14 papers
SmoothRL: Online Reinforcement Learning During Asynchronous Execution
Guang Gao, Yuxuan Nong, Baifu Huang +1
Deploying robot policies in the physical world requires satisfying two fundamental desiderata: reliability and smooth real-time execution. However, deploying state-of-the-art gener…
Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use
Ding Yi, Yi Ding, Yanzhao Yu +6
This paper integrates end-to-end Visual-Language-Action (VLA) models with agentic tool-use to propose Agentic Robot with Tool-use (ART). ART is a tool-injection framework that tune…
A Glimpse into Long-term Physical Coexistence with Intelligent Robots
Weiqi Jin, Peijun Tang, Kuncheng Luo +5
Long-term physical coexistence with intelligent robots requires more than capable robot policies. A persistent robotic assistant must support diverse user-facing interfaces, mainta…
Towards Predictive, Aligned, and Scalable Robot Learning
Peijun Tang, Shangjin Xie, Baifu Huang +6
Learning, at its core, extends beyond memorization to the ability to reason and solve novel problems by navigating a space of possibilities. We introduce Lumo-2, a latent world-act…
MetaphorVU: Towards Metaphorical Video Understanding
Zhuoqun Li, Boxi Cao, Guiping Jiang +13
Metaphorical videos are prevalent across various real-world scenarios to convey complex ideas, and understanding them typically requires high-order cognitive capabilities. The lack…
StableVLA: Towards Robust Vision-Language-Action Models without Extra Data
Yiyang Fu, Chubin Zhang, Shukai Gong +7
It is infeasible to encompass all possible disturbances within the training dataset. This raises a critical question regarding the robustness of Vision-Language-Action (VLA) models…
When to Trust Imagination: Adaptive Action Execution for World Action Models
Rui Wang, Yue Zhang, Jiehong Lin +5
World Action Models (WAMs) jointly predict future visual observations and actions, but typically execute a fixed number of actions before replanning, regardless of whether the imag…
CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos
Chubin Zhang, Jianan Wang, Zifeng Gao +5
Generalist Vision-Language-Action models remain constrained by the scarcity of robotic data relative to the abundance of human video demonstrations. Existing Latent Action Models a…
Mind to Hand: Purposeful Robotic Control via Embodied Reasoning
Peijun Tang, Shangjin Xie, Binyan Sun +5
Humans act with context and intention, with reasoning playing a central role. While internet-scale data has enabled broad reasoning capabilities in AI systems, grounding these abil…
Refaçade: Editing Object with Given Reference Texture
Youze Huang, Penghui Ruan, Bojia Zi +3
Recent advances in diffusion models have brought remarkable progress in image and video editing, yet some tasks remain underexplored. In this paper, we introduce a new task, Object…
SpaceVista: All-Scale Visual Spatial Reasoning from mm to km
Peiwen Sun, Shiqiang Lang, Dongming Wu +8
With the current surge in spatial reasoning explorations, researchers have made significant progress in understanding indoor scenes, but still struggle with diverse applications su…
Context and Diversity Matter: The Emergence of In-Context Learning in World Models
Fan Wang, Zhiyuan Chen, Yuxuan Zhong +8
The capability of predicting environmental dynamics underpins both biological neural systems and general embodied AI in adapting to their surroundings. Yet prevailing approaches re…
Towards Human-level Intelligence via Human-like Whole-Body Manipulation
Guang Gao, Jianan Wang, Jinbo Zuo +9
Building general-purpose intelligent robots has long been a fundamental goal of robotics. A promising approach is to mirror the evolutionary trajectory of humans: learning through…
ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models
Puhao Li, Yingying Wu, Ziheng Xi +8
Learning real-world robotic manipulation is challenging, particularly when limited demonstrations are available. Existing methods for few-shot manipulation often rely on simulation…