STARE: Scene Text-Aware multimodal Retrieval for Everyday objects
cs.CV
Submitted: 2026-11-04
Updated: 2026-11-04
Project page: https://stare-projectpage.pages.dev
Terminology
Sources
- Meta CLIP 2: A Worldwide Scaling Recipe
- ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge
- DINOv2: Learning Robust Visual Features without Supervision
- Gemini Robotics: Bringing AI into the Physical World
- Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation
- Jasper and Stella: distillation of SOTA embedding models
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