Papers
Wed 1 Dec 2021
203 papers
- A General Language Assistant as a Laboratory for AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
- Information Theoretic Representation DistillationKnowledge distillation → General knowledge distillation methods
- SegDiff: Image Segmentation with Diffusion Probabilistic ModelsDiffusion models → Medical imaging and segmentation
- Scalable Primitives for Generalized Sensor Fusion in Autonomous VehiclesEnd-to-end autonomous driving → End-to-end system architecture
- Topic Analysis of Superconductivity Literature by Semantic Non-negative Matrix Factorization
- Deliberation of Streaming RNN-Transducer by Non-autoregressive Decoding
- NEORL: NeuroEvolution Optimization with Reinforcement Learning
- A Novel Gaussian Process Based Ground Segmentation Algorithm with Local-Smoothness Estimation
- Pose2Room: Understanding 3D Scenes from Human Activities
- D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions
- On the algebraic structures of the space of interval-valued intuitionistic fuzzy numbers
- Domain-oriented Language Pre-training with Adaptive Hybrid Masking and Optimal Transport Alignment
- A Methodology for Thermal Simulation of Interconnects Enabled by Model Reduction with Material Property Variation
- Towards More Robust Natural Language Understanding
- Cyberphysical Sequencing for Distributed Asset Management with Broad Traceability
- Learning to automate cryo-electron microscopy data collection with Ptolemy
- Automatic tumour segmentation in H&E-stained whole-slide images of the pancreas
- Analysis of an adaptive lead weighted ResNet for multiclass classification of 12-lead ECGs
- Structural Sieves
- Homotopy Based Reinforcement Learning with Maximum Entropy for Autonomous Air Combat
- A modified limited memory Nesterov's accelerated quasi-Newton
- Multi-task fusion for improving mammography screening data classification
- Monolith to Microservices: Representing Application Software through Heterogeneous Graph Neural Network
- Detecting Extratropical Cyclones of the Northern Hemisphere with Single Shot Detector
- Analyzing High-Resolution Clouds and Convection using Multi-Channel VAEs
- DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning
- Robust and Adaptive Temporal-Difference Learning Using An Ensemble of Gaussian Processes
- Learning Invariant Representations with Missing Data
- Generating Diverse 3D Reconstructions from a Single Occluded Face Image
- Neural Stochastic Dual Dynamic Programming
- Decomposing Representations for Deterministic Uncertainty Estimation
- GANORCON: Are Generative Models Useful for Few-shot Segmentation?
- Interpretable Deep Learning-Based Forensic Iris Segmentation and Recognition
- First Steps of an Approach to the ARC Challenge based on Descriptive Grid Models and the Minimum Description Length Principle
- CLAWS: Contrastive Learning with hard Attention and Weak Supervision
- Improving Differentially Private SGD via Randomly Sparsified Gradients
- Convergence of Batch Greenkhorn for Regularized Multimarginal Optimal Transport
- Inducing Causal Structure for Interpretable Neural Networks
- Output-weighted and relative entropy loss functions for deep learning precursors of extreme events
- FaSS-MVS -- Fast Multi-View Stereo with Surface-Aware Semi-Global Matching from UAV-borne Monocular Imagery
- CO-STAR: Conceptualisation of Stereotypes for Analysis and Reasoning
- Models of fairness in federated learning
- Evolving Open Complexity
- Revisiting dequantization and quantum advantage in learning tasks
- ReIGNN: State Register Identification Using Graph Neural Networks for Circuit Reverse Engineering
- PreViTS: Contrastive Pretraining with Video Tracking Supervision
- Iconary: A Pictionary-Based Game for Testing Multimodal Communication with Drawings and Text
- Fast Sparse Decision Tree Optimization via Reference Ensembles
- DFTS2: Simulating Deep Feature Transmission Over Packet Loss Channels
- Using Deep Image Prior to Assist Variational Selective Segmentation Deep Learning Algorithms
- Controlling Conditional Language Models without Catastrophic Forgetting
- Provable Guarantees for Understanding Out-of-distribution Detection
- Quantum advantage in learning from experiments
- Routing with Self-Attention for Multimodal Capsule Networks
- Collaborative Artificial Intelligence Needs Stronger Assurances Driven by Risks
- Incomplete Multi-view Clustering via Cross-view Relation Transfer
- Aiding Medical Diagnosis Through the Application of Graph Neural Networks to Functional MRI Scans
- Hardware-friendly Deep Learning by Network Quantization and Binarization
- Reference-guided Pseudo-Label Generation for Medical Semantic Segmentation
- Personalized Federated Learning with Adaptive Batchnorm for Healthcare
- Efficient Symptom Inquiring and Diagnosis via Adaptive Alignment of Reinforcement Learning and Classification
- Asymptotic properties of one-layer artificial neural networks with sparse connectivity
- Highly accelerated MR parametric mapping by undersampling the k-space and reducing the contrast number simultaneously with deep learning
- Total-Body Low-Dose CT Image Denoising using Prior Knowledge Transfer Technique with Contrastive Regularization Mechanism
