Safety
Accelerating Visual On-Policy Distillation with Batched Speculative Jacobi Rollouts
arXiv:2608.18183v1 Announce Type: new Abstract: Visual on-policy distillation (OPD) improves the training of compact visual autoregressive models by learning from trajectories generated by the current
arXiv:2608.18183v1 Announce Type: new Abstract: Visual on-policy distillation (OPD) improves the training of compact visual autoregressive models by learning from trajectories generated by the current student. However, these online rollouts are still produced token by token with autoregressive decoding, which adds substantial cost to every on-policy training step. Speculative Jacobi Decoding (SJD) provides an alternative because it can process multiple tokens in parallel without an auxiliary draft model, but the original method is designed for single-sequence inference. We introduce HB-SJD, a batched SJD rollout backend for visual OPD. HB-SJD allows each image to advance independently according to its own decoding progress, while images at different sequence positions are still verified in batched model forwards. As images finish, HB-SJD switches between Full and Compact execution to reduce the cost of later rollout rounds. HB-SJD only replaces the student rollout backend and leaves the teacher, distillation objective, and optimization procedure unchanged. Experiments with LlamaGen show that HB-SJD substantially reduces rollout and end-to-end training time while preserving the generation quality of the distilled student.
Related
- Prefix-Guided On-Policy Distillation: Mining Golden Trajectories from Rollouts
- Distill What the Student Can See: Fisher-Projected On-Policy Distillation for Vision-Language Models
- Self-Boosting Vision-Language Models with Noisy Student On-Policy Self-Distillation
Source: arXiv cs.LG | 2026-08-20