🤖 LLMs - deglon · Scour

How to Build Your Own Language-Specific LLM [Full Handbook] 🔍RAG

freecodecamp.org·5d

This survey presents a comprehensive and structured synthesis of memory in LLMs and MLLMs, organizing the literature into a cohesive taxonomy comprising implicit, explicit, and agentic memory paradigms. 🛠️AI Tools

Show HN: How LLMs Work – Interactive visual guide based on Karpathy's lecture 🔍RAG

ynarwal.github.io·6d·Hacker News

AI hallucinations, bias and data leaks: Expanding LLM risk landscape 🤖AI

devdiscourse.com·2d

Speculative Decoding vs MoE: 3.2x Cost Gap on Llama 3 🤖AI

tildalice.io·2d

Language Generation in the Limit 🔍RAG

openreview.net·5d

Statistical Structure and the Failure of Pointing: A System-Class Law for Compression-Based Generative Systems 🔍RAG

philsci-archive.pitt.edu·3d

Adaptive Thinking: Large Language Models Know When to Think in Latent Space 🔍RAG

machinelearning.apple.com·1d

Ziggit and Large Language Models 🔍RAG

FlowBot: Inducing LLM Workflows with Bilevel Optimization and Textual Gradients 🛠️AI Tools

Winning a Kaggle Competition with Generative AI–Assisted Coding 🤖AI

developer.nvidia.com·6d

umbecanessa/neural-ledger-system: An inference architecture that makes LLMs stateful. Patent pending (US 64/050,345). 🛠️Prompt Engineering

github.com·1d·Hacker News

Libraries and Archives, a Natural Home for Language Models 🔍RAG

rsdoiel.github.io·4d

Granite 4.1 LLMs: How They’re Built 🤖AI

huggingface.co·1d·Hacker News

RNN to Transformer NMT: PyTorch Migration with 2.8x BLEU Gain 🔍RAG

tildalice.io·5d

MoRFI: Monotonic Sparse Autoencoder Feature Identification 🤖AI

Training a Transformer to Compose One Step Per Layer (and Proving It) 🔍RAG

lesswrong.com·3d

Language Anchoring: A Systematic Method for LLM Multilingual Adaptation 🛠️Prompt Engineering

github.com·3d·Hacker News

Large Language Models for Multilingual Code Intelligence: A Survey 🔍RAG

Delineating Knowledge Boundaries for Honest Large Vision-Language Models 🔍RAG

Log in to enable infinite scrolling