1
EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoning
首个面向自我中心视频的长程场景预测基准,挑战模型在未见环境中的多模态推理极限。
arXiv:2603.09731v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) are increasingly considered as a foundation for emb…