A curated archive of frontier intelligence, operator-grade guides, and strategic analysis.
LLHKG framework enables lightweight large language models to construct knowledge graphs with performance comparable to GPT-3.5, automating entity and relation extraction.
Read the briefing
Researchers evaluate GPT-4, Gemini, and other LLMs across social media tasks including authorship verification, post generation, and user attribute inference...
Comprehensive evaluation of GPT-4, GPT-4o, Gemini 1.5 Pro, and other LLMs across social media authorship verification, post generation, and user...
Qwen3.5-Omni is Alibaba's latest multimodal AI model with hundreds of billions of parameters, 256k context length, and advanced audio-visual capabilities...
Researchers evaluated GPT-4, GPT-4o, Gemini 1.5 Pro, DeepSeek-V3, and other LLMs across three social media analytics tasks using Twitter data...
Comprehensive evaluation of GPT-4, GPT-4o, Gemini 1.5 Pro, and other LLMs across social media authorship verification, post generation, and user...
LLHKG framework uses lightweight large language models to automatically construct knowledge graphs from text, achieving performance comparable to GPT-3.5 for...
Comprehensive evaluation of GPT-4, GPT-4o, Gemini 1.5 Pro, DeepSeek-V3, and other LLMs across three core social media analytics tasks on...
LLHKG framework uses lightweight large language models to automatically construct knowledge graphs from text, achieving GPT-3.5 comparable performance in entity...
Researchers evaluated GPT-4, Gemini 1.5 Pro, and other LLMs across three social media analytics tasks using Twitter data, establishing new...
