Papers
Wed 26 Apr 2023
186 papers
- Multimodal Composite Association Score: Measuring Gender Bias in Generative Multimodal ModelsDiffusion models → Image generation, text-to-image and editing
- Multi-Party Chat: Conversational Agents in Group Settings with Humans and ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
- Distance Weighted Supervised Learning for Offline Interaction DataOffline RL and imitation learning from data → Offline RL algorithms
- Hopfield model with planted patterns: a teacher-student self-supervised learning modelKnowledge distillation → General knowledge distillation methods
- DiffuseExpand: Expanding dataset for 2D medical image segmentation using diffusion modelsDiffusion models → Medical imaging and segmentation
- From Association to Generation: Text-only Captioning by Unsupervised Cross-modal MappingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Score-based Generative Modeling Through Backward Stochastic Differential Equations: Inversion and GenerationDiffusion models → Diffusion foundations and sampling
- Single-View Height Estimation with Conditional Diffusion Probabilistic ModelsDiffusion models → Inverse problems and image restoration
- Safe Deployment for Counterfactual Learning to Rank with Exposure-Based Risk Minimization
- Noise-Tolerance GPU-based Age Estimation Using ResNet-50
- An Edge Assisted Robust Smart Traffic Management and Signalling System for Guiding Emergency Vehicles During Peak Hours
- An EEG Channel Selection Framework for Driver Drowsiness Detection via Interpretability Guidance
- ScatterFormer: Locally-Invariant Scattering Transformer for Patient-Independent Multispectral Detection of Epileptiform Discharges
- Human Activity Recognition Using Self-Supervised Representations of Wearable Data
- Training Large Scale Polynomial CNNs for E2E Inference over Homomorphic Encryption
- SSTM: Spatiotemporal Recurrent Transformers for Multi-frame Optical Flow Estimation
- Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining
- Deep Learning Techniques for Hyperspectral Image Analysis in Agriculture: A Review
- MasonNLP+ at SemEval-2023 Task 8: Extracting Medical Questions, Experiences and Claims from Social Media using Knowledge-Augmented Pre-trained Language Models
- Typical and atypical solutions in non-convex neural networks with discrete and continuous weights
- Transferring Procedural Knowledge across Commonsense Tasks
- highway2vec -- representing OpenStreetMap microregions with respect to their road network characteristics
- Ensoul: A framework for the creation of self organizing intelligent ultra low power systems (SOULS) through evolutionary enerstatic networks
- The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks
- Enhancing Inverse Problem Solutions with Accurate Surrogate Simulators and Promising Candidates
- Understand the Dynamic World: An End-to-End Knowledge Informed Framework for Open Domain Entity State Tracking
- Categorising Products in an Online Marketplace: An Ensemble Approach
- Do SSL Models Have D'ej`a Vu? A Case of Unintended Memorization in Self-supervised Learning
- Bootstrapped Edge Count Tests for Nonparametric Two-Sample Inference Under Heterogeneity
- Extracting Structured Seed-Mediated Gold Nanorod Growth Procedures from Literature with GPT-3
- GazeSAM: What You See is What You Segment
- AI-based Predictive Analytic Approaches for safeguarding the Future of Electric/Hybrid Vehicles
- A Deep Learning Framework for Verilog Autocompletion Towards Design and Verification Automation
- On Pitfalls of textitRemOve-And-Retrain: Data Processing Inequality Perspective
- Mixtures of Gaussian process experts based on kernel stick-breaking processes
- Adaptation to Misspecified Kernel Regularity in Kernelised Bandits
- Programmatically Grounded, Compositionally Generalizable Robotic Manipulation
- MAPConNet: Self-supervised 3D Pose Transfer with Mesh and Point Contrastive Learning
- Guaranteed Quantization Error Computation for Neural Network Model Compression
- A Data-Driven Hybrid Automaton Framework to Modeling Complex Dynamical Systems
- Translate to Disambiguate: Zero-shot Multilingual Word Sense Disambiguation with Pretrained Language Models
- Latent Fingerprint Recognition: Fusion of Local and Global Embeddings
- Physics-informed neural networks for predicting gas flow dynamics and unknown parameters in diesel engines
- Generalized generalized linear models: Convex estimation and online bounds
- Surrogate Assisted Generation of Human-Robot Interaction Scenarios
- Customized Segment Anything Model for Medical Image Segmentation
- Fine Tuning with Abnormal Examples
- Advancing Ischemic Stroke Diagnosis: A Novel Two-Stage Approach for Blood Clot Origin Identification
- Towards ethical multimodal systems
- PhagoStat a scalable and interpretable end to end framework for efficient quantification of cell phagocytosis in neurodegenerative disease studies
- Enhancing Robustness of Gradient-Boosted Decision Trees through One-Hot Encoding and Regularization
- TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation
