2024 年热门更新
2024年12月
- deepmind.google
FACTS Grounding: A new benchmark for evaluating the factuality of large language models
Our comprehensive benchmark and online leaderboard offer a much-needed measure of how accurately LLMs ground their responses in provided source material and avoid hallucinations
- blog.google
State-of-the-art video and image generation with Veo 2 and Imagen 3
Google DeepMind and Google Labs released Veo 2, a new video model, and the latest version of Imagen 3, which the post says achieved state-of-the-art results in human rater comparisons against leading …
