Papers
Fri 17 Nov 2023
193 papers
- The Hidden Linear Structure in Score-Based Models and its ApplicationDiffusion models → Diffusion foundations and sampling
- SDDPM: Speckle Denoising Diffusion Probabilistic ModelsDiffusion models → Medical imaging and segmentation
- A Language Agent for Autonomous DrivingEnd-to-end autonomous driving → Large language models for driving +1
- A Study on Altering the Latent Space of Pretrained Text to Speech Models for Improved ExpressivenessDiffusion models → Audio, speech and music
- TaCo: Enhancing Cross-Lingual Transfer for Low-Resource Languages in LLMs through Translation-Assisted Chain-of-Thought ProcessesLLM reasoning → Reasoning benchmarks and evaluation
- Text-to-Sticker: Style Tailoring Latent Diffusion Models for Human ExpressionDiffusion models → Image generation, text-to-image and editing
- SelfEval: Leveraging the discriminative nature of generative models for evaluationDiffusion models → Image generation, text-to-image and editing
- Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2LLM alignment / RLHF / preference optimisation → LLM preference optimization methods
- Testing Language Model Agents Safely in the WildLLM agents and tool use → Agent threats, guardrails and governance
- DeepClean: Machine Unlearning on the Cheap by Resetting Privacy Sensitive Weights using the Fisher DiagonalLLM safety and security → Machine unlearning
- Complementary Advantages of ChatGPTs and Human Readers in Reasoning: Evidence from English Text Reading ComprehensionLLM reasoning → Reasoning benchmarks and evaluation
- High-fidelity Person-centric Subject-to-Image SynthesisDiffusion models → Image generation, text-to-image and editing
- Imagination-Augmented Hierarchical Reinforcement Learning for Safe and Interactive Autonomous Driving in Urban EnvironmentsEnd-to-end autonomous driving → Reinforcement learning for driving
- From "Thumbs Up" to "10 out of 10": Reconsidering Scalar Feedback in Interactive Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Advancements in Generative AI: A Comprehensive Review of GANs, GPT, Autoencoders, Diffusion Model, and TransformersDiffusion models → Image generation, text-to-image and editing
- Automatic measurement of coverage area of water-based pesticides-surfactant formulation on plant leaves using deep learning tools
- The possibility of making 138,000 from shredded banknote pieces using computer vision
- Randomly Weighted Neuromodulation in Neural Networks Facilitates Learning of Manifolds Common Across Tasks
- Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis
- Image Collage on Arbitrary Shape via Shape-Aware Slicing and Optimization
- Compositional Representation of Polymorphic Crystalline Materials
- Autonomous Port Navigation With Ranging Sensors Using Model-Based Reinforcement Learning
- Talent-Interview: Web-Client Cheating Detection for Online Exams
- Informative Priors Improve the Reliability of Multimodal Clinical Data Classification
- Artificial Intelligence in Sustainable Vertical Farming
- Efficient Domain Adaptation via Generative Prior for 3D Infant Pose Estimation
- Automated Detection of hidden Damages and Impurities in Aluminum Die Casting Materials and Fibre-Metal Laminates using Low-quality X-ray Radiography, Synthetic X-ray Data Augmentation by Simulation, and Machine Learning
- TransCDR: a deep learning model for enhancing the generalizability of cancer drug response prediction through transfer learning and multimodal data fusion for drug representation
- Equivariant Neural Operator Learning with Graphon Convolution
- Flexible Model Interpretability through Natural Language Model Editing
- Closely-Spaced Object Classification Using MuyGPyS
- OCT2Confocal: 3D CycleGAN based Translation of Retinal OCT Images to Confocal Microscopy
- Max-Rank: Efficient Multiple Testing for Conformal Prediction
- Extraction and Summarization of Explicit Video Content using Multi-Modal Deep Learning
- On Functional Activations in Deep Neural Networks
- Point Cloud Self-supervised Learning via 3D to Multi-view Masked Learner
- A Whole New Ball Game: A Primal Accelerated Method for Matrix Games and Minimizing the Maximum of Smooth Functions
- A Video-Based Activity Classification of Human Pickers in Agriculture
- Labeling Indoor Scenes with Fusion of Out-of-the-Box Perception Models
- Pre- to Post-Contrast Breast MRI Synthesis for Enhanced Tumour Segmentation
