Braided magnetic flux ropes found at both human and light year scales
phys.org·18h
⚙️Tape Engineering
ISALux: Illumination and Segmentation Aware Transformer Employing Mixture of Experts for Low Light Image Enhancement
arxiv.org·8h
👁️OCR Enhancement
Quantifying Out-of-Training Uncertainty of Neural-Network based Turbulence Closures
arxiv.org·8h
📊Quantization
DocHop-QA: Towards Multi-Hop Reasoning over Multimodal Document Collections
arxiv.org·1d
📇Dublin Core
Route-and-Execute: Auditable Model-Card Matching and Specialty-Level Deployment
arxiv.org·8h
🦋Format Metamorphosis
FedKLPR: Personalized Federated Learning for Person Re-Identification with Adaptive Pruning
arxiv.org·8h
🧠Machine Learning
Tractable Stochastic Hybrid Model Predictive Control using Gaussian Processes for Repetitive Tasks in Unseen Environments
arxiv.org·8h
⚡Incremental Computation
Parlant - Renovation AI Open-Source framework
dev.to·4h·
Discuss: DEV
✨Effect Handlers
STRelay: A Universal Spatio-Temporal Relaying Framework for Location Prediction with Future Spatiotemporal Contexts
arxiv.org·8h
🔶Voronoi Diagrams
Rao Differential Privacy
arxiv.org·8h
🛡️Differential Privacy
CausalSent: Interpretable Sentiment Classification with RieszNet
arxiv.org·8h
⚖️Feed Ranking
An Intrinsic Barrier for Resolving P = NP (2-SAT as Flat, 3-SAT as High-Dimensional Void-Rich)
arxiv.org·6d
🎯Performance Proofs
HV Metric For Time-Domain Full Waveform Inversion
arxiv.org·8h
📊Rate-Distortion Theory
Convergence and Generalization of Anti-Regularization for Parametric Models
arxiv.org·8h
🧠Machine Learning
Feature-Refined Unsupervised Model for Loanword Detection
arxiv.org·8h
📏Manuscript Metrics
NinA: Normalizing Flows in Action. Training VLA Models with Normalizing Flows
arxiv.org·8h
🎙️Whisper
HypER: Hyperbolic Echo State Networks for Capturing Stretch-and-Fold Dynamics in Chaotic Flows
arxiv.org·8h
🌀Hyperbolic Geometry
Deep learning-enabled virtual multiplexed immunostaining of label-free tissue for vascular invasion assessment
arxiv.org·1d
🌀Riemannian Computing
Why a simple for loop (brute-force k-NN) becomes computationally impossible for modern AI applications
dev.to·1d·
Discuss: DEV
🧮Kolmogorov Complexity
Benchmarking Class Activation Map Methods for Explainable Brain Hemorrhage Classification on Hemorica Dataset
arxiv.org·8h
🧠Machine Learning