- Scalable, Distributed AI Frameworks: Leveraging Cloud Computing for Enhanced Deep Learning Performance and Efficiency
- AIRIVA: A Deep Generative Model of Adaptive Immune Repertoires
- Automated Whole Slide Imaging for Label-Free Histology using Photon Absorption Remote Sensing Microscopy
- The Internal State of an LLM Knows When It's Lying
- A Control-Centric Benchmark for Video Prediction
- Controllable Image Generation via Collage Representations
- Sparsified Model Zoo Twins: Investigating Populations of Sparsified Neural Network Models
- Association Rules Mining with Auto-Encoders
- Evaluation of GPT-3.5 and GPT-4 for supporting real-world information needs in healthcare delivery
- Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond
- UniNeXt: Exploring A Unified Architecture for Vision Recognition
- HeySQuAD: A Spoken Question Answering Dataset
- Unlocking the Potential of Collaborative AI -- On the Socio-technical Challenges of Federated Machine Learning
- Ray Conditioning: Trading Photo-consistency for Photo-realism in Multi-view Image Generation
- Measuring Bias in AI Models: An Statistical Approach Introducing N-Sigma
- A marker-less human motion analysis system for motion-based biomarker discovery in knee disorders
- FVP: Fourier Visual Prompting for Source-Free Unsupervised Domain Adaptation of Medical Image Segmentation
- Learning battery model parameter dynamics from data with recursive Gaussian process regression
- Using Implicit Feedback to Improve Question Generation
- Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning
- What Happened 3 Seconds Ago? Inferring the Past with Thermal Imaging
- A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering
- Data-driven Piecewise Affine Decision Rules for Stochastic Programming with Covariate Information
- PVP: Pre-trained Visual Parameter-Efficient Tuning
- AutoCure: Automated Tabular Data Curation Technique for ML Pipelines
- HausaNLP at SemEval-2023 Task 12: Leveraging African Low Resource TweetData for Sentiment Analysis
- The Roles of Symbols in Neural-based AI: They are Not What You Think!
- HDR-VDP-3: A multi-metric for predicting image differences, quality and contrast distortions in high dynamic range and regular content
- ChartSumm: A Comprehensive Benchmark for Automatic Chart Summarization of Long and Short Summaries
- Non-rigid Point Cloud Registration for Middle Ear Diagnostics with Endoscopic Optical Coherence Tomography
- CROP: Towards Distributional-Shift Robust Reinforcement Learning using Compact Reshaped Observation Processing
- Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentation
- Multi-View Stereo Representation Revisit: Region-Aware MVSNet
- SIMARA: a database for key-value information extraction from full pages
- Shades of meaning: Uncovering the geometry of ambiguous word representations through contextualised language models
- Video Frame Interpolation with Densely Queried Bilateral Correlation
- Diffsurv: Differentiable sorting for censored time-to-event data
- Thompson Sampling Regret Bounds for Contextual Bandits with sub-Gaussian rewards
- Synthetic Aperture Anomaly Imaging
- Energy-Based Sliced Wasserstein Distance
- Multi-Modality Deep Network for Extreme Learned Image Compression
- Improvements on Recommender System based on Mathematical Principles
- Tissue Classification During Needle Insertion Using Self-Supervised Contrastive Learning and Optical Coherence Tomography
- Quantum Natural Policy Gradients: Towards Sample-Efficient Reinforcement Learning
- Toxic comments reduce the activity of volunteer editors on Wikipedia
- Technical Report: Impact of Position Bias on Language Models in Token Classification
- Towards Multi-Modal DBMSs for Seamless Querying of Texts and Tables
- Killing Two Birds with One Stone: Quantization Achieves Privacy in Distributed Learning
All 186
- Tensor Decomposition for Model Reduction in Neural Networks: A Review
- A mean-field games laboratory for generative modeling
- Key-value information extraction from full handwritten pages
- Super-NeRF: View-consistent Detail Generation for NeRF super-resolution
- Cluster Entropy: Active Domain Adaptation in Pathological Image Segmentation
- EasyPortrait -- Face Parsing and Portrait Segmentation Dataset
- Towards clinical AI fairness: A translational perspective
- Mixing Data Augmentation with Preserving Foreground Regions in Medical Image Segmentation
- Fundamental Tradeoffs in Learning with Prior Information
- Effect of latent space distribution on the segmentation of images with multiple annotations
- OPDN: Omnidirectional Position-aware Deformable Network for Omnidirectional Image Super-Resolution
- Unsupervised classification of fully kinetic simulations of plasmoid instability using Self-Organizing Maps (SOMs)
- Polynomial-Time Solvers for the Discrete ∞-Optimal Transport Problems
- A Comparative Analysis of Multiple Methods for Predicting a Specific Type of Crime in the City of Chicago
- Multidimensional Evaluation for Text Style Transfer Using ChatGPT
