A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913779662454784 |
|---|---|
| author | Li, Zongxia Wu, Xiyang Du, Hongyang Liu, Fuxiao Nghiem, Huy Shi, Guangyao |
| author_facet | Li, Zongxia Wu, Xiyang Du, Hongyang Liu, Fuxiao Nghiem, Huy Shi, Guangyao |
| contents | Multimodal Vision Language Models (VLMs) have emerged as a transformative topic at the intersection of computer vision and natural language processing, enabling machines to perceive and reason about the world through both visual and textual modalities. For example, models such as CLIP, Claude, and GPT-4V demonstrate strong reasoning and understanding abilities on visual and textual data and beat classical single modality vision models on zero-shot classification [93]. With their rapid advancements in research and growing popularity in various applications, we provide a comprehensive survey of VLMs. Specifically, we provide a systematic overview of VLMs in the following aspects: [1] model information of the major VLMs developed up to 2025; [2] the transition of VLM architectures and the newest VLM alignment methods; [3] summary and categorization of the popular benchmarks and evaluation metrics of VLMs; [4] the challenges and issues faced by current VLMs such as hallucination, alignment, fairness, and safety. Detailed collections including papers and model repository links are listed in https://github.com/zli12321/Vision-Language-Models-Overview. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_02189 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges Li, Zongxia Wu, Xiyang Du, Hongyang Liu, Fuxiao Nghiem, Huy Shi, Guangyao Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning Robotics Multimodal Vision Language Models (VLMs) have emerged as a transformative topic at the intersection of computer vision and natural language processing, enabling machines to perceive and reason about the world through both visual and textual modalities. For example, models such as CLIP, Claude, and GPT-4V demonstrate strong reasoning and understanding abilities on visual and textual data and beat classical single modality vision models on zero-shot classification [93]. With their rapid advancements in research and growing popularity in various applications, we provide a comprehensive survey of VLMs. Specifically, we provide a systematic overview of VLMs in the following aspects: [1] model information of the major VLMs developed up to 2025; [2] the transition of VLM architectures and the newest VLM alignment methods; [3] summary and categorization of the popular benchmarks and evaluation metrics of VLMs; [4] the challenges and issues faced by current VLMs such as hallucination, alignment, fairness, and safety. Detailed collections including papers and model repository links are listed in https://github.com/zli12321/Vision-Language-Models-Overview. |
| title | A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning Robotics |
| url | https://arxiv.org/abs/2501.02189 |