Visual Question Answering on GQA (test val)
61.9AccuracyVanilla
Evaluation Results
| Method | Links | |
|---|---|---|
| VanillaVenue=NeurIPS’23, Location=—, Tokens=576, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 61.9 | |
| SVD-PruneVenue=CVPR’25, Location=Encoder, Tokens=192, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 59.88 | |
| HIREDVenue=AAAI’25, Location=Encoder, Tokens=192, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 58.8 | |
| SVD-PruneVenue=—, Location=Encoder, Tokens=128, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 58.7 | |
| VisionZipVenue=CVPR’25, Location=Encoder, Tokens=128, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 57.6 | |
| PyramidDropVenue=AAAI’25, Location=LLM, Tokens=192, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 57.3 | |
| HIREDVenue=AAAI’25, Location=Encoder, Tokens=128, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 57.1 | |
| PyramidDropVenue=CVPR’25, Location=LLM, Tokens=128, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 57.1 | |
| ToMeVenue=ICLR’23, Location=Encoder, Tokens=192, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 54.3 | |
| SVD-PruneVenue=—, Location=Encoder, Tokens=64, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 53.77 | |
| SparseVLMVenue=ICLR’25, Location=LLM, Tokens=64, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 53.7 | |
| SVD-PruneVenue=—, Location=Encoder, Tokens=32, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 53.52 | |
| SVD-PruneVenue=—, Location=Encoder, Tokens=16, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 53.04 | |
| FastVVenue=ECCV’24, Location=LLM, Tokens=192, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 52.88 | |
| ToMeVenue=ICLR’23, Location=Encoder, Tokens=128, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 52.4 | |
| VisionZipVenue=CVPR’25, Location=Encoder, Tokens=32, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 51.8 | |
| TRIMVenue=arXiv’25, Location=Encoder, Tokens=64, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 50.9 | |
| HIREDVenue=AAAI’25, Location=Encoder, Tokens=64, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 50.6 | |
| FastVVenue=ECCV’24, Location=LLM, Tokens=128, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 49.6 | |
| ToMeVenue=ICLR’23, Location=Encoder, Tokens=64, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 48.6 | |
| SparseVLMVenue=ICML’25, Location=LLM, Tokens=32, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 48.3 | |
| PyramidDropVenue=CVPR’25, Location=LLM, Tokens=64, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 47.5 | |
| FastVVenue=ECCV’24, Location=LLM, Tokens=64, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 46.1 | |
| ToMeVenue=ICLR’23, Location=Encoder, Tokens=32, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 43.6 | |
| FastVVenue=ECCV’24, Location=LLM, Tokens=32, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.04 | 41.5 |