paper-with-me

Temporal/Casual QA 벤치마크

Temporal/Casual QA on NExT-QA

8개 결과 · ⬇ CSV · JSON

WUPS

23.4 27.12 30.85 34.57 38.3 2022-04 2026-09 Flamingo(32-shot) — 33.5 (2022-04-29) Flamingo(0-shot) — 26.7 (2022-04-29) PaLI-X — 38.3 (2023-05-29) R2A — 34.7 (2023-06-15) Emu(0-shot) — 23.4 (2023-07-11) PaLI-3 — 37.7 (2023-10-13) Gemini Ultra (zero-shot) — 29.9 (2023-12-19) Gemini Pro (zero-shot) — 28.0 (2023-12-19) Flamingo(32-shot) — 33.5 (2022-04-29) PaLI-X — 38.3 (2023-05-29)
RankModel WUPS Extra Training Data PaperCodeYear
1 PaLI-X 38.3 ✓ PaLI-X: On Scaling up a Multilingual Vision and Language Model kyegomez/PALI · doc-doc/NExT-OE 2023
2 PaLI-3 37.7 ✓ PaLI-3 Vision Language Models: Smaller, Faster, Stronger kyegomez/PALI3 2023
3 R2A 34.7 ✓ Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models 2023
4 Flamingo(32-shot) 33.5 ✓ Flamingo: a Visual Language Model for Few-Shot Learning mlfoundations/open_flamingo · lucidrains/flamingo-pytorch · unispac/visual-adversarial-examples-jailbreak-large-language-models · +2 2022
5 Gemini Ultra (zero-shot) 29.9 Gemini: A Family of Highly Capable Multimodal Models valdecy/pybibx 2023
6 Gemini Pro (zero-shot) 28.0 Gemini: A Family of Highly Capable Multimodal Models valdecy/pybibx 2023
7 Flamingo(0-shot) 26.7 ✓ Flamingo: a Visual Language Model for Few-Shot Learning mlfoundations/open_flamingo · lucidrains/flamingo-pytorch · unispac/visual-adversarial-examples-jailbreak-large-language-models · +2 2022
8 Emu(0-shot) 23.4 ✓ Emu: Generative Pretraining in Multimodality baaivision/emu · doc-doc/NExT-OE 2023
1–8 / 8 페이지당 10 20 50 100