Papers
Thu 13 Apr 2023
200 papers
- Soundini: Sound-Guided Diffusion for Natural Video EditingDiffusion models → Audio, speech and music
- RAFT: Reward rAnked FineTuning for Generative Foundation Model AlignmentLLM reasoning → Reinforcement learning for reasoning +1
- Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive StudyRetrieval-augmented generation → Generation and context integration
- Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and ReconstructionDiffusion models → 3D, point cloud and scene generation
- What does CLIP know about a red circle? Visual prompt engineering for VLMsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Control3Diff: Learning Controllable 3D Diffusion Models from Single-view ImagesDiffusion models → 3D, point cloud and scene generation
- DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-TuningDiffusion models → Diffusion foundations and sampling
- Intriguing properties of synthetic images: from generative adversarial networks to diffusion modelsDiffusion models → Image generation, text-to-image and editing
- [CLS] Token is All You Need for Zero-Shot Semantic SegmentationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- ChatGPT Needs SPADE (Sustainability, PrivAcy, Digital divide, and Ethics) Evaluation: A Review
- Deep state-space modeling for explainable representation, analysis, and generation of professional human poses
- A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services
- Automated Mapping of CVE Vulnerability Records to MITRE CWE Weaknesses
- A Reference Architecture for Designing Foundation Model based Systems
- PowerGAN: A Machine Learning Approach for Power Side-Channel Attack on Compute-in-Memory Accelerators
- Real-Time Helmet Violation Detection in AI City Challenge 2023 with Genetic Algorithm-Enhanced YOLOv5
- SigSegment: A Signal-Based Segmentation Algorithm for Identifying Anomalous Driving Behaviours in Naturalistic Driving Videos
- PALF: Pre-Annotation and Camera-LiDAR Late Fusion for the Easy Annotation of Point Clouds
- Accurate and Definite Mutational Effect Prediction with Lightweight Equivariant Graph Neural Networks
- DeepSegmenter: Temporal Action Localization for Detecting Anomalies in Untrimmed Naturalistic Driving Videos
- Real-time Multi-Class Helmet Violation Detection Using Few-Shot Data Sampling Technique and YOLOv8
- Bus Ridership Prediction with Time Section, Weather, and Ridership Trend Aware Multiple LSTM
- Supervised Machine Learning for Breast Cancer Risk Factors Analysis and Survival Prediction
- Road Network Representation Learning: A Dual Graph based Approach
- Language Instructed Reinforcement Learning for Human-AI Coordination
- MLOps Spanning Whole Machine Learning Life Cycle: A Survey
- Experts' cognition-driven safe noisy labels learning for precise segmentation of residual tumor in breast cancer
- Dynamic Mobile-Former: Strengthening Dynamic Convolution with Attention and Residual Connection in Kernel Space
- Evaluation of Social Biases in Recent Large Pre-Trained Models
- Vax-Culture: A Dataset for Studying Vaccine Discourse on Twitter
- Enhancing Self-Supervised Learning for Remote Sensing with Elevation Data: A Case Study with Scarce And High Level Semantic Labels
- CAR-DESPOT: Causally-Informed Online POMDP Planning for Robots in Confounded Environments
- SemEval-2023 Task 12: Sentiment Analysis for African Languages (AfriSenti-SemEval)
- PIE: Personalized Interest Exploration for Large-Scale Recommender Systems
- Video alignment using unsupervised learning of local and global features
- Structured Pruning for Multi-Task Deep Neural Networks
- Neural Network Architectures for Optical Channel Nonlinear Compensation in Digital Subcarrier Multiplexing Systems
- Estimate-Then-Optimize versus Integrated-Estimation-Optimization versus Sample Average Approximation: A Stochastic Dominance Perspective
