Wenyu Liu
Huazhong University of Science and Technology
収録論文 21本 ・ フィジカルAI/ロボット学習
VLA
※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
- DreamWAM: RGB未来予測を超えた世界行動モデルVLA2026/8/5
世界行動モデル（WAM）の未来予測をRGBだけでなく、外観・動き・幾何・意味の複数視点で行う構造化世界モデルを提案し、ロボット操作タスクの成功率とロバスト性を向上させた。
- DreamWAM: Beyond RGB Future Prediction for World Action Models2026/8/1
- Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report2026/7/8
- Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report2026/7/1
- MotionVLA: Injecting Geometric Motion into Vision-Language-Action Model2026/6/1
- UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving2026/4/1
- OmniTrack: General Motion Tracking via Physics-Consistent Reference2026/2/1
- ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving2025/6/1
- AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning2025/3/1
- RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning2025/2/1
- Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving2024/10/1
- Occupancy as Set of Points2024/7/1
- Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation2024/4/1
- VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning2024/2/1
- MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction2023/8/1
- Symphonize 3D Semantic Scene Completion with Contextual Instance Queries2023/6/1
- LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation2023/4/1
- VAD: Vectorized Scene Representation for Efficient Autonomous Driving2023/3/1
- Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction2023/3/1
- Perceive, Interact, Predict: Learning Dynamic and Static Clues for End-to-End Motion Prediction2022/12/1
- MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction2022/8/1