An-Chieh Cheng

发表论文 10 篇 · 总被引 156 次 · h-index 3

代表论文

• EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos (2025 · arXiv.org · 被引 122)
• OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM (2025 · arXiv.org · 被引 49)
• Cosmos 3: Omnimodal World Models for Physical AI (2026 · 被引 34)
• 3D Aware Region Prompted Vision Language Model (2025 · arXiv.org · 被引 26)
• Long-Horizon Manipulation via Trace-Conditioned VLA Planning (2026 · arXiv.org · 被引 5)
• A Long-Context Generative Foundation Model Deciphers RNA Design Principles (2026 · bioRxiv · 被引 1)