lmms-lab/RefCOCO
Viewer • Updated • 17.6k • 8.5k • 31
AI & ML interests
Feeling and building the multimodal intelligence.
Recent Activity
View all activity
Papers
A Simple Baseline for Streaming Video Understanding
OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
lmms-lab/Ferret-Bench
Viewer • Updated • 120 • 14 • 6
lmms-lab/HallusionBench
Viewer • Updated • 1.13k • 3.29k • 10
lmms-lab/COCO-Caption
Viewer • Updated • 81.3k • 4.43k • 12
lmms-lab/COCO-Caption2017
Viewer • Updated • 45.7k • 4.35k • 22
lmms-lab/flickr30k
Viewer • Updated • 31.8k • 4.91k • 18
lmms-lab/SEED-Bench-2
Viewer • Updated • 24.4k • 540 • 2
lmms-lab/SEED-Bench
Viewer • Updated • 18k • 12.3k • 4
lmms-lab/CMMMU
Viewer • Updated • 12k • 409 • 4
lmms-lab/MP-DocVQA
Viewer • Updated • 10.2k • 1.64k • 5
lmms-lab/ST-VQA
Viewer • Updated • 4.07k • 114 • 5
lmms-lab/RoboVQA
Preview • Updated • 41 • 1
lmms-lab/VQAv2
Viewer • Updated • 770k • 20.2k • 32
lmms-lab/DC200_CN
Viewer • Updated • 200 • 4
lmms-lab/DC100_EN
Preview • Updated • 15
lmms-lab/MME
Viewer • Updated • 2.37k • 36.5k • 29