Shijia Yang

shijiay's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

commented a paper 3 days ago

CaptionQA: Is Your Caption as Useful as the Image Itself?

Paper • 2511.21025 • Published 9 days ago • 24 •

3

authored a paper 3 days ago

CaptionQA: Is Your Caption as Useful as the Image Itself?

Paper • 2511.21025 • Published 9 days ago • 24

upvoted an article 5 days ago

view article

Article

📌 Rethinking Multimodality from an Industry Perspective: Captioning Is Far More Important Than You Think

• 

5 days ago

•

3

upvoted a paper 5 days ago

CaptionQA: Is Your Caption as Useful as the Image Itself?

Paper • 2511.21025 • Published 9 days ago • 24

published an article 5 days ago

view article

Article

📌 Rethinking Multimodality from an Industry Perspective: Captioning Is Far More Important Than You Think

• 

5 days ago

•

3

liked a dataset 7 days ago

Borise/CaptionQA

Viewer • Updated 7 days ago • 1.31k • 525 • 4

upvoted a paper 4 months ago

SAND-Math: Using LLMs to Generate Novel, Difficult and Useful Mathematics Questions and Answers

Paper • 2507.20527 • Published Jul 28 • 5

upvoted a paper 12 months ago

AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?

Paper • 2412.02611 • Published Dec 3, 2024 • 26

authored a paper about 1 year ago

AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?

Paper • 2412.02611 • Published Dec 3, 2024 • 26

commented a paper about 1 year ago

Law of Vision Representation in MLLMs

Paper • 2408.16357 • Published Aug 29, 2024 • 95 •

8

commented a paper over 1 year ago

Law of Vision Representation in MLLMs

Paper • 2408.16357 • Published Aug 29, 2024 • 95 •

8

updated 9 models over 1 year ago

shijiay/llava_clip224_stage1

Image-Text-to-Text • Updated Sep 3, 2024 • 5

shijiay/llava_clip224_stage2

Image-Text-to-Text • Updated Sep 3, 2024 • 4

shijiay/llava_dinov2_stage2

Image-Text-to-Text • 7B • Updated Sep 3, 2024 • 9 • 1

shijiay/llava_clip_stage1

Image-Text-to-Text • Updated Sep 3, 2024 • 7

shijiay/llava_clip_stage2

Image-Text-to-Text • Updated Sep 3, 2024 • 4

shijiay/llava_openclip_stage1

Image-Text-to-Text • Updated Sep 3, 2024 • 6

shijiay/llava_openclip_stage2

Image-Text-to-Text • Updated Sep 3, 2024 • 9

shijiay/llava_siglip_stage1

Image-Text-to-Text • Updated Sep 3, 2024 • 6

shijiay/llava_siglip_stage2

Image-Text-to-Text • 7B • Updated Sep 3, 2024 • 4