Agentic visual generation produces experience that can improve the native understanding (agent) and generation roles of a unified multimodal backbone, but task success alone does not determine which role should learn. Generator updates can also make the agent's action supervision stale. We introduce RSIgen, a task-cent...
Yi-Di Liu, Hao-Zhe Wang, Jie Xiao et al.· 1 citation· ⚡1
Post-training is crucial for improving text-to-image models, yet existing pipelines typically rely on manually curated training data and fixed training distributions. We introduce APT (Agentic Post-Training), a fully automated framework that adaptively post-trains a base model according to its evolving capability profi...
Si-Rui Zhang, Fang-Yun Wei, Dong Chen et al.· 0 citations
This work introduces PEBench, the first unified benchmark for direct PE evaluation across text-to-video, image-to-video, and reference-to-video prompt enhancement, and develops PEBench evaluation, an evidence-grounded framework that combines modality-aware fact extraction with rubric-based assessment across 24 criteria...
Ya-Wen Shao, Yu-Bo Zhu, Zi-Yun Dai et al.· 1 citation
Extensive experiments demonstrate that the CoDeR framework substantially extends the capabilities of existing world models, enabling long-term memory, open-ended interactions, autonomous evolution, and persistent multi-agent dynamics, while achieving state-of-the-art performance across multiple evaluation settings.
Zi-Xun Fang, Ya-Wen Shao, Kai Zhu et al.· 0 citations
This work introduces Process Aligned Policy Optimization (PAPO), a novel framework that holistically aligns the RL update with the dLLM's generative trajectory via Step-Aware Process Rewards (SPR) that transform sparse terminal rewards into dense, step-wise credit, and Entropy-Guided Historical Re-enactment that replay...
Ya-Wen Shao, Jie Xiao, Kai Zhu et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.