5 papers · 1 filter
NormAct: Benchmarking Embodied Agents' Proactive Compliance with Unspoken Social Norms
Shiyun Zhao, Xinwei Song, Tianyu Guo +7
Embodied agents driven by multimodal large language models (MLLMs) can often complete everyday tasks from visual observations, but goal achievement does not establish whether they…
TeachAnything: A Multimodal Crowdsourcing Platform for Training Embodied AI Agents in Symmetrical Reality
Zidong Liu, Rongkai Liu, Yue Li +1
Symmetrical Reality (SR) is emerging as a future trend for human-agent coexistence, placing higher demands on agents to acquire human-like intelligence. It calls for richer and mor…
TongSIM: A General Platform for Simulating Intelligent Machines
Zhe Sun, Kunlun Wu, Chuanjian Fu +24
As artificial intelligence (AI) rapidly advances, especially in multimodal large language models (MLLMs), research focus is shifting from single-modality text processing to the mor…
SIT: A Benchmark for Spatially Situated Social Intelligence Test
Zhe Sun, Xueyuan Yang, Yujie Lu +1
The integration of embodied agents into human environments demands embodied social intelligence: reasoning over both social norms and physical constraints. However, existing evalua…
Evaluating Multimodal Large Language Models with Daily Composite Tasks in Home Environments
Zhenliang Zhang, Yuxi Wang, Hongzhao Xie +6
A key feature differentiating artificial general intelligence (AGI) from traditional AI is that AGI can perform composite tasks that require a wide range of capabilities. Although…