2 citations · 2 across the 12 of their papers we have counts for
14 papers
SEES: A Self-Evolving Embodied System via Failure-Guided VLA Policy Adaptation
Ziwen Li, Hanlue Zhang, Zhenyang Ren +9
Recent vision-language-action (VLA) policies demonstrate promising generalization across diverse short-horizon tasks. However, they remain unreliable on long-horizon tasks, partly…
The Geometry of Flow-Matching Uncertainty: A Cost-free Uncertainty Proxy and Its Application in Flow-based VLA Failure Detection
Ziyang Rao, Yiren Zhao, Weiyu Guo +3
Flow matching (FM) has become a popular action head paradigm for modern embodied models. However, as a conditional generative model, it does not explicitly expose its inherent unce…
Suppression Sticks, Locality Is Fragile: A Closed-Loop Target-and-Control Audit of Task-Vector Negation in VLA Policies
Shaoguang Wang, Weiyu Guo, Rushi Dai +3
Task-vector arithmetic offers a closed-form way to modify a model, yet its behavioral locality remains unclear in closed-loop robot control. We present a target-and-control audit o…
How Should Vision-Language-Action Models Use Proprioceptive State?
Yiren Zhao, Ziyang Chen, Ziyang Rao +5
Recent Vision-Language-Action (VLA) models almost universally take robot proprioceptive state as input, yet wire it in incompatible ways -- serialized into text prompts, projected…
Source-Lifted Flow Matching for Intervenable Multimodal Imitation
He Zhang, Ying Sun, Pengteng Li +7
Flow-matching policies are promising for imitation learning because they model complex multimodal action distributions. However, their stochasticity is largely passive: repeated sa…
Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Action
Pengteng Li, Weiyu Guo, He Zhang +4
We introduce SOMA, the Spatial Memory framework for Out-of-Vision Manipulation in Vision-Language-Action (VLA) models. Most existing VLAs implicitly assume that task-relevant objec…
Mirage2Matter: A Physically Grounded Gaussian World Model from Video
Zhengqing Gao, Ziwen Li, Xin Wang +12
The scalability of embodied intelligence is fundamentally constrained by the scarcity of real-world interaction data. While simulation platforms provide a promising alternative, ex…
NeuroVLA: A Brain-inspired Embodied Intelligence for Fluid and Fast Reflexive Robotics Control
Weiyu Guo, He Zhang, Pengteng Li +7
Vision-language-action (VLA) models inherit powerful semantic representations from large language models, but carrying over their design priorities can leave the demands of physica…
PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention
Ziwen Li, Xin Wang, Hanlue Zhang +8
The Vision-Language-Action (VLA) models have demonstrated remarkable performance on embodied tasks and shown promising potential for real-world applications. However, current VLAs…
SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes
Jiaxin Huang, Ziwen Li, Hanlve Zhang +6
The integration of language and 3D perception is critical for embodied AI and robotic systems to perceive, understand, and interact with the physical world. Spatial reasoning, a ke…
MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation
Jiaxin Huang, Runnan Chen, Ziwen Li +5
Reasoning segmentation aims to segment target objects in complex scenes based on human intent and spatial reasoning. While recent multimodal large language models (MLLMs) have demo…
UrbanGS: Semantic-Guided Gaussian Splatting for Urban Scene Reconstruction
Ziwen Li, Jiaxin Huang, Runnan Chen +5
Reconstructing urban scenes is challenging due to their complex geometries and the presence of potentially dynamic objects. 3D Gaussian Splatting (3DGS)-based methods have shown st…
Training-Free Robust Interactive Video Object Segmentation
Xiaoli Wei, Zhaoqing Wang, Yandong Guo +3
Interactive video object segmentation is a crucial video task, having various applications from video editing to data annotating. However, current approaches struggle to accurately…
Open-Vocabulary Segmentation with Unpaired Mask-Text Supervision
Zhaoqing Wang, Xiaobo Xia, Ziye Chen +4
Current state-of-the-art open-vocabulary segmentation methods typically rely on image-mask-text triplet annotations for supervision. However, acquiring such detailed annotations is…