- From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection
- Neural-PBIR Reconstruction of Shape, Material, and Illumination
- Optimizing Energy Efficiency in Metro Systems Under Uncertainty Disturbances Using Reinforcement Learning
- Implicit Counterfactual Data Augmentation for Robust Learning
- GENIE-NF-AI: Identifying Neurofibromatosis Tumors using Liquid Neural Network (LTC) trained on AACR GENIE Datasets
- Compensation Learning in Semantic Segmentation
- Training-Free Location-Aware Text-to-Image Synthesis
- FLEX: an Adaptive Exploration Algorithm for Nonlinear Systems
- Learnable Ophthalmology SAM
- Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories
- Conjunctive Query Based Constraint Solving For Feature Model Configuration
- Are Explainability Tools Gender Biased? A Case Study on Face Presentation Attack Detection
- Regression with Sensor Data Containing Incomplete Observations
- Secure Communication Model For Quantum Federated Learning: A Post Quantum Cryptography (PQC) Framework
- Mutual information of spin systems from autoregressive neural networks
- Improving Adversarial Transferability via Intermediate-level Perturbation Decay
- Efficient Explainable Face Verification based on Similarity Score Argument Backpropagation
- FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models
- Development of a Realistic Crowd Simulation Environment for Fine-grained Validation of People Tracking Methods
- Filter Pruning via Filters Similarity in Consecutive Layers
- STIR: Siamese Transformer for Image Retrieval Postprocessing
- Group Equivariant BEV for 3D Object Detection
- VGOS: Voxel Grid Optimization for View Synthesis from Sparse Inputs
- Low-field magnetic resonance image enhancement via stochastic image quality transfer
- Blockchain-based Access Control for Secure Smart Industry Management Systems
- Streamlined Global and Local Features Combinator (SGLC) for High Resolution Image Dehazing
- SEAL: Simultaneous Label Hierarchy Exploration And Learning
- Feed-Forward Optimization With Delayed Feedback for Neural Network Training
- LoRaWAN-enabled Smart Campus: The Dataset and a People Counter Use Case
- Deep Lifelong Cross-modal Hashing
- Neuro-symbolic Zero-Shot Code Cloning with Cross-Language Intermediate Representation
- Discrepancy-Guided Reconstruction Learning for Image Forgery Detection
- TextDeformer: Geometry Manipulation using Text Guidance
- Concept-Monitor: Understanding DNN training through individual neurons
- SCM: Enhancing Large Language Model with Self-Controlled Memory Framework
- Multi-Task Learning Regression via Convex Clustering
- OpenBox: A Python Toolkit for Generalized Black-box Optimization
- Nominal Topology for Data Languages
- Evaluation of Regularization-based Continual Learning Approaches: Application to HAR
- A Portrait of Emotion: Empowering Self-Expression through AI-Generated Art
- Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNs
- HiQ -- A Declarative, Non-intrusive, Dynamic and Transparent Observability and Optimization System
- Prompting GPT-3.5 for Text-to-SQL with De-semanticization and Skeleton Retrieval
- Zero-Shot Slot and Intent Detection in Low-Resource Languages
- Membrane Potential Distribution Adjustment and Parametric Surrogate Gradient in Spiking Neural Networks
- ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot Learning
- The Closeness of In-Context Learning and Weight Shifting for Softmax Regression
- Federated Learning with Uncertainty-Based Client Clustering for Fleet-Wide Fault Diagnosis
- Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inference
- Games for Artificial Intelligence Research: A Review and Perspectives
- Bayesian Federated Learning: A Survey
- StepFormer: Self-supervised Step Discovery and Localization in Instructional Videos
- SHIELD: Thwarting Code Authorship Attribution
- Analyzing In-browser Cryptojacking
- Exploring the Curious Case of Code Prompts
- A Security Verification Framework of Cryptographic Protocols Using Machine Learning
- Learning to Predict Navigational Patterns from Partial Observations
- Structure Diagram Recognition in Financial Announcements
- Numerical Approximation of Andrews Plots with Optimal Spatial-Spectral Smoothing
- An Efficient Doubly-Robust Test for the Kernel Treatment Effect
- Multi-criteria Hardware Trojan Detection: A Reinforcement Learning Approach
- UNADON: Transformer-based model to predict genome-wide chromosome spatial position
- Generating Adversarial Examples with Task Oriented Multi-Objective Optimization
- Reinforcement Learning with Partial Parametric Model Knowledge
- Nonlocality and Nonlinearity Implies Universality in Operator Learning
- ZRG: A Dataset for Multimodal 3D Residential Rooftop Understanding
- Exploiting CNNs for Semantic Segmentation with Pascal VOC
- EverLight: Indoor-Outdoor Editable HDR Lighting Estimation
- Splitting physics-informed neural networks for inferring the dynamics of integer- and fractional-order neuron models
- Kernel Methods are Competitive for Operator Learning
- Graph-CoVis: GNN-based Multi-view Panorama Global Pose Estimation