·
AI & ML interests
None yet
Organizations
None yet
📌 Rethinking Multimodality from an Industry Perspective: Captioning Is Far More Important Than You Think
models 27
shijiay/llava_clip224_stage1
Image-Text-to-Text
• Updated
shijiay/llava_clip224_stage2
Image-Text-to-Text
• Updated
shijiay/llava_dinov2_stage2
Image-Text-to-Text
• 7B • Updated
• 4
• 1
shijiay/llava_clip_stage1
Image-Text-to-Text
• Updated
shijiay/llava_clip_stage2
Image-Text-to-Text
• Updated
• 3
shijiay/llava_openclip_stage1
Image-Text-to-Text
• Updated
• 1
shijiay/llava_openclip_stage2
Image-Text-to-Text
• Updated
shijiay/llava_siglip_stage1
Image-Text-to-Text
• Updated
• 1
shijiay/llava_siglip_stage2
Image-Text-to-Text
• 7B • Updated
• 3
shijiay/llava_sdim_stage1
Image-Text-to-Text
• Updated
• 2