This work proposes MoR-MLLM, a computation-sparse MLLM based on the recent Mixture-of-Recursions (MoR) framework, which introduces adaptive per-token recursion, allowing the model to dynamically adjust its recursive depth and allocate more computation to visually or linguistically challenging tokens while skipping redu...
Peng-Cheng Zheng, Chao-Ning Zhang, Jia-Xing Yan et al.· IEEE transactions on multime...· 1 citation
Qwen-Planner-Agent is built, which achieves the best overall performance among all evaluated models and systems on MobilePA-Bench, improving over its base model across tool use, memory, skills, and sub-agent coordination.
Tingyu Qu, Wei-Gao Sun, Yuecheng Liu et al.· arXiv.org· 2 citations
A budget-aware framework that systematically orchestrates when and what to teach and integrates a solvability-aware teacher gate to dictate the teacher model and a score-guided turn selection mechanism to decide what informative turns to retain is proposed.
Jian-Wei Zhang, Si-Han Cao, Peng-Cheng Zheng et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.