Ship Broken Things
matmul.net·10h·
Discuss: Hacker News
🔗Topological Sorting
From Matmul to Meaning
evis.dev·3d·
Discuss: Hacker News
📐Linear Algebra
Quantifying AI Coverage on Hacker News
beuke.org·16h·
Discuss: Hacker News
🧠Intelligence Compression
ACMID: Automatic Curation of Musical Instrument Dataset for 7-Stem Music Source Separation
arxiv.org·1h
🎵Audio Formats
Bridging Reasoning to Learning: Unmasking Illusions using Complexity Out of Distribution Generalization
arxiv.org·1d
🧠Intelligence Compression
StaR-KVQA: Structured Reasoning Traces for Implicit-Knowledge Visual Question Answering
arxiv.org·1d
🧠Intelligence Compression
Cluster Paths: Navigating Interpretability in Neural Networks
arxiv.org·1d
🧠Machine Learning
ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving
arxiv.org·1h
🌀Riemannian Computing
Learning Mixtures of Linear Dynamical Systems (MoLDS) via Hybrid Tensor-EM Method
arxiv.org·2d
🌀Differential Geometry
CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion
arxiv.org·1d
📊Learned Metrics
Enhancing Synthetic Data Generation via Adaptive Kernel Density Estimation with Bayesian Optimization
dev.to·23h·
Discuss: DEV
🧠Machine Learning
On Convex Functions of Gaussian Variables
arxiv.org·1d
📐Compression Mathematics
AdaRD-key: Adaptive Relevance-Diversity Keyframe Sampling for Long-form Video understanding
arxiv.org·4d
🎬AV1 Encoding
Unsupervised Active Learning via Natural Feature Progressive Framework
arxiv.org·3d
🧠Machine Learning
Forecasting the Buzz: Enriching Hashtag Popularity Prediction with LLM Reasoning
arxiv.org·1h
⚖️Feed Ranking
Unsupervised Radio Map Construction in Mixed LoS/NLoS Indoor Environments
arxiv.org·1h
📊Computational Geometry
Grouped Differential Attention
arxiv.org·1d
⧗Information Bottleneck
Fast Leave-One-Out Approximation from Fragment-Target Prevalence Vectors (molFTP) : From Dummy Masking to Key-LOO for Leakage-Free Feature Construction
arxiv.org·2d
🧮SMT Solvers
Approximate Gaussianity Beyond Initialisation in Neural Networks
arxiv.org·2d
🕸️Tensor Networks
StruSR: Structure-Aware Symbolic Regression with Physics-Informed Taylor Guidance
arxiv.org·1d
🧠Machine Learning