yongxianwei/Qwen2-VL-7B-Geometry
Image-Text-to-Text • 8B • Updated • 302
MLLMerging
-
-
yongxianwei/Qwen2-VL-7B-Chart
Image-Text-to-Text • 8B • Updated • 318 -
yongxianwei/Qwen2-VL-7B-Grounding
Image-Text-to-Text • 8B • Updated • 324 -
yongxianwei/Qwen2-VL-7B-VQA
Image-Text-to-Text • 8B • Updated • 331 -
yongxianwei/Qwen2-VL-7B-OCR
Image-Text-to-Text • 8B • Updated • 324 -
yongxianwei/InternVL2_5-1B_OCR
Image-Text-to-Text • 0.9B • Updated • 338 -
yongxianwei/InternVL2_5-1B_Geometry
Image-Text-to-Text • 0.9B • Updated • 336 -
yongxianwei/InternVL2_5-1B_Chart
Image-Text-to-Text • 0.9B • Updated • 343 -
yongxianwei/InternVL2_5-1B_Grounding
Image-Text-to-Text • 0.9B • Updated • 347 -
yongxianwei/InternVL2_5-1B_VQA
Image-Text-to-Text • 0.9B • Updated • 347 -
yongxianwei/clip-base-32_DTD
Updated -
yongxianwei/clip-base-32_sun397
Updated -
yongxianwei/clip-base-32_cars
Updated -
yongxianwei/clip-base-32_svhn
Updated -
yongxianwei/clip-base-32_resisc
Updated -
yongxianwei/clip-base-32_EuroSAT
Updated -
yongxianwei/clip-base-32_mnist
Updated -
yongxianwei/clip-base-32_gtsrb
Updated -
yongxianwei/Qwen2.5-VL-32B-Chart
Image-Text-to-Text • 33B • Updated • 561 -
yongxianwei/Qwen2.5-VL-32B-Grounding
Image-Text-to-Text • 33B • Updated • 567 -
yongxianwei/Qwen2.5-VL-32B-Geometry
Image-Text-to-Text • 33B • Updated • 575 -
yongxianwei/Qwen2.5-VL-32B-OCR
Image-Text-to-Text • 33B • Updated • 562 -
yongxianwei/Qwen2.5-VL-32B-VQA
Image-Text-to-Text • 33B • Updated • 574 -
Unifying Multimodal Large Language Model Capabilities and Modalities via Model Merging
Paper • 2505.19892 • Published -
Closed-Form Spectral Regularization for Multi-Task Model Merging
Paper • 2606.07289 • Published • 2