👁️ Medieval OCR

Gothic Scripts, Character Segmentation, Historical Text Recognition, Paleographic AI

Fantastic Flowers: Early Colour Cinema Restored Through ACE’s Joint Restoration Grant
ace-film.eu·6h
🎞️Cinema Preservation
Experimenting with Apple’s AI models inside Shortcuts
sixcolors.com·1d
⚡Proof Automation
Blazing matrix products
panadestein.github.io·9h·
Discuss: Lobsters
⚡SIMD Optimization
The most efficient algorithm for detecting claws in general graphs, with a runtime of O(m Δ) — where m is the number of edges and Δ is the maximum degree — is n...
dev.to·2d·
Discuss: DEV
🔗Topological Sorting
The Internal Inconsistency of Large Language Models
blog.kortlepel.com·2d·
Discuss: Hacker News
💻Local LLMs
Our Coding Adventure: Using LLMs to Personalise the Narrative of a Tangible Programming Robot for Preschoolers
arxiv.org·2h
🎙️Whisper
GLIMPSE: Gradient-Layer Importance Mapping for Prompted Visual Saliency Explanation for Generative LVLMs
arxiv.org·2d
📊Learned Metrics
Timed Prediction Problem for Sandpile Models
arxiv.org·2h
🔲Cellular Automata
Biomed-Enriched: A Biomedical Dataset Enriched with LLMs for Pretraining and Extracting Rare and Hidden Content
arxiv.org·1d
🔍Information Retrieval
CCRS: A Zero-Shot LLM-as-a-Judge Framework for Comprehensive RAG Evaluation
arxiv.org·1d
📏Linear Logic
SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization
arxiv.org·1d
🔍BitFunnel
StoryGem: Voronoi treemap Approach for Semantics-Preserving Text Visualization
arxiv.org·3d
🔶Voronoi Diagrams
LunarLoc: Segment-Based Global Localization on the Moon
arxiv.org·4d
🌀Differential Geometry
Fully lifted \emph{blirp} interpolation -- a large deviation view
arxiv.org·2d
🌀Fractal Compression
Normality Prior Guided Multi-Semantic Fusion Network for Unsupervised Image Anomaly Detection
arxiv.org·3d
👁️Perceptual Hashing
Angio-Diff: Learning a Self-Supervised Adversarial Diffusion Model for Angiographic Geometry Generation
arxiv.org·2d
🌀Riemannian Computing
COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees
arxiv.org·1d
🧠Intelligence Compression
MTSIC: Multi-stage Transformer-based GAN for Spectral Infrared Image Colorization
arxiv.org·3d
🧠Neural Codecs
A Novel Large Vision Foundation Model (LVFM)-based Approach for Generating High-Resolution Canopy Height Maps in Plantations for Precision Forestry Management
arxiv.org·1d
🤖Advanced OCR
LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning
arxiv.org·3d
📝Concrete Syntax