Dataset and Models focus on long video-language understanding.
Jingyang Lin
jylins
AI & ML interests
vision-and-language
Recent Activity
updated a dataset about 11 hours ago
jylins/perceptionbench upvoted a paper 15 days ago
VideoLoop: Looped Working Memory Against Semantic Thrashing in Long-Form Video Agents liked a dataset 23 days ago
secemp9/arxiv-completeOrganizations
models 9
jylins/LongPAI-8B
8B • Updated • 9 • 1
jylins/hourllava-qwen25-3b-s3
4B • Updated • 8
jylins/hourllava-qwen25-3b-s2
4B • Updated • 8
jylins/hourllava-qwen25-3b-s1
4B • Updated • 8
jylins/hourllava-qwen2-7b-s3
9B • Updated • 11
jylins/hourllava-qwen2-7b-s2
9B • Updated • 11
jylins/hourllava-qwen2-7b-s1
9B • Updated • 12
jylins/llava-onevision-qwen25-3b-si
4B • Updated • 7
jylins/vtsum_blip
Updated • 3
datasets 12
jylins/perceptionbench
Viewer • Updated • 3k • 16
jylins/videomme-v2
Viewer • Updated • 3.2k • 24
jylins/hourvideo
Updated • 1.55k
jylins/llava_hound
Preview • Updated • 330
jylins/LongFinanceQA
Updated • 143 • 2
jylins/videomarathon
Viewer • Updated • 3.3M • 238 • 5
jylins/lvbench
Updated • 54
jylins/LLaVA-Mid
Viewer • Updated • 668k • 19
jylins/LLaVA-Pretrain
Updated • 16
jylins/panda-10m
Updated • 783 • 1