Papers
Tue 7 Dec 2021
182 papers
- JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement LearningOffline RL and imitation learning from data → Imitation learning methods
- A graph representation based on fluid diffusion model for data analysis: theoretical aspects and enhanced community detectionDiffusion models → Flow matching, time series and science
- Auxiliary Learning for Self-Supervised Video Representation via Similarity-based Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- Causal Imitative Model for Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
- Differentiable Gaussianization Layers for Inverse Problems Regularized by Deep Generative ModelsDiffusion models → Inverse problems and image restoration
- Membership Inference Attacks From First PrinciplesLLM safety and security → Membership inference attacks
- ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake ImagesKnowledge distillation → General knowledge distillation methods
- A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud CompletionDiffusion models → 3D, point cloud and scene generation
- Combining Learning from Human Feedback and Knowledge Engineering to Solve Hierarchical Tasks in MinecraftLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Improving Neural Cross-Lingual Summarization via Employing Optimal Transport Distance for Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
- Developing a Trusted Human-AI Network for Humanitarian Benefit
- Generative Adversarial Networks for Data Generation in Structural Health Monitoring
- Generative Adversarial Networks for Labelled Vibration Data Generation
- Semantic Answer Type and Relation Prediction Task (SMART 2021)
- Goedel's Incompleteness Theorem
- A Scoping Review of Publicly Available Language Tasks in Clinical Natural Language Processing
- Collaborative Learning over Wireless Networks: An Introductory Overview
- i-SpaSP: Structured Neural Pruning via Sparse Signal Recovery
- Assessing Fairness in the Presence of Missing Data
- Multi-Task Learning on Networks
- Artificial Intelligence and Design of Experiments for Assessing Security of Electricity Supply: A Review and Strategic Outlook
- Adapting Procedural Content Generation to Player Personas Through Evolution
- Truth-tracking via Approval Voting: Size Matters
- Which images to label for few-shot medical landmark detection?
- Vision-Cloud Data Fusion for ADAS: A Lane Change Prediction Case Study
- A Transferable Approach for Partitioning Machine Learning Models on Multi-Chip-Modules
- Presentation Attack Detection Methods based on Gaze Tracking and Pupil Dynamic: A Comprehensive Survey
- DeepDiagnosis: Automatically Diagnosing Faults and Recommending Actionable Fixes in Deep Learning Programs
- Relating transformers to models and neural representations of the hippocampal formation
- Image classifiers can not be made robust to small perturbations
- Accelerating Understanding of Scientific Experiments with End to End Symbolic Regression
- A Robust Completed Local Binary Pattern (RCLBP) for Surface Defect Detection
- DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover's Distance Improves Out-Of-Distribution Face Identification
- Unsupervised Representation Learning via Neural Activation Coding
- A deep learning model for data-driven discovery of functional connectivity
- Multinational Address Parsing: A Zero-Shot Evaluation
- SHRIMP: Sparser Random Feature Models via Iterative Magnitude Pruning
- Nuclei Segmentation in Histopathology Images using Deep Learning with Local and Global Views
- Emotion-Cause Pair Extraction in Customer Reviews
- Tailored neural networks for learning optimal value functions in MPC
- Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks
- Few-Shot Image Classification Along Sparse Graphs
- Scalable 3D Semantic Segmentation for Gun Detection in CT Scans
- BT-Unet: A self-supervised learning framework for biomedical image segmentation using Barlow Twins with U-Net models
- Embedding Gradient-based Optimization in Image Registration Networks
- Synthetic Acute Hypotension and Sepsis Datasets Based on MIMIC-III and Published as Part of the Health Gym Project
- RID-Noise: Towards Robust Inverse Design under Noisy Environments
- Dyadic Sex Composition and Task Classification Using fNIRS Hyperscanning Data
- Vehicle trajectory prediction works, but not everywhere
- Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields
- Cross-modal Manifold Cutmix for Self-supervised Video Representation Learning
- ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints
- MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection
- Information is Power: Intrinsic Control via Information Capture
