Encoder-free multimodal large language models(MLLMs) eliminate the need for a well-trained vision encoder by directly processing image tokens before the language model. While this approach reduces computational overhead and model complexity, it often requires large amounts of training data to effectively capture the visual knowledge typically encoded by vision models like CLIP. The absence of a vision encoder implies that the model is likely to rely on substantial data to learn the necessary visual-semantic alignments. In this work, we present BREEN, a data-efficient encoder-free multimodal architecture that mitigates this issue. BREEN leverages a learnable query and image experts to achieve comparable performance with significantly less training data. The learnable query, positioned between image and text tokens, is supervised by the output of a pretrained CLIP model to distill visual knowledge, bridging the gap between visual and textual modalities. Additionally, the image expert processes image tokens and learnable queries independently, improving efficiency and reducing interference with the LLM's textual capabilities. BREEN achieves comparable performance to prior encoder-free state-of-the-art models like Mono-InternVL, using only 13 million text-image pairs in training about one percent of the data required by existing methods. Our work highlights a promising direction for data-efficient encoder-free multimodal learning, offering an alternative to traditional encoder-based approaches.

One evening in September of 1957, viewers across America could turn on their television sets and tune in to a CBS broadcast during which a young woman dropped acid. She sat next to a man in a suit: Sidney Cohen, the researcher who had given her the LSD. The woman wore lipstick and nail polish, and her eyes were shining. "I wish I could talk in Technicolor," she said. And, at another point, "I can see the molecules. Were some families maybe--oh, I don't know--eating meat loaf on TV trays as they watched this nice lady undergo her mind-bending, molecule-revealing journey through inner space? Did they switch to "Father Knows Best" or "The Perry Como Show" afterward? One of the feats that the historian Benjamin Breen pulls off in his lively and engrossing new book, "Tripping on Utopia: Margaret Mead, the Cold War, and the Troubled Birth of Psychedelic Science" (Grand Central), is to make a cultural moment like the anonymous woman's televised trip seem less incongruous, if no less ...

The Minister of State for Trade, Employment, Business, EU Digital Single Market and Data Protection Pat Breen is keeping abreast of pioneering work in cutting edge technology. On Friday, he visited the University of Limerick's Digital District at the Park Point Facility in the city for a briefing with Dr Mary Shire, vice president of research and enterprise and Dr Ann Ledwith, Dean of Graduate and Professional Studies. The Digital District will host a newly established Digital Skills Academy, the Nexus Digital Accelerator and the confirm centre for smart manufacturing. Ireland's first Masters in Artificial Intelligence (AI) was launched on January 25 by the Minister for Business, Enterprise and Innovation, Heather Humphreys. The programme will run in UL's Digital District from September, in association with the Irish Centre for High End Computing.

For an industry that has proven resistant to change for centuries, insurance is now undergoing a digital revolution. With the advent of more machine learning algorithms, underwriters are bringing in more information to better gauge risk and offer more tailor-made premium pricing. On the back end, the insurance process is being streamlined to connect applicants with carriers more efficiently and with fewer errors. This drastic level of rapid change means big things for insurers and applicants alike. Here's how artificial intelligence, or AI, is on the frontier of the insurance industry and where it might be heading in years to come.

Social media has caused an explosion in the amount of data generated by people and businesses in the last five years. That has led to the rise of artificial intelligence and machine learning coupled with the input of humans to make sense of streams of data, according to experts on Argo Digital's panel Sunday at South by Southwest on "How Data and Machine Learning/AI Affect Risk Transfer in the 21st Century." Jason Abbruzzese, business reporter with Mashable, moderated the panel for Argo Digital, an emerging insure tech practice within property and casualty carrier Argo Group, based in San Antonio. By analyzing the data, all businesses are trying to make themselves smarter, said Andy Breen, senior vice president for Argo Digital and adjunct professor at NYU Stern School of Business and one of the panelists. Until recently, the tools did not exist to sift through all the data and extract insights that make a business operate better, he said.