5 citations · 7 across the 19 of their papers we have counts for
19 papers
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…
GeoSem-WAM: Geometry- and Semantic-Aware World Action Models
Fulong Ma, Daojie Peng, Wenjun Yue +4
Recent World Action Models (WAMs) have demonstrated impressive capabilities in embodied decision-making. However, whether their effectiveness stems from explicit future imagination…
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…
MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics via Learning Residual Anisotropy
Jiaxu Wang, Junhao He, Jingkai Sun +5
Learning real-world dynamics from visual observations is crucial for various domains. A common strategy is to calibrate simulators by estimating physical parameters, yet accuracy i…
Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation
Yicheng Jiang, Jiaxu Wang, Junhao He +8
Current 3D-aware pretraining methods for embodied perception and manipulation are largely built on differentiable rendering frameworks, producing either fully implicit neural field…
Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots
Wei Cui, Haoyu Wang, Wenkang Qin +19
Humanoid robot technology is advancing rapidly, with manufacturers introducing diverse heterogeneous visual perception modules tailored to specific scenarios. Among various percept…
LOVON: Legged Open-Vocabulary Object Navigator
Daojie Peng, Jiahang Cao, Qiang Zhang +1
Object navigation in open-world environments remains a formidable and pervasive challenge for robotic systems, particularly when it comes to executing long-horizon tasks that requi…
Modality-Composable Diffusion Policy via Inference-Time Distribution-level Composition
Jiahang Cao, Qiang Zhang, Hanzhong Guo +3
Diffusion Policy (DP) has attracted significant attention as an effective method for policy representation due to its capacity to model multi-distribution dynamics. However, curren…
Exploring Typographic Visual Prompts Injection Threats in Cross-Modality Generation Models
Hao Cheng, Erjia Xiao, Yichi Wang +8
Current Cross-Modality Generation Models (GMs) demonstrate remarkable capabilities in various generative tasks. Given the ubiquity and information richness of vision modality input…
MapNav: A Novel Memory Representation via Annotated Semantic Maps for Vision-and-Language Navigation
Lingfeng Zhang, Xiaoshuai Hao, Qinwen Xu +7
Vision-and-language navigation (VLN) is a key task in Embodied AI, requiring agents to navigate diverse and unseen environments while following natural language instructions. Tradi…
Event Masked Autoencoder: Point-wise Action Recognition with Event-Based Cameras
Jingkai Sun, Qiang Zhang, Jiaxu Wang +2
Dynamic vision sensors (DVS) are bio-inspired devices that capture visual information in the form of asynchronous events, which encode changes in pixel intensity with high temporal…
A Dual-Agent Adversarial Framework for Robust Generalization in Deep Reinforcement Learning
Zhengpeng Xie, Yulong Zhang
Recently, empowered with the powerful capabilities of neural networks, reinforcement learning (RL) has successfully tackled numerous challenging tasks. However, while these models…
Representation Convergence: Mutual Distillation is Secretly a Form of Regularization
Zhengpeng Xie, Jiahang Cao, Changwei Wang +5
In this paper, we argue that mutual distillation between reinforcement learning policies serves as an implicit regularization, preventing them from overfitting to irrelevant featur…
Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models
Hao Cheng, Erjia Xiao, Jiayan Yang +6
Current image generation models can effortlessly produce high-quality, highly realistic images, but this also increases the risk of misuse. In various Text-to-Image or Image-to-Ima…
Spiking Neural Network as Adaptive Event Stream Slicer
Jiahang Cao, Mingyuan Sun, Ziqing Wang +4
Event-based cameras are attracting significant interest as they provide rich edge information, high dynamic range, and high temporal resolution. Many state-of-the-art event-based a…
Spiking Diffusion Models
Jiahang Cao, Hanzhong Guo, Ziqing Wang +4
Recent years have witnessed Spiking Neural Networks (SNNs) gaining attention for their ultra-low energy consumption and high biological plausibility compared with traditional Artif…
Transfer Attack for Bad and Good: Explain and Boost Adversarial Transferability across Multimodal Large Language Models
Hao Cheng, Erjia Xiao, Jiayan Yang +8
Multimodal Large Language Models (MLLMs) demonstrate exceptional performance in cross-modality interaction, yet they also suffer adversarial vulnerabilities. In particular, the tra…
Spiking Denoising Diffusion Probabilistic Models
Jiahang Cao, Ziqing Wang, Hanzhong Guo +3
Spiking neural networks (SNNs) have ultra-low energy consumption and high biological plausibility due to their binary and bio-driven nature compared with artificial neural networks…
Masked Spiking Transformer
Ziqing Wang, Yuetong Fang, Jiahang Cao +3
The combination of Spiking Neural Networks (SNNs) and Transformers has attracted significant attention due to their potential for high energy efficiency and high-performance nature…