The embryos weren't used to try to establish a pregnancy, but the researchers behind the technique say it could one day be used to address infertility. In a controversial step that raises the possibility of a new kind of infertility treatment, scientists report that they have produced functional human eggs in the lab that were able to be fertilized with sperm. The proof-of-concept study, published today in the journal Nature Communications, involves using human skin cells to generate eggs, some of which were capable of producing early-stage embryos. None of the embryos were used to try to establish a pregnancy, and it's unlikely that they would have developed much further in the womb. Yet the authors, from Oregon Health and Science University, say the technique could one day be used as an alternative to in vitro fertilization, or IVF.

This is the second in a series of short reports that seek to help business, education, and policy leaders understand the technical details of working with AI through rigorous testing. In this report, we investigate Chain-of-Thought (CoT) prompting, a technique that encourages a large language model (LLM) to "think step by step" (Wei et al., 2022). CoT is a widely adopted method for improving reasoning tasks, however, our findings reveal a more nuanced picture of its effectiveness. We demonstrate two things: - The effectiveness of Chain-of-Thought prompting can vary greatly depending on the type of task and model. For non-reasoning models, CoT generally improves average performance by a small amount, particularly if the model does not inherently engage in step-by-step processing by default. However, CoT can introduce more variability in answers, sometimes triggering occasional errors in questions the model would otherwise get right. We also found that many recent models perform some form of CoT reasoning even if not asked; for these models, a request to perform CoT had little impact. Performing CoT generally requires far more tokens (increasing cost and time) than direct answers. - For models designed with explicit reasoning capabilities, CoT prompting often results in only marginal, if any, gains in answer accuracy. However, it significantly increases the time and tokens needed to generate a response.

Farmers rely on in-field observations to make well-informed crop management decisions to maximize profit and minimize adverse environmental impact. However, obtaining real-world crop state measurements is labor-intensive, time-consuming and expensive. In most cases, it is not feasible to gather crop state measurements before every decision moment. Moreover, in previous research pertaining to farm management optimization, these observations are often assumed to be readily available without any cost, which is unrealistic. Hence, enabling optimization without the need to have temporally complete crop state observations is important. An approach to that problem is to include measuring as part of decision making. As a solution, we apply reinforcement learning (RL) to recommend opportune moments to simultaneously measure crop features and apply nitrogen fertilizer. With realistic considerations, we design an RL environment with explicit crop feature measuring costs. While balancing costs, we find that an RL agent, trained with recurrent PPO, discovers adaptive measuring policies that follow critical crop development stages, with results aligned by what domain experts would consider a sensible approach. Our results highlight the importance of measuring when crop feature measurements are not readily available.

The emergence of Retrieval-augmented generation (RAG) has alleviated the issues of outdated and hallucinatory content in the generation of large language models (LLMs), yet it still reveals numerous limitations. When a general-purpose LLM serves as the RAG generator, it often suffers from inadequate response informativeness, response robustness, and citation quality. Past approaches to tackle these limitations, either by incorporating additional steps beyond generating responses or optimizing the generator through supervised fine-tuning (SFT), still failed to align with the RAG requirement thoroughly. Consequently, optimizing the RAG generator from multiple preference perspectives while maintaining its end-to-end LLM form remains a challenge. To bridge this gap, we propose Multiple Perspective Preference Alignment for Retrieval-Augmented Generation (PA-RAG), a method for optimizing the generator of RAG systems to align with RAG requirements comprehensively. Specifically, we construct high-quality instruction fine-tuning data and multi-perspective preference data by sampling varied quality responses from the generator across different prompt documents quality scenarios. Subsequently, we optimize the generator using SFT and Direct Preference Optimization (DPO). Extensive experiments conducted on four question-answer datasets across three LLMs demonstrate that PA-RAG can significantly enhance the performance of RAG generators. Our code and datasets are available at https://github.com/wujwyi/PA-RAG.

