CL-VISTA: Benchmarking Continual Learning in Video Large Language Models
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 catast...
| Authors | Haiyang Guo, Yichen Shi, Fei Zhu et al. |
|---|---|
| Primary category | cs.CV |
| Published | 1 April 2026 |
| Last updated at source | 1 April 2026 |
Models and datasets referencing this paper
- MLLM-CL/CL-VISTADataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.