-negative matrix factorization for pattern identification in environmental mixtures
- POSSE: Patterns of Systems During Software Encryption
- Deep Neural Networks for Blind Image Quality Assessment: Addressing the Data Challenge
- AI Explainability 360: Impact and Design
- Airfoil's Aerodynamic Coefficients Prediction using Artificial Neural Network
- Spatial Aggregation and Temporal Convolution Networks for Real-time Kriging
- Attentive Contractive Flow with Lipschitz-constrained Self-Attention
- Automatic Map Update Using Dashcam Videos
- Use of the Deep Learning Approach to Measure Alveolar Bone Level
- Identifying Women with Mammographically-Occult Breast Cancer Leveraging GAN-Simulated Mammograms
- MCTS Based Agents for Multistage Single-Player Card Game
- ImplicitVol: Sensorless 3D Ultrasound Reconstruction with Deep Implicit Representation
- Faithful Target Attribute Prediction in Neural Machine Translation
- GERNERMED -- An Open German Medical NER Model
- MLIMC: Machine learning-based implicit-solvent Monte Carlo
- CLIPort: What and Where Pathways for Robotic Manipulation
- A spatiotemporal machine learning approach to forecasting COVID-19 incidence at the county level in the USA
- SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction
- Text-based NP Enrichment
- Equivariant representations for molecular Hamiltonians and N-center atomic-scale properties
- Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansion
- Deep Social Force
- The Mirror Langevin Algorithm Converges with Vanishing Bias
- Towards A Measure Of General Machine Intelligence
- A Graph Policy Network Approach for Volt-Var Control in Power Distribution Systems
- SD-QA: Spoken Dialectal Question Answering for the Real World
- Zero-shot Object Detection Through Vision-Language Embedding Alignment
- DeepStroke: An Efficient Stroke Screening Framework for Emergency Rooms with Multimodal Adversarial Deep Learning
- Reduced-Lead ECG Classifier Model Trained with DivideMix and Model Ensemble
- SGDE: Secure Generative Data Exchange for Cross-Silo Federated Learning
- Optimized Power Normalized Cepstral Coefficients towards Robust Deep Speaker Verification
- Parameterized Channel Normalization for Far-field Deep Speaker Verification
- Monolingual and Cross-Lingual Acceptability Judgments with the Italian CoLA corpus
- Sample Efficient Model Evaluation
- Combining Discrete Choice Models and Neural Networks through Embeddings: Formulation, Interpretability and Performance
- From images in the wild to video-informed image classification
- Transformers Generalize Linearly
- Identifying Distributional Differences in Convective Evolution Prior to Rapid Intensification in Tropical Cyclones
- Investigating Post-pretraining Representation Alignment for Cross-Lingual Question Answering
- Description-based Label Attention Classifier for Explainable ICD-9 Classification
- Indirectly Supervised English Sentence Break Prediction Using Paragraph Break Probability Estimates
- Pythia: A Customizable Hardware Prefetching Framework Using Online Reinforcement Learning
- Distributed Estimation of Sparse Inverse Covariances
- A data acquisition setup for data driven acoustic design
- Unsupervised Translation of German--Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language
- Separating Retention from Extraction in the Evaluation of End-to-end Relation Extraction
- Entropic estimation of optimal transport maps
- Optimal policy evaluation using kernel-based temporal difference methods
- Optimisation of MCTS Player for The Lord of the Rings: The Card Game
- Optimization-based Causal Estimation from Heterogenous Environments
- Quantitative Matching of Forensic Evidence Fragments Utilizing 3D Microscopy Analysis of Fracture Surface Replicas
- Rethinking Crowd Sourcing for Semantic Similarity
- Visual Scene Graphs for Audio Source Separation
- Evaluating X-vector-based Speaker Anonymization under White-box Assessment
- Two-Stage Mesh Deep Learning for Automated Tooth Segmentation and Landmark Localization on 3D Intraoral Scans
- Discovering PDEs from Multiple Experiments
- Towards Autonomous Visual Navigation in Arable Fields
- Is the Number of Trainable Parameters All That Actually Matters?
