Latest Articles

Explore our collection of translated and curated content from China's leading AI researchers and companies.

Technology

Decoding Strategies for Large Language Models Explained

# Decoding Strategies for Large Language Models (LLMs) At the core of every large language model (LLM) is a sophisticated process for generating text. Instead of selecting words at random, the model...

AI Insights Portal

large language model decoding strategiesLLM sampling methodsGreedy Search
Technology

Kimi Researcher: End-to-End RL for Advanced AI Agents

## Kimi Researcher: Advancing AI Agents with End-to-End Reinforcement Learning Kimi Researcher is the flagship product of the Kimi Agent initiative, designed to revolutionize research automation thr...

AI Insights Portal

Kimi Researcherend-to-end reinforcement learningAI agent
Technology

Qwen3 QK-Norm: Improved On-Device AI Stability

## Qwen3 Model Family: QK-Norm and Enhanced Attention Mechanism The Qwen3 model family, Alibaba's latest large language model release, introduces a significant upgrade for on-device AI: the adoption...

AI Insights Portal

Qwen3QK-Normattention mechanism