Study pits super-recognizers against digitally manipulated face images
phys.org·23h
🎯Threat Hunting
How we made our streaming joins 50% faster
blog.epsiolabs.com·7h·
Discuss: Hacker News
🧬PostgreSQL Forensics
Foundation models are going multimodal
twelvelabs.io·2d·
Discuss: Hacker News
📊Learned Metrics
BiXSE: Improving Dense Retrieval via Probabilistic Graded Relevance Distillation
arxiv.org·1d
🔍Information Retrieval
LightShed: Defeating Perturbation-based Image Copyright Protections
usenix.org·9h
👁️Perceptual Hashing
Edge Detection for Organ Boundaries via Top Down Refinement and SubPixel Upsampling
arxiv.org·1d
🤖Advanced OCR
Geometry-Aware Spiking Graph Neural Network
arxiv.org·1d
🌀Hyperbolic Geometry
GS4Buildings: Prior-Guided Gaussian Splatting for 3D Building Reconstruction
arxiv.org·1d
🏺Computational Archaeology
Unveiling the Secrets of Data Grouping: A Deep Dive into Hierarchical Clustering and DBSCAN
dev.to·2d·
Discuss: DEV
📚Document Clustering
Dynamic Pattern Alignment Learning for Pretraining Lightweight Human-Centric Vision Models
arxiv.org·1d
📊Learned Metrics
CROP: Integrating Topological and Spatial Structures via Cross-View Prefixes for Molecular LLMs
arxiv.org·1d
🤖Paleographic ML
Neural Tangent Knowledge Distillation for Optical Convolutional Networks
arxiv.org·12h
🧠Neural Codecs
Learning More by Seeing Less: Line Drawing Pretraining for Efficient, Transferable, and Human-Aligned Vision
arxiv.org·1d
📊Learned Metrics
BigTokDetect: A Clinically-Informed Vision-Language Model Framework for Detecting Pro-Bigorexia Videos on TikTok
arxiv.org·1d
📊Learned Metrics
STELAR-VISION: Self-Topology-Aware Efficient Learning for Aligned Reasoning in Vision
arxiv.org·12h
💻Local LLMs
Scaled-Dot-Product Attention as One-Sided Entropic Optimal Transport
arxiv.org·12h
🧠Machine Learning
Automated Spectral Deconvolution & Artifact Removal via Deep Causal Graph Prioritization in Cryo-EM Data
dev.to·1d·
Discuss: DEV
📄Document Digitization
Remote Sensing Image Intelligent Interpretation with the Language-Centered Perspective: Principles, Methods and Challenges
arxiv.org·1d
📸TIFF Archaeology
What is PCA? A Simplified Explanation
dev.to·14h·
Discuss: DEV
📐Vector Dimensionality
RORPCap: Retrieval-based Objects and Relations Prompt for Image Captioning
arxiv.org·1d
🤖Advanced OCR