- Sinkhorn Distributionally Robust Optimization
- A Bayesian Optimization Approach for Attenuation Correction in SPECT Brain Imaging
- Learning to maximize global influence from local observations
- RSDet++: Point-based Modulated Loss for More Accurate Rotated Object Detection
- Graph-based Approximate Message Passing Iterations
- Adaptivity for clustering-based reduced-order modeling of localized history-dependent phenomena
- Tackling Inter-Class Similarity and Intra-Class Variance for Microscopic Image-based Classification
- Robustness and Sensitivity of BERT Models Predicting Alzheimer's Disease from Text
- Learning-based Noise Component Map Estimation for Image Denoising
- Localizing Infinity-shaped fishes: Sketch-guided object localization in the wild
- Catadioptric Stereo on a Smartphone
All 150
- Understanding Spending Behavior: Recurrent Neural Network Explanation and Interpretation
- The f-Divergence Reinforcement Learning Framework
- Learning Multi-Layered GBDT Via Back Propagation
- Training dataset generation for bridge game registration
- Approximate Latent Force Model Inference
- Explanation Strategies as an Empirical-Analytical Lens for Socio-Technical Contextualization of Machine Learning Interpretability
- How to find a good image-text embedding for remote sensing visual question answering?
- Learnable Triangulation for Deep Learning-based 3D Reconstruction of Objects of Arbitrary Topology from Single RGB Images
- Frequency Pooling: Shift-Equivalent and Anti-Aliasing Downsampling
- GSIP: Green Semantic Segmentation of Large-Scale Indoor Point Clouds
- A Diversity-Enhanced and Constraints-Relaxed Augmentation for Low-Resource Classification
- The More, the Better? A Study on Collaborative Machine Learning for DGA Detection
- MODNet-V: Improving Portrait Video Matting via Background Restoration
- Predicting pigging operations in oil pipelines
- A Dynamic Programming Algorithm for Finding an Optimal Sequence of Informative Measurements
- A Multi-stage Transfer Learning Framework for Diabetic Retinopathy Grading on Small Data
- Local Intrinsic Dimensionality Signals Adversarial Perturbations
- SIM2REALVIZ: Visualizing the Sim2Real Gap in Robot Ego-Pose Estimation
- How Does Knowledge Graph Embedding Extrapolate to Unseen Data: A Semantic Evidence View
- Adversarial Domain Feature Adaptation for Bronchoscopic Depth Estimation
- Edge but not Least: Cross-View Graph Pooling
- Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability
- Learning Dual Dynamic Representations on Time-Sliced User-Item Interaction Graphs for Sequential Recommendation
- Parameter-free Reduction of the Estimation Bias in Deep Reinforcement Learning for Deterministic Policy Gradients
- Dense Contrastive Visual-Linguistic Pretraining
- Quantifying point cloud realism through adversarially learned latent representations
- Non-Euclidean Self-Organizing Maps
- Improved Soft Actor-Critic: Mixing Prioritized Off-Policy Samples with On-Policy Experience
- Dimension Reduction for Data with Heterogeneous Missingness
- Lacking the embedding of a word? Look it up into a traditional dictionary
- LIBRA: Enabling Workload-aware Multi-dimensional Network Topology Optimization for Distributed Training of Large AI Models
- Indoor Localization Using Smartphone Magnetic with Multi-Scale TCN and LSTM
- Fine-Grained Image Generation from Bangla Text Description using Attentional Generative Adversarial Network
- Multi-View Video-Based 3D Hand Pose Estimation
- DACT-BERT: Differentiable Adaptive Computation Time for an Efficient BERT Inference
- Estimating R'enyi's α-Cross-Entropies in a Matrix-Based Way
- Unaligned Image-to-Image Translation by Learning to Reweight
- Holistic Semi-Supervised Approaches for EEG Representation Learning
- Adversarial Neural Trip Recommendation
- GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction
- AES Systems Are Both Overstable And Oversensitive: Explaining Why And Proposing Defenses
- Morse-STF: Improved Protocols for Privacy-Preserving Machine Learning
- Combining Contention-Based Spectrum Access and Adaptive Modulation using Deep Reinforcement Learning
- Online Adaptation of Parameters using GRU-based Neural Network with BO for Accurate Driving Model
- A 3D Mesh-based Lifting-and-Projection Network for Human Pose Transfer
- Training Automatic View Planner for Cardiac MR Imaging via Self-Supervision by Spatial Relationship between Views
- Feasibility study of urban flood mapping using traffic signs for route optimization
- Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding
- An Improved Frequent Directions Algorithm for Low-Rank Approximation via Block Krylov Iteration
- Untrained Graph Neural Networks for Denoising