Humanoid robots promise general-purpose assistance, yet real-world humanoid loco-manipulation remains challenging because it requires whole-body stability, dexterous hands, and contact-aware perception under frequent contact changes. In this work, we study dexterous, contact-rich humanoid loco-manipulation. We first develop an RL-based whole-body controller that provides stable lower-body and torso execution during complex manipulation. Built on this controller, we develop a whole-body humanoid data collection system that combines VR-based teleoperation with a unified reference frame for human-to-humanoid motion mapping, enabling efficient collection of real-world demonstrations. We then propose Humanoid Transformer with Touch Dreaming (HTD), a multimodal encoder-decoder Transformer that treats touch as a first-class modality alongside multi-view vision and proprioception. HTD is trained with a single-stage behavioral cloning objective augmented with touch dreaming: in addition to predicting action chunks, the policy predicts future hand finger forces and future tactile latents, encouraging the shared Transformer trunk to learn contact-aware representations for dexterous interaction. Across five contact-rich tasks, Insert-T, Book Organization, Towel Folding, Cat Litter Scooping, and Tea Serving, our system enables versatile, high-dexterity humanoid manipulation in the real world.

Explore touch dreaming predictions interactively. The left panel shows the robot's head camera view. The right panel visualizes predicted vs. ground-truth touch signals—switch between Force, Latent Tactile, and Raw Tactile modes. For the latent tactile heatmaps, each latent dimension is independently normalized over the episode, with a minimum-range threshold derived from the most active dimension across all fingers to distinguish active from inactive latent contact regions. Note that this per-dimension normalization amplifies subtle changes and prediction errors in the latent space for better visibility.