method · first seen 26 Oct 2026
vision-language model grounding
Also: VLM grounding
Linking language references to objects and locations in images so vision-language models can act on them.
Mentions per week
PapersCodeDiscussion
Earliest sources
- TrySee: Modular Perception-Enhanced VLM Grounding for Closed-Loop Robot Task Planning in Specialized DomainsPapers · 26 Oct 2026 · Elias Hofele, Thomas Trapp, David Timmermann, Tristan Schnell, Georg Heppner, Ar…
- CounterSketch: Physics-Grounded Counterfactual Reasoning for Sketch-to-Video GenerationPapers · 3 Nov 2026 · Hien Trinh, Tan-Hiep To, Dinh-Khoi Vo, Tam V. Nguyen, Minh-Triet Tran, Trung-Ngh…
Latest sources
- CounterSketch: Physics-Grounded Counterfactual Reasoning for Sketch-to-Video GenerationPapers · 3 Nov 2026 · Hien Trinh, Tan-Hiep To, Dinh-Khoi Vo, Tam V. Nguyen, Minh-Triet Tran, Trung-Ngh…
- TrySee: Modular Perception-Enhanced VLM Grounding for Closed-Loop Robot Task Planning in Specialized DomainsPapers · 26 Oct 2026 · Elias Hofele, Thomas Trapp, David Timmermann, Tristan Schnell, Georg Heppner, Ar…