Coping with Complexity
slott56.github.io·5d
🔗Concatenative Programming
DEVONthink 4.0 Copernicus
devontechnologies.com·22h·
Discuss: Hacker News
🕸️Knowledge Graphs
The Distribution of Prime Numbers: A Geometrical Perspective
blog.computationalcomplexity.org·19h·
Discuss: blog.computationalcomplexity.org, Hacker News
📐Mathematical Art
Greedy Is Good. Less Greedy May Be Better
gojiberries.io·2d·
Discuss: Hacker News
🧮Kolmogorov Complexity
Structural Optimal Jacobian Accumulation and Minimum Edge Count are NP-Complete Under Vertex Elimination
arxiv.org·3d
🎯Performance Proofs
Dive Deep into Higher-Order Functions: Essential Resources for Functional Programmers
dev.to·3d·
Discuss: DEV
🧬Functional Programming
Single Core Hundred Thousand Concurrency（1750947668443300）
dev.to·18h·
Discuss: DEV
🌊Stream Processing
Existing LLMs Are Not Self-Consistent For Simple Tasks
arxiv.org·3d
💻Local LLMs
On Union-Closedness of Language Generation
arxiv.org·3d
🔗Monadic Parsing
Black-Box Test Code Fault Localization Driven by Large Language Models and Execution Estimation
arxiv.org·2d
🔍Concolic Testing
TITAN: Query-Token based Domain Adaptive Adversarial Learning
arxiv.org·4h
📊Learned Metrics
Recall and Refine: A Simple but Effective Source-free Open-set Domain Adaptation Framework
arxiv.org·4h
💻Local LLMs
A large deviation view of \emph{stationarized} fully lifted blirp interpolation
arxiv.org·2d
📐Compression Bounds
PATCH! {P}sychometrics-{A}ssis{T}ed Ben{CH}marking of Large Language Models against Human Populations: A Case Study of Proficiency in 8th Grade Mathematics
arxiv.org·2d
🧠Intelligence Compression
Flame Graph Performance Truth Analysis（1750839255230100）
dev.to·2d·
Discuss: DEV
⚡Performance Tools
CCRS: A Zero-Shot LLM-as-a-Judge Framework for Comprehensive RAG Evaluation
arxiv.org·1d
📏Linear Logic
From Codicology to Code: A Comparative Study of Transformer and YOLO-based Detectors for Layout Analysis in Historical Documents
arxiv.org·1d
📃Manuscript Tokenization
Argumentative Ensembling for Robust Recourse under Model Multiplicity
arxiv.org·1d
🔗Parser Combinators
Contextualizing SUTRA: Advancements in Multilingual & Efficient LLMs
hackernoon.com·1d
💻Local LLMs
Leveraging LLM-Assisted Query Understanding for Live Retrieval-Augmented Generation
arxiv.org·4h
🔍Information Retrieval