Things to Do in L.A. Tap to enable a layout that focuses on the article. Bill Pulte, director of the Federal Housing Finance Agency, speaks to reporters at the White House in July. Voice comes from the use of AI. Please report any issues or inconsistencies here . Bill Pulte, director of the Federal Housing Finance Agency, alleges that U.S. Sen. Adam Schiff and others President Trump has clashed with misrepresented facts in mortgage documents to secure favorable tax or loan terms.

Large-scale generative language and vision-language models (LLMs and VLMs) excel in few-shot in-context learning for decision making and instruction following. However, they require high-quality exemplar demonstrations to be included in their context window. In this work, we ask: Can LLMs and VLMs generate their own prompt examples from generic, sub-optimal demonstrations? We propose In-Context Abstraction Learning (ICAL), a method that builds a memory of multimodal experience insights from sub-optimal demonstrations and human feedback. Given a noisy demonstration in a new domain, VLMs abstract the trajectory into a general program by fixing inefficient actions and annotating cognitive abstractions: task relationships, object state changes, temporal subgoals, and task construals. These abstractions are refined and adapted interactively through human feedback while the agent attempts to execute the trajectory in a similar environment. The resulting abstractions, when used as exemplars in the prompt, significantly improve decision-making in retrieval-augmented LLM and VLM agents. Our ICAL agent surpasses the state-of-the-art in dialogue-based instruction following in TEACh, multimodal web agents in VisualWebArena, and action anticipation in Ego4D. In TEACh, we achieve a 12.6% improvement in goal-condition success. In VisualWebArena, our task success rate improves over the SOTA from 14.3% to 22.7%. In Ego4D action forecasting, we improve over few-shot GPT-4V and remain competitive with supervised models. We show finetuning our retrieval-augmented in-context agent yields additional improvements. Our approach significantly reduces reliance on expert-crafted examples and consistently outperforms in-context learning from action plans that lack such insights.

Decline in gait features is common in older adults and an indicator of increased risk of disability, morbidity, and mortality. Under dual task walking (DTW) conditions, further degradation in the performance of both the gait and the secondary cognitive task were found in older adults which were significantly correlated to falls history. Cortical control of gait, specifically in the pre-frontal cortex (PFC) as measured by functional near infrared spectroscopy (fNIRS), during DTW in older adults has recently been studied. However, the automatic classification of differences in cognitive activations under single and dual task gait conditions has not been extensively studied yet. In this paper, we formulate this as a classification task and leverage deep learning to perform automatic classification of STW, DTW and single cognitive task (STA). We conduct analysis on the data samples which reveals the characteristics on the difference between HbO2 and Hb values that are subsequently used as additional features. We perform feature engineering to formulate the fNIRS features as a 3-channel image and apply various image processing techniques for data augmentation to enhance the performance of deep learning models. Experimental results show that pre-trained deep learning models that are fine-tuned using the collected fNIRS dataset together with gender and cognitive status information can achieve around 81\% classification accuracy which is about 10\% higher than the traditional machine learning algorithms. We further perform an ablation study to identify rankings of features such as the fNIRS levels and/or voxel locations on the contribution of the classification task.

With the success of the prompt-tuning paradigm in Natural Language Processing (NLP), various prompt templates have been proposed to further stimulate specific knowledge for serving downstream tasks, e.g., machine translation, text generation, relation extraction, and so on. Existing prompt templates are mainly shared among all training samples with the information of task description. However, training samples are quite diverse. The sharing task description is unable to stimulate the unique task-related information in each training sample, especially for tasks with the finite-label space. To exploit the unique task-related information, we imitate the human decision process which aims to find the contrastive attributes between the objective factual and their potential counterfactuals. Thus, we propose the \textbf{C}ounterfactual \textbf{C}ontrastive \textbf{Prompt}-Tuning (CCPrompt) approach for many-class classification, e.g., relation classification, topic classification, and entity typing. Compared with simple classification tasks, these tasks have more complex finite-label spaces and are more rigorous for prompts. First of all, we prune the finite label space to construct fact-counterfactual pairs. Then, we exploit the contrastive attributes by projecting training instances onto every fact-counterfactual pair. We further set up global prototypes corresponding with all contrastive attributes for selecting valid contrastive attributes as additional tokens in the prompt template. Finally, a simple Siamese representation learning is employed to enhance the robustness of the model. We conduct experiments on relation classification, topic classification, and entity typing tasks in both fully supervised setting and few-shot setting. The results indicate that our model outperforms former baselines.

