Zhizheng Zhang
収録論文 24本 ・ フィジカルAI/ロボット学習
※arXiv著者名で収集。同姓同名の別人の論文が含まれる場合があります。
論文
- WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time2026/7/1
- Cosmos 3: Omnimodal World Models for Physical AI2026/6/1
- AllDayNav: Lifelong Navigation via Real-World Reinforcement Learning2026/6/1
- NavGSim: High-Fidelity Gaussian Splatting Simulator for Large-Scale Navigation2026/3/1
- SPAN-Nav: Generalized Spatial Awareness for Versatile Vision-Language Navigation2026/3/1
- Emerging Extrinsic Dexterity in Cluttered Scenes via Dynamics-aware Policy Learning2026/3/1
- LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion2026/2/1
- Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds2026/2/1
- StereoVLA: Enhancing Vision-Language-Action Models with Stereo Vision2025/12/1
- RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation2025/11/1
- UrbanVLA: A Vision-Language-Action Model for Urban Micromobility2025/10/1
- MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning2025/10/1
- TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking2025/10/1
- Embodied Navigation Foundation Model2025/9/1
- DexVLG: Dexterous Vision-Language-Grasp Model at Scale2025/7/1
- DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge2025/7/1
- CLAR: Learning 3D Representations for Robotic Manipulation by Fusing Masked Reconstruction with Multi-Level Contrastive Alignment2025/7/1
- TrackVLA: Embodied Visual Tracking in the Wild2025/5/1
- GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data2025/5/1
- FetchBot: Learning Generalizable Object Fetching in Cluttered Scenes via Zero-Shot Sim2Real2025/2/1
- SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation2025/2/1
- Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection2024/12/1
- Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks2024/12/1
- NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation2024/2/1