Papers
Fri 31 Mar 2023
203 papers
- Reference-based Image Composition with Sketch via Structure-aware Diffusion ModelDiffusion models → Image generation, text-to-image and editing
- Selective Reincarnation: Offline-to-Online Multi-Agent Reinforcement LearningOffline RL and imitation learning from data → Offline multi-agent RL
- Secure Federated Learning against Model Poisoning Attacks via Client FilteringLLM safety and security → Federated unlearning and poisoning
- ∞-Diff: Infinite Resolution Diffusion with Subsampled Mollified StatesDiffusion models → Diffusion foundations and sampling
- DIME-FM: DIstilling Multimodal and Efficient Foundation ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- A Closer Look at Parameter-Efficient Tuning in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- One-shot Unsupervised Domain Adaptation with Personalized Diffusion ModelsDiffusion models → Medical imaging and segmentation
- Knowledge Distillation for Feature Extraction in Underwater VSLAMKnowledge distillation → Detection and dense prediction distillation
- Grounding Object Relations in Language-Conditioned Robotic Manipulation with Semantic-Spatial ReasoningLLM reasoning → Spatial and embodied reasoning
- Selective Knowledge Distillation for Non-Autoregressive Neural Machine TranslationKnowledge distillation → Knowledge distillation for LLMs
- Trade-offs in Fine-tuned Diffusion Models Between Accuracy and InterpretabilityDiffusion models → Medical imaging and segmentation
- 3D-aware Image Generation using 2D Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
- CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model SocietyLLM agents and tool use → General LLM agent frameworks and benchmarks
- CQSumDP: A ChatGPT-Annotated Resource for Query-Focused Abstractive Summarization Based on Debatepedia
- A hybrid quantum-classical approach for inference on restricted Boltzmann machines
- "Genlangs" and Zipf's Law: Do languages generated by ChatGPT statistically look human?
- Improving Scene Text Recognition for Character-Level Long-Tailed Distribution
- Towards Mitigating ChatGPT's Negative Impact on Education: Optimizing Question Design through Bloom's Taxonomy
- FIR-based Future Trajectory Prediction in Nighttime Autonomous Driving
- A Novel Two-level Causal Inference Framework for On-road Vehicle Quality Issues Diagnosis
- Por'ownanie metod detekcji zajketo'sci widma radiowego z wykorzystaniem uczenia federacyjnego z oraz bez wkezla centralnego
- textite-Uber: A Crowdsourcing Platform for Electric Vehicle-based Ride- and Energy-sharing
- A Practitioner's Guide to Bayesian Inference in Pharmacometrics using Pumas
- Constructing Phylogenetic Networks via Cherry Picking and Machine Learning
- Temporal Dynamic Synchronous Functional Brain Network for Schizophrenia Diagnosis and Lateralization Analysis
- DoE2Vec: Deep-learning Based Features for Exploratory Landscape Analysis
- POLAR-Express: Efficient and Precise Formal Reachability Analysis of Neural-Network Controlled Systems
- Quick Dense Retrievers Consume KALE: Post Training Kullback Leibler Alignment of Embeddings for Asymmetrical dual encoders
- Adaptive structure evolution and biologically plausible synaptic plasticity for recurrent spiking neural networks
- Self-Supervised Multimodal Learning: A Survey
- Bandits for Sponsored Search Auctions under Unknown Valuation Model: Case Study in E-Commerce Advertising
- Deep Learning-based Diffusion Tensor Cardiac Magnetic Resonance Reconstruction: A Comparison Study
- FCC: Fusing Conversation History and Candidate Provenance for Contextual Response Ranking in Dialogue Systems
- Hierarchical Vision Transformers for Cardiac Ejection Fraction Estimation
- Improving extreme weather events detection with light-weight neural networks
- Lego-Features: Exporting modular encoder features for streaming and deliberation ASR
- Practical Conformer: Optimizing size, speed and flops of Conformer for on-Device and cloud ASR
- Soft-Bellman Equilibrium in Affine Markov Games: Forward Solutions and Inverse Learning
- Online Reinforcement Learning in Markov Decision Process Using Linear Programming
- Learning the Distribution of Errors in Stereo Matching for Joint Disparity and Uncertainty Estimation
- E(3) Equivariant Graph Neural Networks for Particle-Based Fluid Mechanics
- On the Relationships between Graph Neural Networks for the Simulation of Physical Systems and Classical Numerical Methods
- Directional Connectivity-based Segmentation of Medical Images
- A Surface-Based Federated Chow Test Model for Integrating APOE Status, Tau Deposition Measure, and Hippocampal Surface Morphometry
- DeforestVis: Behavior Analysis of Machine Learning Models with Surrogate Decision Stumps
- Decoding the End-to-end Writing Trajectory in Scholarly Manuscripts
- Enhancing Large Language Models with Climate Resources
- Extracting Thyroid Nodules Characteristics from Ultrasound Reports Using Transformer-based Natural Language Processing Methods
- Dense Sparse Retrieval: Using Sparse Language Models for Inference Efficient Dense Retrieval
- Identifying Symptoms of Delirium from Clinical Narratives Using Natural Language Processing
- Deep Factor Model: A Novel Approach for Motion Compensated Multi-Dimensional MRI
- SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tail
- DynamoPMU: A Physics Informed Anomaly Detection and Prediction Methodology using non-linear dynamics from μPMU Measurement Data
- Machine Learning for Economics Research: When What and How?
