ViRA: visual agents that zoom into high-resolution photos, trained with CrossRPO on contrast sets. Models, benchmark and training data.
Huawei Lin PRO
huaweilin
AI & ML interests
None yet
Recent Activity
updated a dataset 1 day ago
huaweilin/ViRA-Train updated a dataset 1 day ago
huaweilin/ViRA-Bench updated a model 1 day ago
huaweilin/ViRA-27BOrganizations
None yet
models 9
huaweilin/ViRA-27B
Image-Text-to-Text • 27B • Updated • 69
huaweilin/ViRA-9B
Image-Text-to-Text • 9B • Updated • 67
huaweilin/VTBench_models
Updated
huaweilin/stable-diffusion-3.5-large-vae
Text-to-Image • Updated • 4
huaweilin/bsqvit_256x256
Updated • 13
huaweilin/chameleon_vqvae
Updated
huaweilin/imagenet_caption_generation
Updated
huaweilin/DMin_sd3_medium_lora_r4
Updated
huaweilin/rapidin-alpaca-llama2-7b
Updated • 6
datasets 10
huaweilin/ViRA-Train
Updated • 75
huaweilin/ViRA-Bench
Viewer • Updated • 840 • 97
huaweilin/LatComm
Viewer • Updated • 2.37M • 163 • 1
huaweilin/waste-classification
Viewer • Updated • 1.98k • 141
huaweilin/VTBench
Viewer • Updated • 50.9k • 290 • 1
huaweilin/cat_and_dog_text_to_text_image
Viewer • Updated • 30k • 14
huaweilin/image_captions_text_to_text_image
Viewer • Updated • 507k • 51
huaweilin/imagenet-1k-vl-enriched-any
Viewer • Updated • 9.31k • 5
huaweilin/DMin_mixed_datasets_8846
Viewer • Updated • 11.1k • 257
huaweilin/DMin_sd3_medium_lora_r4_caching_8846
Updated • 229