Papers
Wed 18 May 2022
144 papers
- [Re] Distilling Knowledge via Knowledge ReviewKnowledge distillation → General knowledge distillation methods
- Entailment Tree Explanations via Iterative Retrieval-Generation ReasonerLLM reasoning → Knowledge- and tool-augmented reasoning
- Pluralistic Image Completion with Probabilistic Mixture-of-ExpertsMixture-of-experts → Vision mixture-of-experts
- Lessons Learned: Defending Against Property Inference AttacksLLM safety and security → Membership inference attacks
- LogiGAN: Learning Logical Reasoning via Adversarial Pre-trainingLLM reasoning → Reasoning benchmarks and evaluation
- CARNet: A Dynamic Autoencoder for Learning Latent Dynamics in Autonomous Driving TasksEnd-to-end autonomous driving → End-to-end system architecture
- Counting Phases and Faces Using Bayesian Thermodynamic Integration
- Exploring the stimulative effect on following drivers in a consecutive lane-change using microscopic vehicle trajectory data
- Topic Segmentation of Research Article Collections
- Efficient Mixed Dimension Embeddings for Matrix Factorization
- PASH at TREC 2021 Deep Learning Track: Generative Enhanced Model for Multi-stage Ranking
- Agent-Based modeling in Medical Research. Example in Health Economics
- Federated learning: Applications, challenges and future directions
- Practical Skills Demand Forecasting via Representation Learning of Temporal Dynamics
- On the Limits of Evaluating Embodied Agent Model Generalization Using Validation Sets
- MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes
- Transformer-based Program Synthesis for Low-Data Environments
- Riemannian Metric Learning via Optimal Transport
- Neural ODE Control for Trajectory Approximation of Continuity Equation
- Debiasing Neural Retrieval via In-batch Balancing Regularization
- GRACE-C: Generalized Rate Agnostic Causal Estimation via Constraints
- PromptDA: Label-guided Data Augmentation for Prompt-based Few-shot Learners
- Scalable Multi-view Clustering with Graph Filtering
- Modeling Multi-hop Question Answering as Single Sequence Prediction
- A Classification of G-invariant Shallow Neural Networks
- "I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Dataset
- Torchhd: An Open Source Python Library to Support Research on Hyperdimensional Computing and Vector Symbolic Architectures
- Mimicking Behaviors in Separated Domains
- A False Sense of Security? Revisiting the State of Machine Learning-Based Industrial Intrusion Detection
- Hybrid Machine Learning Modeling of Engineering Systems -- A Probabilistic Perspective Tested on a Multiphase Flow Modeling Case Study
- High-Order Multilinear Discriminant Analysis via Order-textitn Tensor Eigendecomposition
- AI-assisted Optimization of the ECCE Tracking System at the Electron Ion Collider
- Computing the ensemble spread from deterministic weather predictions using conditional generative adversarial networks
- Learning Rate Curriculum
- PreQuEL: Quality Estimation of Machine Translation Outputs in Advance
- Carbon Figures of Merit Knowledge Creation with a Hybrid Solution and Carbon Tables API
- Color Overmodification Emerges from Data-Driven Learning and Pragmatic Reasoning
- Backdoor Attacks on Bayesian Neural Networks using Reverse Distribution
- An Invariant Matching Property for Distribution Generalization under Intervened Response
- Stochastic uncertainty analysis of gravity gradient tensor components and their combinations
- ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrieval
- DDXPlus: A New Dataset For Automatic Medical Diagnosis
- Relational representation learning with spike trains
- A2C is a special case of PPO
- On the efficiency of Stochastic Quasi-Newton Methods for Deep Learning
- Fast matrix multiplication for binary and ternary CNNs on ARM CPU
- Neighborhood Mixup Experience Replay: Local Convex Interpolation for Improved Sample Efficiency in Continuous Control Tasks
- Masked Autoencoders As Spatiotemporal Learners
- BodyMap: Learning Full-Body Dense Correspondence Map
- Single-Shot Optical Neural Network
- Achieving Risk Control in Online Learning Settings
- Dialog Inpainting: Turning Documents into Dialogs
- On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias
- Exact Gaussian Processes for Massive Datasets via Non-Stationary Sparsity-Discovering Kernels
- VRAG: Region Attention Graphs for Content-Based Video Retrieval
- Automatic Rule Induction for Interpretable Semi-Supervised Learning
- Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generator
- Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs
- Position Aided Beam Prediction in the Real World: How Useful GPS Locations Actually Are?
