Papers
Wed 9 Mar 2022
178 papers
- Temporal Difference Learning for Model Predictive ControlWorld models → Latent predictive world models
- Learning from Physical Human Feedback: An Object-Centric One-Shot Adaptation MethodLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Rethinking Task Sampling for Few-shot Vision-Language Transfer LearningLLM reasoning → Multimodal reasoning +1
- Efficient Sub-structured Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- How many Observations are Enough? Knowledge Distillation for Trajectory ForecastingKnowledge distillation → Multimodal distillation
- Sequential Multi-task Learning with Task Dependency for Appeal Judgment Prediction
- Deep Bidirectional Transformers for SoC Flow Specification Mining
- Filter Drug-induced Liver Injury Literature with Natural Language Processing and Ensemble Learning
- CITS: Coherent Ising Tree Search Algorithm Towards Solving Combinatorial Optimization Problems
- Towards a Roadmap on Software Engineering for Responsible AI
- Human Attention Detection Using AM-FM Representations
- SuperCone: Unified User Segmentation over Heterogeneous Experts via Concept Meta-learning
- Identifying the root cause of cable network problems with machine learning
- Deep Convolutional Neural Network for Roadway Incident Surveillance Using Audio Data
- An error correction scheme for improved air-tissue boundary in real-time MRI video for speech production
- A Weibo Dataset for the 2022 Russo-Ukrainian Crisis
- Online User Profiling to Detect Social Bots on Twitter
- Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice
- HDL: Hybrid Deep Learning for the Synthesis of Myocardial Velocity Maps in Digital Twins for Cardiac Analysis
- Artificial Intelligence Solution for Effective Treatment Planning for Glioblastoma Patients
- Deep Learning for the Benes Filter
- Detecting and Diagnosing Terrestrial Gravitational-Wave Mimics Through Feature Learning
- Givens Coordinate Descent Methods for Rotation Matrix Learning in Trainable Embedding Indexes
- NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks
- SAGE: Generating Symbolic Goals for Myopic Models in Deep Reinforcement Learning
- Connecting sufficient conditions for domain adaptation: source-guided uncertainty, relaxed divergences and discrepancy localization
- The Transitive Information Theory and its Application to Deep Generative Models
- On the influence of over-parameterization in manifold based surrogates and deep neural operators
- Universal Regression with Adversarial Responses
- HealthPrompt: A Zero-shot Learning Paradigm for Clinical Natural Language Processing
- On Linking Level Segments
- SynWoodScape: Synthetic Surround-view Fisheye Camera Dataset for Autonomous Driving
- Optical Flow Training under Limited Label Budget via Active Learning
- Evaluating Proposed Fairness Models for Face Recognition Algorithms
- Adaptive Trajectory Prediction via Transferable GNN
- Dynamic Instance Domain Adaptation
- Transfer Learning as an Essential Tool for Digital Twins in Renewable Energy Systems
- Power-of-Two Quantization for Low Bitwidth and Hardware Compliant Neural Networks
- Learning to control from expert demonstrations
- Sentence-Select: Large-Scale Language Model Data Selection for Rare-Word Speech Recognition
- Resource-Efficient Invariant Networks: Exponential Gains by Unrolled Optimization
- UNeXt: MLP-based Rapid Medical Image Segmentation Network
- Metastatic Cancer Outcome Prediction with Injective Multiple Instance Pooling
- Neural Data-Dependent Transform for Learned Image Compression
- Learning the Degradation Distribution for Blind Image Super-Resolution
- Renyi Fair Information Bottleneck for Image Classification
- Do better ImageNet classifiers assess perceptual similarity better?
- Data-Efficient Structured Pruning via Submodular Optimization
- Addressing Bias in Visualization Recommenders by Identifying Trends in Training Data: Improving VizML Through a Statistical Analysis of the Plotly Community Feed
- Deep Generative Models for Downlink Channel Estimation in FDD Massive MIMO Systems
- Triangular Character Animation Sampling with Motion, Emotion, and Relation
- DISCO: Comprehensive and Explainable Disinformation Detection
- Investigation of Factorized Optical Flows as Mid-Level Representations
- Correlated quantization for distributed mean estimation and optimization
- The Severity Prediction of The Binary And Multi-Class Cardiovascular Disease -- A Machine Learning-Based Fusion Approach
- Effects of Epileptiform Activity on Discharge Outcome in Critically Ill Patients
- Monitoring Time Series With Missing Values: a Deep Probabilistic Approach
- Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers
- DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering
- Rethinking data-driven point spread function modeling with a differentiable optical model
- KPE: Keypoint Pose Encoding for Transformer-based Image Generation
- What Matters For Meta-Learning Vision Regression Tasks?
- Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction
- A Brain-Inspired Low-Dimensional Computing Classifier for Inference on Tiny Devices
- Low-light Image and Video Enhancement via Selective Manipulation of Chromaticity
- Efficient Image Representation Learning with Federated Sampled Softmax
- Reverse Engineering ℓp attacks: A block-sparse optimization approach with recovery guarantees
- VGQ-CNN: Moving Beyond Fixed Cameras and Top-Grasps for Grasp Quality Prediction
- CEU-Net: Ensemble Semantic Segmentation of Hyperspectral Images Using Clustering
- Unsupervised Alignment of Distributional Word Embeddings
- PET: An Annotated Dataset for Process Extraction from Natural Language Text
- Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inference
- Binary Classification Under ℓ0 Attacks for General Noise Distribution
- Federated Minimax Optimization: Improved Convergence Analyses and Algorithms
- Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction
- CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers
- Computing unsatisfiable cores for LTLf specifications
- Automatic Language Identification for Celtic Texts
- A high-precision underwater object detection based on joint self-supervised deblurring and improved spatial transformer network
- Machine Learning based Optimal Feedback Control for Microgrid Stabilization
- Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancement
- A high-precision self-supervised monocular visual odometry in foggy weather based on robust cycled generative adversarial networks and multi-task learning aided depth estimation
- Benchmarking Graphormer on Large-Scale Molecular Modeling Datasets
- One-Shot Learning from a Demonstration with Hierarchical Latent Language
- NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimation
- Evaluation of YOLO Models with Sliced Inference for Small Object Detection
- Geometric Optimisation on Manifolds with Applications to Deep Learning
- Dimensionality Reduction and Prioritized Exploration for Policy Search
- No Efficient Disjunction or Conjunction of Switch-Lists
- Enhance Topics Analysis based on Keywords Properties
- Multiscale Convolutional Transformer with Center Mask Pretraining for Hyperspectral Image Classification
- Autoregressive based Drift Detection Method
- Explainable Machine Learning for Predicting Homicide Clearance in the United States
- Human Gaze Guided Attention for Surgical Activity Recognition
- SkinningNet: Two-Stream Graph Convolutional Neural Network for Skinning Prediction of Synthetic Characters
- Regularized Deep Signed Distance Fields for Reactive Motion Generation
- Anomaly Detection for Unmanned Aerial Vehicle Sensor Data Using a Stacked Recurrent Autoencoder Method with Dynamic Thresholding
- Pretrained Domain-Specific Language Model for General Information Retrieval Tasks in the AEC Domain
- Language Diversity: Visible to Humans, Exploitable by Machines
- Defending Black-box Skeleton-based Human Activity Classifiers
All 178
- On a linear fused Gromov-Wasserstein distance for graph structured data
- A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection
- Data Representativity for Machine Learning and AI Systems
- FlexIT: Towards Flexible Semantic Image Translation
- LEMON: LanguagE ModeL for Negative Sampling of Knowledge Graph Embeddings
- ModulE: Module Embedding for Knowledge Graphs
- Multi-robot Cooperative Pursuit via Potential Field-Enhanced Reinforcement Learning
- Gym-saturation: an OpenAI Gym environment for saturation provers
- Robust Federated Learning Against Adversarial Attacks for Speech Emotion Recognition
- Align-Deform-Subtract: An Interventional Framework for Explaining Object Differences
- FragmGAN: Generative Adversarial Nets for Fragmentary Data Imputation and Prediction
- The Cross-evaluation of Machine Learning-based Network Intrusion Detection Systems
- SparseChem: Fast and accurate machine learning model for small molecules
- Deep learning-based reconstruction of highly accelerated 3D MRI
- Structure-Aware Flow Generation for Human Body Reshaping
- Towards Inadequately Pre-trained Models in Transfer Learning
- Quantum neural networks force fields generation
- Nested Named Entity Recognition as Latent Lexicalized Constituency Parsing
- ASET: Ad-hoc Structured Exploration of Text Collections [Extended Abstract]
- Simulation of Plenoptic Cameras
- Creating Realistic Ground Truth Data for the Evaluation of Calibration Methods for Plenoptic and Conventional Cameras
- Ray Tracing-Guided Design of Plenoptic Cameras
- Slangvolution: A Causal Analysis of Semantic Change and Frequency Dynamics in Slang