NASA inaugurated its 23rd class of new astronauts on Monday, which includes 10 individuals who are set to walk on the moon and maybe even Mars. Deemed the'Artemis Generation,' this group consists of several former US military, an ex-SpaceX medical director and a bioengineer who also participated in the 2020 Tokyo Olympics as a track cyclist. The name is a reference to NASA's Artemis program, which aims to send the first woman and the first person of color to moon as early as 2025. The astronaut candidates for 2021 are: Nichole Ayers, Marcos Berríos, Guaynabo, Christina Birch, Deniz Burnham, Luke Delaney, Andre Douglas, Jack Hathaway, Anil Menon, Christopher Williams and Jessica Wittner. This is NASA first new class in four years and the group is set to begin the two-year training process in January 2022.

Z Advanced Computing, Inc. (ZAC), the pioneer Cognitive Explainable-AI (Artificial Intelligence) (Cognitive XAI) software startup, has made AI and Machine Learning (ML) breakthroughs: ZAC has achieved 3D Image Recognition using only a few training samples, and using only an average laptop with low power CPU, for both training and recognition, for the US Air Force (USAF). This is in sharp contrast to the other algorithms in industry that require thousands to billions of samples, being trained on large GPU servers. "ZAC requires much less computing power and much less electrical power to run, which is great for mobile and edge computing, as well as environment, with less Carbon footprint," emphasized Dr. Saied Tadayon, CTO of ZAC. ZAC is the first to demonstrate the novel and superior algorithms Cognition-based Explainable-AI (XAI), where various attributes and details of 3D (three dimensional) objects are recognized from any view or angle. "You cannot do this task with the other algorithms, such as Deep Convolutional Neural Networks (CNN) or ResNets, even with an extremely large number of training samples, on GPU servers. That's basically hitting the limitations of CNNs or Neural Nets, which all other companies are using now," said Dr. Bijan Tadayon, CEO of ZAC.

Many decisions involve choosing an uncertain course of actions in deep and wide decision trees, as when we plan to visit an exotic country for vacation. In these cases, exhaustive search for the best sequence of actions is not tractable due to the large number of possibilities and limited time or computational resources available to make the decision. Therefore, planning agents need to balance breadth (exploring many actions at each level of the tree) and depth (exploring many levels in the tree) to allocate optimally their finite search capacity. We provide efficient analytical solutions and numerical analysis to the problem of allocating finite sampling capacity in one shot to large decision trees. We find that in general the optimal policy is to allocate few samples per level so that deep levels can be reached, thus favoring depth over breadth search. In contrast, in poor environments and at low capacity, it is best to broadly sample branches at the cost of not sampling deeply, although this policy is marginally better than deep allocations. Our results provide a theoretical foundation for the optimality of deep imagination for planning and show that it is a generally valid heuristic that could have evolved from the finite constraints of cognitive systems.

The following article is a written adaptation of an episode of Thrilling Tales of Modern Capitalism, Slate's new podcast about companies in the news and how they got there. The story of Epic Games begins with a programming prodigy named Tim Sweeney. When he was still in elementary school, Sweeney received an Apple II computer as a gift from his older brother. He almost immediately started programming very simple games on that computer, and then he began to test those games out by letting other kids play them while he watched. "He was quite savvy for a teenager," says Simon Parkin, a writer who covers the video game industry, "because he knew that if he wanted his games to be successful, he needed to make sure that players of different abilities could get into them and understand what they were doing. So he would invite all the kids from the local neighborhood over to come and play his games that he was designing, and he would watch them while they were playing and make adjustments or take notes based on if they got confused or if they got stuck in a certain bit, and then he'd go away and adjust the game accordingly."