- A Generative Framework for Low-Cost Result Validation of Machine Learning-as-a-Service Inference
- A Meta-Summary of Challenges in Building Products with ML Components -- Collecting Experiences from 4758+ Practitioners
- A Physics-Informed Machine Learning for Electricity Markets: A NYISO Case Study
- To be Robust and to be Fair: Aligning Fairness with Robustness
- Weakly-Supervised Text-driven Contrastive Learning for Facial Behavior Understanding
- LivePose: Online 3D Reconstruction from Monocular Video with Dynamic Camera Poses
- Almost Linear Constant-Factor Sketching for ℓ1 and Logistic Regression
- Batch Normalization in Cytometry Data by kNN-Graph Preservation
- Ranking Regularization for Critical Rare Classes: Minimizing False Positives at a High True Positive Rate
- PEOPL: Characterizing Privately Encoded Open Datasets with Public Labels
- Accelerating exploration and representation learning with offline pre-training
- A robust deep learning-based damage identification approach for SHM considering missing data
- Understanding Reinforcement Learning Algorithms: The Progress from Basic Q-learning to Proximal Policy Optimization
- Demo Alleviate: Demonstrating Artificial Intelligence Enabled Virtual Assistance for Telehealth: The Mental Health Case
- What Makes for Effective Few-shot Point Cloud Classification?
- SemiMemes: A Semi-supervised Learning Approach for Multimodal Memes Analysis
- Video text tracking for dense and small text based on pp-yoloe-r and sort algorithm
- Towards Flexible Multi-modal Document Models
- Adaptive Sparse Pairwise Loss for Object Re-Identification
- 3D Human Pose Estimation via Intuitive Physics
- Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?
- Hypothesis testing on invariant subspaces of non-diagonalizable matrices with applications to network statistics
- Procedure-Aware Pretraining for Instructional Video Understanding
- A Survey of Large Language Models
- Fluctuation without dissipation: Microcanonical Langevin Monte Carlo
- SemHint-MD: Learning from Noisy Semantic Labels for Self-Supervised Monocular Depth Estimation
- A Scale-Invariant Sorting Criterion to Find a Causal Order in Additive Noise Models
- A Closer Look at Few-Shot 3D Point Cloud Classification
- Simple Contrastive Representation Learning for Time Series Forecasting
- GVP: Generative Volumetric Primitives
- Assessing Language Model Deployment with Risk Cards
- STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition
- Single Image Depth Prediction Made Better: A Multivariate Gaussian Take
- ViMMRC 2.0 -- Enhancing Machine Reading Comprehension on Vietnamese Literature Text
- Constrained Optimization of Rank-One Functions with Indicator Variables
- MAGNNETO: A Graph Neural Network-based Multi-Agent system for Traffic Engineering
- Large Dimensional Independent Component Analysis: Statistical Optimality and Computational Tractability
- Can AI Chatbots Pass the Fundamentals of Engineering (FE) and Principles and Practice of Engineering (PE) Structural Exams?
