How to Read a Book: 002, A Few Thoughts on Books
janusworx.com·16h
🔢Coding Theory
From Tables to Relationships: Visualizing Iceberg Data as a Graph
blog.min.io·15h
🔄Sync Engine
Announcing crabstep: A pure Rust, cross-platform, zero-dependency Apple/NeXTSTEP typedstream deserializer
github.com·2d
🔒Linear Types
A CRDT-based Messenger in 12 Lines of Bash Using a Synced Folder
holdtherobot.com·1d·
Discuss: Lobsters, Hacker News, Hacker News
🔀CRDT
Using an LLM for query planning in RAG –> 40% better answer relevance
techcommunity.microsoft.com·3d·
Discuss: Hacker News
🔍Information Retrieval
The Age of Integrity
schneier.com·20h·
Discuss: Hacker News
🔗Data Provenance
[memo] Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding
dev.to·6h·
Discuss: DEV
👁️Perceptual Coding
Show HN: I made a fast, offline-first developer toolkit with no ads or tracking
news.ycombinator.com·1d·
Discuss: Hacker News
🚀Indie Hacking
NSFW-Classifier Guided Prompt Sanitization for Safe Text-to-Image Generation
arxiv.org·4d
👁️Constructive OCR
Unveiling Insights: 18 Essential Resources for Exploratory Data Analysis (EDA)
dev.to·3d·
Discuss: DEV
⛏️Archive Mining
scMamba: A Scalable Foundation Model for Single-Cell Multi-Omics Integration Beyond Highly Variable Feature Selection
arxiv.org·1d
🧠Machine Learning
Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights
arxiv.org·4d
📝Text Parsing
LLMs for Customized Marketing Content Generation and Evaluation at Scale
arxiv.org·4d
📊Feed Optimization
MemeMind: A Large-Scale Multimodal Dataset with Chain-of-Thought Reasoning for Harmful Meme Detection
arxiv.org·3d
🧮Vector Embeddings
Deception Detection in Dyadic Exchanges Using Multimodal Machine Learning: A Study on a Swedish Cohort
arxiv.org·1d
🧠Machine Learning
Dialogic Pedagogy for Large Language Models: Aligning Conversational AI with Proven Theories of Learning
arxiv.org·3d
🤖Grammar Induction
Accurate and Energy Efficient: Local Retrieval-Augmented Generation Models Outperform Commercial Large Language Models in Medical Tasks
arxiv.org·2d
🌀Brotli Internals
JavaScript Concept: Currying and its implementation in Redux
dev.to·10h·
Discuss: DEV
⬆️Lambda Lifting
Probabilistic and reinforced mining of association rules
arxiv.org·4d
🧠Learned Indexes
PARALLELPROMPT: Extracting Parallelism from Large Language Model Queries
arxiv.org·4d
🚀SIMD Text Processing