Dataset and Models focus on long video-language understanding.
Jingyang Lin
jylins
AI & ML interests
vision-and-language
Recent Activity
updated a dataset about 1 month ago
jylins/videomme-v2 published a dataset about 1 month ago
jylins/videomme-v2 updated a dataset 7 months ago
estsafda/asdgOrganizations
models 9
jylins/LongPAI-8B
8B • Updated • 1 • 1
jylins/hourllava-qwen25-3b-s3
4B • Updated • 5
jylins/hourllava-qwen25-3b-s2
4B • Updated • 2
jylins/hourllava-qwen25-3b-s1
4B • Updated • 2
jylins/hourllava-qwen2-7b-s3
9B • Updated • 2
jylins/hourllava-qwen2-7b-s2
9B • Updated • 2
jylins/hourllava-qwen2-7b-s1
9B • Updated • 2
jylins/llava-onevision-qwen25-3b-si
4B • Updated • 3
jylins/vtsum_blip
Updated • 3
datasets 11
jylins/videomme-v2
Viewer • Updated • 3.2k • 61
jylins/hourvideo
Updated • 16
jylins/llava_hound
Preview • Updated • 53
jylins/LongFinanceQA
Updated • 51 • 2
jylins/videomarathon
Viewer • Updated • 3.3M • 1.64k • 4
jylins/lvbench
Updated • 2
jylins/LLaVA-Mid
Preview • Updated • 2
jylins/LLaVA-Pretrain
Updated • 1
jylins/panda-10m
Updated • 35 • 1
jylins/LLaVA-OneVision
Preview • Updated • 14 • 2