MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning
Researchers have developed a new framework called MODF-SIR, which utilizes a lightweight Multimodal Large Language Model (MLLM) for social intelligence reasoning. The framework enhances both training and inference through knowledge distillation, focusing on precise localization of multi-modal social intelligence data. It also incorporates Test-Time Adaptation (TTA) and Low-Rank Adaptation (LoRA) to improve instance-level reasoning and handle long-tail events effectively. AI
IMPACT Introduces a novel approach to social intelligence reasoning in AI, potentially improving performance on complex reasoning tasks.