Meituan Releases LongCat-2.0: A 1.6T-Parameter Open MoE Model with Native 1M Context and LongCat Sparse Attention
Source: MarkTechPost Meituan has released LongCat-2.0, a large-scale Mixture-of-Experts (MoE) language model. It carries 1.6 trillion total parameters...
LlamaIndex ‘legal-kb’: Agentic Retrieval over Index v2 with retrieve, find, read, and grep Tools
Source: MarkTechPost LlamaIndex has published legal-kb, a public reference application on GitHub. It is described as a knowledge...
Structured PDF-to-JSON: A Guide to Open-Source Extraction Models in 2026
Source: MarkTechPost Most enterprise data still sits inside PDFs, scans, and slide decks. Large language models and agents...
Qwen’s Former Lead on What Hybrid Thinking Got Wrong — and Why He Now Backs Agents
Source: MarkTechPost Junyang Lin was the technical lead of Alibaba’s Qwen project. He announced he was stepping down...