Michael M. Jerge

Perturb the Thought, Not the Pixels: Latent-Space Rollout Diversification for Reinforcement Learning of Vision-Language Models

Noise-Contrastive GRPO is introduced, which injects scale-calibrated Gaussian noise into the last hidden layer of the prompt-encoding pass for half of each rollout group, branching those rollouts from a displaced departure state and integrates into a standard RLVR pipeline as a ~50-line change to the inference engine.