lmms-lab/VideoChatGPT
Viewer • Updated • 3.49k • 413 • 11
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/egoschema
Viewer • Updated • 15.6k • 7.27k • 8
lmms-lab/worldqa
Viewer • Updated • 5.09k • 68 • 5
lmms-lab/OlympiadBench
Viewer • Updated • 8.48k • 817 • 5
lmms-lab/VQAv2-FewShot
Viewer • Updated • 1.98M • 24 • 1
lmms-lab/ai2d
Viewer • Updated • 3.09k • 11.7k • 21
lmms-lab/tiny-ai2d-irt
Viewer • Updated • 100 • 6
lmms-lab/MMBench
Viewer • Updated • 24k • 19.9k • 21
lmms-lab/OK-VQA
Viewer • Updated • 5.05k • 2.99k • 8
lmms-lab/ICON-QA
Viewer • Updated • 43k • 492 • 5
lmms-lab/IQ50
Viewer • Updated • 50 • 7 • 4
lmms-lab/VisitBench
Viewer • Updated • 1.36k • 8 • 3
lmms-lab/NLVR2
Viewer • Updated • 17.5k • 95 • 3
lmms-lab/VizWiz-VQA
Viewer • Updated • 12.3k • 8.24k • 7
lmms-lab/MMMU
Viewer • Updated • 11.6k • 30.7k • 7
lmms-lab/textvqa
Viewer • Updated • 45.3k • 23.4k • 23
lmms-lab/ChartQA
Viewer • Updated • 2.5k • 21.5k • 20
lmms-lab/GQA
Viewer • Updated • 24.2M • 25.6k • 28
lmms-lab/MMVet
Viewer • Updated • 218 • 3.05k • 4
lmms-lab/VizWiz-Caps
Viewer • Updated • 15.8k • 88 • 6
lmms-lab/MMBench_CN
Viewer • Updated • 13.2k • 132 • 3
lmms-lab/MMBench_EN
Viewer • Updated • 11.1k • 657 • 7
lmms-lab/ScienceQA
Viewer • Updated • 12.6k • 18.9k • 9
lmms-lab/llava-bench-coco
Viewer • Updated • 90 • 80 • 5
lmms-lab/llava-bench-in-the-wild
Viewer • Updated • 60 • 5.28k • 10
lmms-lab/ScienceQA-IMG
Viewer • Updated • 10.3k • 1.55k • 5
lmms-lab/TextCaps
Viewer • Updated • 28.4k • 1.02k • 14
lmms-lab/NoCaps
Viewer • Updated • 15.1k • 584 • 3
lmms-lab/RefCOCOplus
Viewer • Updated • 7.58k • 1.37k • 5
lmms-lab/RefCOCOg
Viewer • Updated • 12.6k • 1.39k • 9