Evaluating Document Extraction Accuracy
runpulse.com·1h·
Discuss: Hacker News
📋Document Layout
Remote Sensing Image Intelligent Interpretation with the Language-Centered Perspective: Principles, Methods and Challenges
arxiv.org·15h
📸TIFF Archaeology
From Image to Text in Seconds — Tesseract OCR in a Docker Container
dev.to·16h·
Discuss: DEV
📄Document Streaming
Show HN: Building a web search engine from scratch with 3B neural embeddings
blog.wilsonl.in·3h·
Discuss: Hacker News
🔍Semantic Search
How do Live Text and Visual Look Up work now?
eclecticlight.co·12h
🍎Apple Archive
Recto – A Truly 2D Language
masatohagiwara.net·4h·
Discuss: Hacker News
📝Concrete Syntax
Decentralized Proof-of-Location systems for trust, scalability, and privacy
nature.com·1d·
Discuss: Hacker News
🤝Distributed Consensus
Certificate Transparency - Part 2 - Sunlight
ipng.ch·2d
🌳Archive Merkle Trees
LFM2-VL: Efficient Vision-Language Models
liquid.ai·33m·
Discuss: Hacker News
💻Local LLMs
SAEMark: Multi-bit LLM Watermarking with Inference-Time Scaling
arxiv.org·15h
⚙️Compression Benchmarking
Edge Detection for Organ Boundaries via Top Down Refinement and SubPixel Upsampling
arxiv.org·15h
🤖Advanced OCR
CLUE: Leveraging Low-Rank Adaptation to Capture Latent Uncovered Evidence for Image Forgery Localization
arxiv.org·15h
🔍Vector Forensics
Show HN: Generative Graphics LLM Benchmark
ggbench.com·1d·
Discuss: Hacker News
🖥️Terminal Emulators
Fine-Tune Your Topic Modeling Workflow with BERTopic
towardsdatascience.com·2h
📊Feed Optimization
Automated Hierarchical Semantic Graph Analysis for Enhanced Fraud Detection in Financial Transactions
dev.to·2d·
Discuss: DEV
🔍BitFunnel
CROP: Integrating Topological and Spatial Structures via Cross-View Prefixes for Molecular LLMs
arxiv.org·15h
🤖Paleographic ML
InterChart: Benchmarking Visual Reasoning Across Decomposed and Distributed Chart Information
arxiv.org·15h
🤖Advanced OCR
I built a pipeline for automatically translating Chinese news
bednarskiwsieci.pl·2h·
Discuss: Hacker News
🇨🇳Chinese Computing
Bridging Semantic Logic Gaps: A Cognition-Inspired Multimodal Boundary-Preserving Network for Image Manipulation Localization
arxiv.org·15h
🤖Advanced OCR
ContextGuard-LVLM: Enhancing News Veracity through Fine-grained Cross-modal Contextual Consistency Verification
arxiv.org·15h
📰Content Curation