10 papers
Scale Up Strategically: Learning Compositional Generalization via Bias-Aware Evaluation and Data Collection for Robotic Manipulation
Yu Qi, Zhang Ye, Xinyi Xu +6
Compositional generalization is essential for robot to follow diverse instructions. However, pretrained policies are known to take shortcuts, deferring to salient cues rather than…
MME-CoF-Pro: Evaluating Reasoning Coherence in Video Generative Models with Text and Visual Hints
Yu Qi, Xinyi Xu, Ziyu Guo +10
Video generative models show emerging reasoning behaviors. It is essential to ensure that generated events remain causally consistent across frames for reliable deployment, a prope…
Discovering Symmetry Groups with Flow Matching
Yuxuan Chen, Jung Yeon Park, Floor Eijkelboom +4
Symmetry is fundamental to understanding physical systems and can improve performance and sample efficiency in machine learning. Both pursuits require knowledge of the underlying s…
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…
Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation
Yu Qi, Yuanchen Ju, Tianming Wei +3
3D assembly tasks, such as furniture assembly and component fitting, play a crucial role in daily life and represent essential capabilities for future home robots. Existing benchma…
Equivariant Action Sampling for Reinforcement Learning and Planning
Linfeng Zhao, Owen Howell, Xupeng Zhu +4
Reinforcement learning (RL) algorithms for continuous control tasks require accurate sampling-based action selection. Many tasks, such as robotic manipulation, contain inherent pro…