4 papers
Dissecting Embodied Abilities in Multimodal Language Models through Skill-level Evaluation and Diagnosis
Yu Qi, Haibo Zhao, Ziyu Guo +17
Understanding the capability bottlenecks of embodied multimodal large language models (MLLMs) is crucial for improving embodied agents. However, existing embodied benchmarks mainly…
Learning Environment-Aware Affordance for 3D Articulated Object Manipulation under Occlusions
Ruihai Wu, Kai Cheng, Yan Shen +3
Perceiving and manipulating 3D articulated objects in diverse environments is essential for home-assistant robots. Recent studies have shown that point-level affordance provides ac…
EfficientEQA: An Efficient Approach to Open-Vocabulary Embodied Question Answering
Kai Cheng, Zhengyuan Li, Xingpeng Sun +3
Embodied Question Answering (EQA) is an essential yet challenging task for robot assistants. Large vision-language models (VLMs) have shown promise for EQA, but existing approaches…
SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction
Zhengyuan Li, Kai Cheng, Anindita Ghosh +3
Text-based 3D human motion editing is a critical yet challenging task in computer vision and graphics. While training-free approaches have been explored, the recent release of the…