Huajin Chen — accepted AI-conference papers

2026

MIMIC: Mask-Injected Manipulation Video Generation with Interaction Control

Tianxiao Chen, Jintao Rong, Huajin Chen, Jingya Wang, Tao Zhou, Qi Ye +1

ICLR 2026poster

Embodied intelligence faces a fundamental bottleneck from limited large-scale interaction data. Video generation offers a scalable alternative, but manipulation videos remain particularly challenging, as they require capturing subtle, contact-rich dynamics. Despite recent advances, video diffusion m…

Cited by 0 Source ↗Scholar ↗

2025

Temporal-Spatial Representation Fusion for Dexterous Manipulation Learning with Unpaired Visual-Action Data

Guwen Han, Zhengnan Sun, Qingtao Liu, Yu Cui, Anjun Chen, Huajin Chen +3

IROS 2025

Supervised behavioral cloning using robot visual-action data has been widely investigated in robot manipulation. However, these methods typically require simultaneous acquisition of visual and action data, which makes them difficult to utilize unpaired visual-action datasets: e.g. videos on Internet

Cited by 0 Source ↗Scholar ↗