- Task Adaptive Feature Transformation for One-Shot Learning
- DGNN-Booster: A Generic FPGA Accelerator Framework For Dynamic Graph Neural Network Inference
- Ranking from Pairwise Comparisons in General Graphs and Graphs with Locality
- Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction
- Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)
- Unified Out-Of-Distribution Detection: A Model-Specific Perspective
- Designing Nonlinear Photonic Crystals for High-Dimensional Quantum State Engineering
- Level generation for rhythm VR games
- Active Cost-aware Labeling of Streaming Data
- Sample Average Approximation for Black-Box VI
- On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence
- Efficient Sequence Transduction by Jointly Predicting Tokens and Durations
- ChatGPT cites the most-cited articles and journals, relying solely on Google Scholar's citation counts. As a result, AI may amplify the Matthew Effect in environmental science
- Speck: A Smart event-based Vision Sensor with a low latency 327K Neuron Convolutional Neuronal Network Processing Pipeline
- Inpaint Anything: Segment Anything Meets Image Inpainting
- Heterogeneous Oblique Double Random Forest
- A Polynomial Time, Pure Differentially Private Estimator for Binary Product Distributions
- A Distributionally Robust Approach to Regret Optimal Control using the Wasserstein Distance
- Semi-Equivariant Conditional Normalizing Flows
- Online Recognition of Incomplete Gesture Data to Interface Collaborative Robots
- PointCLIMB: An Exemplar-Free Point Cloud Class Incremental Benchmark
- Improving Gradient Methods via Coordinate Transformations: Applications to Quantum Machine Learning
- End-to-end codesign of Hessian-aware quantized neural networks for FPGAs and ASICs
- A Study of Biologically Plausible Neural Network: The Role and Interactions of Brain-Inspired Mechanisms in Continual Learning
- Near-Optimal Degree Testing for Bayes Nets
- PCD2Vec: A Poisson Correction Distance-Based Approach for Viral Host Classification
- Expressive Text-to-Image Generation with Rich Text
- RoboBEV: Towards Robust Bird's Eye View Perception under Corruptions
- Segment Everything Everywhere All at Once
- Representing Volumetric Videos as Dynamic MLP Maps
- STU-Net: Scalable and Transferable Medical Image Segmentation Models Empowered by Large-Scale Supervised Pre-training
- Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance
- DiffusionRig: Learning Personalized Priors for Facial Appearance Editing
- Remote Sensing Change Detection With Transformers Trained from Scratch
- Verbs in Action: Improving verb understanding in video-language models
- Toward Reliable Human Pose Forecasting with Uncertainty
- Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields
- How Will It Drape Like? Capturing Fabric Mechanics from Depth Images
- Gated Multi-Resolution Transfer Network for Burst Restoration and Enhancement
- Learning Personalized Decision Support Policies
- Improving novelty detection with generative adversarial networks on hand gesture data
- OKRidge: Scalable Optimal k-Sparse Ridge Regression
- A Learnheuristic Approach to A Constrained Multi-Objective Portfolio Optimisation Problem
- LSFSL: Leveraging Shape Information in Few-shot Learning
- Diagnostic Benchmark and Iterative Inpainting for Layout-Guided Image Generation
- Deep neural networks have an inbuilt Occam's razor
- DynaMITe: Dynamic Query Bootstrapping for Multi-object Interactive Segmentation Transformer
- D-SVM over Networked Systems with Non-Ideal Linking Conditions
- Deep Learning in Breast Cancer Imaging: A Decade of Progress and Future Directions
- Graph2topic: an opensource topic modeling framework based on sentence embedding and community detection
- ProtoDiv: Prototype-guided Division of Consistent Pseudo-bags for Whole-slide Image Classification
- How Useful are Educational Questions Generated by Large Language Models?
