5 papers
UAM: A Dual-Stream Perspective on Forgetting in VLA Training
Jianke Zhang, Yuanfei Luo, Yucheng Hu +6
Vision--language--action (VLA) models are typically built by fine-tuning a pretrained vision--language model (VLM) on action data. However, we show that this standard recipe system…
BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation
Yucheng Hu, Jianke Zhang, Yuanfei Luo +9
Equipping embodied agents with the ability to reason about tasks, foresee physical outcomes, and generate precise actions is essential for general-purpose manipulation. While recen…
Hydra-Nav: Object Navigation via Adaptive Dual-Process Reasoning
Zixuan Wang, Huang Fang, Shaoan Wang +4
While large vision-language models (VLMs) show promise for object goal navigation, current methods still struggle with low success rates and inefficient localization of unseen obje…
VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memory
Shaoan Wang, Yuanfei Luo, Xingyu Chen +6
VLA models have shown promising potential in embodied navigation by unifying perception and planning while inheriting the strong generalization abilities of large VLMs. However, mo…
UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous Driving
Hao Lu, Ziyang Liu, Guangfeng Jiang +4
Autonomous driving (AD) systems struggle in long-tail scenarios due to limited world knowledge and weak visual dynamic modeling. Existing vision-language-action (VLA)-based methods…