8 papers
SiMDex: Mining Similar Egocentric Videos for Cross-Embodiment Dexterous Manipulation
Nie Lin, Takehiko Ohkawa, Sijin Chen +10
Recent years have witnessed an explosive trend of scaling ego-centric human videos for robot manipulation, yet it remains unclear which data actually benefits dexterous manipulatio…
Multi-Mask Diffusion Language Models for Few-Step Generation
Sijin Chen, Yinuo Ren, Heyang Zhao +3
Masked diffusion models (MDMs) are a promising family of language generators, but achieving high-quality few-step generation remains challenging. In MDMs, all forward trajectories…
Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots
Sijin Chen, Kaixuan Jiang, Haixin Shi +6
We study whether we can learn novel manipulation skills from human actions to a bi-manual robot with parallel grippers. Human action data is cheap, abundant, and diverse, making it…
TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models
Wenbo Zhang, Jianxiong Li, Shuai Yang +4
Vision-Language-Action (VLA) models trained on large-scale data have made remarkable progress, but they remain vulnerable to distribution shifts at deployment time. Recent VLA mode…
From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors
Zhengshen Zhang, Hao Li, Yalun Dai +10
Existing vision-language-action (VLA) models act in 3D real-world but are typically built on 2D encoders, leaving a spatial reasoning gap that limits generalization and adaptabilit…
World Guidance: World Modeling in Condition Space for Action Generation
Yue Su, Sijin Chen, Haixin Shi +7
Leveraging future observation modeling to facilitate action generation presents a promising avenue for enhancing the capabilities of Vision-Language-Action (VLA) models. However, e…