- Multi-entity Video Transformers for Fine-Grained Video Representation Learning
- Zero-Shot Digital Rock Image Segmentation with a Fine-Tuned Segment Anything Model
- Verified Compositional Neuro-Symbolic Control for Stochastic Systems with Temporal Logic Tasks
- Formal concept analysis for evaluating intrinsic dimension of a natural language
- A Quadratic Speedup in Finding Nash Equilibria of Quantum Zero-Sum Games
- WATUNet: A Deep Neural Network for Segmentation of Volumetric Sweep Imaging Ultrasound
- Exploring the Consistency, Quality and Challenges in Manual and Automated Coding of Free-text Diagnoses from Hospital Outpatient Letters
- Token-Level Adaptation of LoRA Adapters for Downstream Task Generalization
- Domain Generalization of 3D Object Detection by Density-Resampling
- Artificial Intelligence in Fetal Resting-State Functional MRI Brain Segmentation: A Comparative Analysis of 3D UNet, VNet, and HighRes-Net Models
- Integration and Implementation Strategies for AI Algorithm Deployment with Smart Routing Rules and Workflow Management
- Accelerating L-shaped Two-stage Stochastic SCUC with Learning Integrated Benders Decomposition
- Exploring Machine Learning Models for Federated Learning: A Review of Approaches, Performance, and Limitations
- SplatArmor: Articulated Gaussian splatting for animatable humans from monocular RGB videos
- A novel post-hoc explanation comparison metric and applications
- Use GPT-J Prompt Generation with RoBERTa for NER Models on Diagnosis Extraction of Periodontal Diagnosis from Electronic Dental Records
- Extracting periodontitis diagnosis in clinical notes with RoBERTa and regular expression
- Multiparameter Persistent Homology for Molecular Property Prediction
- SENetV2: Aggregated dense layer for channelwise and global representations
- SEA++: Multi-Graph-based High-Order Sensor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation
- Towards a Standardized Reinforcement Learning Framework for AAM Contingency Management
- Robustness Enhancement in Neural Networks with Alpha-Stable Training Noise
- Reinforcement Learning with Maskable Stock Representation for Portfolio Management in Customizable Stock Pools
- The Next 700 ML-Enabled Compiler Optimizations
- Adaptive Modelling Approach for Row-Type Dependent Predictive Analysis (RTDPA): A Framework for Designing Machine Learning Models for Credit Risk Analysis in Banking Sector
- INSPECT: A Multimodal Dataset for Pulmonary Embolism Diagnosis and Prognosis
- Emotion-Aware Music Recommendation System: Enhancing User Experience Through Real-Time Emotional Context
- How False Data Affects Machine Learning Models in Electrochemistry?
- Traffic Sign Interpretation in Real Road Scene
- Enhancing Data Efficiency and Feature Identification for Lithium-Ion Battery Lifespan Prediction by Deciphering Interpretation of Temporal Patterns and Cyclic Variability Using Attention-Based Models
- Degeneration of kernel regression with Matern kernels into low-order polynomial regression in high dimension
- Stratified-NMF for Heterogeneous Data
- Efficient Temporally-Aware DeepFake Detection using H.264 Motion Vectors
- Machine learning phase transitions: Connections to the Fisher information
- Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning
- Multimodal Representation Learning by Alternating Unimodal Adaptation
- SpACNN-LDVAE: Spatial Attention Convolutional Latent Dirichlet Variational Autoencoder for Hyperspectral Pixel Unmixing
- Using linear initialisation to improve speed of convergence and fully-trained error in Autoencoders
- PEFT-MedAware: Large Language Model for Medical Awareness
- Versatile Medical Image Segmentation Learned from Multi-Source Datasets via Model Self-Disambiguation
- Optimal Embedding Dimension for Sparse Subspace Embeddings
- Distilling and Retrieving Generalizable Knowledge for Robot Manipulation via Language Corrections
- Fuse It or Lose It: Deep Fusion for Multimodal Simulation-Based Inference
- Online Calibration of Deep Learning Sub-Models for Hybrid Numerical Modeling Systems
- Learning Realistic Joint Space Boundaries for Range of Motion Analysis of Healthy and Impaired Human Arms
- 3D-TexSeg: Unsupervised Segmentation of 3D Texture using Mutual Transformer Learning
- Self-trained Panoptic Segmentation
- Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers
- Multi-delay arterial spin-labeled perfusion estimation with biophysics simulation and deep learning
- Concept-free Causal Disentanglement with Variational Graph Auto-Encoder
- Predicting the Probability of Collision of a Satellite with Space Debris: A Bayesian Machine Learning Approach
- Astronomical Images Quality Assessment with Automated Machine Learning
- A Self-enhancement Approach for Domain-specific Chatbot Training via Knowledge Mining and Digest
- A Poincar'e Inequality and Consistency Results for Signal Sampling on Large Graphs
- Scaling TabPFN: Sketching and Feature Selection for Tabular Prior-Data Fitted Networks
- Active Inference on the Edge: A Design Study
- CA-Jaccard: Camera-aware Jaccard Distance for Person Re-identification
- Multimodal Indoor Localization Using Crowdsourced Radio Maps
- Chatbots as social companions: How people perceive consciousness, human likeness, and social health benefits in machines
- Designing Reconfigurable Intelligent Systems with Markov Blankets
All 193
- Hashing it Out: Predicting Unhealthy Conversations on Twitter
- D'etection d'objets c'elestes dans des images astronomiques par IA explicable
- FOCAL: A Cost-Aware Video Dataset for Active Learning
- EduGym: An Environment and Notebook Suite for Reinforcement Learning Education
- Countering Misinformation via Emotional Response Generation
- Human motion trajectory prediction using the Social Force Model for real-time and low computational cost applications
- Implicit Maximum a Posteriori Filtering via Adaptive Optimization
- Graph Neural Networks for Pressure Estimation in Water Distribution Systems
- SSB: Simple but Strong Baseline for Boosting Performance of Open-Set Semi-Supervised Learning
- Direct Amortized Likelihood Ratio Estimation
- Phase Guided Light Field for Spatial-Depth High Resolution 3D Imaging
- RONAALP: Reduced-Order Nonlinear Approximation with Active Learning Procedure
- Archtree: on-the-fly tree-structured exploration for latency-aware pruning of deep neural networks
- Unified theory for joint covariance properties under geometric image transformations for spatio-temporal receptive fields according to the generalized Gaussian derivative model for visual receptive fields
- Detection and Analysis of Offensive Online Content in Hausa Language
- Enhancing the Reliability of Segment Anything Model for Auto-Prompting Medical Image Segmentation with Uncertainty Rectification
- Utilizing VQ-VAE for End-to-End Health Indicator Generation in Predicting Rolling Bearing RUL
- Removing Adverse Volumetric Effects From Trained Neural Radiance Fields
- Enhancing Object Coherence in Layout-to-Image Synthesis
- Mind the map! Accounting for existing map information when estimating online HDMaps from sensor
- When a Language Question Is at Stake. A Revisited Approach to Label Sensitive Content
- A Framework of Landsat-8 Band Selection based on UMDA for Deforestation Detection
- Causal Fairness-Guided Dataset Reweighting using Neural Networks
- CNL2ASP: converting controlled natural language sentences into ASP
- From Principle to Practice: Vertical Data Minimization for Machine Learning
- A Relay System for Semantic Image Transmission based on Shared Feature Extraction and Hyperprior Entropy Compression
- Handling Overlapping Asymmetric Datasets -- A Twice Penalized P-Spline Approach
- FRCSyn Challenge at WACV 2024:Face Recognition Challenge in the Era of Synthetic Data
- End-to-end autoencoding architecture for the simultaneous generation of medical images and corresponding segmentation masks
- Regions are Who Walk Them: a Large Pre-trained Spatiotemporal Model Based on Human Mobility for Ubiquitous Urban Sensing
- Using Cooperative Game Theory to Prune Neural Networks
- Correlation-Distance Graph Learning for Treatment Response Prediction from rs-fMRI
- Accurate and Fast Fischer-Tropsch Reaction Microkinetics using PINNs
- DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection
- Sinhala-English Word Embedding Alignment: Introducing Datasets and Benchmark for a Low Resource Language
- Causal Graph in Language Model Rediscovers Cortical Hierarchy in Human Narrative Processing
- Deep Residual CNN for Multi-Class Chest Infection Diagnosis
- Is Your Anomaly Detector Ready for Change? Adapting AIOps Solutions to the Real World
- DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines
- Deep Learning based CNN Model for Classification and Detection of Individuals Wearing Face Mask
