Physics-informed AI excels at large-scale discovery of new materials
phys.org·1d
🧠Machine Learning
Efficient and accurate search in petabase-scale sequence repositories
nature.com·3d·
Discuss: Hacker News
🔄Burrows-Wheeler
Show HN: Using an LLM to sensibly sort a shopping receipt
treblig.org·2d·
Discuss: Hacker News
🔗Constraint Handling
Eon – An Effects-Based OCaml Nameserver
ryan.freumh.org·15h·
Discuss: Lobsters, Hacker News
🌐DNS Security
Fundamental Interconnectedness of All Things on Talking Postgres Podcast
talkingpostgres.com·23h·
Discuss: Hacker News
🧬PostgreSQL Forensics
LLM Optimization Notes: Memory, Compute and Inference Techniques
gaurigupta19.github.io·5d·
Discuss: Hacker News
💻Local LLMs
Multi-Core By Default
rfleury.com·1d·
Discuss: Lobsters, Hacker News
🔩Systems Programming
H1B-KV: Hybrid One-Bit Caches for Memory-Efficient Large Language Model Inference
arxiv.org·3d
💨Cache Optimization
Integral Signatures of Activation Functions: A 9-Dimensional Taxonomy and Stability Theory for Deep Learning
arxiv.org·1d
🧠Machine Learning
Activation Alchemist: Sculpting Stability with Functional Signatures
dev.to·1d·
Discuss: DEV
🔍Concolic Testing
In-Depth Analysis: "Attention Is All You Need"
dev.to·1d·
Discuss: DEV
🧠Intelligence Compression
Building an AI Internal Linking Plugin for WordPress
dev.to·14h·
Discuss: DEV
🌀Brotli Internals
Nearest Neighbor CCP-Based Molecular Sequence Analysis
arxiv.org·1d
🔄Burrows-Wheeler
DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization
arxiv.org·4d
🎯Performance Proofs
Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization
arxiv.org·4d
💻Local LLMs
Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning
arxiv.org·4d
⚡Incremental Computation
CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension
arxiv.org·3d
📝Concrete Syntax
Benchmarking LLM Causal Reasoning with Scientifically Validated Relationships
arxiv.org·2d
💻Programming languages
Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
arxiv.org·2d
💻Local LLMs
Comparing human and language models sentence processing difficulties on complex structures
arxiv.org·2d
🔗Parser Combinators