lmms-lab/RefCOCO
Viewer • Updated • 17.6k • 10k • 34
AI & ML interests
Feeling and building the multimodal intelligence.
Recent Activity
View all activity
Papers
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
A Simple Baseline for Streaming Video Understanding
lmms-lab/Ferret-Bench
Viewer • Updated • 120 • 49 • 6
lmms-lab/HallusionBench
Viewer • Updated • 1.13k • 4.78k • 10
lmms-lab/COCO-Caption
Viewer • Updated • 81.3k • 4.08k • 13
lmms-lab/COCO-Caption2017
Viewer • Updated • 45.7k • 4.49k • 23
lmms-lab/flickr30k
Viewer • Updated • 31.8k • 5.11k • 18
lmms-lab/SEED-Bench-2
Viewer • Updated • 24.4k • 384 • 2
lmms-lab/SEED-Bench
Viewer • Updated • 18k • 15.1k • 4
lmms-lab/CMMMU
Viewer • Updated • 12k • 1.38k • 4
lmms-lab/MP-DocVQA
Viewer • Updated • 10.2k • 2.18k • 5
lmms-lab/ST-VQA
Viewer • Updated • 4.07k • 207 • 5
lmms-lab/RoboVQA
Preview • Updated • 60 • 1
lmms-lab/VQAv2
Viewer • Updated • 770k • 25.2k • 34
lmms-lab/DC200_CN
Viewer • Updated • 200 • 3
lmms-lab/DC100_EN
Preview • Updated • 38
lmms-lab/MME
Viewer • Updated • 2.37k • 46.9k • 33