TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/CuMo-7B

CuMo-7B

Reported on 7 benchmarks across 3 tasks · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing7 results

  • Visual Question Answering (VQA)onMMBench
    GPT-3.5 score· 2024-05-09
    73
    best: 73.8 (LLaVA-InternLM2-ViT + MoSLoRA)
    SOTA
    CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-ExpertsarXiv:2405.05949
  • Instruction FollowingonLLaVA-Bench
    avg score· 2024-05-09
    85.7
    SOTA
    CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-ExpertsarXiv:2405.05949
  • Visual Question AnsweringonMMBench
    GPT-3.5 score· 2024-05-09
    73
    best: 73.8 (LLaVA-InternLM2-ViT + MoSLoRA)
    SOTA
    CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-ExpertsarXiv:2405.05949
  • Visual Question Answering (VQA)onGQA test-dev
    Accuracy· uses extra data· 2024-05-09
    64.9
    best: 72.1 (CFR)
    CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-ExpertsarXiv:2405.05949
  • Visual Question Answering (VQA)onVQA v2 test-dev
    Accuracy· uses extra data· 2024-05-09
    82.2
    best: 84.3 (PaLI)
    CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-ExpertsarXiv:2405.05949
  • Visual Question Answering (VQA)onMM-Vet
    GPT-4 score· 2024-05-09
    51
    best: 74.24 (MMCTAgent (GPT-4 + GPT-4V))
    CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-ExpertsarXiv:2405.05949
  • Visual Question AnsweringonMM-Vet
    GPT-4 score· 2024-05-09
    51
    best: 74.24 (MMCTAgent (GPT-4 + GPT-4V))
    CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-ExpertsarXiv:2405.05949