- Lattice-Based Methods Surpass Sum-of-Squares in Clustering
- Gradient and Projection Free Distributed Online Min-Max Resource Optimization
- Image Enhancement via Bilateral Learning
- EmTract: Extracting Emotions from Social Media
- Towards a Shared Rubric for Dataset Annotation
- Universalizing Weak Supervision
- Reducing Target Group Bias in Hate Speech Detectors
- Grounded Language-Image Pre-training
- Policy Search for Model Predictive Control with Application to Agile Drone Flight
- Natural Answer Generation: From Factoid Answer to Full-length Answer using Grammar Correction
- A Survey on Intrinsic Images: Delving Deep Into Lambert and Beyond
- Augment & Valuate : A Data Enhancement Pipeline for Data-Centric AI
- Attention-Based Model and Deep Reinforcement Learning for Distribution of Event Processing Tasks
- A Deep Learning Driven Algorithmic Pipeline for Autonomous Navigation in Row-Based Crops
- Accurate parameter estimation using scan-specific unsupervised deep learning for relaxometry and MR fingerprinting
- A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial Images
- Disentangled Counterfactual Recurrent Networks for Treatment Effect Inference over Time
- Polarimetric Pose Prediction
- Automated Story Generation as Question-Answering
- raceBERT -- A Transformer-based Model for Predicting Race and Ethnicity from Names
- OOD-GNN: Out-of-Distribution Generalized Graph Neural Network
- Suppressing Static Visual Cues via Normalizing Flows for Self-Supervised Video Representation Learning
- A pragmatic account of the weak evidence effect
- PTR-PPO: Proximal Policy Optimization with Prioritized Trajectory Replay
- Variance-Aware Weight Initialization for Point Convolutional Neural Networks
- On the Effectiveness of Mode Exploration in Bayesian Model Averaging for Neural Networks
- Machine Learning in the Search for New Fundamental Physics
- In-flight Novelty Detection with Convolutional Neural Networks
- Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning
- Bridging the Model-Reality Gap with Lipschitz Network Adaptation
- A Continuous-time Stochastic Gradient Descent Method for Continuous Data
- Tell me why! Explanations support learning relational and causal structure
- Wild ToFu: Improving Range and Quality of Indirect Time-of-Flight Depth with RGB Fusion in Challenging Environments
- Interpolating between BSDEs and PINNs: deep learning for elliptic and parabolic boundary value problems
- Dilated convolution with learnable spacings
- UCD-CS at TREC 2021 Incident Streams Track
- Gaussian map predictions for 3D surface feature localisation and counting
- Towards Modeling and Resolving Singular Parameter Spaces using Stratifolds
- A coarse space acceleration of deep-DDM
- SalFBNet: Learning Pseudo-Saliency Distribution via Feedback Convolutional Networks
- Flexible Networks for Learning Physical Dynamics of Deformable Objects
- RFGAN: RF-Based Human Synthesis
- Shrub Ensembles for Online Classification
- GKS: Graph-based Knowledge Selector for Task-oriented Dialog System
- A Bayesian take on option pricing with Gaussian processes
- Image Compressed Sensing Using Non-local Neural Network
All 182
- CapsProm: A Capsule Network For Promoter Prediction
- Low-rank Tensor Decomposition for Compression of Convolutional Neural Networks Using Funnel Regularization
- PLACE dropout: A Progressive Layer-wise and Channel-wise Dropout for Domain Generalization
- Hybrid Self-Attention NEAT: A novel evolutionary approach to improve the NEAT algorithm
- Cross-domain User Preference Learning for Cold-start Recommendation
- A generalization gap estimation for overparameterized models via the Langevin functional variance
- Understanding Square Loss in Training Overparametrized Neural Network Classifiers
- Activation to Saliency: Forming High-Quality Labels for Completely Unsupervised Salient Object Detection
- Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection
- CCasGNN: Collaborative Cascade Prediction Based on Graph Neural Networks
- QKSA: Quantum Knowledge Seeking Agent -- resource-optimized reinforcement learning using quantum process tomography
- Gram-SLD: Automatic Self-labeling and Detection for Instance Objects
- Scaling Structured Inference with Randomization
- Godot Reinforcement Learning Agents
- Change Summarization of Diachronic Scholarly Paper Collections by Semantic Evolution Analysis
- Generation of Non-Deterministic Synthetic Face Datasets Guided by Identity Priors
- SSAT: A Symmetric Semantic-Aware Transformer Network for Makeup Transfer and Removal
- Phase transitions in nonparametric regressions
- Parsing with Pretrained Language Models, Multiple Datasets, and Dataset Embeddings
