Papers
-
Enhancing SHAP Explainability for Diagnostic and Prognostic ML Models in Alzheimer Disease
-
Learning Where the Physics Is: Probabilistic Adaptive Sampling for Stiff PDEs
-
FlowMotion: Training-Free Flow Guidance for Video Motion Transfer
-
The EpisTwin: A Knowledge Graph-Grounded Neuro-Symbolic Architecture for Personal AI
-
Enhanced Protein Intrinsic Disorder Prediction Through Dual-View Multiscale Features and Multi-objective Evolutionary Algorithm
-
3D CBCT Artefact Removal Using Perpendicular Score-Based Diffusion Models
-
DEX-AR: A Dynamic Explainability Method for Autoregressive Vision-Language Models
-
Polarized Direct Cross-Attention Message Passing in GNNs for Machinery Fault Diagnosis
-
Continual Adaptation for Pacific Indigenous Speech Recognition
-
Latent Transfer Attack: Adversarial Examples via Generative Latent Spaces
-
WMoE-CLIP: Wavelet-Enhanced Mixture-of-Experts Prompt Learning for Zero-Shot Anomaly Detection
-
Gradient-based Nested Co-Design of Aerodynamic Shape and Control for Winged Robots
-
From Entropy to Calibrated Uncertainty: Training Language Models to Reason About Uncertainty
-
P-SLCR: Unsupervised Point Cloud Semantic Segmentation via Prototypes Structure Learning and Consistent Reasoning
-
The Art That Poses Back: Assessing AI Pastiches after Contemporary Artworks
-
Diversity-Aware Adaptive Collocation for Physics-Informed Neural Networks via Sparse QUBO Optimization and Hybrid Coresets
-
Prediction of Steady-State Flow through Porous Media Using Machine Learning Models
-
Metalearning traffic assignment for network disruptions with graph convolutional neural networks
-
Structured Exploration vs. Generative Flexibility: A Field Study Comparing Bandit and LLM Architectures for Personalised Health Behaviour Interventions
-
WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching
-
SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement
-
AI End-to-End Radiation Treatment Planning Under One Second
-
K-MaT: Knowledge-Anchored Manifold Transport for Cross-Modal Prompt Learning in Medical Imaging
-
Transparent AI for Mathematics: Transformer-Based Large Language Models for Mathematical Entity Relationship Extraction with XAI
-
MoEless: Efficient MoE LLM Serving via Serverless Computing
-
Dynamic Chunking Diffusion Transformer
-
Frequency-Separable Hamiltonian Neural Network for Multi-Timescale Dynamics
-
LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtents
-
Tiny, Hardware-Independent, Compression-based Classification
-
CLAIRE: Compressed Latent Autoencoder for Industrial Representation and Evaluation -- A Deep Learning Framework for Smart Manufacturing
-
Computer vision-based estimation of invertebrate biomass
-
HiDE: Hierarchical Dictionary-Based Entropy Modeling for Learned Image Compression
-
ESAA-Security: An Event-Sourced, Verifiable Architecture for Agent-Assisted Security Audits of AI-Generated Code
-
OralGPT-Plus: Learning to Use Visual Tools via Reinforcement Learning for Panoramic X-ray Analysis
-
Adaptive Lipschitz-Free Conditional Gradient Methods for Stochastic Composite Nonconvex Optimization
-
Rewis3d: Reconstruction Improves Weakly-Supervised Semantic Segmentation
-
Failure Detection in Chemical Processes using Symbolic Machine Learning: A Case Study on Ethylene Oxidation
-
MoEMambaMIL: Structure-Aware Selective State Space Modeling for Whole-Slide Image Analysis
-
Kinetic-based regularization: Learning spatial derivatives and PDE applications
-
CHMv2: Improvements in Global Canopy Height Mapping using DINOv3
-
Prompt Group-Aware Training for Robust Text-Guided Nuclei Segmentation
-
REACT++: Efficient Cross-Attention for Real-Time Scene Graph Generation
-
Solving Jigsaw Puzzles in the Wild: Human-Guided Reconstruction of Cultural Heritage Fragments
-
Talk Freely, Execute Strictly: Schema-Gated Agentic AI for Flexible and Reproducible Scientific Workflows
-
Efficient, Property-Aligned Fan-Out Retrieval via RL-Compiled Diffusion
-
DiffInf: Influence-Guided Diffusion for Supervision Alignment in Facial Attribute Learning
-
U6G XL-MIMO Radiomap Prediction: Multi-Config Dataset and Beam Map Approach
-
Adapter-Augmented Bandits for Online Multi-Constrained Multi-Modal Inference Scheduling
-
Locating and Editing Figure-Ground Organization in Vision Transformers
-
Physical Simulator In-the-Loop Video Generation
