Robotic manipulation involves kinematic and semantic transitions that are inherently coupled via underlying actions. However, existing approaches plan within either semantic or latent space without explicitly aligning these cross-modal transitions. To address this, we propose CLaD, a framework that models how proprioceptive and semantic states jointly evolve under actions through asymmetric cross-attention that allows kinematic transitions to query semantic ones. CLaD predicts grounded latent foresights via self-supervised objectives with EMA target encoders and auxiliary reconstruction losses, preventing representation collapse while anchoring predictions to observable states. Predicted foresights are modulated with observations to condition a diffusion policy for action generation. On LIBERO-LONG benchmark, CLaD achieves 94.7\% success rate, competitive with large VLAs with significantly fewer parameters.
@article{arxiv.2603.29409,
title = {CLaD: Planning with Grounded Foresight via Cross-Modal Latent Dynamics},
author = {Andrew Jeong and Jaemin Kim and Sebin Lee and Sung-Eui Yoon},
journal= {arXiv preprint arXiv:2603.29409},
year = {2026}
}