VILA-1.5 (34B)

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA

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

Natural Language Processing2 results

Question AnsweringonVideo-MME (w/o subs)
Accuracy (%)· 2023-12-12
61.4
best: 77.4 (Video-RAG (based on LLaVA-Video))
SOTA
VILA: On Pre-training for Visual Language Models arXiv:2312.07533
Question AnsweringonVideo-MME
Accuracy (%)· 2023-12-12
64.1
best: 81.3 (Gemini 1.5 Pro)
SOTA
VILA: On Pre-training for Visual Language Models arXiv:2312.07533

Reasoning2 results

Video Question AnsweringonVideo-MME (w/o subs)
Accuracy (%)· 2023-12-12
61.4
best: 77.4 (Video-RAG (based on LLaVA-Video))
SOTA
VILA: On Pre-training for Visual Language Models arXiv:2312.07533
Video Question AnsweringonVideo-MME
Accuracy (%)· 2023-12-12
64.1
best: 81.3 (Gemini 1.5 Pro)
SOTA
VILA: On Pre-training for Visual Language Models arXiv:2312.07533