Ren Nie
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Vision×1AI×1
Frequent co-authors
Research Timeline
2026
ROVER: Routing Object-Centric Visual Evidence for Grounded Multi-Image Reasoning
ROVER is a lightweight, learnable plugin that efficiently routes and integrates object-centric visual evidence across multiple images and objects, significantly improving performance on grounded multi-image reasoning tasks.
Highlighted terms show continued research focus across papers