GUI agents accumulate high-resolution screenshots as the trajectory unfolds, increasing inference latency and memory usage. Training-free visual token pruning can reduce this cost, but cache reuse introduces a fundamental constraint. Once tokens are discarded, the corresponding visual evidence cannot be recovered witho...
Yu-Hao Wang, Mu Qiao, Xin-Dong Zhang et al.· 0 citations
FlowPainter is introduced, a diffusion-based optical flow framework that reformulates dense-flow generation as confidence-guided soft inpainting and offers a practical way to integrate reliable discriminative priors with diffusion-based refinement for optical flow estimation.
Yuan Meng, Chen Wu, Xianshun Liu et al.· arXiv.org· 0 citations
ERA establishes logit-preserving visual token pruning as a principled framework for efficient MLLMs, unifying theoretical foundation, algorithmic design, and practical deployment.
Yuhao Wang, Mu Qiao, Haiwen Diao et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.