Author

Dibyendu Ghosh

h-index 1 View on Semantic Scholar

We have 2 of 7 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Vision-Language-Motion Maps: An Open-Vocabulary, Uncertainty-Aware, Queryable Motion Attribute for 3D Scene Maps

Vision-Language-Motion Maps is introduced, an open-vocabulary, language-queryable 3D map queried through a rule-based intent router over open-vocabulary object nouns, in which each element carries a fused motion attribute: a VLM/LLM semantic movability prior combined with geometrically observed cross-frame motion, together with a per-element uncertainty.

Dibyendu Ghosh, Ayushi Shakya · arXiv.org · 2 citations · ⚡1

Jul 2026

Memory for Attention: Language-Conditioned Re-Perception with a Vision-Language-Motion Map

A persistent map's memory yields the best schedule (held-out), matching an oracle, while the memoryless VLM prior is poor, showing a persistent map's memory earns its keep not by telling the robot how to walk around a room, but by telling it what to pay attention to.

Dibyendu Ghosh · arXiv.org · 0 citations