Chunhua Shen

Zhejiang University

収録論文 16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

• GAUGE: 物理的忠実性を測定するための実世界基盤ベンチマーク
  シミュレーション評価2026/8/6

  シミュレーションエンジンと生成ビデオワールドモデルの物理的忠実性を、実世界の軌跡に基づいて診断するベンチマークを提案した。

• GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Models
  2026/8/1
• InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization
  2026/7/1
• Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learning
  2026/7/1
• RoboSnap: One-Shot Real-to-Sim Scene Generation for Generalizable Robot Learning and Evaluation
  2026/7/1
• CoRE-VLA: Towards Scalable and Robust Vision-Language-Action Modeling via Conditional Routing of Experts
  2026/7/1
• HORIZON: Recoverability-Governed Curriculum for Physical-Domain Scaling
  2026/6/1
• Perfect Demo Makes Poor Teacher: Learning Robust Alignment from Critical Motion Segments
  2026/6/1
• EBench: Elemental Diagnosis of Generalist Mobile Manipulation Policies
  2026/6/1
• AGILE: Hand-Object Interaction Reconstruction from Video via Agentic Generation
  2026/2/1
• GAE: Unleashing Physical Potential of VLM with Generalizable Action Expert
  2025/10/1
• NoTVLA: Semantics-Preserving Robot Adaptation via Narrative Action Interfaces
  2025/10/1
• StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation
  2025/10/1
• ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks
  2025/8/1
• Aether: Geometric-Aware Unified World Modeling
  2025/3/1
• Deep Learning Features at Scale for Visual Place Recognition
  2017/1/1