Integral Signatures of Activation Functions: A 9-Dimensional Taxonomy and Stability Theory for Deep Learning
arxiv.org·15h
🧠Machine Learning
When mathematics meets aesthetics: Tessellations as a precise tool for solving complex problems
phys.org·3h
📐Mathematical Art
DEGS: Deformable Event-based 3D Gaussian Splatting from RGB and Event Stream
arxiv.org·15h
📐Projective Geometry
Scalable Hyperbolic Embedding Optimization for Geometric Deep Learning on Modular Surfaces
dev.to·4d·
Discuss: DEV
🌀Hyperbolic Geometry
On knot detection via picture recognition
arxiv.org·1d
🕸️Algebraic Topology
RND1: Simple, Scalable AR-to-Diffusion Conversion
radicalnumerics.ai·23h·
Discuss: Hacker News
💻Local LLMs
6D Phase Space Reconstruction: MENT-Flow Validation on Complex High-Dimensional Distributions
hackernoon.com·2d
💎Information Crystallography
Probabilistically-Safe Bipedal Navigation over Uncertain Terrain via Conformal Prediction and Contraction Analysis
arxiv.org·15h
🌀Riemannian Computing
Nearly Instance-Optimal Parameter Recovery from Many Trajectories via Hellinger Localization
arxiv.org·1d
🧮Kolmogorov Bounds
Learning Mixtures of Linear Dynamical Systems (MoLDS) via Hybrid Tensor-EM Method
arxiv.org·2d
🌀Riemannian Computing
Geometry Meets Vision: Revisiting Pretrained Semantics in Distilled Fields
arxiv.org·4d
🌀Riemannian Computing
On Convex Functions of Gaussian Variables
arxiv.org·1d
📐Compression Mathematics
Physics-informed AI excels at large-scale discovery of new materials
phys.org·4h
🧠Machine Learning
Sub-Field Selection & Research Topic Generation:
dev.to·21h·
Discuss: DEV
🔍Vector Forensics
Evaluating Small Vision-Language Models on Distance-Dependent Traffic Perception
arxiv.org·15h
🧠Machine Learning
TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics
arxiv.org·1d
🤖Advanced OCR
Adaptive Optimizable Gaussian Process Regression Linear Least Squares Regression Filtering Method for SEM Images
arxiv.org·15h
🏺Computational Archaeology
Parallel-in-Time Solution of Allen-Cahn Equations by Integrating Operator Learning into the Parareal Method
arxiv.org·15h
🕸️Tensor Networks
Mass Conservation on Rails -- Rethinking Physics-Informed Learning of Ice Flow Vector Fields
arxiv.org·1d
🌀Riemannian Computing
SliceFine: The Universal Winning-Slice Hypothesis for Pretrained Networks
arxiv.org·15h
🧠Neural Codecs