Papers
Mon 10 Jul 2023
182 papers
- Exact Diffusion Inversion via Bi-directional Integration ApproximationDiffusion models → Inverse problems and image restoration
- KU-DMIS-MSRA at RadSum23: Pre-trained Vision-Language Model for Radiology Report SummarizationMultimodal LLMs / vision-language models → Medical vision-language models
- Linear Alignment of Vision-language Models for Image CaptioningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Articulated 3D Head Avatar Generation using Text-to-Image Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
- CREPE: Learnable Prompting With CLIP Improves Visual Relationship PredictionMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Comparison of Point Cloud and Image-based Models for Calorimeter Fast SimulationDiffusion models → Flow matching, time series and science
- Divide, Evaluate, and Refine: Evaluating and Improving Text-to-Image Alignment with Iterative VQA FeedbackDiffusion models → Image generation, text-to-image and editing
- Diffusion Policies for Out-of-Distribution Generalization in Offline Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
- AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific TuningDiffusion models → Video generation
- BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference DatasetLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
- Learning Fine Pinch-Grasp Skills using Tactile Sensing from A Few Real-world DemonstrationsOffline RL and imitation learning from data → Robot manipulation imitation learning
- InPars Toolkit: A Unified and Reproducible Synthetic Data Generation Pipeline for Neural Information RetrievalSynthetic data and self-improvement for LLMs → LLM synthetic data generation
- Timbre transfer using image-to-image denoising diffusion implicit modelsDiffusion models → Audio, speech and music
- Gradient Surgery for One-shot Unlearning on Generative ModelLLM safety and security → Vision-language and text-to-image safety
- Customizing Synthetic Data for Data-Free Student LearningKnowledge distillation → General knowledge distillation methods
- Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A SurveyEnd-to-end autonomous driving → End-to-end system architecture
- Enhancing Adversarial Robustness via Score-Based OptimizationDiffusion models → Robustness, privacy and adversarial aspects
- Cloud Render Farm Services Discovery Using NLP And Ontology Based Knowledge Graph
- Proceeding of the 1st Workshop on Social Robots Personalisation At the crossroads between engineering and humanities (CONCATENATE)
- ChatGPT for Digital Forensic Investigation: The Good, The Bad, and The Unknown
- Important Clues that Facilitate Visual Emergence: Three Psychological Experiments
- StyleGAN2-based Out-of-Distribution Detection for Medical Imaging
- Graph Representation of the Magnetic Field Topology in High-Fidelity Plasma Simulations for Machine Learning Applications
- PapagAI:Automated Feedback for Reflective Essays
- Detecting LLM-Generated Text in Computing Education: A Comparative Study for ChatGPT Cases
- Retrieval of phonemes and Kohonen algorithm
- AI For Global Climate Cooperation 2023 Competition Proceedings
- Pathway toward prior knowledge-integrated machine learning in engineering
- Data-driven Nonlinear Parametric Model Order Reduction Framework using Deep Hierarchical Variational Autoencoder
- Exploring Large Language Model for Graph Data Understanding in Online Job Recommendations
- Online Ad Procurement in Non-stationary Autobidding Worlds
- Impact of Feature Encoding on Malware Classification Explainability
- Substance or Style: What Does Your Image Embedding Know?
- Can You Improve My Code? Optimizing Programs with Local Search
- Unsupervised Domain Adaptation with Deep Neural-Network
- Compositional Generalization from First Principles
- Functional PCA and Deep Neural Networks-based Bayesian Inverse Uncertainty Quantification with Transient Experimental Data
- Active Learning for Video Classification with Frame Level Queries
- Code Generation for Machine Learning using Model-Driven Engineering and SysML
- DBFed: Debiasing Federated Learning Framework based on Domain-Independent
- Hate Speech Detection via Dual Contrastive Learning
- Some Preliminary Steps Towards Metaverse Logic
- Event Extraction as Question Generation and Answering
- Unmasking the giant: A comprehensive evaluation of ChatGPT's proficiency in coding algorithms and data structures
- Towards Fair Graph Neural Networks via Graph Counterfactual
- Probabilistic Counterexample Guidance for Safer Reinforcement Learning (Extended Version)
- Count-Free Single-Photon 3D Imaging with Race Logic
- Kinematically-Decoupled Impedance Control for Fast Object Visual Servoing and Grasping on Quadruped Manipulators
- Rapid Deforestation and Burned Area Detection using Deep Multimodal Learning on Satellite Imagery
- Planar Curve Registration using Bayesian Inversion
- SimpleMTOD: A Simple Language Model for Multimodal Task-Oriented Dialogue with Symbolic Scene Representation
- FedYolo: Augmenting Federated Learning with Pretrained Transformers
- Fast dynamic time warping and clustering in C++
- Learning to Solve Constraint Satisfaction Problems with Recurrent Transformer
- Choosing Well Your Opponents: How to Guide the Synthesis of Programmatic Strategies
- Entity Identifier: A Natural Text Parsing-based Framework For Entity Relation Extraction
- Accelerated Discovery of Machine-Learned Symmetries: Deriving the Exceptional Lie Groups G2, F4 and E6
- Measuring and Mitigating Interference in Reinforcement Learning
- RACH-Space: Reconstructing Adaptive Convex Hull Space with Applications in Weak Supervision
- Fed-CPrompt: Contrastive Prompt for Rehearsal-Free Federated Continual Learning
- Leveraging an Alignment Set in Tackling Instance-Dependent Label Noise
- Gait Event Detection and Travel Distance Using Waist-Worn Accelerometers across a Range of Speeds: Automated Approach
