Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

Models/LLaMA-VID-7B (2 Token)

LLaMA-VID-7B (2 Token)

Reported on 31 benchmarks across 5 tasks · 1 paper

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

Reasoning20 results

Video Question AnsweringonActivityNet-QA
Accuracy· 2023-11-28
47.4
best: 61.6 (Tarsier (34B))
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Video Question AnsweringonActivityNet-QA
Confidence score· 2023-11-28
3.3
best: 2.2 (Video Chat)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Video Question AnsweringonMSVD-QA
Accuracy· 2023-11-28
69.7
best: 80.3 (Tarsier (34B))
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Video Question AnsweringonMSVD-QA
Confidence Score· 2023-11-28
3.7
best: 2.5 (Video LLaMA-7B)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Video Question AnsweringonMSRVTT-QA
Accuracy· 2023-11-28
57.7
best: 72.4 (Flash-VStream)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Video Question AnsweringonMSRVTT-QA
Confidence Score· 2023-11-28
3.2
best: 1.8 (Video LLaMA-7B)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Video Question AnsweringonActivityNet-QA
Accuracy· 2023-11-28
47.4
best: 61.6 (Tarsier (34B))
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Video Question AnsweringonActivityNet-QA
Confidence Score· 2023-11-28
3.3
best: 1.1 (Video LLaMA)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Generative Visual Question AnsweringonVideoInstruct
Consistency· 2023-11-28
2.51
best: 3.81 (PPLLaVA-7B-dpo)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Generative Visual Question AnsweringonVideoInstruct
Contextual Understanding· 2023-11-28
3.53
best: 4.21 (PPLLaVA-7B-dpo)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Generative Visual Question AnsweringonVideoInstruct
Correctness of Information· 2023-11-28
2.96
best: 3.85 (PPLLaVA-7B-dpo)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Generative Visual Question AnsweringonVideoInstruct
Detail Orientation· 2023-11-28
3
best: 3.56 (PPLLaVA-7B-dpo)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Generative Visual Question AnsweringonVideoInstruct
Temporal Understanding· 2023-11-28
2.46
best: 3.23 (VLM-RLAIF)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Generative Visual Question AnsweringonVideoInstruct
mean· 2023-11-28
2.89
best: 3.73 (PPLLaVA-7B-dpo)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Video-based Generative Performance BenchmarkingonVideoInstruct
Consistency· 2023-11-28
2.51
best: 3.81 (PPLLaVA-7B-dpo)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Video-based Generative Performance BenchmarkingonVideoInstruct
Contextual Understanding· 2023-11-28
3.53
best: 4.21 (PPLLaVA-7B-dpo)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Video-based Generative Performance BenchmarkingonVideoInstruct
Correctness of Information· 2023-11-28
2.96
best: 3.85 (PPLLaVA-7B-dpo)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Video-based Generative Performance BenchmarkingonVideoInstruct
Detail Orientation· 2023-11-28
3
best: 3.56 (PPLLaVA-7B-dpo)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Video-based Generative Performance BenchmarkingonVideoInstruct
Temporal Understanding· 2023-11-28
2.46
best: 3.23 (VLM-RLAIF)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Video-based Generative Performance BenchmarkingonVideoInstruct
mean· 2023-11-28
2.89
best: 3.73 (PPLLaVA-7B-dpo)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043

Natural Language Processing12 results

Question AnsweringonMSVD-QA
Accuracy· 2023-11-28
69.7
best: 80.3 (Tarsier (34B))
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Question AnsweringonMSVD-QA
Confidence Score· 2023-11-28
3.7
best: 2.5 (Video LLaMA-7B)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Question AnsweringonMSRVTT-QA
Accuracy· 2023-11-28
57.7
best: 72.4 (Flash-VStream)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Question AnsweringonMSRVTT-QA
Confidence Score· 2023-11-28
3.2
best: 1.8 (Video LLaMA-7B)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Question AnsweringonActivityNet-QA
Accuracy· 2023-11-28
47.4
best: 61.6 (Tarsier (34B))
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Question AnsweringonActivityNet-QA
Confidence Score· 2023-11-28
3.3
best: 1.1 (Video LLaMA)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Visual Question Answering (VQA)onVideoInstruct
Consistency· 2023-11-28
2.51
best: 3.81 (PPLLaVA-7B-dpo)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Visual Question Answering (VQA)onVideoInstruct
Contextual Understanding· 2023-11-28
3.53
best: 4.21 (PPLLaVA-7B-dpo)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Visual Question Answering (VQA)onVideoInstruct
Correctness of Information· 2023-11-28
2.96
best: 3.85 (PPLLaVA-7B-dpo)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Visual Question Answering (VQA)onVideoInstruct
Detail Orientation· 2023-11-28
3
best: 3.56 (PPLLaVA-7B-dpo)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Visual Question Answering (VQA)onVideoInstruct
Temporal Understanding· 2023-11-28
2.46
best: 3.23 (VLM-RLAIF)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043
Visual Question Answering (VQA)onVideoInstruct
mean· 2023-11-28
2.89
best: 3.73 (PPLLaVA-7B-dpo)
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models arXiv:2311.17043