Group Relative Policy Optimization (GRPO) has advanced generative model post-training in verifiable domains such as code and mathematics, but evaluating video quality, especially emotional expression, often depends on subjective aesthetics and has no uniquely correct target. Existing approaches typically rely on fixed...
Mingzhe Zheng, Yue Wu, Jing Tan et al.· 0 citations
An event-centric evaluation framework that disentangles audio and visual events at the event level, analyzes each event independently, cross-validates relations across modalities, and aggregates the judgments into a coarse-to-fine, three-level consistency metric, providing a general formulation for audio-video consiste...
Yu-Ruo Wu, Kai-Hang Pan, Kai Shen et al.· 0 citations
Natively training joint video-audio generation models at higher resolutions empowers them to learn richer visual details and sharper motion dynamics. However, full attention incurs quadratic cost and, as resolution increases, spreads attention over increasingly redundant tokens, diluting learning signals for informativ...
Shu-Yuan Tu, Qi Tian, Yin-Ming Huang et al.· 1 citation
VA-Judger is proposed, a chain-of-thought omni-reward model that learns from pairs with clear quality gaps to establish structured output and coarse preference discrimination, then distills reliable preference explanations for harder near-quality comparisons via rejection sampling verified against human annotations, an...
Yin-Ming Huang, Shu-Yuan Tu, Xi Yan et al.· 6 citations· ⚡1
Iron is introduced, an intent-aligned, self-improved, and annotation-efficient framework for training GUI agents that employs a novel dual learning strategy that utilizes a stepwise cycle-consistent reward to achieve fine-grained alignment between low-level actions and high-level intents, thereby improving instruction...
Jia-He Ying, Wen-Dong Bu, Kai-Hang Pan et al.· arXiv.org· 0 citations
This work states that existing visual generative models are not yet ready for RL due to the following two fundamental drawbacks that undermine the foundations of RL.
Bohan Wang, Min Zhou, Zhongqi Yue et al.· Neural Information Processin...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.