20 papers
RawVLA: Embodied Neural Image Signal Processor For Robotic Manipulation
Shuhong Liu, Heng Zhou, Lingfeng Qian +7
Vision-language-action (VLA) models typically operate on RGB images produced by a fixed camera image signal processor (ISP), leaving the imaging pipeline outside the learning and e…
Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI
Wenkang Qin, Yukun Zhou, Noah Shen +5
Scalable simulation is essential for robot data generation, policy training, evaluation, and safe iteration, yet real-world interaction is costly and conventional simulators requir…
World-Model-Augmented Visual Locomotion for Humanoids on Foothold-Constrained Terrain
Yuxi Liu, Lijun Han, Ziming Wang +3
Foothold-constrained terrain is characterized by sparse, discontinuous, or geometrically restricted feasible foot contacts, as encountered on stepping stones, across gaps, and on n…
EA-Nav: Learning Safe Visual Navigation Policies with Embodiment Awareness
Jialu Zhang, Yong Du, Xianda Guo +6
Cross-embodiment navigation is a key challenge in embodied intelligence. Due to differences in embodiment, the same visual observation may imply different actions for different age…
SkillNav: Score-Level Skill Intervention for Zero-Shot Object Goal Navigation
Ruijie Sang, Yiqun Duan, Pinhan Fu +3
Vision-Language Model (VLM) agents have advanced zero-shot object-goal navigation, yet single-frame reasoning leaves them without the cross-step behavioral awareness an embodied na…
X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras
Heng Zhou, Shuhong Liu, Yonghao He +6
We present X-lens, a compact feed-forward model for metric depth estimation from a variable number of calibrated fisheye and pinhole views. To support real-time downstream percepti…
TrustVLA: Mechanism-Guided Inference-Time Defense Against Vision-Language-Action Backdoors
Pinhan Fu, Xianda Guo, Xuetao Li +5
Vision-Language-Action (VLA) models are deployed through pipelines that end users cannot audit, and a poisoned VLA can behave normally on clean observations while a small visual tr…
dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models
Yuhao Wu, Yitian Liu, Weijie Shen +13
Vision-Language-Action (VLA) models have established a powerful paradigm for generalist robotic manipulation by grounding control into the semantic reasoning of VLMs. Prevailing ar…
HoloAgent-0: A Unified Embodied Agent Framework with 3D Spatial Memory
Xiaolin Zhou, Liu Liu, Tingyang Xiao +9
LLM agents follow a practical execution loop in digital environments: they reason over structured states, invoke tools, inspect feedback, and revise actions. Extending this loop to…
Humanoid-OmniOcc: Stereo-Based Full-View Occupancy Dataset for Embodied AI
Xianda Guo, Bohao Zhang, Chenwei Huang +6
Occupancy prediction at voxel-level granularity is essential for safe robotic navigation and interaction in complex environments. Existing occupancy datasets, however, are predomin…
Improving Robotic Imitation Learning via Trajectory Standardization
Licheng Yang, Lingfeng Qian, Fei Zheng +4
Imitation learning for robotic manipulation relies on large sets of human demonstration trajectories, which are often noisy and temporally irregular due to variable operator speed,…
GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning
Yufei Jia, Heng Zhang, Ziheng Zhang +39
Embodied AI research is undergoing a shift toward vision-centric perceptual paradigms. While massively parallel simulators have catalyzed breakthroughs in proprioception-based loco…
Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Models
Dehui Wang, Rong Wei, Yue Shi +9
The growing demand for Embodied AI and VR applications has highlighted the need for synthesizing high-quality 3D indoor scenes from sparse inputs. However, existing approaches stru…
R3DP: Real-Time 3D-Aware Policy for Embodied Manipulation
Yuhao Zhang, Wanxi Dong, Yue Shi +13
Embodied manipulation requires accurate 3D understanding of objects and their spatial relations to plan and execute contact-rich actions. While large-scale 3D vision models provide…
RSGen: Enhancing Layout-Driven Remote Sensing Image Generation with Diverse Edge Guidance
Xianbao Hou, Yonghao He, Zeyd Boukhers +4
Diffusion models have significantly mitigated the impact of annotated data scarcity in remote sensing (RS). Although recent approaches have successfully harnessed these models to e…
RoleMotion: A Large-Scale Dataset towards Robust Scene-Specific Role-Playing Motion Synthesis with Fine-grained Descriptions
Junran Peng, Yiheng Huang, Silei Shen +8
In this paper, we introduce RoleMotion, a large-scale human motion dataset that encompasses a wealth of role-playing and functional motion data tailored to fit various specific sce…
TabletopGen: Tabletop Scene Generation and Interactive Simulation for Robotic Manipulation
Ziqian Wang, Yonghao He, Licheng Yang +6
Simulation provides a low-cost, scalable pathway to large-scale robotic manipulation data collection. However, existing 3D scene generation methods can rarely be applied directly t…
VO-DP: Semantic-Geometric Adaptive Diffusion Policy for Vision-Only Robotic Manipulation
Zehao Ni, Yonghao He, Lingfeng Qian +7
In the context of imitation learning, visuomotor-based diffusion policy learning is one of the main directions in robotic manipulation. Most of these approaches rely on point cloud…
MarketGen: A Scalable Simulation Platform with Auto-Generated Embodied Supermarket Environments
Xu Hu, Yiyang Feng, Junran Peng +7
The development of embodied agents for complex commercial environments is hindered by a critical gap in existing robotics datasets and benchmarks, which primarily focus on househol…
SIG-Chat: Spatial Intent-Guided Conversational Gesture Generation Involving How, When and Where
Yiheng Huang, Junran Peng, Silei Shen +11
The accompanying actions and gestures in dialogue are often closely linked to interactions with the environment, such as looking toward the interlocutor or using gestures to point…