11 papers
Systematically Exploring the Capabilities of GPT-6 Astra as Embodied Policies
Galbot Team, Xuchuan Chen, Xiaoqian Cheng +31
GPT-6 Astra exhibits a remarkable ability to generate numerical robot actions, extending its role beyond high-level planning. To assess Astra's capabilities as general-purpose embo…
HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark
Dairu Liu, Zekun Qi, Jiayu Zeng +11
Humanoid motion tracking is central to teleoperation and whole-body imitation, yet evaluation often disagrees with what people perceive in videos. Kinematic errors average per-fram…
DeformGen: Dynamics-Based Topology Augmentation for Deformable Manipulation Policy Learning
Zili Lin, Wenyao Zhang, Yuyang Zhang +9
Demonstration augmentation is proposed for cost-efficient data acquisition, but existing methods are fundamentally limited in deformable manipulation due to two challenges: (1) the…
ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?
Yuyang Zhang, Wenyao Zhang, Zekun Qi +7
World Action Models (WAMs) commonly rely on video generation to bridge visual world modeling and robot control. However, video-based WAMs face three coupled limitations: dense mult…
Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining
Wenyao Zhang, Bozhou Zhang, Zekun Qi +3
Vision-language-action (VLA) models have shown great potential in building generalist robots, but still face a dilemma-misalignment of 2D image forecasting and 3D action prediction…
Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data
Zhikai Zhang, Haofei Lu, Yunrui Lian +12
Human athletes demonstrate versatile and highly-dynamic tennis skills to successfully conduct competitive rallies with a high-speed tennis ball. However, reproducing such behaviors…
VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model
Jingwen Sun, Wenyao Zhang, Zekun Qi +6
Pretraining Vision-Language-Action (VLA) policies on internet-scale video is appealing, yet current latent-action objectives often learn the wrong thing: they remain anchored to pi…
ReWorld: Multi-Dimensional Reward Modeling for Embodied World Models
Baorui Peng, Wenyao Zhang, Liang Xu +5
Recently, video-based world models that learn to simulate the dynamics have gained increasing attention in robot learning. However, current approaches primarily emphasize visual ge…
Switch-JustDance: Benchmarking Whole Body Motion Tracking Controllers Using a Commercial Console Game
Jeonghwan Kim, Wontaek Kim, Yidan Lu +9
Recent advances in whole-body robot control have enabled humanoid and legged robots to perform increasingly agile and coordinated motions. However, standardized benchmarks for eval…
Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation
Wenyao Zhang, Hongsi Liu, Bohan Li +7
Current self-supervised monocular depth estimation (MDE) approaches encounter performance limitations due to insufficient semantic-spatial knowledge extraction. To address this cha…
MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning
Tianyu Xu, Jiawei Chen, Jiazhao Zhang +5
Visual navigation policy is widely regarded as a promising direction, as it mimics humans by using egocentric visual observations for navigation. However, optical information of vi…