Announcement of the release of 'Build a Reasoning Model (From Scratch)', a book on implementing modern reasoning techniques for AI.
Explores Mixture of Experts (MoE) in AI models, its sparse routing principle, and how it enables large model capacity with low compute cost per token.
A technical analysis of the DeepSeek model series, from V3 to the latest V3.2, covering architecture, performance, and release timeline.
Analysis of DeepSeek V3.2's architecture, sparse attention mechanism, and RL updates compared to its predecessor and proprietary models.
Analyzes the architectural advancements in OpenAI's new open-weight gpt-oss models, comparing them to GPT-2 and other modern LLMs.
Explores how large language models (LLMs) are transforming industrial recommendation systems and search, covering hybrid architectures, data generation, and unified frameworks.
A Google researcher's curated review of key AI research papers from 2024, covering LLMs, new architectures, agents, and security.
An overview of the top 10 open research challenges in Large Language Models (LLMs), focusing on reducing hallucinations and optimizing context learning.
