We introduce the Concept Bottleneck Large Language Model (CB-LLM), a pioneering approach to creating inherently interpretable Large Language Models (LLMs). Unlike traditional black-box LLMs that rely on post-hoc interpretation methods with limited neuron function insights, CB-LLM sets a new standard with its built-in interpretability, scalability, and ability to provide clear, accurate explanations. We investigate two essential tasks in the NLP domain: text classification and text generation. In text classification, CB-LLM narrows the performance gap with traditional black-box models and provides clear interpretability. In text generation, we show how interpretable neurons in CB-LLM can be used for concept detection and steering text generation. Our CB-LLMs enable greater interaction between humans and LLMs across a variety of tasks -- a feature notably absent in existing LLMs. Large Language Models (LLMs) have become instrumental in advancing Natural Language Processing (NLP) tasks.

Multifidelity surrogate modelling combines data of varying accuracy and cost from different sources. It strategically uses low-fidelity models for rapid evaluations, saving computational resources, and high-fidelity models for detailed refinement. It improves decision-making by addressing uncertainties and surpassing the limits of single-fidelity models, which either oversimplify or are computationally intensive. Blending high-fidelity data for detailed responses with frequent low-fidelity data for quick approximations facilitates design optimisation in various domains. Despite progress in interpolation, regression, enhanced sampling, error estimation, variable fidelity, and data fusion techniques, challenges persist in selecting fidelity levels and developing efficient data fusion methods. This study proposes a new fusion approach to construct multi-fidelity surrogate models by constructing gradient-only surrogates that use only gradients to construct regression surfaces. Results are demonstrated on foundational example problems that isolate and illustrate the fusion approach's efficacy, avoiding the need for complex examples that obfuscate the main concept.

In this work, we perform a systematic comparison of the effectiveness and efficiency of generative and non-generative models in constructing design spaces for novel and efficient design exploration and shape optimization. We apply these models in the case of airfoil/hydrofoil design and conduct the comparison on the resulting design spaces. A conventional Generative Adversarial Network (GAN) and a state-of-the-art generative model, the Performance-Augmented Diverse Generative Adversarial Network (PaDGAN), are juxtaposed with a linear non-generative model based on the coupling of the Karhunen-Loève Expansion and a physics-informed Shape Signature Vector (SSV-KLE). The comparison demonstrates that, with an appropriate shape encoding and a physics-augmented design space, non-generative models have the potential to cost-effectively generate high-performing valid designs with enhanced coverage of the design space. In this work, both approaches are applied to two large foil profile datasets comprising real-world and artificial designs generated through either a profile-generating parametric model or deep-learning approach. These datasets are further enriched with integral properties of their members' shapes as well as physics-informed parameters. Our results illustrate that the design spaces constructed by the non-generative model outperform the generative model in terms of design validity, generating robust latent spaces with none or significantly fewer invalid designs when compared to generative models. We additionally compare the performance and diversity of generated designs to provide further insights about the quality of the resulting spaces. We aspire that these findings will aid the engineering design community in making informed decisions when constructing designs spaces for shape optimization, as we have demonstrated that under certain conditions computationally inexpensive approaches can closely match or even outperform state-of-the art generative models.

Dr. Stephen Szabo, an OB/GYN with Pinehurst Surgical Clinic (PSC), reached a milestone on Thursday, Sept. 19 with his 805th robotic surgery -- a hysterectomy with sacrocolpopexy and bladder suspension. Dr. Szabo first performed a robotically-assisted surgery in 2006 after coming to Pinehurst Surgical in 1998. He and Pinehurst Surgical Urologists Dr. Robert Chamberlain and Dr. Greg Griewe, along with Dr. Walter Fasolak, from FirstHealth's Southern Pines Women's Center, formed the core group of physicians who spearheaded the introduction of robotic surgery in Moore County. With 805 surgeries complete, Dr. Szabo is now in the company of an elite and distinguished group of surgeons practicing the art of robotic-assisted healthcare. The minimally invasive approach means that advanced gynecologic surgeries, which would have resulted in a three-to-five-day hospital stay, now only require a stay of three to five hours -- and carry a reduced risk of complications or infection.

At one of the busiest shipping terminals in the U.S., more than two dozen giant red robots wheeled cargo containers along the docks on a recent morning, handing the boxes off to another set of androids gliding along long rows of stacked containers before smoothly setting the boxes down in precise spots. The tightly designed dance at TraPac LLC's Los Angeles terminal offers a window on how global trade will move in the near future: using highly automated systems and machinery, with minimal human intervention, to handle the flood of goods that new free-trade agreements will push to the docks. Many in the industry believe automation, which boosts terminal productivity and reliability while cutting labor costs, is critical to the ability of ports to cope with the surging trade volumes and the huge megaships that are beginning to arrive in the U.S. Analysts estimate the technology can reduce the amount of time ships spend in port and improve productivity by as much as 30%. "We have to do it for productivity purposes, to stay relevant and to be able to service these large ships," said Peter Stone, a member of TraPac's board. Yet the TraPac site is one of only four cargo terminals in the U.S. using the technology.