Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration

The quadratic complexity of Multimodal Large Language Models (MLLMs) with respect to context length poses significant computational and memory challenges, hindering their real-world deployment. In the paper, we devise a ``\textbf{\textit{filter-correlate-compress}}'' framework to accelerate the MLLM by systematically optimizing multimodal context length during prefilling. The framework first implements \textbf{\textit{FiCoCo-V}}, a training-free method operating within the vision encoder. It employs a redundancy-based token discard mechanism that uses a novel integrated metric to accurately \textit{filter} out redundant visual tokens. To mitigate information loss, the framework introduces a correlation-based information recycling mechanism that allows preserved tokens to selectively recycle information from \textit{correlate}d discarded tokens with a self-preserving \textit{compress}ion, thereby preventing the dilution of their own core content. The framework's \textbf{\textit{FiCoCo-L}} variant further leverages task-aware textual priors to perform token reduction directly within the LLM decoder. Extensive experiments demonstrate that the \textit{FiCoCo} series effectively accelerates a range of MLLMs, achieves up to \textbf{14.7×} FLOPs reduction with \textbf{93.6\%} performance retention. Our methods consistently outperform state-of-the-art training-free approaches, showcasing effectiveness and generalizability across model architectures, sizes, and tasks without requiring retraining. \textit{Code is available in supplementary materials.}