- Decentralized Energy Marketplace via NFTs and AI-based Agents
- Optimized Deep Learning Models for AUV Seabed Image Analysis
- Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads
- Two-Factor Authentication Approach Based on Behavior Patterns for Defeating Puppet Attacks
- Stable Attractors for Neural networks classification via Ordinary Differential Equations (SA-nODE)
- Delete My Account: Impact of Data Deletion on Machine Learning Classifiers
- Single-Shot and Multi-Shot Feature Learning for Multi-Object Tracking
- MSE-Nets: Multi-annotated Semi-supervised Ensemble Networks for Improving Segmentation of Medical Image with Ambiguous Boundaries
- Quantum Data Encoding: A Comparative Analysis of Classical-to-Quantum Mapping Techniques and Their Impact on Machine Learning Accuracy
- FOAL: Fine-grained Contrastive Learning for Cross-domain Aspect Sentiment Triplet Extraction
- Few-shot Message-Enhanced Contrastive Learning for Graph Anomaly Detection
- Exploring the Relationship between In-Context Learning and Instruction Tuning
- Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations Using Image Models
- Dates Fruit Disease Recognition using Machine Learning
- Quantum-Assisted Simulation: A Framework for Developing Machine Learning Models in Quantum Computing
- Video-based Sequential Bayesian Homography Estimation for Soccer Field Registration
- FIKIT: Priority-Based Real-time GPU Multi-tasking Scheduling with Kernel Identification
- Garment Recovery with Shape and Deformation Priors
- Pseudo Label-Guided Data Fusion and Output Consistency for Semi-Supervised Medical Image Segmentation
- Enhancing Student Engagement in Online Learning through Facial Expression Analysis and Complex Emotion Recognition using Deep Learning
- Federated Knowledge Graph Completion via Latent Embedding Sharing and Tensor Factorization
- A2XP: Towards Private Domain Generalization
- Cooperative Perception with Learning-Based V2V communications
- Leveraging Multimodal Fusion for Enhanced Diagnosis of Multiple Retinal Diseases in Ultra-wide OCTA
- TransONet: Automatic Segmentation of Vasculature in Computed Tomographic Angiograms Using Deep Learning
- Clustering Techniques for Stable Linear Dynamical Systems with applications to Hard Disk Drives
- Towards Machine Learning-based Quantitative Hyperspectral Image Guidance for Brain Tumor Resection
- Boosting Multimodal Remote Sensing Image Classification with Transformer-based Heterogeneously Salient Graph Representation
- Shifting to Machine Supervision: Annotation-Efficient Semi and Self-Supervised Learning for Automatic Medical Image Segmentation and Classification
- Nonparametric Teaching for Multiple Learners
- Graph Sparsifications using Neural Network Assisted Monte Carlo Tree Search
- Interpretable Modeling of Single-cell perturbation Responses to Novel Drugs Using Cycle Consistence Learning
- MPSeg : Multi-Phase strategy for coronary artery Segmentation
- Semi-supervised ViT knowledge distillation network with style transfer normalization for colorectal liver metastases survival prediction
- Supervised structure learning
- BiHRNet: A Binary high-resolution network for Human Pose Estimation
- Hierarchical Pruning of Deep Ensembles with Focal Diversity
- Leveraging Function Space Aggregation for Federated Learning at Scale
- SSASS: Semi-Supervised Approach for Stenosis Segmentation
- Physics-Enhanced Multi-fidelity Learning for Optical Surface Imprint
- Sobol Sequence Optimization for Hardware-Efficient Vector Symbolic Architectures
- Prompt Pool based Class-Incremental Continual Learning for Dialog State Tracking
- Multiscale Hodge Scattering Networks for Data Analysis
- Interpretable pap smear cell representation for cervical cancer screening
- Energy and Carbon Considerations of Fine-Tuning BERT
- Diagnosing and Debiasing Corpus-Based Political Bias and Insults in GPT2
- Stable Differentiable Causal Discovery
- Vision meets mmWave Radar: 3D Object Perception Benchmark for Autonomous Driving
- FREE: The Foundational Semantic Recognition for Modeling Environmental Ecosystems
- UniMOS: A Universal Framework For Multi-Organ Segmentation Over Label-Constrained Datasets
- Identifying the Truth of Global Model: A Generic Solution to Defend Against Byzantine and Backdoor Attacks in Federated Learning (full version)
- Surprisal Driven k-NN for Robust and Interpretable Nonparametric Learning
- Segment Anything in Defect Detection