- Siamese DETR
- Efficient View Synthesis and 3D-based Multi-Frame Denoising with Multiplane Feature Representations
- Towards Nonlinear-Motion-Aware and Occlusion-Robust Rolling Shutter Correction
- BERTino: an Italian DistilBERT model
- UKP-SQuARE v3: A Platform for Multi-Agent QA Research
- Markerless 3D human pose tracking through multiple cameras and AI: Enabling high accuracy, robustness, and real-time performance
- A two-head loss function for deep Average-K classification
- Pair Programming with Large Language Models for Sampling and Estimation of Copulas
All 203
- The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASR
- Automatic Detection of Out-of-body Frames in Surgical Videos for Privacy Protection Using Self-supervised Learning and Minimal Labels
- Dataset and Baseline System for Multi-lingual Extraction and Normalization of Temporal and Numerical Expressions
- INoD: Injected Noise Discriminator for Self-Supervised Representation Learning in Agricultural Fields
- Evaluation Challenges for Geospatial ML
- RDMNet: Reliable Dense Matching Based Point Cloud Registration for Autonomous Driving
- Analysis and Comparison of Two-Level KFAC Methods for Training Deep Neural Networks
- Synergistic Graph Fusion via Encoder Embedding
- No Place to Hide: Dual Deep Interaction Channel Network for Fake News Detection based on Data Augmentation
- Differentially Private Stochastic Convex Optimization in (Non)-Euclidean Space Revisited
- Long-Short Temporal Co-Teaching for Weakly Supervised Video Anomaly Detection
- Scardina: Scalable Join Cardinality Estimation by Multiple Density Estimators
- Traffic Sign Recognition Dataset and Data Augmentation
- Simple Domain Generalization Methods are Strong Baselines for Open Domain Generalization
- Evaluating GPT-4 and ChatGPT on Japanese Medical Licensing Examinations
- The Topology-Overlap Trade-Off in Retinal Arteriole-Venule Segmentation
- Live image-based neurosurgical guidance and roadmap generation using unsupervised embedding
- Rapid prediction of lab-grown tissue properties using deep learning
- LaCViT: A Label-aware Contrastive Fine-tuning Framework for Vision Transformers
- Exploiting Multilingualism in Low-resource Neural Machine Translation via Adversarial Learning
- Augmented Collective Intelligence in Collaborative Ideation: Agenda and Challenges
- Asking Better Questions -- The Art and Science of Forecasting: A mechanism for truer answers to high-stakes questions
- Artificial Intelligence in Ovarian Cancer Histopathology: A Systematic Review
- You Only Train Once: Learning a General Anomaly Enhancement Network with Random Masks for Hyperspectral Anomaly Detection
- Neural Network Entropy (NNetEn): Entropy-Based EEG Signal and Chaotic Time Series Classification, Python Package for NNetEn Calculation
- A Second-Order Majorant Algorithm for Nonnegative Matrix Factorization
- Unsupervised crack detection on complex stone masonry surfaces
- varepsilon K'U <MASK>: Integrating Yor`ub'a cultural greetings into machine translation
- Rule Enforcing Through Ordering
- VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization
- Learning with Explicit Shape Priors for Medical Image Segmentation
- HD-GCN:A Hybrid Diffusion Graph Convolutional Network
- Learning-Based Optimal Control with Performance Guarantees for Unknown Systems with Latent States
- Diffusion Action Segmentation
- Ensemble Methods for Multi-Organ Segmentation in CT Series
- FP8 versus INT8 for efficient deep learning inference
- Unsupervised Anomaly Detection and Localization of Machine Audio: A GAN-based Approach
- CIMI4D: A Large Multimodal Climbing Motion Dataset under Human-scene Interactions
- Social Honeypot for Humans: Luring People through Self-managed Instagram Pages
- Benchmarking FedAvg and FedCurv for Image Classification Tasks
- Comparing Adversarial and Supervised Learning for Organs at Risk Segmentation in CT images
- Per-Example Gradient Regularization Improves Learning Signals from Noisy Data
- STFAR: Improving Object Detection Robustness at Test-Time by Self-Training with Feature Alignment Regularization
- Conflict-Averse Gradient Optimization of Ensembles for Effective Offline Model-Based Optimization
- Learning-based Observer Evaluated on the Kinematic Bicycle Model
- Trimming Phonetic Alignments Improves the Inference of Sound Correspondence Patterns from Multilingual Wordlists
