Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
UGround: Towards Unified Visual Grounding with Unrolled Transformers
Rui Qian, Xin Yin, Chuanhang Deng +4
We present UGround, a \textbf{U}nified visual \textbf{Ground}ing paradigm that dynamically selects intermediate layers across \textbf{U}nrolled transformers as ``mask as prompt,''…
cs.CV2026
AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation
Rui Qian, Chuanhang Deng, Qiang Huang +6
Reasoning segmentation requires models to ground complex, implicit textual queries into precise pixel-level masks. Existing approaches rely on a single segmentation token $\texttt{…
cs.CV2026
Reasoning to Attend: Try to Understand How <SEG> Token Works
Rui Qian, Xin Yin, Dejing Dou
Current Large Multimodal Models (LMMs) empowered visual grounding typically rely on tokens as a text prompt to jointly optimize the vision-language model (e.g., LL…