Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration
This addresses a critical bottleneck for deploying MLLMs in real-world applications by accelerating them without retraining, though it is incremental as it builds on existing token reduction methods.
The paper tackles the computational inefficiency of Multimodal Large Language Models (MLLMs) due to quadratic complexity by proposing a training-free token reduction framework, achieving up to 14.7x FLOPs reduction with 93.6% performance retention.
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 ''filter-correlate-compress'' framework to accelerate the MLLM by systematically optimizing multimodal context length during prefilling. The framework first implements 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 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 correlated discarded tokens with a self-preserving compression, thereby preventing the dilution of their own core content. The framework's FiCoCo-L variant further leverages task-aware textual priors to perform token reduction directly within the LLM decoder. Extensive experiments demonstrate that the FiCoCo series effectively accelerates a range of MLLMs, achieves up to 14.7x FLOPs reduction with 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. Code: https://github.com/kawhiiiileo/FiCoCo