- PGTask: Introducing the Task of Profile Generation from Dialogues
- CoSDA: Continual Source-Free Domain Adaptation
- Exploring the State of the Art in Legal QA Systems
- Class-Incremental Learning of Plant and Disease Detection: Growing Branches with Knowledge Distillation
- Convergence rate of Tsallis entropic regularized optimal transport
- False Claims against Model Ownership Resolution
- A-CAP: Anticipation Captioning with Commonsense Knowledge
- Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation
- Beyond Submodularity: A Unified Framework of Randomized Set Selection with Group Fairness Constraints
- Solving Tensor Low Cycle Rank Approximation
All 200
- Bayesian Inference for Jump-Diffusion Approximations of Biochemical Reaction Networks
- Brain Structure Ages -- A new biomarker for multi-disease classification
- ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning
- Adversarial Examples from Dimensional Invariance
- Bayes classifier cannot be learned from noisy responses with unknown noise rates
- counterfactuals: An R Package for Counterfactual Explanation Methods
- Deep reinforcement learning applied to an assembly sequence planning problem with user preferences
- NeRD: Neural field-based Demosaicking
- Real-Time Wheel Detection and Rim Classification in Automotive Production
- Are LLMs All You Need for Task-Oriented Dialogue?
- Decentralized federated learning methods for reducing communication cost and energy consumption in UAV networks
- Non-asymptotic convergence bounds for Sinkhorn iterates and their gradients: a coupling approach
- Multi-kernel Correntropy-based Orientation Estimation of IMUs: Gradient Descent Methods
- RadarGNN: Transformation Invariant Graph Neural Network for Radar-based Perception
- DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videos
- Temporal Knowledge Sharing enable Spiking Neural Network Learning from Past and Future
- Transfer Knowledge from Head to Tail: Uncertainty Calibration under Long-tailed Distribution
- Event-based tracking of human hands
- SepicNet: Sharp Edges Recovery by Parametric Inference of Curves in 3D Shapes
- Power-seeking can be probable and predictive for trained agents
- Dynamics-Based Intrinsic Signal Model for High-Dimensional, Small-Sample Data
- A Comprehensive Comparison of Projections in Omnidirectional Super-Resolution
- Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation Learning
- Masakhane-Afrisenti at SemEval-2023 Task 12: Sentiment Analysis using Afro-centric Language Models and Adapters for Low-resource African Languages
- CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network with Large Input
- PDFVQA: A New Dataset for Real-World VQA on PDF Documents
- SpectFormer: Frequency and Attention is what you need in a Vision Transformer
- Zoom-VQA: Patches, Frames and Clips Integration for Video Quality Assessment
- High-Fidelity Zero-Shot Texture Anomaly Localization Using Feature Correspondence Analysis
- Certified Zeroth-order Black-Box Defense with Robust UNet Denoiser
- In-Distribution and Out-of-Distribution Self-supervised ECG Representation Learning for Arrhythmia Detection
- Tracking by 3D Model Estimation of Unknown Objects in Videos
- Quantifying and Explaining Machine Learning Uncertainty in Predictive Process Monitoring: An Operations Research Perspective
- Meta-Auxiliary Learning for Adaptive Human Pose Prediction
- Leveraging triplet loss for unsupervised action segmentation
- Why Existing Multimodal Crowd Counting Datasets Can Lead to Unfulfilled Expectations in Real-World Applications
- Learning Accurate Performance Predictors for Ultrafast Automated Model Compression
- VISION DIFFMASK: Faithful Interpretation of Vision Transformers with Differentiable Patch Masking
- TransHP: Image Classification with Hierarchical Prompting
- Multi-Subset Approach to Early Sepsis Prediction
- Generalizable Deep Learning Method for Suppressing Unseen and Multiple MRI Artifacts Using Meta-learning
- Emergence of Symbols in Neural Networks for Semantic Understanding and Communication
- Signal Reconstruction from Samples at Unknown Locations with Application to 2D Unknown View Tomography
- Towards hypergraph cognitive networks as feature-rich models of knowledge
- 3DoF Localization from a Single Image and an Object Map: the Flatlandia Problem and Dataset
