Papers
Fri 29 Apr 2022
131 papers
- Flamingo: a Visual Language Model for Few-Shot LearningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Training Language Models with Language FeedbackLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
- PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model PretrainingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Fast Sampling of Diffusion Models with Exponential IntegratorDiffusion models → Diffusion foundations and sampling
- Vision-Language Pre-Training for Boosting Scene Text DetectorsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Hysteretic Behavior Simulation Based on Pyramid Neural Network:Principle, Network Architecture, Case Study and Explanation
- Measuring Plagiarism in Introductory Programming Course Assignments
- Characterizing TMS-EEG perturbation indexes using signal energy: initial study on Alzheimer's Disease classification
- Multichannel Synthetic Preictal EEG Signals to Enhance the Prediction of Epileptic Seizures
- Concept Activation Vectors for Generating User-Defined 3D Shapes
- A Novel Fully Annotated Thermal Infrared Face Dataset: Recorded in Various Environment Conditions and Distances From The Camera
- The scope for AI-augmented interpretation of building blueprints in commercial and industrial property insurance
- Adversarial attacks on an optical neural network
- Distributed intelligence on the Edge-to-Cloud Continuum: A systematic literature review
- Enhanced Physics-Informed Neural Networks with Augmented Lagrangian Relaxation Method (AL-PINNs)
- Markov Abstractions for PAC Reinforcement Learning in Non-Markov Decision Processes
- Family of Two Dimensional Transition Metal Dichlorides Fundamental Properties, Structural Defects, and Environmental Stability
- Bridging Differential Privacy and Byzantine-Robustness via Model Aggregation
- Who's the Expert? On Multi-source Belief Change
- A Simple Method to Boost Human Pose Estimation Accuracy by Correcting the Joint Regressor for the Human3.6m Dataset
- On Negative Sampling for Audio-Visual Contrastive Learning from Movies
- Doubting AI Predictions: Influence-Driven Second Opinion Recommendation
- Birds' Eye View: Measuring Behavior and Posture of Chickens as a Metric for Their Well-Being
- The Directional Bias Helps Stochastic Gradient Descent to Generalize in Kernel Regression Models
- Implicit Regularization Properties of Variance Reduced Stochastic Mirror Descent
- Prompt Consistency for Zero-Shot Task Generalization
- Joint Multisided Exposure Fairness for Recommendation
- Logically Consistent Adversarial Attacks for Soft Theorem Provers
- Answer Consolidation: Formulation and Benchmarking
- What do we Really Know about State of the Art NER?
- A Human-Centric Perspective on Fairness and Transparency in Algorithmic Decision-Making
- Self-Aware Feedback-Based Self-Learning in Large-Scale Conversational AI
- Graph Learning from Multivariate Dependent Time Series via a Multi-Attribute Formulation
- End-to-end Spoken Conversational Question Answering: Task, Dataset and Model
- How Robust is Neural Machine Translation to Language Imbalance in Multilingual Tokenizer Training?
- Polyglot Prompt: Multilingual Multitask PrompTraining
- Finite Entailment of UCRPQs over ALC Ontologies
- Handling and Presenting Harmful Text in NLP Research
- Human-in-the-loop online multi-agent approach to increase trustworthiness in ML models through trust scores and data augmentation
- OSSGAN: Open-Set Semi-Supervised Image Generation
- CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification
- Training Naturalized Semantic Parsers with Very Little Data
- EndoMapper dataset of complete calibrated endoscopy procedures
- Combining Lipschitz and RBF Surrogate Models for High-dimensional Computationally Expensive Problems
- Hardware Trojan Detection Using Unsupervised Deep Learning on Quantum Diamond Microscope Magnetic Field Images
- TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models
- Preoperative brain tumor imaging: models and software for segmentation and standardized reporting
- Improving Transferability for Domain Adaptive Detection Transformers
- Industry-academia research collaboration and knowledge co-creation: Patterns and anti-patterns
- Segmentation of kidney stones in endoscopic video feeds
- Explainable AI via Learning to Optimize
- Frontiers and Exact Learning of ELI Queries under DL-Lite Ontologies
- Tractable Uncertainty for Structure Learning
- OPERA:Operation-Pivoted Discrete Reasoning over Text
- A Framework for Constructing Machine Learning Models with Feature Set Optimisation for Evapotranspiration Partitioning
- Learning Anisotropic Interaction Rules from Individual Trajectories in a Heterogeneous Cellular Population
- Towards Automatic Parsing of Structured Visual Content through the Use of Synthetic Data
- Wide and Deep Neural Networks Achieve Optimality for Classification
- On the Optimization of Margin Distribution
- SATfeatPy -- A Python-based Feature Extraction System for Satisfiability
- Developmental Negation Processing in Transformer Language Models
- Seeing without Looking: Analysis Pipeline for Child Sexual Abuse Datasets
- Reducing Neural Architecture Search Spaces with Training-Free Statistics and Computational Graph Clustering
- Adversarial Distortion Learning for Medical Image Denoising
- Climate and Weather: Inspecting Depression Detection via Emotion Recognition
- Bayesian Information Criterion for Event-based Multi-trial Ensemble data