- MonoScene: Monocular 3D Semantic Scene Completion
- The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image
- RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs
- Infinite Neural Network Quantum States: Entanglement and Training Dynamics
- HyperInverter: Improving StyleGAN Inversion via Hypernetwork
- Improving GAN Equilibrium by Raising Spatial Awareness
- STEM: Unsupervised STructural EMbedding for Stance Detection
- Clustering Mixtures with Almost Optimal Separation in Polynomial Time
- Semi-supervised music emotion recognition using noisy student training and harmonic pitch class profiles
- CondenseNeXt: An Ultra-Efficient Deep Neural Network for Embedded Systems
- DeepAoANet: Learning Angle of Arrival from Software Defined Radios with Deep Neural Networks
- Label-Free Model Evaluation with Semi-Structured Dataset Representations
- MDFM: Multi-Decision Fusing Model for Few-Shot Learning
- CYBORG: Blending Human Saliency Into the Loss Improves Deep Learning
- Iterative Saliency Enhancement using Superpixel Similarity
- Graph Conditioned Sparse-Attention for Improved Source Code Understanding
- MOMO -- Deep Learning-driven classification of external DICOM studies for PACS archivation
- Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselines
- Object-aware Video-language Pre-training for Retrieval
- Efficient and Local Parallel Random Walks
- Equivariant graph neural networks for fast electron density estimation of molecules, liquids, and solids
- Digital Twinning Remote Laboratories for Online Practical Learning
- Remixing Functionally Graded Structures: Data-Driven Topology Optimization with Multiclass Shape Blending
- A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?
- TEDGE-Caching: Transformer-based Edge Caching Towards 6G Networks
- DeepSportLab: a Unified Framework for Ball Detection, Player Instance Segmentation and Pose Estimation in Team Sports Scenes
- Towards Futuristic Autonomous Experimentation--A Surprise-Reacting Sequential Experiment Policy
- Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation
- AI Assurance using Causal Inference: Application to Public Policy
- Building astroBERT, a language model for Astronomy & Astrophysics
- Outlier Detection using AI: A Survey
- Neural Emotion Director: Speech-preserving semantic control of facial expressions in "in-the-wild" videos
- The Shape Part Slot Machine: Contact-based Reasoning for Generating 3D Shapes from Parts
- Meta Arcade: A Configurable Environment Suite for Meta-Learning
- Transformer-based Network for RGB-D Saliency Detection
- Background Activation Suppression for Weakly Supervised Object Localization
All 203
- Conditional Expectation based Value Decomposition for Scalable On-Demand Ride Pooling
- Systematic Generalization with Edge Transformers
- Collective discrete optimisation as judgment aggregation
- Toward Foundation Models for Earth Monitoring: Proposal for a Climate Change Benchmark
- Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learning
- DPRK-BERT: The Supreme Language Model
- NLP Research and Resources at DaSciM, Ecole Polytechnique
- On Mixing Times of Metropolized Algorithm With Optimization Step (MAO) : A New Framework
- Attribute Artifacts Removal for Geometry-based Point Cloud Compression
- 3D Reconstruction Using a Linear Laser Scanner and a Camera
- Semi-Supervised Surface Anomaly Detection of Composite Wind Turbine Blades From Drone Imagery
- SaDe: Learning Models that Provably Satisfy Domain Constraints
- Molecular Contrastive Learning with Chemical Element Knowledge Graph
- Empirical evaluation of shallow and deep learning classifiers for Arabic sentiment analysis
- FaceTuneGAN: Face Autoencoder for Convolutional Expression Transfer Using Neural Generative Adversarial Networks
- Subtask-dominated Transfer Learning for Long-tail Person Search
- Trimap-guided Feature Mining and Fusion Network for Natural Image Matting
- Learning Oriented Remote Sensing Object Detection via Naive Geometric Computing
- Zero-Shot Cross-Lingual Machine Reading Comprehension via Inter-sentence Dependency Graph
- Structure-Aware Label Smoothing for Graph Neural Networks
- Revisiting the Transferability of Supervised Pretraining: an MLP Perspective
- Closeness Centrality via the Condorcet Principle
- Human-Object Interaction Detection via Weak Supervision
- Learning Transformer Features for Image Quality Assessment
- Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding
- On the Practical Consistency of Meta-Reinforcement Learning Algorithms
- Weakly-Supervised Video Object Grounding via Causal Intervention
- Seeking Sinhala Sentiment: Predicting Facebook Reactions of Sinhala Posts
- The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization
- Machine learning Hadron Spectral Functions in Lattice QCD
- On-Device Spatial Attention based Sequence Learning Approach for Scene Text Script Identification
- Training Experimentally Robust and Interpretable Binarized Regression Models Using Mixed-Integer Programming
- A benchmark with decomposed distribution shifts for 360 monocular depth estimation
- MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions
- Adv-4-Adv: Thwarting Changing Adversarial Perturbations via Adversarial Domain Adaptation
