Metraipolis › archive › dc_5a2c2eb87f7c
Aligning Human Sense: Calibrated Distributional Reward Learning for Video Generation — arXiv:2608.21425
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.21425
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T07:42:13.430Z
- SHA-256 of the archived text
6b1af0d98250a3ddf1030a6b1f825fc6c2a312c326961f4c865e10c278e012e3- Stable URL of this page
https://metraipolis.com/documento/dc_5a2c2eb87f7c
How to cite
Aligning Human Sense: Calibrated Distributional Reward Learning for Video Generation — arXiv:2608.21425 — arXiv (en), https://arxiv.org/abs/2608.21425 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5a2c2eb87f7c (Metraipolis archive dc_5a2c2eb87f7c, sha256 6b1af0d98250a3ddf1030a6b1f825fc6c2a312c326961f4c865e10c278e012e3)
BibTeX
@misc{dc5a2c2eb87f7c,
title = {Aligning Human Sense: Calibrated Distributional Reward Learning for Video Generation — arXiv:2608.21425},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.21425},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5a2c2eb87f7c; sha256 6b1af0d98250a3ddf1030a6b1f825fc6c2a312c326961f4c865e10c278e012e3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21425. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Video generation is central to AI-powered content creation. Aligning generated videos with human preferences is a key criterion for evaluating generation quality. Despite significant progress in visual quality, three key challenges remain. First, the reliability of reward signals is constrained by the quality of human preference data, which is often affected by subjective noise and bias. Second, standard scalar reward models collapse multi-aspect human preferences into a single value, leading to the loss of dynamic trade-offs across multiple preference dimensions. Third, in policy optimization, the widely adopted KL divergence imposes primarily local constraints and may fail to capture the global structure of human preferences. To address these challenges, we propose a unified preference-aware learning framework for video generation. First, we introduce elite-guided filtering to calibrate preference data and construct reliable supervision for reward model training. We then model video quality as a multidimensional reward distribution to capture the uncertainty inherent in human preferences, and use the Wasserstein distance to align the learned reward distribution with the empirical human preference distribution. Finally, we introduce Wasserstein-based distributional alignment into GRPO, guiding policy optimization to better match the global structure of human preferences over videos. Experiments on reward modeling and video generation demonstrate that our approach improves the reliability of reward signals and the perceptual consistency of generated videos. Our code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.21425 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T07:37:52.810Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).