7 papers
ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play Adaptation
Zeyuan He, Bowen Yang, Zhirui Fang +9
Vision-Language-Action (VLA) models have shown promise for robotic manipulation, yet most existing policies operate reactively by directly regressing actions from current observati…
ESCAPE: Episodic Spatial Memory and Adaptive Execution Policy for Long-Horizon Mobile Manipulation
Jingjing Qian, Zeyuan He, Chen Shi +2
Coordinating navigation and manipulation with robust performance is essential for embodied AI in complex indoor environments. However, as tasks extend over long horizons, existing…
InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulation
Junhao Cai, Zetao Cai, Jiafei Cao +39
Prevalent Vision-Language-Action (VLA) models are typically built upon Multimodal Large Language Models (MLLMs) and demonstrate exceptional proficiency in semantic understanding, b…
Nimbus: A Unified Embodied Synthetic Data Generation Framework
Zeyu He, Yuchang Zhang, Yuanzhen Zhou +10
Scaling data volume and diversity is critical for generalizing embodied intelligence. While synthetic data generation offers a scalable alternative to expensive physical data acqui…
MoTiC: Momentum Tightness and Contrast for Few-Shot Class-Incremental Learning
Zeyu He, Shuai Huang, Yuwu Lu +1
Few-Shot Class-Incremental Learning (FSCIL) must contend with the dual challenge of learning new classes from scarce samples while preserving old class knowledge. Existing methods…
LandMarkSystem Technical Report
Zhenxiang Ma, Zhenyu Yang, Miao Tao +5
3D reconstruction is vital for applications in autonomous driving, virtual reality, augmented reality, and the metaverse. Recent advancements such as Neural Radiance Fields(NeRF) a…