8 papers
LAMP: Latent Motion Prior-Guided Real-World Learning for Dexterous Hand Manipulation
Xinye Yang, Zhiyuan Ma, Hongze Yu +5
Real-world learning for dexterous hands remains brittle because high-dimensional hand actions amplify imitation errors and make reinforcement-learning exploration prone to contact-…
VideoAfford: Grounding 3D Affordance from Human-Object-Interaction Videos via Multimodal Large Language Model
Hanqing Wang, Mingyu Liu, Xiaoyu Chen +9
3D affordance grounding aims to highlight the actionable regions on 3D objects, which is crucial for robotic manipulation. Previous research primarily focused on learning affordanc…
CADGrasp: Learning Contact and Collision Aware General Dexterous Grasping in Cluttered Scenes
Jiyao Zhang, Zhiyuan Ma, Tianhao Wu +2
Dexterous grasping in cluttered environments presents substantial challenges due to the high degrees of freedom of dexterous hands, occlusion, and potential collisions arising from…
Towards Cross-View Point Correspondence in Vision-Language Models
Yipu Wang, Yuheng Ji, Yuyang Liu +10
Cross-view correspondence is a fundamental capability for spatial understanding and embodied AI. However, it is still far from being realized in Vision-Language Models (VLMs), espe…
UniTransfer: Video Concept Transfer via Progressive Spatial and Timestep Decomposition
Guojun Lei, Rong Zhang, Chi Wang +4
We propose a novel architecture UniTransfer, which introduces both spatial and diffusion timestep decomposition in a progressive paradigm, achieving precise and controllable video…
Dream3DAvatar: Text-Controlled 3D Avatar Reconstruction from a Single Image
Gaofeng Liu, Hengsen Li, Ruoyu Gao +3
With the rapid advancement of 3D representation techniques and generative models, substantial progress has been made in reconstructing full-body 3D avatars from a single image. How…
Diffusion Models are Open-World Affordance Learners: Leveraging Generative Priors for 3D Affordance Learning
Hanqing Wang, Zhenhao Zhang, Kaiyang Ji +12
3D affordance grounding aims to understand how diverse objects can be manipulated, making it a cornerstone of embodied interaction. However, prior works struggle to generalize to o…
VideoDirector: Precise Video Editing via Text-to-Video Models
Yukun Wang, Longguang Wang, Zhiyuan Ma +3
Despite the typical inversion-then-editing paradigm using text-to-image (T2I) models has demonstrated promising results, directly extending it to text-to-video (T2V) models still s…