GUI grounding is a critical capability for GUI agents powered by vision-language models, helping them execute user instructions by locating the corresponding elements in screenshots. Single-step grounding struggles with small elements and dense layouts, motivating multi-step visual search. However, existing approaches...
Kai-Yu Wu, Bei-Chen Zheng, Wei-Yao Huang et al.· 0 citations
ProSA is proposed, a lightweight output-level auditing framework that decouples controlled probing, policy-driven targeting, and structure-aware diagnosis to analyze where structural identity is lost, at what exposure granularity failures emerge, and how failures propagate.
History-Aware Routing is proposed, a dynamic routing framework that resolves this mismatch by introducing a router memory mechanism to maintain an explicit routing state across model depth, validating that explicit routing memory enables more accurate and adaptive dynamic routing than solely conditioning on hidden stat...
Token-Budget Distillation (TBD) is presented, a parameter-efficient fine-tuning framework for adapting video VLMs under a fixed token budget and consistently outperforms compression-only baselines under both moderate and aggressive compression.
Xiao-Yang Guo, Guoping Luo, Jusheng Zhang et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
