Huchuan Lu

发表论文 29 篇 · 总被引 1666 次 · h-index 12

代表论文

• PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation (2024 · European Conference on Computer Vision · 被引 349)
• Automated Evaluation of Large Vision-Language Models on Self-Driving Corner Cases (2024 · IEEE Workshop/Winter Conference on Applications of Computer Vision · 被引 95)
• CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation (2025 · International Conference on Computer Graphics and Interactive Techniques · 被引 74)
• VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior (2025 · IEEE International Conference on Computer Vision · 被引 44)
• StableIdentity: Inserting Anybody Into Anywhere at First Sight (2024 · IEEE transactions on multimedia · 被引 42)
• MultiShotMaster: A Controllable Multi-Shot Video Generation Framework (2025 · arXiv.org · 被引 29)