- Time-Equivariant Contrastive Video Representation Learning
- Evaluating Generic Auto-ML Tools for Computational Pathology
- Permutation Equivariant Generative Adversarial Networks for Graphs
- Saliency Diversified Deep Ensemble for Robustness to Adversaries
- DCAN: Improving Temporal Action Detection via Dual Context Aggregation
- Decision-Focused Learning: Through the Lens of Learning to Rank
- Handwritten Mathematical Expression Recognition via Attention Aggregation based Bi-directional Mutual Learning
- E2(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition
- State-of-the-art predictive and prescriptive analytics for IEEE CIS 3rd Technical Challenge
- Parallel Discrete Convolutions on Adaptive Particle Representations of Images
- Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition
- A deep language model to predict metabolic network equilibria
- TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning
- Pragmatic Implementation of Reinforcement Algorithms For Path Finding On Raspberry Pi
- MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance
- Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matrices
- Neural Networks for Infectious Diseases Detection: Prospects and Challenges
- Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints
- More layers! End-to-end regression and uncertainty on tabular data with deep learning
- CMA-CLIP: Cross-Modality Attention CLIP for Image-Text Classification
- Graph Neural Controlled Differential Equations for Traffic Forecasting
- Multi-speaker Emotional Text-to-speech Synthesizer
- FedDAG: Federated DAG Structure Learning
- Bootstrapping ViTs: Towards Liberating Vision Transformers from Pre-training
- GaTector: A Unified Framework for Gaze Object Prediction
- Private Robust Estimation by Stabilizing Convex Relaxations
- Self-Organized Polynomial-Time Coordination Graphs
- Predicting the Travel Distance of Patients to Access Healthcare using Deep Neural Networks
- Learning Pixel-Adaptive Weights for Portrait Photo Retouching
- A Time-domain Real-valued Generalized Wiener Filter for Multi-channel Neural Separation Systems
- Ground-Truth, Whose Truth? -- Examining the Challenges with Annotating Toxic Text Datasets
- Physics guided deep learning generative models for crystal materials discovery
- UNITER-Based Situated Coreference Resolution with Rich Multimodal Input
- Genetic Algorithm for Constrained Molecular Inverse Design
- CG-NeRF: Conditional Generative Neural Radiance Fields
- Training Deep Models to be Explained with Fewer Examples
- A Generic Approach for Enhancing GANs by Regularized Latent Optimization
- A Piece-wise Polynomial Filtering Approach for Graph Neural Networks
- Dataset Geography: Mapping Language Data to Language Users
- Learning Instance and Task-Aware Dynamic Kernels for Few Shot Learning
- Decision-based Black-box Attack Against Vision Transformers via Patch-wise Adversarial Removal
- Explicitly antisymmetrized neural network layers for variational Monte Carlo simulation
- Enhanced Exploration in Neural Feature Selection for Deep Click-Through Rate Prediction Models via Ensemble of Gating Layers
- VizExtract: Automatic Relation Extraction from Data Visualizations
- Generative Adversarial Networks for Labeled Acceleration Data Augmentation for Structural Damage Detection
- BDFA: A Blind Data Adversarial Bit-flip Attack on Deep Neural Networks
- Defending against Model Stealing via Verifying Embedded External Features
- Voxelized 3D Feature Aggregation for Multiview Detection
- Emulating Spatio-Temporal Realizations of Three-Dimensional Isotropic Turbulence via Deep Sequence Learning Models
- Spectral Complexity-scaled Generalization Bound of Complex-valued Neural Networks
- Federated Deep Reinforcement Learning for the Distributed Control of NextG Wireless Networks
- GraphPAS: Parallel Architecture Search for Graph Neural Networks
- A Novel Convergence Analysis for Algorithms of the Adam Family
- Glue: Adaptively Merging Single Table Cardinality to Estimate Join Query Size
- RSBNet: One-Shot Neural Architecture Search for A Backbone Network in Remote Sensing Image Recognition
- Hybrid guiding: A multi-resolution refinement approach for semantic segmentation of gigapixel histopathological images
- Location Leakage in Federated Signal Maps
- Deep Level Set for Box-supervised Instance Segmentation in Aerial Images
- GPU-Based Homotopy Continuation for Minimal Problems in Computer Vision
- Approximating Nash Equilibrium in Random Graphical Games
- A Unified Framework for Multi-distribution Density Ratio Estimation
- First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach
- Mesh-Based Solutions for Nonparametric Penalized Regression