| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| Perception Encoder: The best visual embeddings are not at the output of the network | ✓ Link | 78.5 | PE-Core G | 2025-04-17 |
| EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters | ✓ Link | 77.7 | EVA-CLIP-18B | 2024-02-06 |
| Demystifying CLIP Data | ✓ Link | 75.1 | MetaCLIP ViT-bigG/14 | 2023-09-28 |
| Multi-label Cluster Discrimination for Visual Representation Learning | ✓ Link | 72.1 | MLCD ViT-L/14 | 2024-07-24 |
| SmartCLIP: Modular Vision-language Alignment with Identification Guarantees | ✓ Link | 72.1 | SmartCLIP (ViT-L/14) | 2025-07-29 |
| Learning Transferable Visual Models From Natural Language Supervision | ✓ Link | 58.5 | CLIP | 2021-02-26 |
| Learning Visual N-Grams from Web Data | 23.0 | Visual N-Grams | 2016-12-29 |