論文 深掘り Hugging Face 発表: 2026-06-08 HF ↑165

Kwai Keye-VL-2.0 Technical Report

Kwai Keye-VL-2.0 Technical Report

著者: Kwai Keye Team, Bin Wen, Changyi Liu, Chengru Song, Chongling Rao ほか48名

要約

We introduce Kwai Keye-VL-2.0-30B-A3B, an open-source Mixture-of-Experts (MoE) multimodal foundation model designed to advance long-video understanding and agentic intelligence. To address the challenges of ultra-long contexts, information redundancy, and prohibitive computational costs inherent in …

#multimodal#agent#alignment#benchmark

同じカテゴリの記事