CL-VISTA: Benchmarking Continual Learning in Video Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914437097586688 |
|---|---|
| author | Guo, Haiyang Shi, Yichen Zhu, Fei Liu, Wenzhuo Zhao, Hongbo Zeng, Fanhu Ma, Shijie Wang, Da-Han Zhang, Xu-Yao |
| author_facet | Guo, Haiyang Shi, Yichen Zhu, Fei Liu, Wenzhuo Zhao, Hongbo Zeng, Fanhu Ma, Shijie Wang, Da-Han Zhang, Xu-Yao |
| contents | Video Large Language Models (Video-LLMs) require continual learning to adapt to non-stationary real-world data. However, existing benchmarks fall short of evaluating modern foundation models: many still rely on models without large-scale pre-training, and prevailing benchmarks typically partition a single dataset into sub-tasks, resulting in high task redundancy and negligible forgetting on pre-trained Video-LLMs. To address these limitations, we propose CL-VISTA, a benchmark tailored for continual video understanding of Video-LLMs. By curating 8 diverse tasks spanning perception, understanding, and reasoning, CL-VISTA induces substantial distribution shifts that effectively expose catastrophic forgetting. To systematically assess CL methods, we establish a comprehensive evaluation framework comprising 6 distinct protocols across 3 critical dimensions: performance, computational efficiency, and memory footprint. Notably, the performance dimension incorporates a general video understanding assessment to assess whether CL methods genuinely enhance foundational intelligence or merely induce task-specific overfitting. Extensive benchmarking of 10 mainstream CL methods reveals a fundamental trade-off: no single approach achieves universal superiority across all dimensions. Methods that successfully mitigate catastrophic forgetting tend to compromise generalization or incur prohibitive computational and memory overheads. We hope CL-VISTA provides critical insights for advancing continual learning in multimodal foundation models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_00677 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CL-VISTA: Benchmarking Continual Learning in Video Large Language Models Guo, Haiyang Shi, Yichen Zhu, Fei Liu, Wenzhuo Zhao, Hongbo Zeng, Fanhu Ma, Shijie Wang, Da-Han Zhang, Xu-Yao Computer Vision and Pattern Recognition Video Large Language Models (Video-LLMs) require continual learning to adapt to non-stationary real-world data. However, existing benchmarks fall short of evaluating modern foundation models: many still rely on models without large-scale pre-training, and prevailing benchmarks typically partition a single dataset into sub-tasks, resulting in high task redundancy and negligible forgetting on pre-trained Video-LLMs. To address these limitations, we propose CL-VISTA, a benchmark tailored for continual video understanding of Video-LLMs. By curating 8 diverse tasks spanning perception, understanding, and reasoning, CL-VISTA induces substantial distribution shifts that effectively expose catastrophic forgetting. To systematically assess CL methods, we establish a comprehensive evaluation framework comprising 6 distinct protocols across 3 critical dimensions: performance, computational efficiency, and memory footprint. Notably, the performance dimension incorporates a general video understanding assessment to assess whether CL methods genuinely enhance foundational intelligence or merely induce task-specific overfitting. Extensive benchmarking of 10 mainstream CL methods reveals a fundamental trade-off: no single approach achieves universal superiority across all dimensions. Methods that successfully mitigate catastrophic forgetting tend to compromise generalization or incur prohibitive computational and memory overheads. We hope CL-VISTA provides critical insights for advancing continual learning in multimodal foundation models. |
| title | CL-VISTA: Benchmarking Continual Learning in Video Large Language Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.00677 |