10 papers
Encoded but Not in Control: Revealing the Grounding Gap in Vision-Language Robot Policies
Shaohan Jiang, Jiahang Cao, Qiduo He +9
Instruction following is central to language-conditioned robot policies: language should determine what to do when the same scene permits multiple valid actions. Yet successful exe…
Function-Preserving Data Generation for Zero-Shot Real-to-Sim-to-Real Manipulation
Tianyi Xiang, Xupeng Xie, Jiahang Cao +3
Robotic data generation is a promising paradigm for scaling robot learning without collecting large-scale real-world data. However, generating geometrically diverse yet physically…
GenHOI: Contact-Aware Humanoid-Object Interaction by Imitating Generated Videos without Task-Specific Training
Zhihai Bi, Qiang Zhang, Guoyang Zhao +8
Humanoid-Object Interaction (HOI) is a fundamental capability for humanoid robots, yet it remains challenging due to the tight coupling between dynamic balance and stable interacti…
AttenA+: Rectifying Action Inequality in Robotic Foundation Models
Daojie Peng, Fulong Ma, Jiahang Cao +7
Existing robotic foundation models, while powerful, are predicated on an implicit assumption of temporal homogeneity: treating all actions as equally informative during optimizatio…
Frequency Bias and OOD Generalization in Neural Operators under a Variable-Coefficient Wave Equation
Runlong Xie, An Luo
Neural operators learn to map initial conditions to the terminal solution of partial differential equations (PDEs), providing a surrogate for the full operator mapping. This enable…
Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores
Alan Z. Song, Yinjie Chen, Mu Nan +8
Vision Transformers (ViTs) learn rich visual-semantic representations through all-to-all self-attention among patch tokens. However, this design implicitly assumes that direct pair…
NeuroFlow: Toward Unified Visual Encoding and Decoding from Neural Activity
Weijian Mai, Mu Nan, Yu Zhu +6
Visual encoding and decoding models act as gateways to understanding the neural mechanisms underlying human visual perception. Typically, visual encoding models that predict brain…
Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding
Mu Nan, Muquan Yu, Weijian Mai +12
Visual decoding from brain signals is a key challenge at the intersection of computer vision and neuroscience, requiring methods that bridge neural representations and computationa…
Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition
Jiahang Cao, Yize Huang, Hanzhong Guo +15
Diffusion-based models for robotic control, including vision-language-action (VLA) and vision-action (VA) policies, have demonstrated significant capabilities. Yet their advancemen…
SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning
Weijian Mai, Jiamin Wu, Yu Zhu +6
Deciphering how visual stimuli are transformed into cortical responses is a fundamental challenge in computational neuroscience. This visual-to-neural mapping is inherently a one-t…