Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) technology is an effective method to improve the performance of Large Language Models (LLMs) in medical question answering tasks. However, there is an inherent difference between structured knowledge graphs and sequential LLMs. The existing method of converting triples of knowledge graph into text through predefined templates leads to loss of structural information and excessive context length, resulting in alignment difficulties between the two. In this paper, we propose a GNN-LLM Aligned Medical knowledge QuestionAnswering model (GLAM-QA). The model first pretrains a GNN to extract structural information from the knowledge graph, realizes the interactive fusion of graph representations and LLM vocabulary embeddings through a cross attention layer, and then generates graph tokens via a projector for input to the LLM. It can retain graph structural information without finetuning the LLM and provide accurate and concise answers. Experiments on three public datasets show that compared with five comparative algorithms, the proposed GLAM-QA achieves better performance in BertScore, F1-Score, and BLEU-1 metrics. This research provides an effective solution to the alignment problem between knowledge graphs and LLMs, and improves the accuracy and practicality of medical question answering systems.

Recent progress in diffusion models has revolutionized the popular technology of text-to-image generation. While existing approaches could produce photorealistic high-resolution images with text conditions, there are still several open problems to be solved, which limits the further improvement of image fidelity and text relevancy. In this paper, we propose ERNIE-ViLG 2.0, a large-scale Chinese text-to-image diffusion model, to progressively upgrade the quality of generated images by: (1) incorporating fine-grained textual and visual knowledge of key elements in the scene, and (2) utilizing different denoising experts at different denoising stages. With the proposed mechanisms, ERNIE-ViLG 2.01not only achieves a new state-of-the-art on MS-COCO with zero-shot FID-30k score of 6.75, but also significantly outperforms recent models in terms of image fidelity and image-text alignment, with side-by-side human evaluation on the bilingual prompt set ViLG-300.

Estimated time of arrival (ETA) prediction, also known as travel time estimation, is a fundamental task for a wide range of intelligent transportation applications, such as navigation, route planning, and ride-hailing services. To accurately predict the travel time of a route, it is essential to take into account both contextual and predictive factors, such as spatial-temporal interaction, driving behavior, and traffic congestion propagation inference. The ETA prediction models previously deployed at Baidu Maps have addressed the factors of spatial-temporal interaction (ConSTGAT) and driving behavior (SSML). In this work, we believe that modeling traffic congestion propagation patterns is of great importance toward accurately performing ETA prediction, and we focus on this factor to improve ETA performance. Traffic congestion propagation pattern modeling is challenging, and it requires accounting for impact regions over time and cumulative effect of delay variations over time caused by traffic events on the road network. In this paper, we present a practical industrial-grade ETA prediction framework named DuETA. Specifically, we construct a congestion-sensitive graph based on the correlations of traffic patterns, and we develop a route-aware graph transformer to directly learn the long-distance correlations of the road segments. This design enables DuETA to capture the interactions between the road segment pairs that are spatially distant but highly correlated with traffic conditions. Extensive experiments are conducted on large-scale, real-world datasets collected from Baidu Maps. Experimental results show that ETA prediction can significantly benefit from the learned traffic congestion propagation patterns, which demonstrates the effectiveness and practical applicability of DuETA. In addition, DuETA has already been deployed in production at Baidu Maps, serving billions of requests every day. This demonstrates that DuETA is an industrial-grade and robust solution for large-scale ETA prediction services.