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/CAT-7B

CAT-7B

Reported on 26 benchmarks across 5 tasks · 1 paper · 3 SOTA

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

Reasoning16 results

Video Question AnsweringonMSRVTT-QA
Accuracy· 2024-03-07
62.1
best: 72.4 (Flash-VStream)
SOTA
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Video Question AnsweringonMSRVTT-QA
Confidence Score· 2024-03-07
3.5
best: 1.8 (Video LLaMA-7B)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Video Question AnsweringonActivityNet-QA
Accuracy· 2024-03-07
50.2
best: 61.6 (Tarsier (34B))
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Video Question AnsweringonActivityNet-QA
Confidence Score· 2024-03-07
3.5
best: 1.1 (Video LLaMA)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Generative Visual Question AnsweringonVideoInstruct
Consistency· 2024-03-07
2.89
best: 3.81 (PPLLaVA-7B-dpo)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Generative Visual Question AnsweringonVideoInstruct
Contextual Understanding· 2024-03-07
3.49
best: 4.21 (PPLLaVA-7B-dpo)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Generative Visual Question AnsweringonVideoInstruct
Correctness of Information· 2024-03-07
3.08
best: 3.85 (PPLLaVA-7B-dpo)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Generative Visual Question AnsweringonVideoInstruct
Detail Orientation· 2024-03-07
2.95
best: 3.56 (PPLLaVA-7B-dpo)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Generative Visual Question AnsweringonVideoInstruct
Temporal Understanding· 2024-03-07
2.81
best: 3.23 (VLM-RLAIF)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Generative Visual Question AnsweringonVideoInstruct
mean· 2024-03-07
3.07
best: 3.73 (PPLLaVA-7B-dpo)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Video-based Generative Performance BenchmarkingonVideoInstruct
Consistency· 2024-03-07
2.89
best: 3.81 (PPLLaVA-7B-dpo)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Video-based Generative Performance BenchmarkingonVideoInstruct
Contextual Understanding· 2024-03-07
3.49
best: 4.21 (PPLLaVA-7B-dpo)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Video-based Generative Performance BenchmarkingonVideoInstruct
Correctness of Information· 2024-03-07
3.08
best: 3.85 (PPLLaVA-7B-dpo)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Video-based Generative Performance BenchmarkingonVideoInstruct
Detail Orientation· 2024-03-07
2.95
best: 3.56 (PPLLaVA-7B-dpo)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Video-based Generative Performance BenchmarkingonVideoInstruct
Temporal Understanding· 2024-03-07
2.81
best: 3.23 (VLM-RLAIF)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Video-based Generative Performance BenchmarkingonVideoInstruct
mean· 2024-03-07
3.07
best: 3.73 (PPLLaVA-7B-dpo)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640

Natural Language Processing10 results

Question AnsweringonMSRVTT-QA
Accuracy· 2024-03-07
62.1
best: 72.4 (Flash-VStream)
SOTA
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Question AnsweringonActivityNet-QA
Accuracy· 2024-03-07
50.2
best: 61.6 (Tarsier (34B))
SOTA
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Question AnsweringonMSRVTT-QA
Confidence Score· 2024-03-07
3.5
best: 1.8 (Video LLaMA-7B)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Question AnsweringonActivityNet-QA
Confidence Score· 2024-03-07
3.5
best: 1.1 (Video LLaMA)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Visual Question Answering (VQA)onVideoInstruct
Consistency· 2024-03-07
2.89
best: 3.81 (PPLLaVA-7B-dpo)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Visual Question Answering (VQA)onVideoInstruct
Contextual Understanding· 2024-03-07
3.49
best: 4.21 (PPLLaVA-7B-dpo)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Visual Question Answering (VQA)onVideoInstruct
Correctness of Information· 2024-03-07
3.08
best: 3.85 (PPLLaVA-7B-dpo)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Visual Question Answering (VQA)onVideoInstruct
Detail Orientation· 2024-03-07
2.95
best: 3.56 (PPLLaVA-7B-dpo)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Visual Question Answering (VQA)onVideoInstruct
Temporal Understanding· 2024-03-07
2.81
best: 3.23 (VLM-RLAIF)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640
Visual Question Answering (VQA)onVideoInstruct
mean· 2024-03-07
3.07
best: 3.73 (PPLLaVA-7B-dpo)
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios arXiv:2403.04640