Xiaodan Liang
収録論文 33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
- STEAM: Self-Supervised Temporal Ensemble Advantage Modeling for Real-World Robot Learning2026/6/1
- RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models2026/5/1
- A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model2026/4/1
- AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robots2026/3/1
- Choose What to Observe: Task-Aware Semantic-Geometric Representations for Visuomotor Policy2026/3/1
- ManipArena: Comprehensive Real-world Evaluation of Reasoning-Oriented Generalist Robot Manipulation2026/3/1
- Implicit Geometry Representations for Vision-and-Language Navigation from Web Videos2026/3/1
- GLaD: Geometric Latent Distillation for Vision-Language-Action Models2025/12/1
- ArtiSG: Functional 3D Scene Graph Construction via Human-demonstrated Articulated Objects Manipulation2025/12/1
- EchoVLA: Robotic Vision-Language-Action Model with Synergistic Declarative Memory for Mobile Manipulation2025/11/1
- Embodied Arena: A Comprehensive, Unified, and Evolving Evaluation Platform for Embodied AI2025/9/1
- RoboPearls: Editable Video Simulation for Robot Manipulation2025/6/1
- PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly2025/6/1
- RoBridge: A Hierarchical Architecture Bridging Cognition and Execution for General Robotic Manipulation2025/5/1
- A0: An Affordance-Aware Hierarchical Model for General Robotic Manipulation2025/4/1
- Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation2025/3/1
- RoboTron-Drive: All-in-One Large Multimodal Model for Autonomous Driving2024/12/1
- RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation2024/12/1
- InfiniteWorld: A Unified Scalable Simulation Framework for General Visual-Language Robot Interaction2024/12/1
- InstruGen: Automatic Instruction Generation for Vision-and-Language Navigation Via Large Multimodal Models2024/11/1
- VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot Manipulation2024/11/1
- PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation2024/10/1
- All Robots in One: A New Standard and Unified Dataset for Versatile, General-Purpose Embodied Agents2024/8/1
- Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI2024/7/1
- Affordances-Oriented Planning using Foundation Models for Continuous Vision-Language Navigation2024/7/1
- NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning2024/3/1
- Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning2024/3/1
- MapGPT: Map-Guided Prompting with Adaptive Path Planning for Vision-and-Language Navigation2024/1/1
- Surfer: Progressive Reasoning with World Models for Robotic Manipulation2023/6/1
- CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving2022/3/1
- Deep Learning for Embodied Vision Navigation: A Survey2021/8/1
- Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp2020/11/1
- CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving2018/7/1