PAIRS: Parametric-Verified Adaptive Information Retrieval and Selection for Efficient RAG
arxiv.org·17h
📊Multi-vector RAG
Cross-Entropy. Intuition and Applications
hclimente.eu·20h·
Discuss: Hacker News
📈Entropy Estimation
Neurosymbolic AI: Why, What, and How
muratbuffalo.blogspot.com·6h·
Discuss: www.blogger.com
🧠Intelligence Compression
SAT Requires Exhaustive Search
link.springer.com·3d·
Discuss: Hacker News
🎯Performance Proofs
Parametric Matrix Models
nature.com·3h·
Discuss: Hacker News
📐Linear Algebra
(BT) Diversity from (LC) Diversity
golem.ph.utexas.edu·2d
📐Information Geometry
Pushing the limits of long-context LLM training for 1M-token+ medical records
akasa.com·3h·
Discuss: Hacker News
🎵Audio ML
LLMs can predict educational and psychological outcomes from childhood essays with remarkable accuracy
phys.org·10h
🧠Intelligence Compression
Enhanced Algal Bloom Prediction and Mitigation via Multi-Modal Data Fusion and Bayesian Optimization
dev.to·13h·
Discuss: DEV
🧮Kolmogorov Bounds
The Channel-Wise Attention | Squeeze and Excitation
towardsdatascience.com·3h
📊Learned Metrics
Hierarchical Verification of Speculative Beams for Accelerating LLM Inference
arxiv.org·17h
💻Local LLMs
My blog on zero-knowledge cryptography
kaw101010.github.io·20h·
Discuss: Hacker News
🔐Quantum Security
Estimating Worst-Case Frontier Risks of Open-Weight LLMs
arxiv.org·1d
💻Local LLMs
Show HN: VectorOps Know
vectorops.dev·7h·
Discuss: Hacker News
🌳Incremental Parsing
Optimal Scheduling Algorithms for LLM Inference: Theory and Practice
arxiv.org·2d
💻Local LLMs
Benchmarking Foundation Models for Mitotic Figure Classification
arxiv.org·17h
🧠Machine Learning
LLMs - Embeddings 01
dev.to·3d·
Discuss: DEV
🧮Vector Embeddings
Why Your AI Never Works on the First Try
fluxus.io·7h·
Discuss: Hacker News
🧠Intelligence Compression
LLM Inflation
tratt.net·1d·
Discuss: Hacker News
📊Compression Proofs
NeuralMorse – Reinventing Morse Code with Neural Networks
masatohagiwara.net·2d·
Discuss: Hacker News
📝Text Compression