TacFiLM is a lightweight post-training fusion method that conditions a VLA’s intermediate visual features on pretrained tactile representations through feature-wise linear modulation, improving success rate, completion time, and force stability on contact-rich insertion and drawer-opening tasks.
CDPs add a contraction regularizer to diffusion policies that pulls nearby sampling flows together, suppressing solver and score-matching errors and unwanted action variance. Backed by theory and a practical recipe with a single extra hyperparameter, they often outperform standard diffusion policies in simulation and on real robots, most clearly when data is scarce.
VOCALoco predicts the viability and cost of transport of several pretrained locomotion skills from local heightmaps, then executes the safest, most efficient one. It improves robustness on stair ascent and descent over an end-to-end DRL policy and transfers to a real ANYmal-D quadruped.