method · first seen 16 Oct 2026
multimodal large language model grounding
Training multimodal language models to produce region masks from their own visual representations for grounded reasoning.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Xiaomi-Lens-0 Technical ReportPapers · 16 Oct 2026 · Pei Fu, Yike Liu, Yue Sun, Hanmo Wang, Xiuwen Xi, Ruoceng Zhang, Shaojie Zhang,…
Latest sources
- Xiaomi-Lens-0 Technical ReportPapers · 16 Oct 2026 · Pei Fu, Yike Liu, Yue Sun, Hanmo Wang, Xiuwen Xi, Ruoceng Zhang, Shaojie Zhang,…