Research map / Vision-language and multimodal / Human and embodied modeling
GIVL: Improving Geographical Inclusivity of Vision-Language Models With Pre-Training Methods
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add IKM objective (ablation) | GIVL · Dollar Street | accuracy: 21.37 -> 27.25 | Helped |
| add IEC objective (ablation) | GIVL · Dollar Street | accuracy: 12.96 -> 27.25 | Helped |
| replace binary IKM with three-way IKM that distinguishes category similarity (ablation) | GIVL · Dollar Street | accuracy: 20.35 -> 27.25 | Helped |
| add IKM objective (ablation) | GIVL · MaRVL | accuracy: 72.11 -> 72.50 | Helped |
| add IEC objective (ablation) | GIVL · MaRVL | accuracy: 68.58 -> 72.50 | Helped |
| replace binary IKM with three-way IKM that distinguishes category similarity (ablation) | GIVL · MaRVL | accuracy: 70.26 -> 72.50 | Helped |
| add IKM objective (ablation) | GIVL · GD-VCR | accuracy: 69.56 -> 70.32 | Helped |
| add IEC objective (ablation) | GIVL · GD-VCR | accuracy: 69.89 -> 70.32 | Helped |
| replace binary IKM with three-way IKM that distinguishes category similarity (ablation) | GIVL · GD-VCR | accuracy: 69.56 -> 70.32 | Helped |
| replace object-level visual encoding with CLIP and omit object-level IEC (ablation) | GIVL · GD-VCR | accuracy: 70.32 -> 70.43 | Mixed |
| increase pre-training from 500K to 900K steps | GIVL · MaRVL | accuracy: 72.50 -> 72.70 | Helped |
Closest papers by meaning
- No Filter: Cultural and Socioeconomic Diversity in Contrastive Vision-Language Models (NeurIPS 2024 · similarity 0.88)
- GS-Bias: Global-Spatial Bias Learner for Single-Image Test-Time Adaptation of Vision-Language Models (ICML 2025 · similarity 0.88)
- Multilingual Diversity Improves Vision-Language Representations (NeurIPS 2024 · similarity 0.87)
- Incorporating Geo-Diverse Knowledge into Prompting for Increased Geographical Robustness in Object Recognition (CVPR 2024 · similarity 0.87)
- GTR-Bench: Evaluating Geo-Temporal Reasoning in Vision-Language Models (ICLR 2026 · similarity 0.87)
- Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models (NeurIPS 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.