Similarity-Shift Refinement (SSR), a training-free post-hoc method for improving object-centric masks with a frozen self-supervised Vision Transformer, provides a simple and transferable signal for training-free object-centric mask refinement.
Navigation World Models (NWMs) predict action-conditioned visual futures for planning. Two practical challenges are central to their design: selecting a suitable visual representation and efficiently modeling observation history for repeated candidate queries. Standard Global-Softmax attention provides flexible interac...
Guang-Fu Guo, Xiao-Qian Lu, Rui Liu et al.· 0 citations
A question-relevant saliency map identifies and organizes key visual regions, explicitly modeling the spatial distribution of visual importance, and induces a curriculum-like semantic progression from primary to secondary cues, validating structured and sequential visual cognition.
DeltaFlow is a promising alternative to dense attention for efficient continuous language denoising and noise-adaptive memory control and scheduled Temporal State Consistency to stabilize hidden representations across nearby noise levels are introduced.
Guang-Fu Guo, Xiao-Qian Lu, Linsey Pang 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.