Papers
Thu 17 Jun 2021
198 papers
- Learning Knowledge Graph-based World Models of Textual EnvironmentsWorld models → World models for language agents
- Modeling Worlds in TextWorld models → World models for language agents
- Knowledge distillation from multi-modal to mono-modal segmentation networksKnowledge distillation → Distillation for medical imaging
- Dynamic Knowledge Distillation With Noise Elimination for RGB-D Salient Object DetectionKnowledge distillation → Detection and dense prediction distillation
- CRIL: Continual Robot Imitation Learning via Generative and Prediction ModelOffline RL and imitation learning from data → Robot manipulation imitation learning
- Seeing Differently, Acting Similarly: Heterogeneously Observable Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World AttacksEnd-to-end autonomous driving → Adversarial scenarios and safety testing
- Immune Moral Models? Pro-Social Rule Breaking as a Moral Enhancement Approach for Ethical AI
- SE-MD: A Single-encoder multiple-decoder deep network for point cloud generation from 2D images
- Pre-treatment of outliers and anomalies in plant data: Methodology and case study of a Vacuum Distillation Unit
- Dungeon and Platformer Level Blending and Generation using Conditional VAEs
- Evo* 2021 -- Late-Breaking Abstracts Volume
- Sphynx: ReLU-Efficient Network Design for Private Inference
- A data-based comparative review and AI-driven symbolic model for longitudinal dispersion coefficient in natural streams
- Dual-view Molecule Pre-training
- PAC Prediction Sets Under Covariate Shift
- Disinformation, Stochastic Harm, and Costly Effort: A Principal-Agent Analysis of Regulating Social Media Platforms
- Dual-Teacher Class-Incremental Learning With Data-Free Generative Replay
- AI-Enabled Ultra-Low-Dose CT Reconstruction
- Hybrid graph convolutional neural networks for landmark-based anatomical segmentation
- On Effects of Compression with Hyperdimensional Computing in Distributed Randomized Neural Networks
- Many Agent Reinforcement Learning Under Partial Observability
- Generalized Learning Vector Quantization for Classification in Randomized Neural Networks and Hyperdimensional Computing
- Escaping strict saddle points of the Moreau envelope in nonsmooth optimization
- Deep reinforcement learning with automated label extraction from clinical reports accurately classifies 3D MRI brain volumes
- Shuffle Private Stochastic Convex Optimization
- Wide stochastic networks: Gaussian limit and PAC-Bayesian training
- LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linking
- A Distance-based Separability Measure for Internal Cluster Validation
- Multi-Task Learning and Adapted Knowledge Models for Emotion-Cause Extraction
- Topological Indoor Mapping through WiFi Signals
- Guided Integrated Gradients: An Adaptive Path Method for Removing Noise
- Efficient Self-supervised Vision Transformers for Representation Learning
- Gradient-free optimization of chaotic acoustics with reservoir computing
- Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses
- On Invariance Penalties for Risk Minimization
- Adapting the Function Approximation Architecture in Online Reinforcement Learning
- An Information Retrieval Approach to Building Datasets for Hate Speech Detection
- A probabilistic database approach to autoencoder-based data cleaning
- Causal Bias Quantification for Continuous Treatments
- Unsupervised Resource Allocation with Graph Neural Networks
- Multi-mode Transformer Transducer with Stochastic Future Context
- Synthetic COVID-19 Chest X-ray Dataset for Computer-Aided Diagnosis
- Discovering Relationships between Object Categories via Universal Canonical Maps
- CIRA Guide to Custom Loss Functions for Neural Networks in Environmental Sciences -- Version 1
- PyKale: Knowledge-Aware Machine Learning from Multiple Sources in Python
- Optimizing robotic swarm based construction tasks
- DeepLab2: A TensorFlow Library for Deep Labeling
- IFCNet: A Benchmark Dataset for IFC Entity Classification
- Visual Correspondence Hallucination
- Multi-Label Learning from Single Positive Labels
- Learning to Predict Visual Attributes in the Wild
- MaCLR: Motion-aware Contrastive Learning of Representations for Videos
- Spectral goodness-of-fit tests for complete and partial network data
- Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning
- Scientific Language Models for Biomedical Knowledge Base Completion: An Empirical Study
- BABEL: Bodies, Action and Behavior with English Labels
- Orthogonal-Pad'e Activation Functions: Trainable Activation functions for smooth and faster convergence in deep networks
- Hi-Phy: A Benchmark for Hierarchical Physical Reasoning
- Statistical Query Lower Bounds for List-Decodable Linear Regression
- How Low Can We Go: Trading Memory for Error in Low-Precision Training
- LoRA: Low-Rank Adaptation of Large Language Models
- PAC-Bayes, MAC-Bayes and Conditional Mutual Information: Fast rate bounds that handle general VC classes
- XCiT: Cross-Covariance Image Transformers
- Accuracy, Interpretability, and Differential Privacy via Explainable Boosting
- JOKR: Joint Keypoint Representation for Unsupervised Cross-Domain Motion Retargeting
- SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies
- Adaptive Low-Rank Regularization with Damping Sequences to Restrict Lazy Weights in Deep Networks
- Gone Fishing: Neural Active Learning with Fisher Embeddings
- The 2021 Image Similarity Dataset and Challenge
