Qifu Technology's Paper Accepted by IJCAI 2025, Using MLLM to Pave New Path in Fintech

Company Overview - Qifu Technology, a leading fintech company in China, has achieved a significant milestone by having its research paper accepted at the prestigious International Joint Conference on Artificial Intelligence (IJCAI) 2025 [1][2] - The company is listed on NASDAQ (QFIN) and HKEX (3660) [1] Research Achievement - The paper titled "Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning" focuses on Compositional Zero-Shot Learning, which aims to identify novel combinations of attributes and objects using existing knowledge [3] - The acceptance rate for IJCAI is only 19.3%, highlighting the competitiveness and prestige of the conference [2] Technological Innovation - The research introduces an innovative framework named TRIDENT, which integrates Multimodal Large Language Model (MLLM) embeddings and attribute smoothing to overcome traditional challenges in the field [3] - TRIDENT utilizes modules like Feature Adaptive Aggregation (FAA) to mitigate background noise and enhance semantic representation, demonstrating state-of-the-art performance across multiple datasets [3] Applications in Fintech - In the fintech sector, TRIDENT shows potential in intelligent risk control by analyzing multimodal data to detect emerging fraud patterns more quickly than traditional models, thereby improving assessment accuracy and reducing losses [4] - The framework also enhances customer service by enabling a more precise understanding of complex user inquiries, leading to personalized and efficient support [4] Commitment to AI Innovation - This achievement underscores Qifu Technology's commitment to AI innovation, with plans to increase R&D investment and deepen collaborations with academic institutions to drive advancements in AI applications [5]