- Sign Language Translation from Instructional Videos
- Robust Multiview Multimodal Driver Monitoring System Using Masked Multi-Head Self-Attention
- IBIA: An Incremental Build-Infer-Approximate Framework for Approximate Inference of Partition Function
- AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models
- Deep Metric Multi-View Hashing for Multimedia Retrieval
- ODAM: Gradient-based instance-specific visual explanations for object detection
- Neuromorphic Event-based Facial Expression Recognition
- Neural State-Space Models: Empirical Evaluation of Uncertainty Quantification
- Decidability of Querying First-Order Theories via Countermodels of Finite Width
- DDT: Dual-branch Deformable Transformer for Image Denoising
- ASR: Attention-alike Structural Re-parameterization
- Streamlined Framework for Agile Forecasting Model Development towards Efficient Inventory Management
- RoSI: Recovering 3D Shape Interiors from Few Articulation Images
- Computational modeling of semantic change
- Attributed Multi-order Graph Convolutional Network for Heterogeneous Graphs
- Deep Learning-based Fall Detection Algorithm Using Ensemble Model of Coarse-fine CNN and GRU Networks
- iDisc: Internal Discretization for Monocular Depth Estimation
- Priors for symbolic regression
- Understanding Overfitting in Adversarial Training via Kernel Regression
- Learning-based Spatial and Angular Information Separation for Light Field Compression
- Survey on LiDAR Perception in Adverse Weather Conditions
- Sequential Monte Carlo applied to virtual flow meter calibration
- Out-of-distribution Few-shot Learning For Edge Devices without Model Fine-tuning
- Rule-based detection of access to education and training in Germany
- Efficient Multimodal Fusion via Interactive Prompting
- Boosting Convolutional Neural Networks with Middle Spectrum Grouped Convolution
- ALR-GAN: Adaptive Layout Refinement for Text-to-Image Synthesis
- Improved Naive Bayes with Mislabeled Data
- NeRFVS: Neural Radiance Fields for Free View Synthesis via Geometry Scaffolds
- Automated Cardiovascular Record Retrieval by Multimodal Learning between Electrocardiogram and Clinical Report
- Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learning
- Optimizing Multi-Domain Performance with Active Learning-based Improvement Strategies
- Noisy Correspondence Learning with Meta Similarity Correction
- EWT: Efficient Wavelet-Transformer for Single Image Denoising
- Gamifying Math Education using Object Detection
- Canonical and Noncanonical Hamiltonian Operator Inference
- MProtoNet: A Case-Based Interpretable Model for Brain Tumor Classification with 3D Multi-parametric Magnetic Resonance Imaging
- SPColor: Semantic Prior Guided Exemplar-based Image Colorization
- Fair Grading Algorithms for Randomized Exams
- Enhancing Model Learning and Interpretation Using Multiple Molecular Graph Representations for Compound Property and Activity Prediction
- Importance is Important: Generalized Markov Chain Importance Sampling Methods
- RSIR Transformer: Hierarchical Vision Transformer using Random Sampling Windows and Important Region Windows
- Set-Based Face Recognition Beyond Disentanglement: Burstiness Suppression With Variance Vocabulary
- LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Model
- ShapeClipper: Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-based Consistency
- Computationally-Efficient Neural Image Compression with Shallow Decoders
- Deep learning based ECG segmentation for delineation of diverse arrhythmias
- Cross-View Hierarchy Network for Stereo Image Super-Resolution
- Physics-informed radial basis network (PIRBN): A local approximating neural network for solving nonlinear PDEs
- Situational-Aware Multi-Graph Convolutional Recurrent Network (SA-MGCRN) for Travel Demand Forecasting During Wildfires
- Improving Segmentation of Objects with Varying Sizes in Biomedical Images using Instance-wise and Center-of-Instance Segmentation Loss Function
- Boosting Video Object Segmentation via Space-time Correspondence Learning
- Difficult Lessons on Social Prediction from Wisconsin Public Schools
- LeafAI: query generator for clinical cohort discovery rivaling a human programmer
- SURFSUP: Learning Fluid Simulation for Novel Surfaces