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/LLaVA-Video-7B

LLaVA-Video-7B

Reported on 10 benchmarks across 1 task · 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 Processing10 results

  • Visual Question Answering (VQA)onVLM2-Bench
    Average Score on VLM2-bench (9 subtasks)· 2024-10-03
    43.32
    best: 60.36 (GPT-4o)
    SOTA
    Video Instruction Tuning With Synthetic DataarXiv:2410.02713
  • Visual Question Answering (VQA)onVLM2-Bench
    PC-VID· 2024-10-03
    59
    best: 66.75 (GPT-4o)
    SOTA
    Video Instruction Tuning With Synthetic DataarXiv:2410.02713
  • Visual Question Answering (VQA)onVLM2-Bench
    PC-cnt· 2024-10-03
    66.91
    best: 90.5 (GPT-4o)
    SOTA
    Video Instruction Tuning With Synthetic DataarXiv:2410.02713
  • Visual Question Answering (VQA)onVLM2-Bench
    GC-mat· 2024-10-03
    18.53
    best: 37.45 (GPT-4o)
    Video Instruction Tuning With Synthetic DataarXiv:2410.02713
  • Visual Question Answering (VQA)onVLM2-Bench
    GC-trk· 2024-10-03
    12.79
    best: 43.38 (Qwen2.5-VL-7B)
    Video Instruction Tuning With Synthetic DataarXiv:2410.02713
  • Visual Question Answering (VQA)onVLM2-Bench
    OC-cnt· 2024-10-03
    62.47
    best: 80.62 (GPT-4o)
    Video Instruction Tuning With Synthetic DataarXiv:2410.02713
  • Visual Question Answering (VQA)onVLM2-Bench
    OC-cpr· 2024-10-03
    54.72
    best: 74.17 (GPT-4o)
    Video Instruction Tuning With Synthetic DataarXiv:2410.02713
  • Visual Question Answering (VQA)onVLM2-Bench
    OC-grp· 2024-10-03
    28.5
    best: 57.5 (GPT-4o)
    Video Instruction Tuning With Synthetic DataarXiv:2410.02713
  • Visual Question Answering (VQA)onVLM2-Bench
    PC-cpr· 2024-10-03
    62
    best: 80 (Qwen2.5-VL-7B)
    Video Instruction Tuning With Synthetic DataarXiv:2410.02713
  • Visual Question Answering (VQA)onVLM2-Bench
    PC-grp· 2024-10-03
    25
    best: 69 (Qwen2.5-VL-7B)
    Video Instruction Tuning With Synthetic DataarXiv:2410.02713