Reward-Forcing guides autoregressive video generation with reward feedback to achieve performance comparable to teacher-dependent methods on benchmarks like VBench without relying on distillation.
Poetry2image: An iterative correction framework for images generated from chinese classical poetry.arXiv preprint arXiv:2407.06196,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Reward-Forcing: Autoregressive Video Generation with Reward Feedback
Reward-Forcing guides autoregressive video generation with reward feedback to achieve performance comparable to teacher-dependent methods on benchmarks like VBench without relying on distillation.