We present the Mu-SHROOM shared task which is focused on detecting hallucinations and other overgeneration mistakes in the output of instruction-tuned large language models (LLMs). Mu-SHROOM addresses general-purpose LLMs in 14 languages, and frames the hallucination detection problem as a span-labeling task. We received 2,618 submissions from 43 participating teams employing diverse methodologies. The large number of submissions underscores the interest of the community in hallucination detection. We present the results of the participating systems and conduct an empirical analysis to identify key factors contributing to strong performance in this task. We also emphasize relevant current challenges, notably the varying degree of hallucinations across languages and the high annotator disagreement when labeling hallucination spans.

The Metaverse is driving the next wave of innovation for new opportunities by replacing the digital world (Internet) with the virtual world through a single, shared, immersive, persistent 3D virtual space. In this paper, we present requirements, architecture, standards, challenges, and solutions for Metaverse. Specifically, we provide Metaverse architecture and requirements, and different standards for Metaverse which serve as the basis for the development and deployment. Moreover, we present recent status, challenges such as integration of AI and Metaverse, security and privacy in Metaverse, etc., and perspectives and solutions.

The human ear is generally universal, collectible, distinct, and permanent. Ear-based biometric recognition is a niche and recent approach that is being explored. For any ear-based biometric algorithm to perform well, ear detection and segmentation need to be accurately performed. While significant work has been done in existing literature for bounding boxes, a lack of approaches output a segmentation mask for ears. This paper trains and compares three newer models to the state-of-the-art MaskRCNN (ResNet 101 +FPN) model across four different datasets. The Average Precision (AP) scores reported show that the newer models outperform the state-of-the-art but no one model performs the best over multiple datasets.

The Defense Department, Army and Howard University linked up to collectively push forward artificial intelligence and machine learning-rooted research, technologies and applications through a recently unveiled center of excellence. Work it will underpin will "shape the future," according to an announcement Monday from the Army Research Laboratory--and the $7.5 million center also marks a move by the Pentagon to help expand its pipeline for future personnel. "Diversity of science and diversity of the future [science and technology] talent base go hand-in-hand in this new and exciting partnership," Dr. Brian Sadler, Army senior research scientist for intelligent systems said. Tapped to manage the partnership, Sadler added that Howard University is "an intellectual center for the nation." Encompassing 13 schools and colleges, the institution is a private, historically Black research university that was founded in 1867.

The work will hone in on military-centered machine learning application development, research into trustworthy AI tech--and could help boost DoD's …

We propose a method to efficiently learn diverse strategies in reinforcement learning for query reformulation in the tasks of document retrieval and question answering. In the proposed framework an agent consists of multiple specialized sub-agents and a meta-agent that learns to aggregate the answers from sub-agents to produce a final answer. Sub-agents are trained on disjoint partitions of the training data, while the meta-agent is trained on the full training set. Our method makes learning faster, because it is highly parallelizable, and has better generalization performance than strong baselines, such as an ensemble of agents trained on the full data. We show that the improved performance is due to the increased diversity of reformulation strategies.

Google is opening a university in California to train African-American computer science majors in intensive coding instruction. Josh King has the story (@abridgetoland). Google is opening up the Howard West program to 100 students from Howard and other historically black universities and colleges for a full academic year starting this fall. SAN FRANCISCO -- Last summer, Howard University dispatched 26 students to Google's Mountain View, Calif., campus for an intensive 12-week course on coding. The experimental test run boosted students' technical chops and their confidence, and now -- starting in the fall -- the Internet giant is opening the program to 100 students from Howard and other historically black colleges and universities for a full academic year.