🎯 Dependent Parsing

Context-sensitive Grammars, Type-dependent Syntax, Proof-carrying Parsers, Verified Parsing

Toy Binary Decision Diagrams
philipzucker.com·2d
🧮Algebraic Datatypes
LLM Poisoning [1/3] - Reading the Transformer's Thoughts
synacktiv.com·2d
💻Local LLMs
Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization
arxiv.org·1d
💻Local LLMs
TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning
arxiv.org·9h
🎯Performance Proofs
Quantifying the Accuracy-Interpretability Trade-Off in Concept-Based Sidechannel Models
arxiv.org·9h
🧠Machine Learning
Code-Switching In-Context Learning for Cross-Lingual Transfer of Large Language Models
arxiv.org·9h
🎙️Whisper
Atomic and Saturated Models
functor.network·4d·
Discuss: Hacker News
🔢Denotational Semantics
Read the Scene, Not the Script: Outcome-Aware Safety for LLMs
arxiv.org·1d
🔗Parser Combinators
KEO: Knowledge Extraction on OMIn via Knowledge Graphs and RAG for Safety-Critical Aviation Maintenance
arxiv.org·9h
🧠Intelligence Compression
SigmaEval – statistical evaluation for GenAI apps
github.com·1h·
Discuss: Hacker News
🔍Concolic Testing
Writing an LLM from scratch, part 21 – perplexed by perplexity
gilesthomas.com·18h·
Discuss: Hacker News
🧠Intelligence Compression
ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization
arxiv.org·9h
🧠Machine Learning
LexiCon: a Benchmark for Planning under Temporal Constraints in Natural Language
arxiv.org·9h
🧮Kolmogorov Complexity
Automating construction safety inspections using a multi-modal vision-language RAG framework
arxiv.org·1d
🤖Advanced OCR
Graph-based LLM over Semi-Structured Population Data for Dynamic Policy Response
arxiv.org·9h
💻Local LLMs
Test Case Generation from Bug Reports via Large Language Models: A Cognitive Layered Evaluation Framework
arxiv.org·9h
🔍Concolic Testing
Generalization of LiNGAM that allows confounding
arxiv.org·1d
🔗Monadic Parsing
To model human linguistic prediction, make LLMs less superhuman
arxiv.org·9h
🧠Intelligence Compression
Characteristic Learning for Provable One Step Generation
arxiv.org·1d
🤖Grammar Induction
Optimizing Long-Form Clinical Text Generation with Claim-Based Rewards
arxiv.org·2d
📋Document Grammar