11 papers
VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models
Jianke Zhang, Xiaoyu Chen, Qiuyue Wang +7
Vision-Language-Action (VLA) models, which integrate pretrained large Vision-Language Models (VLM) into their policy backbone, are gaining significant attention for their promising…
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…
UniJEPA: Enhancing Robot Policy via Unified Continuous and Discrete Representation Learning
Jianke Zhang, Yucheng Hu, Yanjiang Guo +5
Building generalist robot policies that can handle diverse tasks in open-ended environments is a central challenge in robotics. To leverage knowledge from large-scale pretraining,…
Veo-Act: How Far Can Frontier Video Models Advance Generalizable Robot Manipulation?
Zhongru Zhang, Chenghan Yang, Qingzhou Lu +4
Video generation models have advanced rapidly and are beginning to show a strong understanding of physical dynamics. In this paper, we investigate how far an advanced video generat…
RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation
Jiajun Zhang, Yuying Li, Zhixun Li +13
Vision-Language Models (VLMs) have demonstrated impressive capabilities in code generation across various domains. However, their ability to replicate complex, multi-panel visualiz…
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…