Grid-based Repulsive Sampler for Distribution Rebalancing in Generative Post-Training

Post-training a generative model begins by reducing a large candidate pool to a small fine-tuning set. Near-duplicates are removed above a similarity threshold and over-represented regions are capped, once, before training, and neither decision can be revisited afterwards. We propose the Grid-based Repulsive Sampler (GridReS), which rebalances the training distribution and keeps the pool intact. GridReS constructs a uniform grid over a low-dimensional projection of a pretrained embedding space. During training, occupancy-aware sampling redistributes probability mass across cells, while intra-cell repulsion scores candidates against a memory of recent draws from the surrounding neighbourhood. The partition supplies the locality that keeps repulsion at a bounded per-draw cost; repulsion controls the redundancy inside a region, which weighting over regions cannot reach. At coverage identical to random sampling, GridReS cuts cross-source near-duplicate co-exposure by 50% on the fine-tuning pool of Kandinsky-6 Lite, a text-to-audio-video model, and by 25% on OpenVid-100k. When Kandinsky-6 Lite is fine-tuned as a single job on the full pool, GridReS improves VBench imaging quality over random sampling by 1.84 points, beyond run-to-run variance, and trained per domain it matches the deployed deduplication pipeline at equal optimizer steps without discarding any data. Code is available at https://github.com/94yvwj2hrj-eng/gridres.