- Pseudo-Euclidean Attract-Repel Embeddings for Undirected Graphs
- Indian Masked Faces in the Wild Dataset
- Improving On-Screen Sound Separation for Open-Domain Videos with Audio-Visual Self-Attention
- Multi-modal fusion with gating using audio, lexical and disfluency features for Alzheimer's Dementia recognition from spontaneous speech
- Poisoning and Backdooring Contrastive Learning
- Design and Analysis of Robust Deep Learning Models for Stock Price Prediction
- A Short Note of PAGE: Optimal Convergence Rates for Nonconvex Optimization
- Automatic Segmentation of the Prostate on 3D Trans-rectal Ultrasound Images using Statistical Shape Models and Convolutional Neural Networks
- WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis
- Non-intrusive Nonlinear Model Reduction via Machine Learning Approximations to Low-dimensional Operators
- Multi-head or Single-head? An Empirical Comparison for Transformer Training
- Deep Learning Through the Lens of Example Difficulty
- Prototypical Graph Contrastive Learning
- MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data
- AttDLNet: Attention-based DL Network for 3D LiDAR Place Recognition
- Multi-Stage Prototype Learning for Interpretable Time Series Classification
- Towards Explainable Student Group Collaboration Assessment Models Using Temporal Representations of Individual Student Roles
- Privacy-Preserving Eye-tracking Using Deep Learning
- Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA
- Robust Model-based Face Reconstruction through Weakly-Supervised Outlier Segmentation
- Meta-Calibration: Learning of Model Calibration Using Differentiable Expected Calibration Error
- Classifying vaccine sentiment tweets by modelling domain-specific representation and commonsense knowledge into context-aware attentive GRU
- End-to-End Cross-Domain Text-to-SQL Semantic Parsing with Auxiliary Task
- SIFT Matching by Context Exposed
- Optimality and Stability in Federated Learning: A Game-theoretic Approach
- Rotation Invariant Graph Neural Networks using Spin Convolutions
- On Anytime Learning at Macroscale
- Element Intervention for Open Relation Extraction
- A Deep Reinforcement Learning Approach towards Pendulum Swing-up Problem based on TF-Agents
- Large-Scale Chemical Language Representations Capture Molecular Structure and Properties
All 198
- Scale-Consistent Fusion: from Heterogeneous Local Sampling to Global Immersive Rendering
- Adversarial Visual Robustness by Causal Intervention
- Exploring the Properties and Evolution of Neural Network Eigenspaces during Training
- Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity
- Machine learning methods for postprocessing ensemble forecasts of wind gusts: A systematic comparison
- Biomedical Interpretable Entity Representations
- Deep HDR Hallucination for Inverse Tone Mapping
- Secure Multi-Function Computation with Private Remote Sources
- Stochastic Bias-Reduced Gradient Methods
- Backward Gradient Normalization in Deep Neural Networks
- Optimising simulations for diphoton production at hadron colliders using amplitude neural networks
- Importance measures derived from random forests: characterisation and extension
- Algorithmic Bias and Data Bias: Understanding the Relation between Distributionally Robust Optimization and Data Curation
- pysentimiento: A Python Toolkit for Opinion Mining and Social NLP tasks
- Modelling resource allocation in uncertain system environment through deep reinforcement learning
- DravidianCodeMix: Sentiment Analysis and Offensive Language Identification Dataset for Dravidian Languages in Code-Mixed Text
- Learning to Associate Every Segment for Video Panoptic Segmentation
- DocNLI: A Large-scale Dataset for Document-level Natural Language Inference
- Semi-Autoregressive Transformer for Image Captioning
- Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers
- Towards Heterogeneous Clients with Elastic Federated Learning
- Unsupervised Training Data Generation of Handwritten Formulas using Generative Adversarial Networks with Self-Attention
- NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go
- Interpretable Machine Learning Classifiers for Brain Tumour Survival Prediction
- Trainable Discrete Feature Embeddings for Variational Quantum Classifier
- Predicting cognitive scores with graph neural networks through sample selection learning
- Class Balancing GAN with a Classifier in the Loop
- Episode Adaptive Embedding Networks for Few-shot Learning
- Quantized Federated Learning under Transmission Delay and Outage Constraints
- A Self-supervised Method for Entity Alignment
- using multiple losses for accurate facial age estimation
- Deep Subdomain Adaptation Network for Image Classification
- Taming Nonconvexity in Kernel Feature Selection -- Favorable Properties of the Laplace Kernel
- On Deep Neural Network Calibration by Regularization and its Impact on Refinement
- Unsupervised Path Representation Learning with Curriculum Negative Sampling
- A deep generative model for probabilistic energy forecasting in power systems: normalizing flows
- Wavelet-Packets for Deepfake Image Analysis and Detection
- Frustratingly Easy Transferability Estimation
- ShuffleBlock: Shuffle to Regularize Deep Convolutional Neural Networks
- Large Scale Private Learning via Low-rank Reparametrization
- Identifiability of AMP chain graph models
- Virtual Reality based Digital Twin System for remote laboratories and online practical learning
- Lost in Interpreting: Speech Translation from Source or Interpreter?
- THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers
- A Simple Generative Network
- Minimax Estimation of Partially-Observed Vector AutoRegressions
- Towards bio-inspired unsupervised representation learning for indoor aerial navigation
- Central Kurdish machine translation: First large scale parallel corpus and experiments
- EMOVIE: A Mandarin Emotion Speech Dataset with a Simple Emotional Text-to-Speech Model
- Controllable Confidence-Based Image Denoising
- Layer Folding: Neural Network Depth Reduction using Activation Linearization
- PEN4Rec: Preference Evolution Networks for Session-based Recommendation
- SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction
- A Multi-task convolutional neural network for blind stereoscopic image quality assessment using naturalness analysis
- How can we learn (more) from challenges? A statistical approach to driving future algorithm development
- Multi-level Motion Attention for Human Motion Prediction
- Voice2Series: Reprogramming Acoustic Models for Time Series Classification
- CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing
- Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterion
- MHNF: Multi-hop Heterogeneous Neighborhood information Fusion graph representation learning
- Smart Contract Vulnerability Detection: From Pure Neural Network to Interpretable Graph Feature and Expert Pattern Fusion
- MatES: Web-based Forward Chaining Expert System for Maternal Care
- Uniform Convergence of Interpolators: Gaussian Width, Norm Bounds, and Benign Overfitting
- Cooperative Multi-Agent Reinforcement Learning Based Distributed Dynamic Spectrum Access in Cognitive Radio Networks
- Pruning Randomly Initialized Neural Networks with Iterative Randomization
- Federated Learning Framework with Straggling Mitigation and Privacy-Awareness for AI-based Mobile Application Services
- Joining datasets via data augmentation in the label space for neural networks
- A Random CNN Sees Objects: One Inductive Bias of CNN and Its Applications
- Knowledge Graphs and Machine Learning in biased C4I applications
- Optical Mouse: 3D Mouse Pose From Single-View Video
- X-FACT: A New Benchmark Dataset for Multilingual Fact Checking
- Federated CycleGAN for Privacy-Preserving Image-to-Image Translation
- Deep Contrastive Graph Representation via Adaptive Homotopy Learning
- CoANE: Modeling Context Co-occurrence for Attributed Network Embedding
- Denoising Distantly Supervised Named Entity Recognition via a Hypergeometric Probabilistic Model
- De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention
- Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction
- Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases
- JSI at the FinSim-2 task: Ontology-Augmented Financial Concept Classification
- An Evaluation of Self-Supervised Pre-Training for Skin-Lesion Analysis
- Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning
- On the Capabilities of Pointer Networks for Deep Deductive Reasoning
- Evaluating the Robustness of Bayesian Neural Networks Against Different Types of Attacks
- Localized Uncertainty Attacks
- Layer Pruning on Demand with Intermediate CTC
- Optimum-statistical Collaboration Towards General and Efficient Black-box Optimization
- Long-Short Temporal Contrastive Learning of Video Transformers
- Square Root Principal Component Pursuit: Tuning-Free Noisy Robust Matrix Recovery
- On the Power of Preconditioning in Sparse Linear Regression
- An Empirical Study on Hyperparameter Optimization for Fine-Tuning Pre-trained Language Models
- Learning from Demonstration without Demonstrations
- Trilateral Attention Network for Real-time Medical Image Segmentation
- A Two-stage Multi-modal Affect Analysis Framework for Children with Autism Spectrum Disorder
- Learning Perceptual Manifold of Fonts
- Physics-informed CoKriging model of a redox flow battery
- RHNAS: Realizable Hardware and Neural Architecture Search
- Amortized Auto-Tuning: Cost-Efficient Bayesian Transfer Optimization for Hyperparameter Recommendation
- On the training of sparse and dense deep neural networks: less parameters, same performance