The grinding trial-and-error process that precedes world-changing scientific discoveries doesn't really lend itself to dramatization. Instead of our heroes chasing bad guys down dark alleys, the exciting story action involves them standing in front of a blackboard or gazing into a microscope. So dramatic tension is injected by financial or political forces threatening to derail a project of urgent importance (Oppenheimer); the scientists fighting for credibility in the face of belonging to a marginalized group (Hidden Figures, The Imitation Game, any biopic of a female scientist); or the old reliable of the main scientist being a difficult, maverick genius (Oppenheimer again). Joy: The Birth of IVF, Ben Taylor's new film out now on Netflix, about the arduous path to develop a viable technique for fertilizing human eggs outside the body and implanting them in the womb, aka in vitro fertilization, hits many of these notes. There's the irascible pioneer, here played by Bill Nighy at his most crotchety but sympathetic as gynecologist Patrick Steptoe, who introduced laparoscopy to the U.K. He's teamed with the driven visionary--physiologist Robert Edwards, played by James Norton, who, like Jude Law, is always required to conceal his innate gorgeousness under an unbecoming wig or glasses to convince as an ordinary guy.

Crop production management is essential for optimizing yield and minimizing a field's environmental impact to crop fields, yet it remains challenging due to the complex and stochastic processes involved. Recently, researchers have turned to machine learning to address these complexities. Specifically, reinforcement learning (RL), a cutting-edge approach designed to learn optimal decision-making strategies through trial and error in dynamic environments, has emerged as a promising tool for developing adaptive crop management policies. RL models aim to optimize long-term rewards by continuously interacting with the environment, making them well-suited for tackling the uncertainties and variability inherent in crop management. Studies have shown that RL can generate crop management policies that compete with, and even outperform, expert-designed policies within simulation-based crop models. In the gym-DSSAT crop model environment, one of the most widely used simulators for crop management, proximal policy optimization (PPO) and deep Q-networks (DQN) have shown promising results. However, these methods have not yet been systematically evaluated under identical conditions. In this study, we evaluated PPO and DQN against static baseline policies across three different RL tasks, fertilization, irrigation, and mixed management, provided by the gym-DSSAT environment. To ensure a fair comparison, we used consistent default parameters, identical reward functions, and the same environment settings. Our results indicate that PPO outperforms DQN in fertilization and irrigation tasks, while DQN excels in the mixed management task. This comparative analysis provides critical insights into the strengths and limitations of each approach, advancing the development of more effective RL-based crop management strategies.

Large language models (LLMs) have demonstrated powerful text generation capabilities, bringing unprecedented innovation to the healthcare field. While LLMs hold immense promise for applications in healthcare, applying them to real clinical scenarios presents significant challenges, as these models may generate content that deviates from established medical facts and even exhibit potential biases. In our research, we develop an augmented LLM framework based on the Unified Medical Language System (UMLS), aiming to better serve the healthcare community. We employ LLaMa2-13b-chat and ChatGPT-3.5 as our benchmark models, and conduct automatic evaluations using the ROUGE Score and BERTScore on 104 questions from the LiveQA test set. Additionally, we establish criteria for physician-evaluation based on four dimensions: Factuality, Completeness, Readability and Relevancy. ChatGPT-3.5 is used for physician evaluation with 20 questions on the LiveQA test set. Multiple resident physicians conducted blind reviews to evaluate the generated content, and the results indicate that this framework effectively enhances the factuality, completeness, and relevance of generated content. Our research demonstrates the effectiveness of using UMLS-augmented LLMs and highlights the potential application value of LLMs in in medical question-answering.

Fox News contributor Dr. Marc Siegel weighs in on how artificial intelligence can change the patient-doctor relationship on'America's Newsroom.' AI's latest product – Remini – allows users to upload photos of themselves and their partner to generate images of what their future child could look like. There are two sides to this. First, the app lets people envision themselves as parents – potentially encouraging people to pursue, rather than delay, parenthood. As one woman said, "I can actually see myself being [pregnant] at some point."

One in four couples in developing countries is impacted by infertility. About 48.5 million couples experience infertility worldwide. Today, infertility is rapidly becoming an epidemic. In vitro fertilization (IVF) is a technique that helps people facing fertility problems have a baby. Despite IVF's potential, the outcomes are unpredictable. To make matters worse, access to fertility care is abysmal.

As it matures, machine learning has been applied to more and bigger challenges. One of the latest is women's health tech, a space where research has traditionally lagged, and that few companies have addressed, until now. In 2015, women's health tech startups raised only $82 million in funding from investment firms. Since then, that number has risen to $1.1 billion. AI health care company Presagen is one of the companies stepping up in this essential health space, with scalable machine learning that can be used by clinics and patients anywhere in the world.