Seeing Space and Motion: Enhancing Latent Actions with Geometric and Dynamic Awareness for Vision-Language-Action Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912960922779648 |
|---|---|
| author | Cai, Zhejia Yang, Yandan Chang, Xinyuan Liang, Shiyi Chen, Ronghan Xiong, Feng Xu, Mu Huang, Ruqi |
| author_facet | Cai, Zhejia Yang, Yandan Chang, Xinyuan Liang, Shiyi Chen, Ronghan Xiong, Feng Xu, Mu Huang, Ruqi |
| contents | Latent Action Models (LAMs) enable Vision- Language-Action (VLA) systems to learn semantic action representations from large-scale unannotated data. Yet, we identify two bottlenecks of LAMs: 1) the commonly adopted end-to-end trained image encoder suffers from poor spatial understanding; 2) LAMs can be fragile when input frames are temporally distant, leading to limited temporal percep- tion. Such factors inevitably hinder stable and clear action modeling. To this end, we propose Farsighted-LAM, a latent action framework with geometry-aware spatial encoding and multi-scale temporal modeling, capturing structural priors and dynamic motion patterns from consecutive frames. We further propose SSM-VLA, an end-to-end VLA framework built upon Farsighted-LAM, which integrates structured perception with a visual Chain-of-Thought module to explicitly reason about environmental dynamics, enhancing decision consistency and interpretability. We validate SSM-VLA on multiple VLA tasks in both simulation and real-world settings, and achieve state-of- the-art performance. Our results demonstrate that our strategy of combining geometry-aware modeling, temporal coherence, and explicit reasoning is effective in enhancing the robustness and generalizability of embodied intelligence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_26251 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Seeing Space and Motion: Enhancing Latent Actions with Geometric and Dynamic Awareness for Vision-Language-Action Models Cai, Zhejia Yang, Yandan Chang, Xinyuan Liang, Shiyi Chen, Ronghan Xiong, Feng Xu, Mu Huang, Ruqi Computer Vision and Pattern Recognition Latent Action Models (LAMs) enable Vision- Language-Action (VLA) systems to learn semantic action representations from large-scale unannotated data. Yet, we identify two bottlenecks of LAMs: 1) the commonly adopted end-to-end trained image encoder suffers from poor spatial understanding; 2) LAMs can be fragile when input frames are temporally distant, leading to limited temporal percep- tion. Such factors inevitably hinder stable and clear action modeling. To this end, we propose Farsighted-LAM, a latent action framework with geometry-aware spatial encoding and multi-scale temporal modeling, capturing structural priors and dynamic motion patterns from consecutive frames. We further propose SSM-VLA, an end-to-end VLA framework built upon Farsighted-LAM, which integrates structured perception with a visual Chain-of-Thought module to explicitly reason about environmental dynamics, enhancing decision consistency and interpretability. We validate SSM-VLA on multiple VLA tasks in both simulation and real-world settings, and achieve state-of- the-art performance. Our results demonstrate that our strategy of combining geometry-aware modeling, temporal coherence, and explicit reasoning is effective in enhancing the robustness and generalizability of embodied intelligence. |
| title | Seeing Space and Motion: Enhancing Latent Actions with Geometric and Dynamic Awareness for Vision-Language-Action Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.26251 |