11 citations · 25 across the 29 of their papers we have counts for
30 papers
EvoGUI: An Evolution-Aware Benchmark for GUI State-Transition Understanding
Yaohan Yang, Minglei Shi, Borui Zhang +2
GUI agents must reason about how actions transform interface states, but end-to-end success rates entangle this ability with perception, grounding, planning, and recovery. We intro…
R2RDreamer: 3D-aware Data Augmentation for Spatially-generalized 2D Manipulation Policies
Xiuwei Xu, Haowen Sun, Angyuan Ma +7
Spatial generalization is critical for imitation-learned manipulation policies, but achieving it typically requires scaling demonstrations across diverse object poses, robot config…
Syll: Open-Source Personal Automation with Cross-Surface Execution
Bo Zhang, Borui Zhang, Chenghao Jiang +5
Personal AI agents must increasingly operate across APIs, shells, web surfaces, and desktop GUIs, yet many systems remain tuned to a single interface and offer limited support for…
ShapeGen: Robotic Data Generation for Category-Level Manipulation
Yirui Wang, Xiuwei Xu, Angyuan Ma +3
Manipulation policies deployed in uncontrolled real-world scenarios are faced with great in-category geometric diversity of everyday objects. In order to function robustly under su…
F2F-AP: Flow-to-Future Asynchronous Policy for Real-time Dynamic Manipulation
Haoyu Wei, Xiuwei Xu, Ziyang Cheng +5
Asynchronous inference has emerged as a prevalent paradigm in robotic manipulation, achieving significant progress in ensuring trajectory smoothness and efficiency. However, a syst…
CMP: Robust Whole-Body Tracking for Loco-Manipulation via Competence Manifold Projection
Ziyang Cheng, Haoyu Wei, Hang Yin +4
While decoupled control schemes for legged mobile manipulators have shown robustness, learning holistic whole-body control policies for tracking global end-effector poses remains f…
R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation
Xiuwei Xu, Angyuan Ma, Hankun Li +4
Towards the aim of generalized robotic manipulation, spatial generalization is the most fundamental capability that requires the policy to work robustly under different spatial dis…
GC-VLN: Instruction as Graph Constraints for Training-free Vision-and-Language Navigation
Hang Yin, Haoyu Wei, Xiuwei Xu +3
In this paper, we propose a training-free framework for vision-and-language navigation (VLN). Existing zero-shot VLN methods are mainly designed for discrete environments or involv…
IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation
Wenxuan Guo, Xiuwei Xu, Hang Yin +4
Visual navigation with an image as goal is a fundamental and challenging problem. Conventional methods either rely on end-to-end RL learning or modular-based policy with topologica…
Vision Generalist Model: A Survey
Ziyi Wang, Yongming Rao, Shuofeng Sun +8
Recently, we have witnessed the great success of the generalist model in natural language processing. The generalist model is a general framework trained with massive data and is a…
UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting
Ziyi Wang, Yanran Zhang, Jie Zhou +1
The scale diversity of point cloud data presents significant challenges in developing unified representation learning techniques for 3D vision. Currently, there are few unified 3D…
Towards provable probabilistic safety for scalable embodied AI systems
Linxuan He, Lingxiang Fan, Qing-Shan Jia +13
Embodied AI systems, comprising AI models and physical plants, are increasingly prevalent across various applications. Due to the rarity of system failures, ensuring their safety i…
EfficientLLaVA:Generalizable Auto-Pruning for Large Vision-language Models
Yinan Liang, Ziwei Wang, Xiuwei Xu +2
While multimodal large language models demonstrate strong performance in complex reasoning tasks, they pose significant challenges related to model complexity during deployment, es…
UniGoal: Towards Universal Zero-shot Goal-oriented Navigation
Hang Yin, Xiuwei Xu, Lingqing Zhao +3
In this paper, we propose a general framework for universal zero-shot goal-oriented navigation. Existing zero-shot methods build inference framework upon large language models (LLM…
XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation
Ziyi Wang, Yanbo Wang, Xumin Yu +2
Existing methodologies in open vocabulary 3D semantic segmentation primarily concentrate on establishing a unified feature space encompassing 3D, 2D, and textual modalities. Nevert…
SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation
Hang Yin, Xiuwei Xu, Zhenyu Wu +2
In this paper, we propose a new framework for zero-shot object navigation. Existing zero-shot object navigation methods prompt LLM with the text of spatially closed objects, which…
OPONeRF: One-Point-One NeRF for Robust Neural Rendering
Yu Zheng, Yueqi Duan, Kangfu Zheng +3
In this paper, we propose a One-Point-One NeRF (OPONeRF) framework for robust scene rendering. Existing NeRFs are designed based on a key assumption that the target scene remains u…
Q-VLM: Post-training Quantization for Large Vision-Language Models
Changyuan Wang, Ziwei Wang, Xiuwei Xu +3
In this paper, we propose a post-training quantization framework of large vision-language models (LVLMs) for efficient multi-modal inference. Conventional quantization methods sequ…
FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner
Wenliang Zhao, Minglei Shi, Xumin Yu +2
Building on the success of diffusion models in visual generation, flow-based models reemerge as another prominent family of generative models that have achieved competitive or bett…
DC-Solver: Improving Predictor-Corrector Diffusion Sampler via Dynamic Compensation
Wenliang Zhao, Haolin Wang, Jie Zhou +1
Diffusion probabilistic models (DPMs) have shown remarkable performance in visual synthesis but are computationally expensive due to the need for multiple evaluations during the sa…
EmbodiedSAM: Online Segment Any 3D Thing in Real Time
Xiuwei Xu, Huangxing Chen, Linqing Zhao +3
Embodied tasks require the agent to fully understand 3D scenes simultaneously with its exploration, so an online, real-time, fine-grained and highly-generalized 3D perception model…
FlowIE: Efficient Image Enhancement via Rectified Flow
Yixuan Zhu, Wenliang Zhao, Ao Li +3
Image enhancement holds extensive applications in real-world scenarios due to complex environments and limitations of imaging devices. Conventional methods are often constrained by…
Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models
Zuyan Liu, Yuhao Dong, Yongming Rao +2
In the realm of vision-language understanding, the proficiency of models in interpreting and reasoning over visual content has become a cornerstone for numerous applications. Howev…
Memory-based Adapters for Online 3D Scene Perception
Xiuwei Xu, Chong Xia, Ziwei Wang +4
In this paper, we propose a new framework for online 3D scene perception. Conventional 3D scene perception methods are offline, i.e., take an already reconstructed 3D scene geometr…