- Research on Event Accumulator Settings for Event-Based SLAM
- Multi-Agent Transfer Learning in Reinforcement Learning-Based Ride-Sharing Systems
- Controlling Wasserstein Distances by Kernel Norms with Application to Compressive Statistical Learning
- The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification
- Rethink, Revisit, Revise: A Spiral Reinforced Self-Revised Network for Zero-Shot Learning
- Compare Where It Matters: Using Layer-Wise Regularization To Improve Federated Learning on Heterogeneous Data
- NER-BERT: A Pre-trained Model for Low-Resource Entity Tagging
- Effective and efficient structure learning with pruning and model averaging strategies
- Dyadic Human Motion Prediction
- A Comprehensive Study on Various Statistical Techniques for Prediction of Movie Success
- Exploration into Translation-Equivariant Image Quantization
- Deep Measurement Updates for Bayes Filters
- ℓ_∞-Robustness and Beyond: Unleashing Efficient Adversarial Training
- CLIPstyler: Image Style Transfer with a Single Text Condition
- Probability-Generating Function Kernels for Spherical Data
- Dimensionality Reduction for Categorical Data
- Score Transformer: Generating Musical Score from Note-level Representation
- Investigation of Training Label Error Impact on RNN-T
- Automatic travel pattern extraction from visa page stamps using CNN models
- Leveraging Sequence Embedding and Convolutional Neural Network for Protein Function Prediction
- Camera Motion Agnostic 3D Human Pose Estimation
- Confidence Propagation Cluster: Unleash Full Potential of Object Detectors
- A Unified Benchmark for the Unknown Detection Capability of Deep Neural Networks
- Multi-View Stereo with Transformer
- VisRuler: Visual Analytics for Extracting Decision Rules from Bagged and Boosted Decision Trees
- Joint Cluster Head Selection and Trajectory Planning in UAV-Aided IoT Networks by Reinforcement Learning with Sequential Model
- A Daily Tourism Demand Prediction Framework Based on Multi-head Attention CNN: The Case of The Foreign Entrant in South Korea
- Optimizing for In-memory Deep Learning with Emerging Memory Technology
- Push Stricter to Decide Better: A Class-Conditional Feature Adaptive Framework for Improving Adversarial Robustness
- FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection
- Object-Aware Cropping for Self-Supervised Learning
- Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification
- Asymmetric error control under imperfect supervision: a label-noise-adjusted Neyman-Pearson umbrella algorithm
- Discriminating Quantum States with Quantum Machine Learning
- Forward Operator Estimation in Generative Models with Kernel Transfer Operators
- Graph Convolutional Module for Temporal Action Localization in Videos
- Invariance principle of random projection for the norm
- Exploring Social Posterior Collapse in Variational Autoencoder for Interaction Modeling
- Multiple Fusion Adaptation: A Strong Framework for Unsupervised Semantic Segmentation Adaptation
- Unsupervised Statistical Learning for Die Analysis in Ancient Numismatics
- Point Cloud Segmentation Using Sparse Temporal Local Attention
- Interactive Model with Structural Loss for Language-based Abductive Reasoning
- Wiki to Automotive: Understanding the Distribution Shift and its impact on Named Entity Recognition
- FDA-GAN: Flow-based Dual Attention GAN for Human Pose Transfer
- Synthetic Design: An Optimization Approach to Experimental Design with Synthetic Controls
- Learning from Mistakes based on Class Weighting with Application to Neural Architecture Search
- Training BatchNorm Only in Neural Architecture Search and Beyond
- GLocal: Global Graph Reasoning and Local Structure Transfer for Person Image Generation
- Ranking Distance Calibration for Cross-Domain Few-Shot Learning
- Shallow Network Based on Depthwise Over-Parameterized Convolution for Hyperspectral Image Classification
- AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactions
- True or False: Does the Deep Learning Model Learn to Detect Rumors?
- Imbalanced Graph Classification via Graph-of-Graph Neural Networks
- VoRTX: Volumetric 3D Reconstruction With Transformers for Voxelwise View Selection and Fusion
- MC-Blur: A Comprehensive Benchmark for Image Deblurring
- Frequency Fitness Assignment: Optimization without Bias for Good Solutions can be Efficient
- A Machine Learning Analysis of COVID-19 Mental Health Data
- Convergence of GANs Training: A Game and Stochastic Control Methodology
- A generic physics-informed neural network-based framework for reliability assessment of multi-state systems
- PoseKernelLifter: Metric Lifting of 3D Human Pose using Sound
- Minimax Analysis for Inverse Risk in Nonparametric Planer Invertible Regression
- Environmental Sound Extraction Using Onomatopoeic Words
- Improved sparse PCA method for face and image recognition
- Querying Labelled Data with Scenario Programs for Sim-to-Real Validation
- 3DVNet: Multi-View Depth Prediction and Volumetric Refinement
- Efficient Online Bayesian Inference for Neural Bandits
- Public Data-Assisted Mirror Descent for Private Model Training
- Is the use of Deep Learning and Artificial Intelligence an appropriate means to locate debris in the ocean without harming aquatic wildlife?