Dongxiu Liu

収録論文 11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

• ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow
  2026/7/1
• X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining
  2026/6/7
• X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining
  2026/6/1
• HoloQ-VLA: Uniform W4A4 Quantization of Vision-Language-Action Models
  2026/5/27
• Wall-OSS-0.5 Technical Report
  2026/5/1
• ManipArena: Comprehensive Real-world Evaluation of Reasoning-Oriented Generalist Robot Manipulation
  2026/3/1
• Demystifying Action Space Design for Robotic Manipulation Policies
  2026/2/1
• X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model
  2025/10/1
• PhysiAgent: An Embodied Agent Framework in Physical World
  2025/9/1
• Efficient Robotic Policy Learning via Latent Space Backward Planning
  2025/5/1
• Universal Actions for Enhanced Embodied Foundation Models
  2025/1/1