Abstract: Approaches presented herein provide for the use of reinforcement learning to fine-tune a generative model, such as a motion diffusion model, for a specific objective, such as to generate representations of human motion corresponding to provided text input. A discriminator can be used to guide the training of the generative model. In at least one embodiment, the discriminator can compare the input text and generated motion representation (or embeddings of each) to determine an alignment value or match score, for example, which can then be used to adjust the network parameters or weights of the generative model to improve the alignment between input text and generated motion.

Abstract: A method for controlling a plurality of surgical devices includes: receiving a foot pedal signal indicating a foot pedal activation of a first foot pedal of a plurality of foot pedals; generating a control signal based on the foot pedal signal, wherein: if the foot pedal signal indicates that only the first foot pedal is pressed, then generating the control signal to cause a generator to activate a first surgical device associated with the first foot pedal; if the foot pedal signal indicates that the first foot pedal remains pressed and a second foot pedal is newly pressed, then generating the control signal to cause the generator to: maintain activation of the first surgical device associated with the first foot pedal; and not activate a second surgical device associated with the second foot pedal; and outputting the control signal to the generator.