- AmadeusGPT: a natural language interface for interactive animal behavioral analysis
- SHAP@k:Efficient and Probably Approximately Correct (PAC) Identification of Top-k Features
- SigOpt Mulch: An Intelligent System for AutoML of Gradient Boosted Trees
- Predicting Tuberculosis from Real-World Cough Audio Recordings and Metadata
- Loss Dynamics of Temporal Difference Reinforcement Learning
- Law of Large Numbers for Bayesian two-layer Neural Network trained with Variational Inference
- Formulating A Strategic Plan Based On Statistical Analyses And Applications For Financial Companies Through A Real-World Use Case
- Semantic-SAM: Segment and Recognize Anything at Any Granularity
- Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos
- Information decomposition in complex systems via machine learning
- Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangement
- RoCo: Dialectic Multi-Robot Collaboration with Large Language Models
- A unifying framework for differentially private quantum algorithms
- Advances and Challenges in Meta-Learning: A Technical Review
- Large Language Models as General Pattern Machines
- On the curvature of the loss landscape
- CVPR MultiEarth 2023 Deforestation Estimation Challenge:SpaceVision4Amazon
- Understanding Real-World AI Planning Domains: A Conceptual Framework
- Cobalt: Optimizing Mining Rewards in Proof-of-Work Network Games
- COMEX: A Tool for Generating Customized Source Code Representations
- VampNet: Music Generation via Masked Acoustic Token Modeling
- FreeDrag: Feature Dragging for Reliable Point-based Image Editing
- Minimax Excess Risk of First-Order Methods for Statistical Learning with Data-Dependent Oracles
- LINFA: a Python library for variational inference with normalizing flow and annealing
- Quantifying the Echo Chamber Effect: An Embedding Distance-based Approach
- On the power of graph neural networks and the role of the activation function
- Joint Salient Object Detection and Camouflaged Object Detection via Uncertainty-aware Learning
- Multimodal brain age estimation using interpretable adaptive population-graph learning
- Measuring Lexical Diversity in Texts: The Twofold Length Problem
- Weakly-supervised positional contrastive learning: application to cirrhosis classification
- MiVOLO: Multi-input Transformer for Age and Gender Estimation
- SPLAL: Similarity-based pseudo-labeling with alignment loss for semi-supervised medical image classification
- Learning Interpretable Heuristics for WalkSAT
- A Memristor-Inspired Computation for Epileptiform Signals in Spheroids
- EchoVest: Real-Time Sound Classification and Depth Perception Expressed through Transcutaneous Electrical Nerve Stimulation
- Bridging MDE and AI: A Systematic Review of Domain-Specific Languages and Model-Driven Practices in AI Software Systems Engineering
- Distill-SODA: Distilling Self-Supervised Vision Transformer for Source-Free Open-Set Domain Adaptation in Computational Pathology
- DWA: Differential Wavelet Amplifier for Image Super-Resolution
All 182
- A Graph Multi-separator Problem for Image Segmentation
- AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System
- TFR: Texture Defect Detection with Fourier Transform using Normal Reconstructed Template of Simple Autoencoder
- A Semi-Automated Solution Approach Recommender for a Given Use Case: a Case Study for AI/ML in Oncology via Scopus and OpenAI
- A Call to Reflect on Evaluation Practices for Age Estimation: Comparative Analysis of the State-of-the-Art and a Unified Benchmark
- Interpreting and generalizing deep learning in physics-based problems with functional linear models
- Automatically detecting activities of daily living from in-home sensors as indicators of routine behaviour in an older population
- SparseVSR: Lightweight and Noise Robust Visual Speech Recognition
- Learning Large Margin Sparse Embeddings for Open Set Medical Diagnosis
- Q-YOLOP: Quantization-aware You Only Look Once for Panoptic Driving Perception
- DADO -- Low-Cost Query Strategies for Deep Active Design Optimization
- QBitOpt: Fast and Accurate Bitwidth Reallocation during Training
- Preventing Errors in Person Detection: A Part-Based Self-Monitoring Framework
- Self-Expanding Neural Networks
- Cluster-Induced Mask Transformers for Effective Opportunistic Gastric Cancer Screening on Non-contrast CT Scans
- Efficient Match Pair Retrieval for Large-scale UAV Images via Graph Indexed Global Descriptor
- On the Computational Modeling of Meaning: Embodied Cognition Intertwined with Emotion
- An Examination of Wearable Sensors and Video Data Capture for Human Exercise Classification
- SAGC-A68: a space access graph dataset for the classification of spaces and space elements in apartment buildings
- Improving Heterogeneous Graph Learning with Weighted Mixed-Curvature Product Manifold
- CoactSeg: Learning from Heterogeneous Data for New Multiple Sclerosis Lesion Segmentation
- Improving Factuality of Abstractive Summarization via Contrastive Reward Learning
- An Algorithm with Optimal Dimension-Dependence for Zero-Order Nonsmooth Nonconvex Stochastic Optimization
- Deductive Controller Synthesis for Probabilistic Hyperproperties
- Model-Driven Engineering Method to Support the Formalization of Machine Learning using SysML
- Geometric Constraints in Probabilistic Manifolds: A Bridge from Molecular Dynamics to Structured Diffusion Processes
- Invertible Low-Dimensional Modelling of X-ray Absorption Spectra for Potential Applications in Spectral X-ray Imaging
- Digital Modeling for Everyone: Exploring How Novices Approach Voice-Based 3D Modeling
- Partial Vessels Annotation-based Coronary Artery Segmentation with Self-training and Prototype Learning
- Test-Time Adaptation for Nighttime Color-Thermal Semantic Segmentation
- Badgers: generating data quality deficits with Python
- Multi-modal Graph Learning over UMLS Knowledge Graphs
- Invex Programs: First Order Algorithms and Their Convergence
- SAM-IQA: Can Segment Anything Boost Image Quality Assessment?
