Papers
Sun 16 Apr 2023
79 papers
- Chain of Thought Prompt Tuning in Vision Language ModelsLLM reasoning → Multimodal reasoning +1
- Robust Cross-Modal Knowledge Distillation for Unconstrained VideosKnowledge distillation → Multimodal distillation
- H2CGL: Modeling Dynamics of Citation Network for Impact Prediction
- Vehicle Safety Management System
- Enhancing Electrical Impedance Tomography reconstruction using Learned Half-Quadratic Splitting Networks with Anderson Acceleration
- Digital Twins in Wind Energy: Emerging Technologies and Industry-Informed Future Directions
- Exploring the Use of ChatGPT as a Tool for Learning and Assessment in Undergraduate Computer Science Curriculum: Opportunities and Challenges
- Fairness in AI and Its Long-Term Implications on Society
- AutoSTL: Automated Spatio-Temporal Multi-Task Learning
- Solving Math Word Problems by Combining Language Models With Symbolic Solvers
- A Field Test of Bandit Algorithms for Recommendations: Understanding the Validity of Assumptions on Human Preferences in Multi-armed Bandits
- A comparison between Recurrent Neural Networks and classical machine learning approaches In Laser induced breakdown spectroscopy
- Likelihood-Based Generative Radiance Field with Latent Space Energy-Based Model for 3D-Aware Disentangled Image Representation
- GaitRef: Gait Recognition with Refined Sequential Skeletons
- CAT-NeRF: Constancy-Aware Tx2Former for Dynamic Body Modeling
- Recognizing Entity Types via Properties
- Brain Tumor classification and Segmentation using Deep Learning
- Harnessing Contrastive Learning and Neural Transformation for Time Series Anomaly Detection
- Out-of-Variable Generalization for Discriminative Models
- Ontology for Healthcare Artificial Intelligence Privacy in Brazil
- Bent & Broken Bicycles: Leveraging synthetic data for damaged object re-identification
- Federated Learning of Shareable Bases for Personalization-Friendly Image Classification
- Sabi'a: Portuguese Large Language Models
- A Neural Network Transformer Model for Composite Microstructure Homogenization
- The Segment Anything foundation model achieves favorable brain tumor autosegmentation accuracy on MRI to support radiotherapy treatment planning
- A Data-Centric Solution to NonHomogeneous Dehazing via Vision Transformer
- Neural Machine Translation For Low Resource Languages
- CEBoosting: Online Sparse Identification of Dynamical Systems with Regime Switching by Causation Entropy Boosting
- Penalized Likelihood Inference with Survey Data
- Towards Better Instruction Following Language Models for Chinese: Investigating the Impact of Training Data and Evaluation
- AI driven shadow model detection in agropv farms
- ChatPLUG: Open-Domain Generative Dialogue System with Internet-Augmented Instruction Tuning for Digital Human
- A Virtual Simulation-Pilot Agent for Training of Air Traffic Controllers
- Enhancing Automated Program Repair through Fine-tuning and Prompt Engineering
- An Interpretable Approach to Load Profile Forecasting in Power Grids using Galerkin-Approximated Koopman Pseudospectra
- The language of sounds unheard: Exploring musical timbre semantics of large language models
- A Random-patch based Defense Strategy Against Physical Attacks for Face Recognition Systems
- Time-dependent Iterative Imputation for Multivariate Longitudinal Clinical Data
- Comparative Study of MPPT and Parameter Estimation of PV cells
- VISAR: A Human-AI Argumentative Writing Assistant with Visual Programming and Rapid Draft Prototyping
- EasyNER: A Customizable Easy-to-Use Pipeline for Deep Learning- and Dictionary-based Named Entity Recognition from Medical and Life Science Text
- EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimation
- Assisting clinical practice with fuzzy probabilistic decision trees
- Harnessing Digital Pathology And Causal Learning To Improve Eosinophilic Esophagitis Dietary Treatment Assignment
- It's All in the Embedding! Fake News Detection Using Document Embeddings
- SikuGPT: A Generative Pre-trained Model for Intelligent Information Processing of Ancient Texts from the Perspective of Digital Humanities
- Syntactic Complexity Identification, Measurement, and Reduction Through Controlled Syntactic Simplification
- PCPNet: An Efficient and Semantic-Enhanced Transformer Network for Point Cloud Prediction
- A Comprehensive Evaluation of Neural SPARQL Query Generation from Natural Language Questions
- Spot The Odd One Out: Regularized Complete Cycle Consistent Anomaly Detector GAN
- Deep learning universal crater detection using Segment Anything Model (SAM)
- MisRoBAERTa: Transformers versus Misinformation
- Arbitrary Reduction of MRI Inter-slice Spacing Using Hierarchical Feature Conditional Diffusion
- GeoMultiTaskNet: remote sensing unsupervised domain adaptation using geographical coordinates
- Language Guided Local Infiltration for Interactive Image Retrieval
- Framework for Quality Evaluation of Smart Roadside Infrastructure Sensors for Automated Driving Applications
- JoB-VS: Joint Brain-Vessel Segmentation in TOF-MRA Images
- SeaThru-NeRF: Neural Radiance Fields in Scattering Media
- Canvas: End-to-End Kernel Architecture Search in Neural Networks
- TransFusionOdom: Interpretable Transformer-based LiDAR-Inertial Fusion Odometry Estimation
- MS-LSTM: Exploring Spatiotemporal Multiscale Representations in Video Prediction Domain
- A Novel end-to-end Framework for Occluded Pixel Reconstruction with Spatio-temporal Features for Improved Person Re-identification
- Data-OOB: Out-of-bag Estimate as a Simple and Efficient Data Value
- Obstacle-Transformer: A Trajectory Prediction Network Based on Surrounding Trajectories
- Non-exemplar Class-incremental Learning by Random Auxiliary Classes Augmentation and Mixed Features
- Handling Heavy Occlusion in Dense Crowd Tracking by Focusing on the Heads
- An Empirical Study of Realized GNN Expressiveness
- A Clustering Framework for Unsupervised and Semi-supervised New Intent Discovery
- Translating Simulation Images to X-ray Images via Multi-Scale Semantic Matching
- Long-term Visual Localization with Mobile Sensors
- Learning Empirical Bregman Divergence for Uncertain Distance Representation
- MLRegTest: A Benchmark for the Machine Learning of Regular Languages
- Autoencoders with Intrinsic Dimension Constraints for Learning Low Dimensional Image Representations
- Using Geographic Location-based Public Health Features in Survival Analysis
- Multimodal Representation Learning of Cardiovascular Magnetic Resonance Imaging
- Explanations of Black-Box Models based on Directional Feature Interactions
- FedBlockHealth: A Synergistic Approach to Privacy and Security in IoT-Enabled Healthcare through Federated Learning and Blockchain
- ArguGPT: evaluating, understanding and identifying argumentative essays generated by GPT models
- Dynamic Exploration-Exploitation Trade-Off in Active Learning Regression with Bayesian Hierarchical Modeling