- Global Contrast Masked Autoencoders Are Powerful Pathological Representation Learners
- Empirical Advocacy of Bio-inspired Models for Robust Image Recognition
- Maslow's Hammer for Catastrophic Forgetting: Node Re-Use vs Node Activation
- Learning latent representations for operational nitrogen response rate prediction
- Exploring the Advantages of Dense-Vector to One-Hot Encoding of Intent Classes in Out-of-Scope Detection Tasks
- A weakly supervised framework for high-resolution crop yield forecasts
- Confidential Machine Learning within Graphcore IPUs
- Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation
- Defending Object Detectors against Patch Attacks with Out-of-Distribution Smoothing
- Trading Positional Complexity vs. Deepness in Coordinate Networks
- Fast Neural Network based Solving of Partial Differential Equations
- One Explanation to Rule them All -- Ensemble Consistent Explanations
- A lightweight multi-scale context network for salient object detection in optical remote sensing images
- Meta-Learning Sparse Compression Networks
- SoK: The Impact of Unlabelled Data in Cyberthreat Detection
- CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-Tuning
- Features of Perceived Metaphoricity on the Discourse Level: Abstractness and Emotionality
- Deep Features for CBIR with Scarce Data using Hebbian Learning
- COVID-Net UV: An End-to-End Spatio-Temporal Deep Neural Network Architecture for Automated Diagnosis of COVID-19 Infection from Ultrasound Videos
- Imagining new futures beyond predictive systems in child welfare: A qualitative study with impacted stakeholders
- Generating Explanations from Deep Reinforcement Learning Using Episodic Memory
- Financial Time Series Data Augmentation with Generative Adversarial Networks and Extended Intertemporal Return Plots
- Price Interpretability of Prediction Markets: A Convergence Analysis
- Remote Sensing Novel View Synthesis with Implicit Multiplane Representations
- FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting
- A Scalable Workflow to Build Machine Learning Classifiers with Clinician-in-the-Loop to Identify Patients in Specific Diseases
- 3D Segmentation Guided Style-based Generative Adversarial Networks for PET Synthesis
- GeoPointGAN: Synthetic Spatial Data with Local Label Differential Privacy
- Transformer based multiple instance learning for weakly supervised histopathology image segmentation
- Multi-disciplinary fairness considerations in machine learning for clinical trials
- BFCAI at SemEval-2022 Task 6: Multi-Layer Perceptron for Sarcasm Detection in Arabic Texts
- The Kernelized Taylor Diagram
- Bridging the gap between QP-based and MPC-based RL
- Positional Information is All You Need: A Novel Pipeline for Self-Supervised SVDE from Videos
- GPoeT-2: A GPT-2 Based Poem Generator
- Large Neural Networks Learning from Scratch with Very Few Data and without Explicit Regularization
- Fair and Green Hyperparameter Optimization via Multi-objective and Multiple Information Source Bayesian Optimization
- Speckle Image Restoration without Clean Data
- World Value Functions: Knowledge Representation for Multitask Reinforcement Learning
- Automating In-Network Machine Learning
- Exploiting Social Media Content for Self-Supervised Style Transfer
All 144
- Regex in a Time of Deep Learning: The Role of an Old Technology in Age Discrimination Detection in Job Advertisements
- Anomaly detection using prediction error with Spatio-Temporal Convolutional LSTM
- PhoCaL: A Multi-Modal Dataset for Category-Level Object Pose Estimation with Photometrically Challenging Objects
- Evaluation of Transfer Learning for Polish with a Text-to-Text Model
- Entity Alignment with Reliable Path Reasoning and Relation-Aware Heterogeneous Graph Transformer
- Markov Chain Monte Carlo for Continuous-Time Switching Dynamical Systems
- On-device modeling of user's social context and familiar places from smartphone-embedded sensor data
- Deep Reinforcement Learning Based on Location-Aware Imitation Environment for RIS-Aided mmWave MIMO Systems
- Cross-subject Action Unit Detection with Meta Learning and Transformer-based Relation Modeling
- Visual Attention-based Self-supervised Absolute Depth Estimation using Geometric Priors in Autonomous Driving
- Probability trees and the value of a single intervention
- Entity Alignment For Knowledge Graphs: Progress, Challenges, and Empirical Studies
- Graph Adaptive Semantic Transfer for Cross-domain Sentiment Classification
- Relation Extraction with Weighted Contrastive Pre-training on Distant Supervision
- Marginal and Joint Cross-Entropies & Predictives for Online Bayesian Inference, Active Learning, and Active Sampling
- Persian Natural Language Inference: A Meta-learning approach
- Revisiting PINNs: Generative Adversarial Physics-informed Neural Networks and Point-weighting Method
- Validation of a photogrammetric approach for the objective study of ancient bowed instruments
- A reproducible experimental survey on biomedical sentence similarity: a string-based method sets the state of the art
- 3D-VFD: A Victim-free Detector against 3D Adversarial Point Clouds
- Deep-learned orthogonal basis patterns for fast, noise-robust single-pixel imaging
- TTAPS: Test-Time Adaption by Aligning Prototypes using Self-Supervision
- RandoMix: A mixed sample data augmentation method with multiple mixed modes
- Data Augmentation to Address Out-of-Vocabulary Problem in Low-Resource Sinhala-English Neural Machine Translation
- (O,G)-granular variable precision fuzzy rough sets based on overlap and grouping functions
- A Regression Approach to Learning-Augmented Online Algorithms
- No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL
- Customizing ML Predictions for Online Algorithms
- End-to-End Multi-Object Detection with a Regularized Mixture Model
- It Isn't Sh!tposting, It's My CAT Posting
- SemiCurv: Semi-Supervised Curvilinear Structure Segmentation
- Accurate Fairness: Improving Individual Fairness without Trading Accuracy
- Optimal Adaptive Prediction Intervals for Electricity Load Forecasting in Distribution Systems via Reinforcement Learning
- The Solvability of Interpretability Evaluation Metrics
- Hyperparameter Optimization with Neural Network Pruning
- Spatial-Temporal Interactive Dynamic Graph Convolution Network for Traffic Forecasting
- Deep learning on rail profiles matching
- Policy Distillation with Selective Input Gradient Regularization for Efficient Interpretability
- Terrain Analysis in StarCraft 1 and 2 as Combinatorial Optimization
- A Pulse-and-Glide-driven Adaptive Cruise Control System for Electric Vehicle
- Dependent Latent Class Models
- Addressing Resource and Privacy Constraints in Semantic Parsing Through Data Augmentation
- K-textures, a self-supervised hard clustering deep learning algorithm for satellite image segmentation
- Learning Monocular Depth Estimation via Selective Distillation of Stereo Knowledge