Show HN: Baby's First International Landline
wip.tf·27m·
Discuss: Hacker News
📻Homebrew Protocols
Vibe engineering
simonwillison.net·23h·
Discuss: Lobsters, Hacker News
📏Code Metrics
MathArena Apex: Unconquered Final-Answer Problems
matharena.ai·3d·
Discuss: Hacker News
🧮SMT Solvers
Decoding the Cosmos: How AI is Making Sense of Starlight's Rhythms by Arvind Sundararajan
dev.to·1h·
Discuss: DEV
📊Quantization
Approximate Gaussianity Beyond Initialisation in Neural Networks
arxiv.org·9h
🕸️Tensor Networks
Digital Twins for Intelligent Intersections: A Literature Review
arxiv.org·9h
🌀Differential Geometry
Finite Time Analysis of Constrained Natural Critic-Actor Algorithm with Improved Sample Complexity
arxiv.org·1d
🔲Cellular Automata
AI-Driven Data Engineering: Building Real-Time Intelligence Pipelines
dev.to·11h·
Discuss: DEV
🌊Stream Processing
IndiCASA: A Dataset and Bias Evaluation Framework in LLMs Using Contrastive Embedding Similarity in the Indian Context
arxiv.org·2d
🤖Grammar Induction
Evaluating Bias in Spoken Dialogue LLMs for Real-World Decisions and Recommendations
arxiv.org·2d
🎙️Whisper
A Trustworthy Industrial Fault Diagnosis Architecture Integrating Probabilistic Models and Large Language Models
arxiv.org·1d
🧠Machine Learning
COSMIR: Chain Orchestrated Structured Memory for Iterative Reasoning over Long Context
arxiv.org·1d
🌀Brotli Internals
SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
arxiv.org·1d
💻Local LLMs
Unsupervised Active Learning via Natural Feature Progressive Framework
arxiv.org·1d
🧠Machine Learning
Can LLMs Detect Ambiguous Plural Reference? An Analysis of Split-Antecedent and Mereological Reference
arxiv.org·1d
🔗Monadic Parsing
Decoding Emotion in the Deep: A Systematic Study of How LLMs Represent, Retain, and Express Emotion
arxiv.org·1d
💻Local LLMs
FocusMed: A Large Language Model-based Framework for Enhancing Medical Question Summarization with Focus Identification
arxiv.org·1d
🔍Information Retrieval
CCD-Bench: Probing Cultural Conflict in Large Language Model Decision-Making
arxiv.org·1d
🌍Cultural Algorithms
RAG Chunking Strategies That Actually Work (and Why Most Don’t)
dev.to·1d·
Discuss: DEV
📄Text Chunking
QDeepGR4J: Quantile-based ensemble of deep learning and GR4J hybrid rainfall-runoff models for extreme flow prediction with uncertainty quantification
arxiv.org·9h
🧠Machine Learning