Runhao Li — accepted AI-conference papers

2026

Distilling Geometry Priors for 3D-Consistent Video Generation

Hongyang Du, Hongyang Du, Xiaoyan Cong, Runhao Li, Jingcheng Ni, Aman Agarwal +4

ICML 2026poster

While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulting in object deformation or spatial drift. We hypothesize that these failures arise because standard denoising objectives lack explicit ince…

Cited by 0 Source ↗Scholar ↗

2026

MAP-VLA: Memory-Augmented Prompting for Vision-Language-Action Model in Robotic Manipulation

Runhao Li, Wenkai Guo, Zhenyu Wu, Changyuan Wang, Haoyuan Deng, Zhenyu Weng +2

ICRA 2026poster

Pre-trained Vision-Language-Action (VLA) models have achieved remarkable success in improving robustness and generalization for end-to-end robotic manipulation. However, these models struggle with long-horizon tasks due to their lack of memory and reliance solely on immediate sensory inputs. To addr…

Cited by 0 Source ↗PDF ↗Scholar ↗