lmms-lab/RefCOCOg
Viewer
•
Updated
•
12.6k
•
1.45k
•
9
AI & ML interests
Feeling and building the multimodal intelligence.
Recent Activity
Papers
OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
lmms-lab/RefCOCO
Viewer
•
Updated
•
17.6k
•
3.57k
•
28
lmms-lab/Ferret-Bench
Viewer
•
Updated
•
120
•
29
•
6
lmms-lab/HallusionBench
Viewer
•
Updated
•
1.13k
•
1.82k
•
9
lmms-lab/COCO-Caption
Viewer
•
Updated
•
81.3k
•
3.9k
•
12
lmms-lab/COCO-Caption2017
Viewer
•
Updated
•
45.7k
•
3.99k
•
22
lmms-lab/flickr30k
Viewer
•
Updated
•
31.8k
•
3.6k
•
18
lmms-lab/SEED-Bench-2
Viewer
•
Updated
•
24.4k
•
248
•
2
lmms-lab/SEED-Bench
Viewer
•
Updated
•
18k
•
5.21k
•
4
lmms-lab/CMMMU
Viewer
•
Updated
•
12k
•
200
•
4
lmms-lab/MP-DocVQA
Viewer
•
Updated
•
10.2k
•
728
•
4
lmms-lab/ST-VQA
Viewer
•
Updated
•
4.07k
•
86
•
5
lmms-lab/RoboVQA
Preview
•
Updated
•
6
•
1
lmms-lab/VQAv2
Viewer
•
Updated
•
770k
•
9.81k
•
28
lmms-lab/DC200_CN
Viewer
•
Updated
•
200
•
7
lmms-lab/DC100_EN
Preview
•
Updated
•
8
lmms-lab/MME
Viewer
•
Updated
•
2.37k
•
25.6k
•
27