Stage-adaptive Token Selection for Efficient Omni-modal LLMs
Researchers have developed SEATS, a new method to make omni-modal large language models (om-LLMs) more efficient. SEATS prunes redundant audio-visual tokens throughout the model's layers, adapting the token selection process based on cross-modal fusion. This approach significantly reduces computational load and speeds up inference while maintaining high performance. AI
IMPACT Reduces computational overhead and speeds up inference for multi-modal LLMs, potentially lowering deployment costs.