| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training | ✓ Link | 53.8 | MobileCLIP-S0 | 2023-11-28 |
| Demystifying CLIP Data | ✓ Link | 48.3 | MetaCLIP ViT-B/32 (2.5B data) | 2023-09-28 |
| Retaining Knowledge and Enhancing Long-Text Representations in CLIP through Dual-Teacher Distillation | 41.4 | LongD-CLIP (ViT-B/16) (extra data) | 2025-06-11 | |
| POGA: Paraphrased and Oppositional Graph Alignment for Fine-Grained Cross-Modal Retrieval | 40.55 | POGA (ViT-B/16) | 2026-06-03 |