Large multimodal models still struggle with text-rich images because of inadequate training data. Self-Instruct provides an annotation-free way for generating instruction data, but its quality is poor, as multimodal alignment remains a hurdle even for the largest models. In this work, we propose LLaVAR-2, to enhance multimodal alignment for text-rich images through hybrid instruction generation between human annotators and large language models. Specifically, it involves detailed image captions from human annotators, followed by the use of these annotations in tailored text prompts for GPT-4o to curate a dataset. It also implements several mechanisms to filter out low-quality data, and the resulting dataset comprises 424k high-quality pairs of instructions. Empirical results show that models fine-tuned on this dataset exhibit impressive enhancements over those trained with self-instruct data.

Dronescapes is a collection of vibrant, mystical paintings of drones by Australian artist Kathryn Brimblecombe-Fox. In a conversation with the Center for the Study of the Drone, the artist shares the meaning of her work, explains her use of traditional Australian motifs, and shares her views on the rise of autonomous technology. The Federal Aviation Administration released a new set of reports of airspace incidents involving drones, including close encounters with manned aircraft and drone use over airports. The dataset includes 1,274 reported incidents that occurred between February and September 2016, around 400 more than occurred during the same period in 2015. At the National Interest, Elsa Kania argues that China could soon overtake the U.S. in the development of autonomous drones.