Abstract
Video Large Language Models (Video LLMs) have achieved remarkable results in video understanding tasks. However, they often suffer from heavy computational overhead due to the large number of visual tokens generated from multiple video frames. Existing visual token compression methods often rely on attention scores from language models as guidance. However, these scores exhibit inherent biases: global bias reflects a tendency to focus on the two ends of the visual token sequence, while local bias leads to an over-concentration on the same spatial positions across different frames. To address the issue of attention bias, we propose ttention-ebised oken runing for Video Large Language Models (), a novel token pruning pipeline for Video LLMs. AdaTP integrates two dedicated debiasing modules into the pipeline, targeting global attention bias and local attention bias, respectively. Without th