- Graph Convolutional Networks for Simulating Multi-phase Flow and Transport in Porous Media
- Learning Behavioral Representations of Routines From Large-scale Unlabeled Wearable Time-series Data Streams using Hawkes Point Process
- Search-time Efficient Device Constraints-Aware Neural Architecture Search
- Automatic diagnosis of knee osteoarthritis severity using Swin transformer
- Global and Local Visual Processing: Influence of Perceptual Field Variables
- Designing Novel Cognitive Diagnosis Models via Evolutionary Multi-Objective Neural Architecture Search
- Observation of high-energy neutrinos from the Galactic plane
- Identification of Hemorrhage and Infarct Lesions on Brain CT Images using Deep Learning
- Towards Enabling Cardiac Digital Twins of Myocardial Infarction Using Deep Computational Models for Inverse Inference
- FedDCT: A Dynamic Cross-Tier Federated Learning Framework in Wireless Networks
- Fairness-aware Federated Minimax Optimization with Convergence Guarantee
- Episodic Gaussian Process-Based Learning Control with Vanishing Tracking Errors
- Enhancing Biomedical Text Summarization and Question-Answering: On the Utility of Domain-Specific Pre-Training
- TIM: Teaching Large Language Models to Translate with Comparison
- Moving pattern-based modeling using a new type of interval ARX model
- Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation
- ARK: Robust Knockoffs Inference with Coupling
- FODVid: Flow-guided Object Discovery in Videos
- CT-based Subchondral Bone Microstructural Analysis in Knee Osteoarthritis via MR-Guided Distillation Learning
- Towards Generalizable Diabetic Retinopathy Grading in Unseen Domains
- Learning to Identify Graphs from Node Trajectories in Multi-Robot Networks
- ECS -- an Interactive Tool for Data Quality Assurance
- One-Shot Pruning for Fast-adapting Pre-trained Models on Devices
- Enhancing Cross-lingual Transfer via Phonemic Transcription Integration
- False Sense of Security: Leveraging XAI to Analyze the Reasoning and True Performance of Context-less DGA Classifiers
- InfLoR-SNN: Reducing Information Loss for Spiking Neural Networks
- Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data
- On Sufficient Graphical Models
- MD-HIT: Machine learning for materials property prediction with dataset redundancy control
- RLTF: Reinforcement Learning from Unit Test Feedback
- Injecting Logical Constraints into Neural Networks via Straight-Through Estimators
- Continual Learning as Computationally Constrained Reinforcement Learning
- Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classification
- Stroke Extraction of Chinese Character Based on Deep Structure Deformable Image Registration
- Miriam: Exploiting Elastic Kernels for Real-time Multi-DNN Inference on Edge GPU
- Privacy-Preserving Graph Machine Learning from Data to Computation: A Survey
- Source-Aware Embedding Training on Heterogeneous Information Networks
- New Variants of Frank-Wolfe Algorithm for Video Co-localization Problem
- Text Descriptions are Compressive and Invariant Representations for Visual Learning
- Robust Feature Learning Against Noisy Labels
- Towards Cross-Table Masked Pretraining for Web Data Mining
- Automatic Piano Transcription with Hierarchical Frequency-Time Transformer
- Learning to Generate Equitable Text in Dialogue from Biased Training Data
- Edge Storage Management Recipe with Zero-Shot Data Compression for Road Anomaly Detection
- K-Space-Aware Cross-Modality Score for Synthesized Neuroimage Quality Assessment
- A Demand-Driven Perspective on Generative Audio AI
- Generalizing Graph ODE for Learning Complex System Dynamics across Environments
- HistRED: A Historical Document-Level Relation Extraction Dataset