- Normal and Visibility Estimation of Human Face from a Single Image
- HAIDA: Biometric technological therapy tools for neurorehabilitation of Cognitive Impairment
- 3D Dense Face Alignment with Fused Features by Aggregating CNNs and GCNs
- Memory Efficient Continual Learning with Transformers
- Speaker Identification Experiments Under Gender De-Identification
- LEBP -- Language Expectation & Binding Policy: A Two-Stream Framework for Embodied Vision-and-Language Interaction Task Learning Agents
- Controllable Evaluation and Generation of Physical Adversarial Patch on Face Recognition
- PALI-NLP at SemEval-2022 Task 4: Discriminative Fine-tuning of Transformers for Patronizing and Condescending Language Detection
- Uni4Eye: Unified 2D and 3D Self-supervised Pre-training via Masked Image Modeling Transformer for Ophthalmic Image Classification
- Object-Based Visual Camera Pose Estimation From Ellipsoidal Model and 3D-Aware Ellipse Prediction
- Practical No-box Adversarial Attacks with Training-free Hybrid Image Transformation
- Attention-effective multiple instance learning on weakly stem cell colony segmentation
- Representation, learning, and planning algorithms for geometric task and motion planning
- Data-driven detector signal characterization with constrained bottleneck autoencoders
- Domain Generalization using Pretrained Models without Fine-tuning
- Mapping global dynamics of benchmark creation and saturation in artificial intelligence
- Unsupervised Domain Adaptation across FMCW Radar Configurations Using Margin Disparity Discrepancy
- Multi-modal Brain Tumor Segmentation via Missing Modality Synthesis and Modality-level Attention Fusion
- Multi-Objective reward generalization: Improving performance of Deep Reinforcement Learning for applications in single-asset trading
- Reinforced Meta Active Learning
- A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices
- CP-ViT: Cascade Vision Transformer Pruning via Progressive Sparsity Prediction
- PHTrans: Parallelly Aggregating Global and Local Representations for Medical Image Segmentation
- All You Need is LUV: Unsupervised Collection of Labeled Images using Invisible UV Fluorescent Indicators
- Region-Aware Face Swapping
- MLNav: Learning to Safely Navigate on Martian Terrains
- Active Self-Semi-Supervised Learning for Few Labeled Samples
- Source-free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition
- ChiTransformer:Towards Reliable Stereo from Cues
- MetaCon: Unified Predictive Segments System with Trillion Concept Meta-Learning
- Monocular Depth Distribution Alignment with Low Computation
- Fast Road Segmentation via Uncertainty-aware Symmetric Network
- Metric Entropy Duality and the Sample Complexity of Outcome Indistinguishability
- Design of Detectors at the Electron Ion Collider with Artificial Intelligence
- Multi-Agent Active Search using Detection and Location Uncertainty
- Update Compression for Deep Neural Networks on the Edge
- Structure and Distribution Metric for Quantifying the Quality of Uncertainty: Assessing Gaussian Processes, Deep Neural Nets, and Deep Neural Operators for Regression
- Revealing the Excitation Causality between Climate and Political Violence via a Neural Forward-Intensity Poisson Process
- ReVar: Strengthening Policy Evaluation via Reduced Variance Sampling
- Onception: Active Learning with Expert Advice for Real World Machine Translation
- Image Steganography based on Style Transfer
- Error-based Knockoffs Inference for Controlled Feature Selection
- Multi-Agent Policy Transfer via Task Relationship Modeling
- 3SD: Self-Supervised Saliency Detection With No Labels
- Part-level Action Parsing via a Pose-guided Coarse-to-Fine Framework
- Boilerplate Detection via Semantic Classification of TextBlocks
- The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks
- On the Evaluation of Answer-Agnostic Paragraph-level Multi-Question Generation
- Autonomous Mosquito Habitat Detection Using Satellite Imagery and Convolutional Neural Networks for Disease Risk Mapping
- Downstream Fairness Caveats with Synthetic Healthcare Data
- Contextual Networks and Unsupervised Ranking of Sentences
- Probabilistic Rotation Representation With an Efficiently Computable Bingham Loss Function and Its Application to Pose Estimation
- Pruning Graph Convolutional Networks to select meaningful graph frequencies for fMRI decoding
- Machine Learning in NextG Networks via Generative Adversarial Networks
- Cooperative Trajectory Planning in Uncertain Environments with Monte Carlo Tree Search and Risk Metrics