Which Objects Stay? Learning Hierarchical Persistence Beliefs for Lifelong Open-Vocabulary Object Maps
cs.CV, cs.RO
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- OASIS-Map: Object-Level Change Detection in Multi-Session Mapping using Semantic Correspondence Matching
- FOCUS: Fine-Grained Open-Vocabulary Change Detection for Uncertainty-Aware Semi-Static Scenes
- PreSIST: Vision-Language-Informed Object Persistence Prediction in Open-World Scenes
- Vision-Language-Motion Maps: An Open-Vocabulary, Uncertainty-Aware, Queryable Motion Attribute for 3D Scene Maps
- AI2-THOR: An Interactive 3D Environment for Visual AI
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs