Yecheng Wu

发表论文 9 篇 · 总被引 939 次 · h-index 6

代表论文

• CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models (2025 · Computer Vision and Pattern Recognition · 被引 508)
• VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation (2024 · International Conference on Learning Representations · 被引 283)
• HART: Efficient Visual Generation with Hybrid Autoregressive Transformer (2024 · International Conference on Learning Representations · 被引 135)
• EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos (2025 · arXiv.org · 被引 122)
• Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation (2026 · arXiv.org · 被引 14)
• DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer (2025 · IEEE International Conference on Computer Vision · 被引 11)