SLIP-VLA, a policy learning framework that equips VLA models with a Single-Step Latent Imagination for future-aware action prediction, 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.
Abstract
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.
Vision-language-action (VLA) models provide a unified framework for visual understanding, language grounding, and robot control, yet anticipating how the scene will evolve beyond the current observation can provide additional information for control. Action supervision alone does not explicitly encourage such anticipat...
Zi-Le Zhong, Yu-Xin Du, Tao Lin et al.· 0 citations
Vision-language-action (VLA) policies excel at generalist robotic manipulation but generate actions without explicitly modeling their environmental consequences. World action models (WAMs) incorporate future prediction, yet most rely on costly video generation, while latent alternatives either use predicted futures onl...
Haomin Wang, An-Qiong Ji, Ke Wang et al.· 1 citation
Learning to predict how the world evolves can provide vision-language-action (VLA) policies with predictive context for long-horizon control, but its effectiveness depends on what future representation is modeled and how it conditions action generation. We introduce PLaW-VLA, which models task-relevant future states in...
Yu Liu, He-Tian Guo, Tianlv Huang et al.· 2 citations
Many vision-language-action policies rely on action-labeled robot demonstrations and lack an explicit mechanism for predicting future visual states. These limitations hinder learning from action-free videos and can encourage overfitting to demonstration conditions, weakening generalization and robustness. We present TS...
Meng-Hao Yin, Jia-Ju Yin, Xi-Yue Dong et al.· 0 citations
Vision-Language-Action (VLA) models generate robot actions from visual observations and language instructions, but effective manipulation also requires anticipating how the environment will change. Existing world-action models explore future image prediction and latent dynamics modeling. However, generating complete fu...
Zhang Yi, Yu-Chen Wang, Chao Li et al.· 1 citation
Imagine-RL is presented, which augments noise-space VLA post-training with action-conditioned visual-torque imagination and improves the average success rate by (23.6%) over DSRL and by (60%) over VLA baselines.