Language Support for Marginalia Search
marginalia.nu·1d
🔍BitFunnel
LLM Optimization Notes: Memory, Compute and Inference Techniques
gaurigupta19.github.io·18h·
Discuss: Hacker News
💻Local LLMs
Certifiable Safe RLHF: Fixed-Penalty Constraint Optimization for Safer Language Models
arxiv.org·6h
🔗Parser Combinators
Small Language Models for Agentic Systems: A Survey of Architectures, Capabilities, and Deployment Trade offs
arxiv.org·6h
⚙️TLA+
Understanding the 4 Main Approaches to LLM Evaluation (From Scratch)
magazine.sebastianraschka.com·1d·
Discuss: Hacker News
✓Automated Theorem Proving
Can LLMs Detect Ambiguous Plural Reference? An Analysis of Split-Antecedent and Mereological Reference
arxiv.org·6h
🔗Monadic Parsing
COSMIR: Chain Orchestrated Structured Memory for Iterative Reasoning over Long Context
arxiv.org·6h
🌀Brotli Internals
Paper2Video: Automatic Video Generation from Scientific Papers
arxiv.org·6h
📊Document Wavelets
Characteristic Learning for Provable One Step Generation
arxiv.org·6h
🤖Grammar Induction
Read the Scene, Not the Script: Outcome-Aware Safety for LLMs
arxiv.org·6h
🔗Parser Combinators
Generalization of LiNGAM that allows confounding
arxiv.org·6h
🔗Monadic Parsing
Detecting Semantic Clones of Unseen Functionality
arxiv.org·6h
🔗Binary Similarity
Distilling Reasoning into Student LLMs: Local Naturalness for Selecting Teacher Data
arxiv.org·6h
💻Local LLMs
A Low-Resource Speech-Driven NLP Pipeline for Sinhala Dyslexia Assistance
arxiv.org·6h
🎙️Whisper
Property-based testing of batch-invariant operations
mmaaz.ca·1d·
Discuss: Hacker News
🧪Property-Based Testing
SliceMoE: Routing Embedding Slices Instead of Tokens for Fine-Grained and Balanced Transformer Scaling
arxiv.org·6h
🧮Kolmogorov Complexity
Relative Code Comprehensibility Prediction
arxiv.org·6h
🧠Intelligence Compression
Generative AI finds antimicrobial peptides against multidrug-resistant bacteria
nature.com·2d·
Discuss: Hacker News
⚙️ABNF Mining
Automating construction safety inspections using a multi-modal vision-language RAG framework
arxiv.org·6h
🤖Advanced OCR
Harnessing LLM for Noise-Robust Cognitive Diagnosis in Web-Based Intelligent Education Systems
arxiv.org·6h
🧠Intelligence Compression