- Learning Localization-aware Target Confidence for Siamese Visual Tracking
- Fix the Noise: Disentangling Source Feature for Transfer Learning of StyleGAN
- Controlled Generation of Unseen Faults for Partial and Open-Partial Domain Adaptation
- Accelerating nuclear-norm regularized low-rank matrix optimization through Burer-Monteiro decomposition
- Topological Data Analysis in Time Series: Temporal Filtration and Application to Single-Cell Genomics
- A Deep Learning based No-reference Quality Assessment Model for UGC Videos
- C3-STISR: Scene Text Image Super-resolution with Triple Clues
- A Challenging Benchmark of Anime Style Recognition
- Neural Implicit Representations for Physical Parameter Inference from a Single Video
- Data+Shift: Supporting visual investigation of data distribution shifts by data scientists
- Exploration and Exploitation in Federated Learning to Exclude Clients with Poisoned Data
- Backdoor Attacks in Federated Learning by Rare Embeddings and Gradient Ensembling
- Local Explanation of Dimensionality Reduction
- Robust Solutions for Multi-Defender Stackelberg Security Games
- Statistical applications of contrastive learning
- AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement
- ExaASC: A General Target-Based Stance Detection Corpus in Arabic Language
- Making sense of violence risk predictions using clinical notes
- Using 3D Shadows to Detect Object Hiding Attacks on Autonomous Vehicle Perception
- Cost Effective MLaaS Federation: A Combinatorial Reinforcement Learning Approach
- Tailored Uncertainty Estimation for Deep Learning Systems
- SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonization
- PIE: a Parameter and Inference Efficient Solution for Large Scale Knowledge Graph Embedding Reasoning
- "My nose is running.""Are you also coughing?": Building A Medical Diagnosis Agent with Interpretable Inquiry Logics
- Deep Geometry Post-Processing for Decompressed Point Clouds
- User Experience Design for Automatic Credibility Assessment of News Content About COVID-19
- PnP-ReG: Learned Regularizing Gradient for Plug-and-Play Gradient Descent
- Short-Term Density Forecasting of Low-Voltage Load using Bernstein-Polynomial Normalizing Flows
- KERMIT -- A Transformer-Based Approach for Knowledge Graph Matching
- Maxmin Participatory Budgeting
- QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevance
- Privacy-Preserving Model Upgrades with Bidirectional Compatible Training in Image Retrieval
- A Mixed-Domain Self-Attention Network for Multilabel Cardiac Irregularity Classification Using Reduced-Lead Electrocardiogram
- A study of tree-based methods and their combination
All 131
- Czech Dataset for Cross-lingual Subjectivity Classification
- Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image Retrieval
- Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time-Series Forecast
- Unsupervised Reinforcement Learning for Transferable Manipulation Skill Discovery
- Framework for Behavioral Disorder Detection Using Machine Learning and Application of Virtual Cognitive Behavioral Therapy in COVID-19 Pandemic
- SideRT: A Real-time Pure Transformer Architecture for Single Image Depth Estimation
- Learning Adaptive Warping for Real-World Rolling Shutter Correction
- Autonomous In-Situ Soundscape Augmentation via Joint Selection of Masker and Gain
- Energy Minimization for Federated Asynchronous Learning on Battery-Powered Mobile Devices via Application Co-running
- Struct-MDC: Mesh-Refined Unsupervised Depth Completion Leveraging Structural Regularities from Visual SLAM
- OA-Mine: Open-World Attribute Mining for E-Commerce Products with Weak Supervision
- Multiple Degradation and Reconstruction Network for Single Image Denoising via Knowledge Distillation
- Por Qu'e N~ao Utiliser Alla Spraak? Mixed Training with Gradient Optimization in Few-Shot Cross-Lingual Transfer
- Where in the World is this Image? Transformer-based Geo-localization in the Wild
- One-Way Matching of Datasets with Low Rank Signals
- Equine radiograph classification using deep convolutional neural networks
- Detecting Textual Adversarial Examples Based on Distributional Characteristics of Data Representations
- H2H: Heterogeneous Model to Heterogeneous System Mapping with Computation and Communication Awareness
- COVID-Net US-X: Enhanced Deep Neural Network for Detection of COVID-19 Patient Cases from Convex Ultrasound Imaging Through Extended Linear-Convex Ultrasound Augmentation Learning
- Goldilocks-curriculum Domain Randomization and Fractal Perlin Noise with Application to Sim2Real Pneumonia Lesion Detection
- Repro: An Open-Source Library for Improving the Reproducibility and Usability of Publicly Available Research Code
- CATNet: Cross-event Attention-based Time-aware Network for Medical Event Prediction
- RoSA: A Robust Self-Aligned Framework for Node-Node Graph Contrastive Learning
- GenDR: A Generalized Differentiable Renderer
- VPNets: Volume-preserving neural networks for learning source-free dynamics
- A Bottom-Up End-User Intelligent Assistant Approach to Empower Gig Workers against AI Inequality
- An Extensive Data Processing Pipeline for MIMIC-IV
- Noise-reducing attention cross fusion learning transformer for histological image classification of osteosarcoma
- Understanding the impact of image and input resolution on deep digital pathology patch classifiers
- Designing for Responsible Trust in AI Systems: A Communication Perspective
- Sparse-Group Log-Sum Penalized Graphical Model Learning For Time Series