Although current Multi-modal Large Language Models (MLLMs) demonstrate promising results in video understanding, processing extremely long videos remains an ongoing challenge. Typically, MLLMs struggle with handling thousands of visual tokens that exceed the maximum context length, and they suffer from the information decay due to token aggregation. Another challenge is the high computational cost stemming from the large number of video tokens. To tackle these issues, we propose Video-XL, an extra-long vision language model designed for efficient hour-scale video understanding. Specifically, we argue that LLMs can be adapted as effective visual condensers and propose Visual Context Latent Summarization which condenses visual contexts into highly compact forms. Extensive experiments demonstrate that our model achieves promising results on popular long video understanding benchmarks. For example, Video-XL outperforms the current state-of-the-art method on VNBench by nearly 10\% in accuracy. Moreover, Video-XL presents an impressive balance between efficiency and effectiveness, processing 2048 frames on a single 80GB GPU while achieving nearly 95% accuracy in the Needle-in-a-Haystack evaluation.
View on arXiv