Latent reward models (LRMs) enable efficient alignment of video diffusion models by scoring intermediate states directly in latent space. However, we find that optimizing against a fixed latent reward rapidly leads to latent reward hacking: the predicted reward stays high while perceptual and motion quality deteriorate...
Zhao-Long Su, Yu-Jin Han, Feng Wang et al.· 0 citations
MILD, a Motion-Preserving Image-to-Video Latent Distillation framework that transfers specialized image expertise while preserving pretrained video dynamics, is proposed and established as an effective route to improving video generation by drawing on the diverse and evolving capabilities of the image-generation ecosys...
Bing Jiang, Li Luo, Zi-Chao Yu et al.· 0 citations
SkillRubric is introduced, which represents each skill through aligned actor-facing guidance and an evaluator-facing rubric, and shows that evolved skills provide more effective guidance for planning and tool use than their preceding versions.
Bing Jiang, Guo-Xi Zhang, Jasper Wang et al.· 0 citations
TIDE (Token-level Independent Deficit-Excess correction), which applies bounded Hellinger shaping to suppress the most severe sampled excesses and an analytic teacher top-$K$ injection to restore deficient probability mass without requiring deficit tokens to be sampled, is proposed.
Zi-Chao Yu, Chengzhi Yu, Sheng-Ze Xu et al.· 4 citations
This work proposes ReBind, a systematic framework that introduces semantic instructions with embedded reference tokens as the intermediate representation for multi-reference image-conditioned video editing and develops ReBind-Instruct, a specialized MLLM that learns to establish explicit bindings between visual attribu...
Xin-Yu Liu, Shi-Hao Li, Weihong Lin et al.· arXiv.org· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
