HALO aligns text-to-video diffusion models by jointly optimizing patch-level and video-level DPO rewards, with modest and partially self-referential benchmark gains.
Training diffusion models with reinforcement learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Harness Local Rewards for Global Benefits: Effective Text-to-Video Generation Alignment with Patch-level Reward Models
HALO aligns text-to-video diffusion models by jointly optimizing patch-level and video-level DPO rewards, with modest and partially self-referential benchmark gains.