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/LITA-13B

LITA-13B

Reported on 18 benchmarks across 3 tasks · 1 paper

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

Reasoning12 results

Generative Visual Question AnsweringonVideoInstruct
Consistency· 2024-03-27
3.19
best: 3.81 (PPLLaVA-7B-dpo)
LITA: Language Instructed Temporal-Localization Assistant arXiv:2403.19046
Generative Visual Question AnsweringonVideoInstruct
Contextual Understanding· 2024-03-27
3.43
best: 4.21 (PPLLaVA-7B-dpo)
LITA: Language Instructed Temporal-Localization Assistant arXiv:2403.19046
Generative Visual Question AnsweringonVideoInstruct
Correctness of Information· 2024-03-27
2.94
best: 3.85 (PPLLaVA-7B-dpo)
LITA: Language Instructed Temporal-Localization Assistant arXiv:2403.19046
Generative Visual Question AnsweringonVideoInstruct
Detail Orientation· 2024-03-27
2.98
best: 3.56 (PPLLaVA-7B-dpo)
LITA: Language Instructed Temporal-Localization Assistant arXiv:2403.19046
Generative Visual Question AnsweringonVideoInstruct
Temporal Understanding· 2024-03-27
2.68
best: 3.23 (VLM-RLAIF)
LITA: Language Instructed Temporal-Localization Assistant arXiv:2403.19046
Generative Visual Question AnsweringonVideoInstruct
mean· 2024-03-27
3.04
best: 3.73 (PPLLaVA-7B-dpo)
LITA: Language Instructed Temporal-Localization Assistant arXiv:2403.19046
Video-based Generative Performance BenchmarkingonVideoInstruct
Consistency· 2024-03-27
3.19
best: 3.81 (PPLLaVA-7B-dpo)
LITA: Language Instructed Temporal-Localization Assistant arXiv:2403.19046
Video-based Generative Performance BenchmarkingonVideoInstruct
Contextual Understanding· 2024-03-27
3.43
best: 4.21 (PPLLaVA-7B-dpo)
LITA: Language Instructed Temporal-Localization Assistant arXiv:2403.19046
Video-based Generative Performance BenchmarkingonVideoInstruct
Correctness of Information· 2024-03-27
2.94
best: 3.85 (PPLLaVA-7B-dpo)
LITA: Language Instructed Temporal-Localization Assistant arXiv:2403.19046
Video-based Generative Performance BenchmarkingonVideoInstruct
Detail Orientation· 2024-03-27
2.98
best: 3.56 (PPLLaVA-7B-dpo)
LITA: Language Instructed Temporal-Localization Assistant arXiv:2403.19046
Video-based Generative Performance BenchmarkingonVideoInstruct
Temporal Understanding· 2024-03-27
2.68
best: 3.23 (VLM-RLAIF)
LITA: Language Instructed Temporal-Localization Assistant arXiv:2403.19046
Video-based Generative Performance BenchmarkingonVideoInstruct
mean· 2024-03-27
3.04
best: 3.73 (PPLLaVA-7B-dpo)
LITA: Language Instructed Temporal-Localization Assistant arXiv:2403.19046

Natural Language Processing6 results

Visual Question Answering (VQA)onVideoInstruct
Consistency· 2024-03-27
3.19
best: 3.81 (PPLLaVA-7B-dpo)
LITA: Language Instructed Temporal-Localization Assistant arXiv:2403.19046
Visual Question Answering (VQA)onVideoInstruct
Contextual Understanding· 2024-03-27
3.43
best: 4.21 (PPLLaVA-7B-dpo)
LITA: Language Instructed Temporal-Localization Assistant arXiv:2403.19046
Visual Question Answering (VQA)onVideoInstruct
Correctness of Information· 2024-03-27
2.94
best: 3.85 (PPLLaVA-7B-dpo)
LITA: Language Instructed Temporal-Localization Assistant arXiv:2403.19046
Visual Question Answering (VQA)onVideoInstruct
Detail Orientation· 2024-03-27
2.98
best: 3.56 (PPLLaVA-7B-dpo)
LITA: Language Instructed Temporal-Localization Assistant arXiv:2403.19046
Visual Question Answering (VQA)onVideoInstruct
Temporal Understanding· 2024-03-27
2.68
best: 3.23 (VLM-RLAIF)
LITA: Language Instructed Temporal-Localization Assistant arXiv:2403.19046
Visual Question Answering (VQA)onVideoInstruct
mean· 2024-03-27
3.04
best: 3.73 (PPLLaVA-7B-dpo)
LITA: Language Instructed Temporal-Localization Assistant arXiv:2403.19046