← Back to all news
arXiv Computer Vision By Zheming Fu, Wenbin Ning, Ruizhe He, Wei Shang, Xiaoxiao Ma, Lianrui Mu, Chang Liu, Lei Wang, Siming Fu

VideoAWR: Reinforcing Video Flow Models with Decoupled-Timestep Advantage-Weighted Rectification

Read the original on arXiv Computer Vision →

VideoAWR introduces a decoupled-timestep advantage‑weighted rectification framework for video flow models, separating guided rollouts from the optimization anchor to avoid geometric guidance blow‑up and cold‑start collapse. The method uses an EMA reference policy for guided rollouts while rectifying against an unguided conditional anchor, proving that the centered advantage cancels the anchor in expectation and retains only reward‑correlated covariance. Experiments on Wan2.1‑1.3B and 14B models show stable training and improved visual and motion quality in both CFG‑free and CFG‑enabled settings.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Oct 12

GraftOOD: Grafting Out-of-Distribution Exemplars into Advantage-Weighted Rectification for Video Reward Optimization

The paper introduces GraftOOD, a method that improves video reward optimization by grafting out‑of‑distribution video exemplars into advantage‑weighted rectification. By replacing parts of online rollouts with exemplar supervision, GraftOOD addresses motion collapse and achieves significant gains in dynamic degree and other metrics on the Wan2.1-1.3B benchmark. The authors also release GraftSet‑Video, a dataset of 9,588 exemplars for 2,397 prompts, and provide code for reproducibility.

By Zheming Fu, Ruizhe He, Wenbin Ning, Xiaoxiao Ma, Xuan Yang, Lianrui Mu, Haoyang Huang, Chang Liu, Lei Wang, Siming Fu
More like this →
arXiv AI
Sep 4

FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience

arXiv:2609. 03241v1 Announce Type: cross Abstract: A reasoning model can improve from its own on-policy experience, but this inner loop is fragile: terminal verifiers provide reliable yet sparse supervision, while dense same-model guidance can reinforce false confidence or overconcentrate learning on a narrow solution mode.

By Zixun Huang, Kishan Panaganti, Haitao Mi, Leowei Liang
More like this →
arXiv Computer Vision
Oct 5

FlowHMR: Physically Plausible Motion Capture from Video

arXiv:2610.03691v1 Announce Type: new Abstract: We present FlowHMR, a framework for recovering physically plausible global 3D human motion from monocular video. Previous learning-based methods typica...

By Zhanke Wang, Chengfeng Zhao, Qing Shuai, Jingzhong Lin, Heng Li, Zeyu Ling, Yuxin Wen, Jing Li, Di Kang, Chunchao Guo, Linchao Bao
diffusionbenchmarks
More like this →