الملخص
Vision-Language-Action models are increasingly effective for robotic manipulation, yet most predict actions directly from current observations without explicitly modeling future scene evolution. Recent methods introduce future prediction to improve action generation, but dense future modeling often requires expensive iterative denoising, while one-step alternatives can underperform their multi-step counterparts. To reconcile efficient future modeling with strong action performance, we present SLIP-VLA, a policy learning framework that equips VLA models with a Single-Step Latent Imagination for future-aware action prediction. SLIP-VLA obtains temporally dense future latent representations with a single denoising update, and we improve the perceptual sufficiency of these representations by aligning intermediate latents with future geometric and semantic features. We further improve their control sufficiency through action-conditioned latent world modeling and inverse dynamics modeling, explicitly coupling latent transitions with robot actions. SLIP-VLA achieves state-of-the-art performance across diverse simulation benchmarks and real-world manipulation tasks, while its single-step latent imagination takes only 12 ms.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Li, T., Xu, H., Chen, W., Li, H., Yang, C., Zheng, X., Ma, J., Liu, Y., Wang, L., & Li, H. (2026). SLIP-VLA: Single-Step Latent Imagination for Policy Learning in Vision-Language-Action Models. https://omanscience.com/ar/articles/slip-vla-single-step-latent-imagination-for-policy-learning-in-vision-language-action-models
MLA 9
Li, Tianfu, et al. "SLIP-VLA: Single-Step Latent Imagination for Policy Learning in Vision-Language-Action Models." https://omanscience.com/ar/articles/slip-vla-single-step-latent-imagination-for-policy-learning-in-vision-language-action-models.
شيكاغو (المؤلف–التاريخ)
Li, Tianfu, Haoxuan Xu, Wenbo Chen, Haitian Li, Changchuan Yang, Xinhu Zheng, Jun Ma, Yuan Liu, Lujia Wang, and Haoang Li. 2026. "SLIP-VLA: Single-Step Latent Imagination for Policy Learning in Vision-Language-Action Models." https://omanscience.com/ar/articles/slip-vla-single-step-latent-imagination-for-policy-learning-in-vision-language-action-models.
هارفارد
Li, T., Xu, H., Chen, W., Li, H., Yang, C., Zheng, X., Ma, J., Liu, Y., Wang, L. and Li, H. (2026) 'SLIP-VLA: Single-Step Latent Imagination for Policy Learning in Vision-Language-Action Models', Available at: https://omanscience.com/ar/articles/slip-vla-single-step-latent-imagination-for-policy-learning-in-vision-language-action-models.
فانكوفر
Li T, Xu H, Chen W, Li H, Yang C, Zheng X, et al. SLIP-VLA: Single-Step Latent Imagination for Policy Learning in Vision-Language-Action Models. https://omanscience.com/ar/articles/slip-vla-single-step-latent-imagination-for-policy-learning-in-vision-language-action-models
IEEE
T. Li, H. Xu, W. Chen, H. Li, C. Yang, X. Zheng, J. Ma, Y. Liu, L. Wang, and H. Li, "SLIP-VLA: Single-Step Latent Imagination for Policy Learning in Vision-Language-Action Models," https://omanscience.com/ar/articles/slip-vla-single-step-latent-imagination-for-policy-learning-in-vision-language-action-models.