Spatial intelligence, the capacity to represent and reason about physical space, underlies embodied perception and real-world visual understanding. Existing benchmarks probe it through spatial relations, perspective-taking, and mental modeling. What remains underexamined is whether a model can maintain a coherent scene...
Hui-Zi Cao, Guan-Yu Xu, Zhi-Xuan Liang et al.· 0 citations
Robot foundation models provide strong visuomotor control, yet their performance can degrade when object positions or task instructions change. Further improvements often require post-training on substantial robot data, which can be costly to collect through methods such as teleoperation. Agentic harnesses can adapt ar...
Python Song, Zhi-Xuan Liang, Kelsey Fu et al.· 9 citations· ⚡1
Pretrained generative Diffusion Transformers (DiTs) capture rich pixel-level visual and language-conditioned structure through large-scale image and video generation training. A growing line of robot policies builds on this generative prior, but how it should be transferred to control remains unclear, and existing appr...
Experimental results demonstrate the proposed ${M}^2$Tok, a Multi-head Multi-codebook Action Tokenizer designed to minimize reconstruction error and enhance policy performance, achieves superior reconstruction fidelity and significantly boosts the success rate of VLA models.
Chun-Pu Xu, Zhi-Xuan Liang, Yu-Hao Zhang et al.· 0 citations
Experiments show that joint pretraining on Ego2Robot-synthesized and robot data consistently improves out-of-distribution generalization across multiple perturbation types, with benefits validated on real-robot deployment.
Ye Wang, Peibin Lin, Xiong-Hui Chen et al.· 13 citations· ⚡1
Across both simulated and real-world settings, MoEActok-based VLA substantially outperforms existing VLA models in both simulated and real-world settings.
Chun-Pu Xu, Zhi-Xuan Liang, Tianshuo Yang et al.· 1 citation
This work proposes COMPACT-VA, a planning-aligned working memory framework built on conditional VQ-VAE, compressing extended context into bounded representations, and evaluates on high-signal dynamic scenarios where historical context is most critical for behavior correctness, and accordingly design behavioral metrics.
Zhixuan Liang, Yuxiao Chen, Yurong You et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.