- JobHam-place with smart recommend job options and candidate filtering options
- Cross-Cultural Transfer Learning for Chinese Offensive Language Detection
- Beyond Multilayer Perceptrons: Investigating Complex Topologies in Neural Networks
- IC-FPS: Instance-Centroid Faster Point Sampling Module for 3D Point-base Object Detection
- Multiple Instance Ensembling For Paranasal Anomaly Classification In The Maxillary Sinus
- CIRCLE: Capture In Rich Contextual Environments
- Predictive Context-Awareness for Full-Immersive Multiuser Virtual Reality with Redirected Walking
- Procedural Generation of Complex Roundabouts for Autonomous Vehicle Testing
- Exploring the Limits of Deep Image Clustering using Pretrained Models
- EA-LSS: Edge-aware Lift-splat-shot Framework for 3D BEV Object Detection
- Interval Logic Tensor Networks
- Fooling Polarization-based Vision using Locally Controllable Polarizing Projection
- Accelerating Wireless Federated Learning via Nesterov's Momentum and Distributed Principle Component Analysis
- Visual Anomaly Detection via Dual-Attention Transformer and Discriminative Flow
- CoSMo: a Framework to Instantiate Conditioned Process Simulation Models
- Fused Depthwise Tiling for Memory Optimization in TinyML Deep Neural Network Inference
- WebQAmGaze: A Multilingual Webcam Eye-Tracking-While-Reading Dataset
- GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generation
- CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer
- MapFormer: Boosting Change Detection by Using Pre-change Information
- Can AI Put Gamma-Ray Astrophysicists Out of a Job?
- Maximum Covariance Unfolding Regression: A Novel Covariate-based Manifold Learning Approach for Point Cloud Data
- WSense: A Robust Feature Learning Module for Lightweight Human Activity Recognition
- Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning
- A Benchmark Generative Probabilistic Model for Weak Supervised Learning
- Learning Procedure-aware Video Representation from Instructional Videos and Their Narrations
- Rethinking interpretation: Input-agnostic saliency mapping of deep visual classifiers
- Improved Difference Images for Change Detection Classifiers in SAR Imagery Using Deep Learning
- Implementation and (Inverse Modified) Error Analysis for implicitly-templated ODE-nets
- An interpretable neural network-based non-proportional odds model for ordinal regression
- An Efficient Off-Policy Reinforcement Learning Algorithm for the Continuous-Time LQR Problem
- APPT : Asymmetric Parallel Point Transformer for 3D Point Cloud Understanding
- Zero-shot Referring Image Segmentation with Global-Local Context Features
- Never a Dull Moment: Distributional Properties as a Baseline for Time-Series Classification
- GPT-4 can pass the Korean National Licensing Examination for Korean Medicine Doctors
- Neural Microfacet Fields for Inverse Rendering
- On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks
- Rethinking Local Perception in Lightweight Vision Transformer
- Time-series Anomaly Detection based on Difference Subspace between Signal Subspaces
- Dialog act guided contextual adapter for personalized speech recognition
- FONT: Flow-guided One-shot Talking Head Generation with Natural Head Motions
- Attention is Not Always What You Need: Towards Efficient Classification of Domain-Specific Text
- Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer
- A Slow-Shifting Concerned Machine Learning Method for Short-term Traffic Flow Forecasting
- AceCoder: Utilizing Existing Code to Enhance Code Generation
- Decentralized Weakly Convex Optimization Over the Stiefel Manifold
- CrossLoc3D: Aerial-Ground Cross-Source 3D Place Recognition
- Learning Internal Representations of 3D Transformations from 2D Projected Inputs
- Semi-Weakly Supervised Object Kinematic Motion Prediction
- Domain Knowledge integrated for Blast Furnace Classifier Design
- Scalable Bayesian Meta-Learning through Generalized Implicit Gradients
- Joint Depth Estimation and Mixture of Rain Removal From a Single Image
- Learning from Similar Linear Representations: Adaptivity, Minimaxity, and Robustness
- Towards Adversarially Robust Continual Learning
- Generalized Information Bottleneck for Gaussian Variables
- Design by Contract Framework for Quantum Software
- MLGCN: An Ultra Efficient Graph Convolution Neural Model For 3D Point Cloud Analysis