9 papers
Copper-Policy: Focus on the Representation for Robust Robot Manipulation
Zexin Feng, Yixu Feng, Lingyu Xiao +6
World Action Models (WAMs) acquire behavioral priors by modeling future scene evolution, but predicting detailed futures in pixel or latent space incurs substantial cost. Recent ev…
GIFT: Goal-Injected Fine-Tuning for Efficient Manipulation Policy Adaptation
Xiaoyuan Fang, Shuo Feng, Yuxuan Wang +3
Compared with relying solely on initial observations and language instructions, predicting goal images with generative models as high-level visual guidance can significantly enhanc…
MeshPriorDiT: Hierarchical Modeling for Action-Conditioned Cloth Dynamics
Zihang Wang, Jianming Hu, Shang Su +4
Action-conditioned cloth dynamics prediction requires both locally plausible deformation and long-range coordination. Existing approaches largely follow two paradigms. Mesh-based G…
AirAlign: Geometry-Aware Relative Pose Alignment for UAV Last-Meter Navigation
Jinyi Zhou, Shuo Feng, Yufei Wu +1
Unmanned aerial vehicle (UAV) navigation in modern low-altitude environments requires more accurate pose alignment in the final approach stage for target information acquisition or…
ViSMoE: Visual-Aware Sparse Mixture-of-Experts for Embodied Referring Expression Grounding
Shuo Feng, Piji Li
Embodied Referring Expression Grounding is the task of enabling an agent to navigate in real environments and to localize a remote object based on natural language instructions. In…
Policy-Level Recursive Self-Improvement for Embodied AI with a Criticality World Model
Linxuan He, Yuying Tian, Lingxiang Fan +5
Despite advances in policy pretraining, embodied AI systems can plateau during task-specific fine-tuning as uniform scenario collection encounters fewer of the remaining failures.…
DC-WAM: Dynamic-Centric Visual Supervision and Reasoning for World-Action Models
Haoyuan Ji, Lingxiang Fan, Shang Su +4
World-Action Models (WAMs) augment robot policies with future visual prediction, but it remains unclear what the visual modality should learn for control. While photorealistic futu…
VPN: Visual Prompt Navigation
Shuo Feng, Zihan Wang, Yuchen Li +6
While natural language is commonly used to guide embodied agents, the inherent ambiguity and verbosity of language often hinder the effectiveness of language-guided navigation in c…
Improving Brain-to-Image Reconstruction via Fine-Grained Text Bridging
Runze Xia, Shuo Feng, Renzhi Wang +3
Brain-to-Image reconstruction aims to recover visual stimuli perceived by humans from brain activity. However, the reconstructed visual stimuli often missing details and semantic i…